From 6aa30ed07441582f671f2b7608cf569e6b6c184b Mon Sep 17 00:00:00 2001 From: Triang3l Date: Sun, 22 May 2022 18:03:09 +0300 Subject: [PATCH] [GPU] 128-thread groups in all texture load shaders Vulkan's minimum requirement (maxComputeWorkGroupInvocations) is 128. --- src/xenia/gpu/d3d12/d3d12_texture_cache.cc | 61 +++++++++++-------- src/xenia/gpu/d3d12/d3d12_texture_cache.h | 16 ++++- .../d3d12_5_1/texture_load_128bpb_cs.h | 12 ++-- .../d3d12_5_1/texture_load_128bpb_scaled_cs.h | 12 ++-- .../d3d12_5_1/texture_load_16bpb_cs.h | 12 ++-- .../d3d12_5_1/texture_load_16bpb_scaled_cs.h | 12 ++-- .../d3d12_5_1/texture_load_64bpb_cs.h | 12 ++-- .../d3d12_5_1/texture_load_64bpb_scaled_cs.h | 12 ++-- .../bytecode/d3d12_5_1/texture_load_8bpb_cs.h | 12 ++-- .../d3d12_5_1/texture_load_8bpb_scaled_cs.h | 12 ++-- .../bytecode/d3d12_5_1/texture_load_ctx1_cs.h | 12 ++-- .../d3d12_5_1/texture_load_dxn_rg8_cs.h | 12 ++-- .../d3d12_5_1/texture_load_dxt1_rgba8_cs.h | 12 ++-- .../d3d12_5_1/texture_load_dxt3_rgba8_cs.h | 12 ++-- .../d3d12_5_1/texture_load_dxt3a_cs.h | 12 ++-- .../texture_load_dxt3aas1111_argb4_cs.h | 12 ++-- .../texture_load_dxt3aas1111_bgra4_cs.h | 12 ++-- .../d3d12_5_1/texture_load_dxt5_rgba8_cs.h | 12 ++-- .../d3d12_5_1/texture_load_dxt5a_r8_cs.h | 12 ++-- .../texture_load_r16_snorm_float_cs.h | 12 ++-- .../texture_load_r16_snorm_float_scaled_cs.h | 12 ++-- .../texture_load_r16_unorm_float_cs.h | 12 ++-- .../texture_load_r16_unorm_float_scaled_cs.h | 12 ++-- .../texture_load_r4g4b4a4_a4r4g4b4_cs.h | 12 ++-- ...texture_load_r4g4b4a4_a4r4g4b4_scaled_cs.h | 12 ++-- .../texture_load_r4g4b4a4_b4g4r4a4_cs.h | 12 ++-- ...texture_load_r4g4b4a4_b4g4r4a4_scaled_cs.h | 12 ++-- .../texture_load_r5g5b5a1_b5g5r5a1_cs.h | 12 ++-- ...texture_load_r5g5b5a1_b5g5r5a1_scaled_cs.h | 12 ++-- ...xture_load_r5g5b6_b5g6r5_swizzle_rbga_cs.h | 12 ++-- ...oad_r5g5b6_b5g6r5_swizzle_rbga_scaled_cs.h | 12 ++-- .../d3d12_5_1/texture_load_r5g6b5_b5g6r5_cs.h | 12 ++-- .../texture_load_r5g6b5_b5g6r5_scaled_cs.h | 12 ++-- .../texture_load_rgba16_snorm_float_cs.h | 12 ++-- ...exture_load_rgba16_snorm_float_scaled_cs.h | 12 ++-- .../texture_load_rgba16_unorm_float_cs.h | 12 ++-- ...exture_load_rgba16_unorm_float_scaled_cs.h | 12 ++-- .../vulkan_spirv/texture_load_128bpb_cs.h | 10 +-- .../texture_load_128bpb_scaled_cs.h | 10 +-- .../vulkan_spirv/texture_load_16bpb_cs.h | 10 +-- .../texture_load_16bpb_scaled_cs.h | 12 ++-- .../vulkan_spirv/texture_load_64bpb_cs.h | 10 +-- .../texture_load_64bpb_scaled_cs.h | 10 +-- .../vulkan_spirv/texture_load_8bpb_cs.h | 10 +-- .../texture_load_8bpb_scaled_cs.h | 10 +-- .../vulkan_spirv/texture_load_ctx1_cs.h | 10 +-- .../vulkan_spirv/texture_load_dxn_rg8_cs.h | 10 +-- .../vulkan_spirv/texture_load_dxt1_rgba8_cs.h | 10 +-- .../vulkan_spirv/texture_load_dxt3_rgba8_cs.h | 12 ++-- .../vulkan_spirv/texture_load_dxt3a_cs.h | 10 +-- .../texture_load_dxt3aas1111_argb4_cs.h | 10 +-- .../texture_load_dxt3aas1111_bgra4_cs.h | 10 +-- .../vulkan_spirv/texture_load_dxt5_rgba8_cs.h | 10 +-- .../vulkan_spirv/texture_load_dxt5a_r8_cs.h | 10 +-- .../texture_load_r16_snorm_float_cs.h | 10 +-- .../texture_load_r16_snorm_float_scaled_cs.h | 12 ++-- .../texture_load_r16_unorm_float_cs.h | 10 +-- .../texture_load_r16_unorm_float_scaled_cs.h | 10 +-- .../texture_load_r4g4b4a4_a4r4g4b4_cs.h | 10 +-- ...texture_load_r4g4b4a4_a4r4g4b4_scaled_cs.h | 12 ++-- .../texture_load_r4g4b4a4_b4g4r4a4_cs.h | 10 +-- ...texture_load_r4g4b4a4_b4g4r4a4_scaled_cs.h | 12 ++-- .../texture_load_r5g5b5a1_b5g5r5a1_cs.h | 10 +-- ...texture_load_r5g5b5a1_b5g5r5a1_scaled_cs.h | 10 +-- ...xture_load_r5g5b6_b5g6r5_swizzle_rbga_cs.h | 10 +-- ...oad_r5g5b6_b5g6r5_swizzle_rbga_scaled_cs.h | 12 ++-- .../texture_load_r5g6b5_b5g6r5_cs.h | 10 +-- .../texture_load_r5g6b5_b5g6r5_scaled_cs.h | 10 +-- .../texture_load_rgba16_snorm_float_cs.h | 10 +-- ...exture_load_rgba16_snorm_float_scaled_cs.h | 10 +-- .../texture_load_rgba16_unorm_float_cs.h | 12 ++-- ...exture_load_rgba16_unorm_float_scaled_cs.h | 10 +-- src/xenia/gpu/shaders/texture_load.xesli | 12 ++++ .../gpu/shaders/texture_load_128bpb.xesli | 3 +- .../gpu/shaders/texture_load_16bpb.xesli | 3 +- .../gpu/shaders/texture_load_32bpb.xesli | 3 +- .../shaders/texture_load_32bpb_64bpb.xesli | 3 +- .../gpu/shaders/texture_load_64bpb.xesli | 3 +- src/xenia/gpu/shaders/texture_load_8bpb.xesli | 3 +- .../gpu/shaders/texture_load_ctx1.cs.xesl | 3 +- .../gpu/shaders/texture_load_dxn_rg8.cs.xesl | 3 +- .../shaders/texture_load_dxt1_rgba8.cs.xesl | 3 +- .../shaders/texture_load_dxt3_rgba8.cs.xesl | 3 +- .../gpu/shaders/texture_load_dxt3a.cs.xesl | 3 +- .../shaders/texture_load_dxt3aas1111.xesli | 3 +- .../shaders/texture_load_dxt5_rgba8.cs.xesl | 3 +- .../gpu/shaders/texture_load_dxt5a_r8.cs.xesl | 3 +- src/xenia/ui/shaders/xesl.xesli | 10 +++ 88 files changed, 491 insertions(+), 434 deletions(-) diff --git a/src/xenia/gpu/d3d12/d3d12_texture_cache.cc b/src/xenia/gpu/d3d12/d3d12_texture_cache.cc index 2fb6e1bb3..46da10934 100644 --- a/src/xenia/gpu/d3d12/d3d12_texture_cache.cc +++ b/src/xenia/gpu/d3d12/d3d12_texture_cache.cc @@ -371,76 +371,79 @@ const D3D12TextureCache::HostFormat D3D12TextureCache::host_formats_[64] = { const D3D12TextureCache::LoadModeInfo D3D12TextureCache::load_mode_info_[] = { {shaders::texture_load_8bpb_cs, sizeof(shaders::texture_load_8bpb_cs), shaders::texture_load_8bpb_scaled_cs, - sizeof(shaders::texture_load_8bpb_scaled_cs), 3, 4, 16}, + sizeof(shaders::texture_load_8bpb_scaled_cs), 3, 4, 4, 16}, {shaders::texture_load_16bpb_cs, sizeof(shaders::texture_load_16bpb_cs), shaders::texture_load_16bpb_scaled_cs, - sizeof(shaders::texture_load_16bpb_scaled_cs), 4, 4, 16}, + sizeof(shaders::texture_load_16bpb_scaled_cs), 4, 4, 4, 16}, {shaders::texture_load_32bpb_cs, sizeof(shaders::texture_load_32bpb_cs), shaders::texture_load_32bpb_scaled_cs, - sizeof(shaders::texture_load_32bpb_scaled_cs), 4, 4, 8}, + sizeof(shaders::texture_load_32bpb_scaled_cs), 4, 4, 3, 8}, {shaders::texture_load_64bpb_cs, sizeof(shaders::texture_load_64bpb_cs), shaders::texture_load_64bpb_scaled_cs, - sizeof(shaders::texture_load_64bpb_scaled_cs), 4, 4, 4}, + sizeof(shaders::texture_load_64bpb_scaled_cs), 4, 4, 2, 4}, {shaders::texture_load_128bpb_cs, sizeof(shaders::texture_load_128bpb_cs), shaders::texture_load_128bpb_scaled_cs, - sizeof(shaders::texture_load_128bpb_scaled_cs), 4, 4, 2}, + sizeof(shaders::texture_load_128bpb_scaled_cs), 4, 4, 1, 2}, {shaders::texture_load_r5g5b5a1_b5g5r5a1_cs, sizeof(shaders::texture_load_r5g5b5a1_b5g5r5a1_cs), shaders::texture_load_r5g5b5a1_b5g5r5a1_scaled_cs, - sizeof(shaders::texture_load_r5g5b5a1_b5g5r5a1_scaled_cs), 4, 4, 16}, + sizeof(shaders::texture_load_r5g5b5a1_b5g5r5a1_scaled_cs), 4, 4, 4, 16}, {shaders::texture_load_r5g6b5_b5g6r5_cs, sizeof(shaders::texture_load_r5g6b5_b5g6r5_cs), shaders::texture_load_r5g6b5_b5g6r5_scaled_cs, - sizeof(shaders::texture_load_r5g6b5_b5g6r5_scaled_cs), 4, 4, 16}, + sizeof(shaders::texture_load_r5g6b5_b5g6r5_scaled_cs), 4, 4, 4, 16}, {shaders::texture_load_r5g5b6_b5g6r5_swizzle_rbga_cs, sizeof(shaders::texture_load_r5g5b6_b5g6r5_swizzle_rbga_cs), shaders::texture_load_r5g5b6_b5g6r5_swizzle_rbga_scaled_cs, sizeof(shaders::texture_load_r5g5b6_b5g6r5_swizzle_rbga_scaled_cs), 4, 4, - 16}, + 4, 16}, {shaders::texture_load_r4g4b4a4_b4g4r4a4_cs, sizeof(shaders::texture_load_r4g4b4a4_b4g4r4a4_cs), shaders::texture_load_r4g4b4a4_b4g4r4a4_scaled_cs, - sizeof(shaders::texture_load_r4g4b4a4_b4g4r4a4_scaled_cs), 4, 4, 16}, + sizeof(shaders::texture_load_r4g4b4a4_b4g4r4a4_scaled_cs), 4, 4, 4, 16}, {shaders::texture_load_r10g11b11_rgba16_cs, sizeof(shaders::texture_load_r10g11b11_rgba16_cs), shaders::texture_load_r10g11b11_rgba16_scaled_cs, - sizeof(shaders::texture_load_r10g11b11_rgba16_scaled_cs), 4, 4, 8}, + sizeof(shaders::texture_load_r10g11b11_rgba16_scaled_cs), 4, 4, 3, 8}, {shaders::texture_load_r10g11b11_rgba16_snorm_cs, sizeof(shaders::texture_load_r10g11b11_rgba16_snorm_cs), shaders::texture_load_r10g11b11_rgba16_snorm_scaled_cs, - sizeof(shaders::texture_load_r10g11b11_rgba16_snorm_scaled_cs), 4, 4, 8}, + sizeof(shaders::texture_load_r10g11b11_rgba16_snorm_scaled_cs), 4, 4, 3, + 8}, {shaders::texture_load_r11g11b10_rgba16_cs, sizeof(shaders::texture_load_r11g11b10_rgba16_cs), shaders::texture_load_r11g11b10_rgba16_scaled_cs, - sizeof(shaders::texture_load_r11g11b10_rgba16_scaled_cs), 4, 4, 8}, + sizeof(shaders::texture_load_r11g11b10_rgba16_scaled_cs), 4, 4, 3, 8}, {shaders::texture_load_r11g11b10_rgba16_snorm_cs, sizeof(shaders::texture_load_r11g11b10_rgba16_snorm_cs), shaders::texture_load_r11g11b10_rgba16_snorm_scaled_cs, - sizeof(shaders::texture_load_r11g11b10_rgba16_snorm_scaled_cs), 4, 4, 8}, + sizeof(shaders::texture_load_r11g11b10_rgba16_snorm_scaled_cs), 4, 4, 3, + 8}, {shaders::texture_load_dxt1_rgba8_cs, - sizeof(shaders::texture_load_dxt1_rgba8_cs), nullptr, 0, 4, 4, 4}, + sizeof(shaders::texture_load_dxt1_rgba8_cs), nullptr, 0, 4, 4, 2, 16}, {shaders::texture_load_dxt3_rgba8_cs, - sizeof(shaders::texture_load_dxt3_rgba8_cs), nullptr, 0, 4, 4, 2}, + sizeof(shaders::texture_load_dxt3_rgba8_cs), nullptr, 0, 4, 4, 1, 8}, {shaders::texture_load_dxt5_rgba8_cs, - sizeof(shaders::texture_load_dxt5_rgba8_cs), nullptr, 0, 4, 4, 2}, + sizeof(shaders::texture_load_dxt5_rgba8_cs), nullptr, 0, 4, 4, 1, 8}, {shaders::texture_load_dxn_rg8_cs, sizeof(shaders::texture_load_dxn_rg8_cs), - nullptr, 0, 4, 4, 2}, + nullptr, 0, 4, 4, 1, 8}, {shaders::texture_load_dxt3a_cs, sizeof(shaders::texture_load_dxt3a_cs), - nullptr, 0, 4, 4, 4}, + nullptr, 0, 4, 4, 2, 16}, {shaders::texture_load_dxt3aas1111_bgra4_cs, - sizeof(shaders::texture_load_dxt3aas1111_bgra4_cs), nullptr, 0, 4, 4, 4}, + sizeof(shaders::texture_load_dxt3aas1111_bgra4_cs), nullptr, 0, 4, 4, 2, + 16}, {shaders::texture_load_dxt5a_r8_cs, - sizeof(shaders::texture_load_dxt5a_r8_cs), nullptr, 0, 4, 4, 4}, + sizeof(shaders::texture_load_dxt5a_r8_cs), nullptr, 0, 4, 4, 2, 16}, {shaders::texture_load_ctx1_cs, sizeof(shaders::texture_load_ctx1_cs), - nullptr, 0, 4, 4, 4}, + nullptr, 0, 4, 4, 2, 16}, {shaders::texture_load_depth_unorm_cs, sizeof(shaders::texture_load_depth_unorm_cs), shaders::texture_load_depth_unorm_scaled_cs, - sizeof(shaders::texture_load_depth_unorm_scaled_cs), 4, 4, 8}, + sizeof(shaders::texture_load_depth_unorm_scaled_cs), 4, 4, 3, 8}, {shaders::texture_load_depth_float_cs, sizeof(shaders::texture_load_depth_float_cs), shaders::texture_load_depth_float_scaled_cs, - sizeof(shaders::texture_load_depth_float_scaled_cs), 4, 4, 8}, + sizeof(shaders::texture_load_depth_float_scaled_cs), 4, 4, 3, 8}, }; D3D12TextureCache::D3D12TextureCache(const RegisterFile& register_file, @@ -1736,6 +1739,8 @@ bool D3D12TextureCache::LoadTextureDataFromResidentMemoryImpl(Texture& texture, // available through buffers, and to create a descriptor, the buffer start // address is required - which may be different for base and mips. bool scaled_mips_source_set_up = false; + uint32_t guest_x_blocks_per_group_log2 = + load_mode_info.GetGuestXBlocksPerGroupLog2(); for (uint32_t loop_level = loop_level_first; loop_level <= loop_level_last; ++loop_level) { bool is_base = loop_level == 0; @@ -1817,8 +1822,14 @@ bool D3D12TextureCache::LoadTextureDataFromResidentMemoryImpl(Texture& texture, // Each thread group processes 32x32x1 source blocks (resolution-scaled, but // still compressed if the host needs decompression). - uint32_t group_count_x = (load_constants.size_blocks[0] + 31) >> 5; - uint32_t group_count_y = (load_constants.size_blocks[1] + 31) >> 5; + uint32_t group_count_x = + (load_constants.size_blocks[0] + + ((UINT32_C(1) << guest_x_blocks_per_group_log2) - 1)) >> + guest_x_blocks_per_group_log2; + uint32_t group_count_y = + (load_constants.size_blocks[1] + + ((UINT32_C(1) << kLoadGuestYBlocksPerGroupLog2) - 1)) >> + kLoadGuestYBlocksPerGroupLog2; const D3D12_PLACED_SUBRESOURCE_FOOTPRINT& host_slice_layout = is_base ? host_slice_layout_base : host_slice_layouts_mips[level]; diff --git a/src/xenia/gpu/d3d12/d3d12_texture_cache.h b/src/xenia/gpu/d3d12/d3d12_texture_cache.h index 2dd418fbd..fe6313cc4 100644 --- a/src/xenia/gpu/d3d12/d3d12_texture_cache.h +++ b/src/xenia/gpu/d3d12/d3d12_texture_cache.h @@ -176,6 +176,9 @@ class D3D12TextureCache final : public TextureCache { void UpdateTextureBindingsImpl(uint32_t fetch_constant_mask) override; private: + static constexpr uint32_t kLoadGuestXThreadsPerGroupLog2 = 2; + static constexpr uint32_t kLoadGuestYBlocksPerGroupLog2 = 5; + enum class LoadMode { k8bpb, k16bpb, @@ -221,10 +224,17 @@ class D3D12TextureCache final : public TextureCache { // may copy multiple blocks per one invocation. uint32_t srv_bpe_log2; uint32_t uav_bpe_log2; - // Number of host blocks (or texels for uncompressed) along X axis written - // by every compute shader thread - rows in the upload buffer are padded to - // at least this amount. + // Log2 of the number of guest blocks along the X axis loaded by a single + // thread shader group. + uint32_t guest_x_blocks_per_thread_log2; + // Number of host blocks (or texels for uncompressed) along the X axis + // written by a single compute shader thread - rows in the upload buffer are + // padded to at least this amount. uint32_t host_x_blocks_per_thread; + + uint32_t GetGuestXBlocksPerGroupLog2() const { + return kLoadGuestXThreadsPerGroupLog2 + guest_x_blocks_per_thread_log2; + } }; struct HostFormat { diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_128bpb_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_128bpb_cs.h index 11fb257c0..4ab0adcee 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_128bpb_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_128bpb_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 5 -dcl_thread_group 16, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(1) mov r0.y, vThreadID.y uge r0.yz, r0.xxyx, CB0[0][1].xxyx @@ -163,10 +163,10 @@ ret const BYTE texture_load_128bpb_cs[] = { - 68, 88, 66, 67, 66, 161, - 179, 56, 188, 255, 28, 7, - 128, 14, 115, 238, 225, 104, - 134, 174, 1, 0, 0, 0, + 68, 88, 66, 67, 241, 77, + 228, 180, 14, 79, 137, 13, + 157, 93, 94, 179, 125, 141, + 65, 44, 1, 0, 0, 0, 68, 19, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -365,7 +365,7 @@ const BYTE texture_load_128bpb_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 5, 0, 0, 0, 155, 0, 0, 4, - 16, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_128bpb_scaled_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_128bpb_scaled_cs.h index b3df0ceca..14e6cbfab 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_128bpb_scaled_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_128bpb_scaled_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 5 -dcl_thread_group 16, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(1) mov r0.y, vThreadID.y uge r0.zw, r0.xxxy, CB0[0][1].xxxy @@ -174,10 +174,10 @@ ret const BYTE texture_load_128bpb_scaled_cs[] = { - 68, 88, 66, 67, 157, 184, - 138, 101, 96, 50, 203, 155, - 85, 158, 177, 53, 241, 194, - 17, 97, 1, 0, 0, 0, + 68, 88, 66, 67, 28, 151, + 105, 189, 132, 41, 87, 165, + 206, 61, 242, 107, 60, 102, + 130, 2, 1, 0, 0, 0, 136, 20, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -376,7 +376,7 @@ const BYTE texture_load_128bpb_scaled_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 5, 0, 0, 0, 155, 0, 0, 4, - 16, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_16bpb_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_16bpb_cs.h index 9ff1b68d0..eba4a1a14 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_16bpb_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_16bpb_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 5 -dcl_thread_group 2, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(4) mov r0.y, vThreadID.y uge r0.yz, r0.xxyx, CB0[0][1].xxyx @@ -149,10 +149,10 @@ ret const BYTE texture_load_16bpb_cs[] = { - 68, 88, 66, 67, 3, 53, - 195, 71, 253, 83, 49, 166, - 57, 124, 131, 59, 142, 42, - 135, 128, 1, 0, 0, 0, + 68, 88, 66, 67, 19, 156, + 73, 177, 105, 201, 0, 54, + 30, 160, 82, 37, 25, 91, + 0, 78, 1, 0, 0, 0, 4, 17, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -351,7 +351,7 @@ const BYTE texture_load_16bpb_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 5, 0, 0, 0, 155, 0, 0, 4, - 2, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_16bpb_scaled_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_16bpb_scaled_cs.h index e3dcac0cf..78022ac11 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_16bpb_scaled_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_16bpb_scaled_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 6 -dcl_thread_group 2, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(4) mov r0.y, vThreadID.y uge r0.yz, r0.xxyx, CB0[0][1].xxyx @@ -162,10 +162,10 @@ ret const BYTE texture_load_16bpb_scaled_cs[] = { - 68, 88, 66, 67, 47, 251, - 141, 86, 24, 33, 181, 188, - 23, 195, 184, 105, 11, 20, - 88, 69, 1, 0, 0, 0, + 68, 88, 66, 67, 189, 222, + 224, 222, 247, 165, 199, 235, + 252, 20, 191, 179, 202, 163, + 51, 248, 1, 0, 0, 0, 232, 18, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -364,7 +364,7 @@ const BYTE texture_load_16bpb_scaled_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 6, 0, 0, 0, 155, 0, 0, 4, - 2, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_64bpb_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_64bpb_cs.h index 0942855a5..1951184eb 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_64bpb_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_64bpb_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 5 -dcl_thread_group 8, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(2) mov r0.y, vThreadID.y uge r0.yz, r0.xxyx, CB0[0][1].xxyx @@ -163,10 +163,10 @@ ret const BYTE texture_load_64bpb_cs[] = { - 68, 88, 66, 67, 231, 35, - 194, 189, 143, 150, 238, 118, - 238, 161, 76, 22, 190, 227, - 170, 14, 1, 0, 0, 0, + 68, 88, 66, 67, 108, 228, + 16, 85, 154, 219, 50, 29, + 190, 1, 95, 243, 12, 156, + 37, 115, 1, 0, 0, 0, 80, 19, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -365,7 +365,7 @@ const BYTE texture_load_64bpb_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 5, 0, 0, 0, 155, 0, 0, 4, - 8, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_64bpb_scaled_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_64bpb_scaled_cs.h index d69375bf3..4a3cf5000 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_64bpb_scaled_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_64bpb_scaled_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 6 -dcl_thread_group 8, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(2) mov r0.y, vThreadID.y uge r0.yz, r0.xxyx, CB0[0][1].xxyx @@ -179,10 +179,10 @@ ret const BYTE texture_load_64bpb_scaled_cs[] = { - 68, 88, 66, 67, 139, 87, - 71, 225, 193, 203, 129, 152, - 68, 60, 27, 36, 135, 81, - 18, 94, 1, 0, 0, 0, + 68, 88, 66, 67, 74, 59, + 137, 121, 93, 62, 64, 66, + 58, 206, 207, 85, 104, 121, + 108, 88, 1, 0, 0, 0, 84, 21, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -381,7 +381,7 @@ const BYTE texture_load_64bpb_scaled_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 6, 0, 0, 0, 155, 0, 0, 4, - 8, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_8bpb_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_8bpb_cs.h index b9e51eece..f9de63c95 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_8bpb_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_8bpb_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 3 -dcl_thread_group 2, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(4) mov r0.y, vThreadID.y uge r0.yz, r0.xxyx, CB0[0][1].xxyx @@ -138,10 +138,10 @@ ret const BYTE texture_load_8bpb_cs[] = { - 68, 88, 66, 67, 73, 208, - 195, 63, 64, 126, 134, 87, - 227, 131, 70, 30, 224, 97, - 168, 220, 1, 0, 0, 0, + 68, 88, 66, 67, 117, 104, + 174, 57, 54, 17, 124, 211, + 120, 21, 220, 160, 25, 233, + 104, 252, 1, 0, 0, 0, 12, 16, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -340,7 +340,7 @@ const BYTE texture_load_8bpb_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 3, 0, 0, 0, 155, 0, 0, 4, - 2, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_8bpb_scaled_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_8bpb_scaled_cs.h index 98488d4e2..39736dfe8 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_8bpb_scaled_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_8bpb_scaled_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 5 -dcl_thread_group 2, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(4) mov r0.y, vThreadID.y uge r0.yz, r0.xxyx, CB0[0][1].xxyx @@ -150,10 +150,10 @@ ret const BYTE texture_load_8bpb_scaled_cs[] = { - 68, 88, 66, 67, 137, 124, - 211, 255, 193, 18, 172, 106, - 100, 61, 126, 121, 49, 36, - 122, 56, 1, 0, 0, 0, + 68, 88, 66, 67, 9, 151, + 191, 205, 75, 177, 78, 3, + 60, 197, 148, 53, 131, 89, + 195, 103, 1, 0, 0, 0, 228, 17, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -352,7 +352,7 @@ const BYTE texture_load_8bpb_scaled_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 5, 0, 0, 0, 155, 0, 0, 4, - 2, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_ctx1_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_ctx1_cs.h index f012d4a56..4658db2e0 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_ctx1_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_ctx1_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 8 -dcl_thread_group 8, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(2) mov r0.y, vThreadID.y uge r0.zw, r0.xxxy, CB0[0][1].xxxy @@ -497,10 +497,10 @@ ret const BYTE texture_load_ctx1_cs[] = { - 68, 88, 66, 67, 220, 20, - 228, 109, 3, 0, 42, 140, - 106, 207, 155, 82, 115, 92, - 184, 29, 1, 0, 0, 0, + 68, 88, 66, 67, 195, 165, + 84, 20, 143, 208, 161, 157, + 218, 200, 160, 149, 211, 193, + 242, 146, 1, 0, 0, 0, 92, 65, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -699,7 +699,7 @@ const BYTE texture_load_ctx1_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 8, 0, 0, 0, 155, 0, 0, 4, - 8, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_dxn_rg8_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_dxn_rg8_cs.h index ccd189f70..4e7452bde 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_dxn_rg8_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_dxn_rg8_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 19 -dcl_thread_group 16, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(1) mov r0.y, vThreadID.y uge r0.zw, r0.xxxy, CB0[0][1].xxxy @@ -755,10 +755,10 @@ ret const BYTE texture_load_dxn_rg8_cs[] = { - 68, 88, 66, 67, 66, 65, - 254, 206, 210, 1, 70, 18, - 99, 171, 203, 179, 168, 99, - 250, 203, 1, 0, 0, 0, + 68, 88, 66, 67, 116, 218, + 57, 138, 30, 63, 167, 44, + 135, 12, 68, 200, 116, 134, + 54, 227, 1, 0, 0, 0, 128, 107, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -957,7 +957,7 @@ const BYTE texture_load_dxn_rg8_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 19, 0, 0, 0, 155, 0, 0, 4, - 16, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_dxt1_rgba8_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_dxt1_rgba8_cs.h index 25d7009bb..174a7e261 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_dxt1_rgba8_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_dxt1_rgba8_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 16 -dcl_thread_group 8, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(2) mov r0.y, vThreadID.y uge r0.zw, r0.xxxy, CB0[0][1].xxxy @@ -963,10 +963,10 @@ ret const BYTE texture_load_dxt1_rgba8_cs[] = { - 68, 88, 66, 67, 35, 48, - 77, 62, 46, 90, 199, 121, - 212, 16, 32, 221, 98, 216, - 129, 21, 1, 0, 0, 0, + 68, 88, 66, 67, 168, 164, + 3, 37, 141, 217, 122, 4, + 64, 190, 42, 138, 121, 126, + 40, 162, 1, 0, 0, 0, 48, 139, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -1165,7 +1165,7 @@ const BYTE texture_load_dxt1_rgba8_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 16, 0, 0, 0, 155, 0, 0, 4, - 8, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_dxt3_rgba8_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_dxt3_rgba8_cs.h index 342311fd7..1d91d9749 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_dxt3_rgba8_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_dxt3_rgba8_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 8 -dcl_thread_group 16, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(1) mov r0.y, vThreadID.y uge r0.zw, r0.xxxy, CB0[0][1].xxxy @@ -401,10 +401,10 @@ ret const BYTE texture_load_dxt3_rgba8_cs[] = { - 68, 88, 66, 67, 90, 62, - 112, 33, 89, 123, 143, 246, - 182, 121, 135, 170, 241, 137, - 153, 219, 1, 0, 0, 0, + 68, 88, 66, 67, 221, 162, + 221, 172, 118, 227, 248, 121, + 138, 108, 34, 48, 107, 56, + 138, 82, 1, 0, 0, 0, 176, 53, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -603,7 +603,7 @@ const BYTE texture_load_dxt3_rgba8_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 8, 0, 0, 0, 155, 0, 0, 4, - 16, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_dxt3a_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_dxt3a_cs.h index b2a46b3d7..d3ec307df 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_dxt3a_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_dxt3a_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 7 -dcl_thread_group 8, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(2) mov r0.y, vThreadID.y uge r0.zw, r0.xxxy, CB0[0][1].xxxy @@ -222,10 +222,10 @@ ret const BYTE texture_load_dxt3a_cs[] = { - 68, 88, 66, 67, 130, 214, - 11, 45, 162, 117, 89, 83, - 222, 115, 81, 72, 115, 95, - 110, 65, 1, 0, 0, 0, + 68, 88, 66, 67, 84, 23, + 8, 117, 124, 43, 39, 88, + 10, 38, 3, 178, 82, 80, + 106, 166, 1, 0, 0, 0, 184, 28, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -424,7 +424,7 @@ const BYTE texture_load_dxt3a_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 7, 0, 0, 0, 155, 0, 0, 4, - 8, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_dxt3aas1111_argb4_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_dxt3aas1111_argb4_cs.h index 670fd7e3d..30593bd7e 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_dxt3aas1111_argb4_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_dxt3aas1111_argb4_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 9 -dcl_thread_group 8, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(2) mov r0.y, vThreadID.y uge r0.zw, r0.xxxy, CB0[0][1].xxxy @@ -403,10 +403,10 @@ ret const BYTE texture_load_dxt3aas1111_argb4_cs[] = { - 68, 88, 66, 67, 158, 202, - 195, 92, 73, 5, 212, 26, - 109, 12, 51, 118, 39, 233, - 156, 49, 1, 0, 0, 0, + 68, 88, 66, 67, 252, 251, + 35, 71, 172, 126, 7, 192, + 94, 52, 25, 231, 237, 30, + 165, 228, 1, 0, 0, 0, 60, 65, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -605,7 +605,7 @@ const BYTE texture_load_dxt3aas1111_argb4_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 9, 0, 0, 0, 155, 0, 0, 4, - 8, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_dxt3aas1111_bgra4_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_dxt3aas1111_bgra4_cs.h index abc85d45a..fbc1621a7 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_dxt3aas1111_bgra4_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_dxt3aas1111_bgra4_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 8 -dcl_thread_group 8, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(2) mov r0.y, vThreadID.y uge r0.zw, r0.xxxy, CB0[0][1].xxxy @@ -387,10 +387,10 @@ ret const BYTE texture_load_dxt3aas1111_bgra4_cs[] = { - 68, 88, 66, 67, 7, 219, - 254, 199, 108, 155, 230, 211, - 206, 89, 99, 210, 111, 24, - 155, 76, 1, 0, 0, 0, + 68, 88, 66, 67, 101, 36, + 240, 2, 58, 233, 10, 60, + 67, 45, 23, 145, 147, 13, + 72, 229, 1, 0, 0, 0, 92, 60, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -589,7 +589,7 @@ const BYTE texture_load_dxt3aas1111_bgra4_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 8, 0, 0, 0, 155, 0, 0, 4, - 8, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_dxt5_rgba8_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_dxt5_rgba8_cs.h index 17582339d..4a5bdc945 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_dxt5_rgba8_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_dxt5_rgba8_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 8 -dcl_thread_group 16, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(1) mov r0.y, vThreadID.y uge r0.zw, r0.xxxy, CB0[0][1].xxxy @@ -903,10 +903,10 @@ ret const BYTE texture_load_dxt5_rgba8_cs[] = { - 68, 88, 66, 67, 131, 51, - 110, 163, 67, 171, 12, 226, - 105, 12, 255, 177, 137, 62, - 160, 56, 1, 0, 0, 0, + 68, 88, 66, 67, 63, 83, + 123, 36, 135, 43, 232, 70, + 138, 99, 93, 184, 30, 171, + 42, 194, 1, 0, 0, 0, 112, 117, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -1105,7 +1105,7 @@ const BYTE texture_load_dxt5_rgba8_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 8, 0, 0, 0, 155, 0, 0, 4, - 16, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_dxt5a_r8_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_dxt5a_r8_cs.h index aa060e002..7d44d7f0e 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_dxt5a_r8_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_dxt5a_r8_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 19 -dcl_thread_group 8, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(2) mov r0.y, vThreadID.y uge r0.zw, r0.xxxy, CB0[0][1].xxxy @@ -819,10 +819,10 @@ ret const BYTE texture_load_dxt5a_r8_cs[] = { - 68, 88, 66, 67, 156, 43, - 145, 68, 199, 134, 36, 11, - 240, 214, 14, 154, 70, 18, - 254, 100, 1, 0, 0, 0, + 68, 88, 66, 67, 102, 74, + 10, 179, 206, 197, 61, 30, + 143, 180, 81, 162, 28, 68, + 29, 52, 1, 0, 0, 0, 12, 112, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -1021,7 +1021,7 @@ const BYTE texture_load_dxt5a_r8_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 19, 0, 0, 0, 155, 0, 0, 4, - 8, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r16_snorm_float_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r16_snorm_float_cs.h index 964ed04f8..dc497a342 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r16_snorm_float_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r16_snorm_float_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 5 -dcl_thread_group 2, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(4) mov r0.y, vThreadID.y uge r0.yz, r0.xxyx, CB0[0][1].xxyx @@ -171,10 +171,10 @@ ret const BYTE texture_load_r16_snorm_float_cs[] = { - 68, 88, 66, 67, 18, 137, - 159, 251, 176, 85, 139, 88, - 42, 171, 60, 212, 145, 226, - 210, 158, 1, 0, 0, 0, + 68, 88, 66, 67, 213, 20, + 32, 150, 241, 192, 218, 105, + 204, 171, 108, 205, 213, 18, + 71, 191, 1, 0, 0, 0, 12, 20, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -373,7 +373,7 @@ const BYTE texture_load_r16_snorm_float_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 5, 0, 0, 0, 155, 0, 0, 4, - 2, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r16_snorm_float_scaled_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r16_snorm_float_scaled_cs.h index 612766d46..7824315f4 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r16_snorm_float_scaled_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r16_snorm_float_scaled_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 6 -dcl_thread_group 2, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(4) mov r0.y, vThreadID.y uge r0.yz, r0.xxyx, CB0[0][1].xxyx @@ -184,10 +184,10 @@ ret const BYTE texture_load_r16_snorm_float_scaled_cs[] = { - 68, 88, 66, 67, 178, 183, - 93, 91, 40, 72, 164, 231, - 152, 39, 172, 195, 143, 247, - 13, 122, 1, 0, 0, 0, + 68, 88, 66, 67, 105, 29, + 204, 74, 59, 55, 155, 169, + 67, 5, 2, 162, 188, 129, + 111, 176, 1, 0, 0, 0, 240, 21, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -386,7 +386,7 @@ const BYTE texture_load_r16_snorm_float_scaled_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 6, 0, 0, 0, 155, 0, 0, 4, - 2, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r16_unorm_float_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r16_unorm_float_cs.h index aac826ac1..99fe763f3 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r16_unorm_float_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r16_unorm_float_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 5 -dcl_thread_group 2, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(4) mov r0.y, vThreadID.y uge r0.yz, r0.xxyx, CB0[0][1].xxyx @@ -167,10 +167,10 @@ ret const BYTE texture_load_r16_unorm_float_cs[] = { - 68, 88, 66, 67, 123, 10, - 201, 118, 4, 125, 207, 228, - 231, 50, 233, 244, 245, 16, - 251, 18, 1, 0, 0, 0, + 68, 88, 66, 67, 84, 17, + 38, 108, 82, 141, 188, 58, + 243, 3, 112, 206, 27, 147, + 254, 121, 1, 0, 0, 0, 68, 19, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -369,7 +369,7 @@ const BYTE texture_load_r16_unorm_float_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 5, 0, 0, 0, 155, 0, 0, 4, - 2, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r16_unorm_float_scaled_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r16_unorm_float_scaled_cs.h index bd87d79bf..dee411922 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r16_unorm_float_scaled_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r16_unorm_float_scaled_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 6 -dcl_thread_group 2, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(4) mov r0.y, vThreadID.y uge r0.yz, r0.xxyx, CB0[0][1].xxyx @@ -180,10 +180,10 @@ ret const BYTE texture_load_r16_unorm_float_scaled_cs[] = { - 68, 88, 66, 67, 6, 80, - 139, 179, 86, 27, 112, 216, - 5, 182, 37, 135, 137, 109, - 109, 7, 1, 0, 0, 0, + 68, 88, 66, 67, 6, 67, + 188, 245, 79, 114, 113, 43, + 185, 113, 116, 43, 89, 21, + 120, 94, 1, 0, 0, 0, 40, 21, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -382,7 +382,7 @@ const BYTE texture_load_r16_unorm_float_scaled_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 6, 0, 0, 0, 155, 0, 0, 4, - 2, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r4g4b4a4_a4r4g4b4_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r4g4b4a4_a4r4g4b4_cs.h index 7af7b18a3..c1a40bcbb 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r4g4b4a4_a4r4g4b4_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r4g4b4a4_a4r4g4b4_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 5 -dcl_thread_group 2, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(4) mov r0.y, vThreadID.y uge r0.yz, r0.xxyx, CB0[0][1].xxyx @@ -159,10 +159,10 @@ ret const BYTE texture_load_r4g4b4a4_a4r4g4b4_cs[] = { - 68, 88, 66, 67, 97, 198, - 223, 170, 99, 139, 58, 208, - 11, 208, 69, 79, 179, 170, - 157, 125, 1, 0, 0, 0, + 68, 88, 66, 67, 203, 228, + 168, 254, 181, 239, 117, 145, + 208, 38, 240, 120, 1, 241, + 21, 133, 1, 0, 0, 0, 124, 18, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -361,7 +361,7 @@ const BYTE texture_load_r4g4b4a4_a4r4g4b4_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 5, 0, 0, 0, 155, 0, 0, 4, - 2, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r4g4b4a4_a4r4g4b4_scaled_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r4g4b4a4_a4r4g4b4_scaled_cs.h index f537e85b1..c3ed08d0c 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r4g4b4a4_a4r4g4b4_scaled_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r4g4b4a4_a4r4g4b4_scaled_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 6 -dcl_thread_group 2, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(4) mov r0.y, vThreadID.y uge r0.yz, r0.xxyx, CB0[0][1].xxyx @@ -172,10 +172,10 @@ ret const BYTE texture_load_r4g4b4a4_a4r4g4b4_scaled_cs[] = { - 68, 88, 66, 67, 252, 124, - 132, 129, 206, 181, 86, 54, - 219, 106, 131, 147, 93, 47, - 74, 222, 1, 0, 0, 0, + 68, 88, 66, 67, 123, 45, + 247, 94, 237, 45, 202, 205, + 243, 146, 50, 186, 143, 134, + 20, 230, 1, 0, 0, 0, 96, 20, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -374,7 +374,7 @@ const BYTE texture_load_r4g4b4a4_a4r4g4b4_scaled_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 6, 0, 0, 0, 155, 0, 0, 4, - 2, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r4g4b4a4_b4g4r4a4_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r4g4b4a4_b4g4r4a4_cs.h index e2ee0a7dd..7e302094e 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r4g4b4a4_b4g4r4a4_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r4g4b4a4_b4g4r4a4_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 5 -dcl_thread_group 2, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(4) mov r0.y, vThreadID.y uge r0.yz, r0.xxyx, CB0[0][1].xxyx @@ -163,10 +163,10 @@ ret const BYTE texture_load_r4g4b4a4_b4g4r4a4_cs[] = { - 68, 88, 66, 67, 155, 134, - 92, 142, 4, 206, 17, 79, - 36, 135, 210, 9, 246, 149, - 211, 120, 1, 0, 0, 0, + 68, 88, 66, 67, 1, 168, + 242, 28, 152, 188, 87, 155, + 62, 248, 187, 184, 16, 39, + 170, 141, 1, 0, 0, 0, 4, 19, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -365,7 +365,7 @@ const BYTE texture_load_r4g4b4a4_b4g4r4a4_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 5, 0, 0, 0, 155, 0, 0, 4, - 2, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r4g4b4a4_b4g4r4a4_scaled_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r4g4b4a4_b4g4r4a4_scaled_cs.h index 867081687..26f005c84 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r4g4b4a4_b4g4r4a4_scaled_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r4g4b4a4_b4g4r4a4_scaled_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 6 -dcl_thread_group 2, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(4) mov r0.y, vThreadID.y uge r0.yz, r0.xxyx, CB0[0][1].xxyx @@ -176,10 +176,10 @@ ret const BYTE texture_load_r4g4b4a4_b4g4r4a4_scaled_cs[] = { - 68, 88, 66, 67, 224, 114, - 69, 211, 90, 132, 121, 223, - 125, 217, 243, 63, 64, 212, - 101, 178, 1, 0, 0, 0, + 68, 88, 66, 67, 122, 140, + 111, 247, 166, 135, 146, 187, + 197, 244, 3, 242, 189, 237, + 186, 24, 1, 0, 0, 0, 232, 20, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -378,7 +378,7 @@ const BYTE texture_load_r4g4b4a4_b4g4r4a4_scaled_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 6, 0, 0, 0, 155, 0, 0, 4, - 2, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r5g5b5a1_b5g5r5a1_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r5g5b5a1_b5g5r5a1_cs.h index 4e6274ca6..706d2b676 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r5g5b5a1_b5g5r5a1_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r5g5b5a1_b5g5r5a1_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 5 -dcl_thread_group 2, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(4) mov r0.y, vThreadID.y uge r0.yz, r0.xxyx, CB0[0][1].xxyx @@ -163,10 +163,10 @@ ret const BYTE texture_load_r5g5b5a1_b5g5r5a1_cs[] = { - 68, 88, 66, 67, 210, 15, - 205, 192, 67, 68, 90, 6, - 231, 14, 12, 38, 8, 162, - 146, 178, 1, 0, 0, 0, + 68, 88, 66, 67, 163, 52, + 227, 168, 115, 213, 149, 240, + 159, 70, 127, 10, 180, 24, + 174, 10, 1, 0, 0, 0, 4, 19, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -365,7 +365,7 @@ const BYTE texture_load_r5g5b5a1_b5g5r5a1_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 5, 0, 0, 0, 155, 0, 0, 4, - 2, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r5g5b5a1_b5g5r5a1_scaled_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r5g5b5a1_b5g5r5a1_scaled_cs.h index 9e06398b5..fd98f8751 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r5g5b5a1_b5g5r5a1_scaled_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r5g5b5a1_b5g5r5a1_scaled_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 6 -dcl_thread_group 2, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(4) mov r0.y, vThreadID.y uge r0.yz, r0.xxyx, CB0[0][1].xxyx @@ -176,10 +176,10 @@ ret const BYTE texture_load_r5g5b5a1_b5g5r5a1_scaled_cs[] = { - 68, 88, 66, 67, 76, 241, - 22, 31, 36, 208, 102, 246, - 131, 111, 104, 135, 216, 142, - 172, 246, 1, 0, 0, 0, + 68, 88, 66, 67, 215, 18, + 93, 255, 38, 158, 12, 115, + 157, 3, 87, 131, 56, 244, + 207, 140, 1, 0, 0, 0, 232, 20, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -378,7 +378,7 @@ const BYTE texture_load_r5g5b5a1_b5g5r5a1_scaled_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 6, 0, 0, 0, 155, 0, 0, 4, - 2, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r5g5b6_b5g6r5_swizzle_rbga_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r5g5b6_b5g6r5_swizzle_rbga_cs.h index 165f2b9a6..4882bb47b 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r5g5b6_b5g6r5_swizzle_rbga_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r5g5b6_b5g6r5_swizzle_rbga_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 5 -dcl_thread_group 2, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(4) mov r0.y, vThreadID.y uge r0.yz, r0.xxyx, CB0[0][1].xxyx @@ -159,10 +159,10 @@ ret const BYTE texture_load_r5g5b6_b5g6r5_swizzle_rbga_cs[] = { - 68, 88, 66, 67, 165, 13, - 164, 49, 120, 178, 143, 129, - 21, 166, 240, 185, 211, 8, - 191, 202, 1, 0, 0, 0, + 68, 88, 66, 67, 207, 189, + 118, 180, 249, 133, 101, 55, + 64, 248, 132, 149, 201, 192, + 78, 198, 1, 0, 0, 0, 124, 18, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -361,7 +361,7 @@ const BYTE texture_load_r5g5b6_b5g6r5_swizzle_rbga_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 5, 0, 0, 0, 155, 0, 0, 4, - 2, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r5g5b6_b5g6r5_swizzle_rbga_scaled_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r5g5b6_b5g6r5_swizzle_rbga_scaled_cs.h index 5f8080155..7930b9919 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r5g5b6_b5g6r5_swizzle_rbga_scaled_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r5g5b6_b5g6r5_swizzle_rbga_scaled_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 6 -dcl_thread_group 2, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(4) mov r0.y, vThreadID.y uge r0.yz, r0.xxyx, CB0[0][1].xxyx @@ -172,10 +172,10 @@ ret const BYTE texture_load_r5g5b6_b5g6r5_swizzle_rbga_scaled_cs[] = { - 68, 88, 66, 67, 106, 156, - 117, 55, 247, 36, 48, 214, - 201, 110, 63, 182, 107, 227, - 119, 97, 1, 0, 0, 0, + 68, 88, 66, 67, 201, 205, + 4, 236, 3, 161, 24, 92, + 130, 65, 46, 189, 195, 74, + 237, 56, 1, 0, 0, 0, 96, 20, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -374,7 +374,7 @@ const BYTE texture_load_r5g5b6_b5g6r5_swizzle_rbga_scaled_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 6, 0, 0, 0, 155, 0, 0, 4, - 2, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r5g6b5_b5g6r5_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r5g6b5_b5g6r5_cs.h index e9c576a96..4d243b241 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r5g6b5_b5g6r5_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r5g6b5_b5g6r5_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 5 -dcl_thread_group 2, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(4) mov r0.y, vThreadID.y uge r0.yz, r0.xxyx, CB0[0][1].xxyx @@ -163,10 +163,10 @@ ret const BYTE texture_load_r5g6b5_b5g6r5_cs[] = { - 68, 88, 66, 67, 28, 243, - 234, 181, 0, 206, 247, 163, - 108, 70, 228, 92, 121, 98, - 101, 40, 1, 0, 0, 0, + 68, 88, 66, 67, 107, 4, + 228, 37, 186, 249, 219, 152, + 175, 129, 84, 40, 196, 172, + 171, 255, 1, 0, 0, 0, 4, 19, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -365,7 +365,7 @@ const BYTE texture_load_r5g6b5_b5g6r5_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 5, 0, 0, 0, 155, 0, 0, 4, - 2, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r5g6b5_b5g6r5_scaled_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r5g6b5_b5g6r5_scaled_cs.h index f69b64272..5962563c3 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r5g6b5_b5g6r5_scaled_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_r5g6b5_b5g6r5_scaled_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 6 -dcl_thread_group 2, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(4) mov r0.y, vThreadID.y uge r0.yz, r0.xxyx, CB0[0][1].xxyx @@ -176,10 +176,10 @@ ret const BYTE texture_load_r5g6b5_b5g6r5_scaled_cs[] = { - 68, 88, 66, 67, 245, 88, - 76, 185, 45, 229, 100, 17, - 157, 204, 236, 175, 63, 171, - 98, 191, 1, 0, 0, 0, + 68, 88, 66, 67, 192, 250, + 177, 53, 225, 112, 242, 9, + 238, 80, 136, 107, 221, 234, + 39, 48, 1, 0, 0, 0, 232, 20, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -378,7 +378,7 @@ const BYTE texture_load_r5g6b5_b5g6r5_scaled_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 6, 0, 0, 0, 155, 0, 0, 4, - 2, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_rgba16_snorm_float_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_rgba16_snorm_float_cs.h index 996fc5ed5..557437a97 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_rgba16_snorm_float_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_rgba16_snorm_float_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 5 -dcl_thread_group 8, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(2) mov r0.y, vThreadID.y uge r0.yz, r0.xxyx, CB0[0][1].xxyx @@ -185,10 +185,10 @@ ret const BYTE texture_load_rgba16_snorm_float_cs[] = { - 68, 88, 66, 67, 130, 84, - 147, 165, 41, 150, 201, 188, - 240, 11, 180, 52, 244, 252, - 250, 246, 1, 0, 0, 0, + 68, 88, 66, 67, 91, 175, + 48, 102, 17, 226, 165, 118, + 162, 155, 35, 75, 247, 35, + 254, 225, 1, 0, 0, 0, 88, 22, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -387,7 +387,7 @@ const BYTE texture_load_rgba16_snorm_float_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 5, 0, 0, 0, 155, 0, 0, 4, - 8, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_rgba16_snorm_float_scaled_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_rgba16_snorm_float_scaled_cs.h index 5af148885..05e339434 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_rgba16_snorm_float_scaled_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_rgba16_snorm_float_scaled_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 6 -dcl_thread_group 8, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(2) mov r0.y, vThreadID.y uge r0.yz, r0.xxyx, CB0[0][1].xxyx @@ -201,10 +201,10 @@ ret const BYTE texture_load_rgba16_snorm_float_scaled_cs[] = { - 68, 88, 66, 67, 216, 73, - 96, 144, 35, 222, 144, 90, - 206, 71, 120, 215, 76, 200, - 160, 161, 1, 0, 0, 0, + 68, 88, 66, 67, 188, 192, + 143, 236, 161, 132, 223, 101, + 119, 138, 119, 49, 238, 72, + 51, 194, 1, 0, 0, 0, 92, 24, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -403,7 +403,7 @@ const BYTE texture_load_rgba16_snorm_float_scaled_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 6, 0, 0, 0, 155, 0, 0, 4, - 8, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_rgba16_unorm_float_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_rgba16_unorm_float_cs.h index 73368816c..372278a43 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_rgba16_unorm_float_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_rgba16_unorm_float_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 5 -dcl_thread_group 8, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(2) mov r0.y, vThreadID.y uge r0.yz, r0.xxyx, CB0[0][1].xxyx @@ -181,10 +181,10 @@ ret const BYTE texture_load_rgba16_unorm_float_cs[] = { - 68, 88, 66, 67, 147, 28, - 136, 178, 186, 243, 81, 210, - 67, 134, 132, 64, 208, 151, - 255, 0, 1, 0, 0, 0, + 68, 88, 66, 67, 241, 5, + 159, 229, 39, 194, 63, 85, + 189, 178, 237, 54, 38, 21, + 161, 135, 1, 0, 0, 0, 144, 21, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -383,7 +383,7 @@ const BYTE texture_load_rgba16_unorm_float_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 5, 0, 0, 0, 155, 0, 0, 4, - 8, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_rgba16_unorm_float_scaled_cs.h b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_rgba16_unorm_float_scaled_cs.h index af3616713..2b6fbf743 100644 --- a/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_rgba16_unorm_float_scaled_cs.h +++ b/src/xenia/gpu/shaders/bytecode/d3d12_5_1/texture_load_rgba16_unorm_float_scaled_cs.h @@ -48,7 +48,7 @@ dcl_resource_buffer (uint,uint,uint,uint) T0[0:0], space=0 dcl_uav_typed_buffer (uint,uint,uint,uint) U0[0:0], space=0 dcl_input vThreadID.xyz dcl_temps 6 -dcl_thread_group 8, 32, 1 +dcl_thread_group 4, 32, 1 ishl r0.x, vThreadID.x, l(2) mov r0.y, vThreadID.y uge r0.yz, r0.xxyx, CB0[0][1].xxyx @@ -197,10 +197,10 @@ ret const BYTE texture_load_rgba16_unorm_float_scaled_cs[] = { - 68, 88, 66, 67, 78, 163, - 84, 208, 189, 134, 83, 8, - 242, 151, 68, 185, 146, 223, - 239, 209, 1, 0, 0, 0, + 68, 88, 66, 67, 199, 193, + 214, 223, 137, 62, 103, 64, + 39, 247, 21, 148, 222, 7, + 163, 228, 1, 0, 0, 0, 148, 23, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 32, 4, 0, 0, 48, 4, @@ -399,7 +399,7 @@ const BYTE texture_load_rgba16_unorm_float_scaled_cs[] = 0, 2, 114, 0, 2, 0, 104, 0, 0, 2, 6, 0, 0, 0, 155, 0, 0, 4, - 8, 0, 0, 0, 32, 0, + 4, 0, 0, 0, 32, 0, 0, 0, 1, 0, 0, 0, 41, 0, 0, 6, 18, 0, 16, 0, 0, 0, 0, 0, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_128bpb_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_128bpb_cs.h index 6b7d0a805..47b19b523 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_128bpb_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_128bpb_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 16 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -92,7 +92,7 @@ %_ptr_Uniform__struct_1973 = OpTypePointer Uniform %_struct_1973 %4218 = OpVariable %_ptr_Uniform__struct_1973 Uniform %_ptr_Uniform_v4uint = OpTypePointer Uniform %v4uint -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_16 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %uint_10 = OpConstant %uint 10 %uint_11 = OpConstant %uint 11 %2510 = OpConstantComposite %v4uint %uint_16711935 %uint_16711935 %uint_16711935 %uint_16711935 @@ -344,7 +344,7 @@ const uint32_t texture_load_128bpb_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000010, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -362,7 +362,7 @@ const uint32_t texture_load_128bpb_cs[] = { 0x00000018, 0x00050048, 0x000007B5, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007B5, 0x00000003, 0x00040047, 0x0000107A, 0x00000022, 0x00000001, 0x00040047, 0x0000107A, 0x00000021, 0x00000000, 0x00040047, - 0x0000006C, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000017, 0x0000000B, 0x00000004, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, 0x00040017, 0x00000012, 0x0000000C, 0x00000002, @@ -400,7 +400,7 @@ const uint32_t texture_load_128bpb_cs[] = { 0x0000140E, 0x00000002, 0x0003001D, 0x000007DD, 0x00000017, 0x0003001E, 0x000007B5, 0x000007DD, 0x00040020, 0x00000A32, 0x00000002, 0x000007B5, 0x0004003B, 0x00000A32, 0x0000107A, 0x00000002, 0x00040020, 0x00000294, - 0x00000002, 0x00000017, 0x0006002C, 0x00000014, 0x0000006C, 0x00000A3A, + 0x00000002, 0x00000017, 0x0006002C, 0x00000014, 0x00000BC3, 0x00000A16, 0x00000A6A, 0x00000A0D, 0x0004002B, 0x0000000B, 0x00000A28, 0x0000000A, 0x0004002B, 0x0000000B, 0x00000A2B, 0x0000000B, 0x0007002C, 0x00000017, 0x000009CE, 0x000008A6, 0x000008A6, 0x000008A6, 0x000008A6, 0x0007002C, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_128bpb_scaled_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_128bpb_scaled_cs.h index 9cfc8571c..1cecdc730 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_128bpb_scaled_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_128bpb_scaled_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 16 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -94,7 +94,7 @@ %_ptr_Uniform__struct_1973 = OpTypePointer Uniform %_struct_1973 %4218 = OpVariable %_ptr_Uniform__struct_1973 Uniform %_ptr_Uniform_v4uint = OpTypePointer Uniform %v4uint -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_16 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %1870 = OpConstantComposite %v2uint %uint_3 %uint_3 %uint_10 = OpConstant %uint 10 %uint_11 = OpConstant %uint 11 @@ -381,7 +381,7 @@ const uint32_t texture_load_128bpb_scaled_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000010, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -399,7 +399,7 @@ const uint32_t texture_load_128bpb_scaled_cs[] = { 0x00000018, 0x00050048, 0x000007B5, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007B5, 0x00000003, 0x00040047, 0x0000107A, 0x00000022, 0x00000001, 0x00040047, 0x0000107A, 0x00000021, 0x00000000, 0x00040047, - 0x0000006C, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000017, 0x0000000B, 0x00000004, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, 0x00040017, 0x00000012, 0x0000000C, 0x00000002, @@ -439,7 +439,7 @@ const uint32_t texture_load_128bpb_scaled_cs[] = { 0x000007DD, 0x00000017, 0x0003001E, 0x000007B5, 0x000007DD, 0x00040020, 0x00000A32, 0x00000002, 0x000007B5, 0x0004003B, 0x00000A32, 0x0000107A, 0x00000002, 0x00040020, 0x00000294, 0x00000002, 0x00000017, 0x0006002C, - 0x00000014, 0x0000006C, 0x00000A3A, 0x00000A6A, 0x00000A0D, 0x0005002C, + 0x00000014, 0x00000BC3, 0x00000A16, 0x00000A6A, 0x00000A0D, 0x0005002C, 0x00000011, 0x0000074E, 0x00000A13, 0x00000A13, 0x0004002B, 0x0000000B, 0x00000A28, 0x0000000A, 0x0004002B, 0x0000000B, 0x00000A2B, 0x0000000B, 0x0007002C, 0x00000017, 0x000009CE, 0x000008A6, 0x000008A6, 0x000008A6, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_16bpb_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_16bpb_cs.h index 64a65dadc..915746563 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_16bpb_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_16bpb_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 2 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -93,7 +93,7 @@ %_ptr_Uniform__struct_1973 = OpTypePointer Uniform %_struct_1973 %4218 = OpVariable %_ptr_Uniform__struct_1973 Uniform %_ptr_Uniform_v4uint = OpTypePointer Uniform %v4uint -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_2 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %2510 = OpConstantComposite %v4uint %uint_16711935 %uint_16711935 %uint_16711935 %uint_16711935 %317 = OpConstantComposite %v4uint %uint_8 %uint_8 %uint_8 %uint_8 %1838 = OpConstantComposite %v4uint %uint_4278255360 %uint_4278255360 %uint_4278255360 %uint_4278255360 @@ -321,7 +321,7 @@ const uint32_t texture_load_16bpb_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000002, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -339,7 +339,7 @@ const uint32_t texture_load_16bpb_cs[] = { 0x00000018, 0x00050048, 0x000007B5, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007B5, 0x00000003, 0x00040047, 0x0000107A, 0x00000022, 0x00000001, 0x00040047, 0x0000107A, 0x00000021, 0x00000000, 0x00040047, - 0x00000BB1, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000017, 0x0000000B, 0x00000004, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, 0x00040017, 0x00000012, 0x0000000C, 0x00000002, @@ -378,7 +378,7 @@ const uint32_t texture_load_16bpb_cs[] = { 0x0003001D, 0x000007DD, 0x00000017, 0x0003001E, 0x000007B5, 0x000007DD, 0x00040020, 0x00000A32, 0x00000002, 0x000007B5, 0x0004003B, 0x00000A32, 0x0000107A, 0x00000002, 0x00040020, 0x00000294, 0x00000002, 0x00000017, - 0x0006002C, 0x00000014, 0x00000BB1, 0x00000A10, 0x00000A6A, 0x00000A0D, + 0x0006002C, 0x00000014, 0x00000BC3, 0x00000A16, 0x00000A6A, 0x00000A0D, 0x0007002C, 0x00000017, 0x000009CE, 0x000008A6, 0x000008A6, 0x000008A6, 0x000008A6, 0x0007002C, 0x00000017, 0x0000013D, 0x00000A22, 0x00000A22, 0x00000A22, 0x00000A22, 0x0007002C, 0x00000017, 0x0000072E, 0x000005FD, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_16bpb_scaled_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_16bpb_scaled_cs.h index 65fab7a63..523400dae 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_16bpb_scaled_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_16bpb_scaled_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 2 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -95,7 +95,7 @@ %_ptr_Uniform__struct_1973 = OpTypePointer Uniform %_struct_1973 %4218 = OpVariable %_ptr_Uniform__struct_1973 Uniform %_ptr_Uniform_v4uint = OpTypePointer Uniform %v4uint -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_2 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %1870 = OpConstantComposite %v2uint %uint_3 %uint_3 %2510 = OpConstantComposite %v4uint %uint_16711935 %uint_16711935 %uint_16711935 %uint_16711935 %317 = OpConstantComposite %v4uint %uint_8 %uint_8 %uint_8 %uint_8 @@ -360,7 +360,7 @@ const uint32_t texture_load_16bpb_scaled_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000002, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -378,7 +378,7 @@ const uint32_t texture_load_16bpb_scaled_cs[] = { 0x00000018, 0x00050048, 0x000007B5, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007B5, 0x00000003, 0x00040047, 0x0000107A, 0x00000022, 0x00000001, 0x00040047, 0x0000107A, 0x00000021, 0x00000000, 0x00040047, - 0x00000BB1, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000017, 0x0000000B, 0x00000004, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, 0x00040017, 0x00000012, 0x0000000C, 0x00000002, @@ -418,8 +418,8 @@ const uint32_t texture_load_16bpb_scaled_cs[] = { 0x00000A31, 0x0000140E, 0x00000002, 0x0003001D, 0x000007DD, 0x00000017, 0x0003001E, 0x000007B5, 0x000007DD, 0x00040020, 0x00000A32, 0x00000002, 0x000007B5, 0x0004003B, 0x00000A32, 0x0000107A, 0x00000002, 0x00040020, - 0x00000294, 0x00000002, 0x00000017, 0x0006002C, 0x00000014, 0x00000BB1, - 0x00000A10, 0x00000A6A, 0x00000A0D, 0x0005002C, 0x00000011, 0x0000074E, + 0x00000294, 0x00000002, 0x00000017, 0x0006002C, 0x00000014, 0x00000BC3, + 0x00000A16, 0x00000A6A, 0x00000A0D, 0x0005002C, 0x00000011, 0x0000074E, 0x00000A13, 0x00000A13, 0x0007002C, 0x00000017, 0x000009CE, 0x000008A6, 0x000008A6, 0x000008A6, 0x000008A6, 0x0007002C, 0x00000017, 0x0000013D, 0x00000A22, 0x00000A22, 0x00000A22, 0x00000A22, 0x0007002C, 0x00000017, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_64bpb_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_64bpb_cs.h index ae6f670aa..4f5bfc8a7 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_64bpb_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_64bpb_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 8 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -92,7 +92,7 @@ %_ptr_Uniform__struct_1973 = OpTypePointer Uniform %_struct_1973 %4218 = OpVariable %_ptr_Uniform__struct_1973 Uniform %_ptr_Uniform_v4uint = OpTypePointer Uniform %v4uint -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_8 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %uint_9 = OpConstant %uint 9 %uint_10 = OpConstant %uint 10 %2510 = OpConstantComposite %v4uint %uint_16711935 %uint_16711935 %uint_16711935 %uint_16711935 @@ -344,7 +344,7 @@ const uint32_t texture_load_64bpb_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000008, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -362,7 +362,7 @@ const uint32_t texture_load_64bpb_cs[] = { 0x00000018, 0x00050048, 0x000007B5, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007B5, 0x00000003, 0x00040047, 0x0000107A, 0x00000022, 0x00000001, 0x00040047, 0x0000107A, 0x00000021, 0x00000000, 0x00040047, - 0x00000024, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000017, 0x0000000B, 0x00000004, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, 0x00040017, 0x00000012, 0x0000000C, 0x00000002, @@ -400,7 +400,7 @@ const uint32_t texture_load_64bpb_cs[] = { 0x0000140E, 0x00000002, 0x0003001D, 0x000007DD, 0x00000017, 0x0003001E, 0x000007B5, 0x000007DD, 0x00040020, 0x00000A32, 0x00000002, 0x000007B5, 0x0004003B, 0x00000A32, 0x0000107A, 0x00000002, 0x00040020, 0x00000294, - 0x00000002, 0x00000017, 0x0006002C, 0x00000014, 0x00000024, 0x00000A22, + 0x00000002, 0x00000017, 0x0006002C, 0x00000014, 0x00000BC3, 0x00000A16, 0x00000A6A, 0x00000A0D, 0x0004002B, 0x0000000B, 0x00000A25, 0x00000009, 0x0004002B, 0x0000000B, 0x00000A28, 0x0000000A, 0x0007002C, 0x00000017, 0x000009CE, 0x000008A6, 0x000008A6, 0x000008A6, 0x000008A6, 0x0007002C, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_64bpb_scaled_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_64bpb_scaled_cs.h index 19a90d32d..1c648e0e1 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_64bpb_scaled_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_64bpb_scaled_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 8 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -94,7 +94,7 @@ %_ptr_Uniform__struct_1973 = OpTypePointer Uniform %_struct_1973 %4218 = OpVariable %_ptr_Uniform__struct_1973 Uniform %_ptr_Uniform_v4uint = OpTypePointer Uniform %v4uint -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_8 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %1870 = OpConstantComposite %v2uint %uint_3 %uint_3 %uint_9 = OpConstant %uint 9 %uint_10 = OpConstant %uint 10 @@ -383,7 +383,7 @@ const uint32_t texture_load_64bpb_scaled_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000008, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -401,7 +401,7 @@ const uint32_t texture_load_64bpb_scaled_cs[] = { 0x00000018, 0x00050048, 0x000007B5, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007B5, 0x00000003, 0x00040047, 0x0000107A, 0x00000022, 0x00000001, 0x00040047, 0x0000107A, 0x00000021, 0x00000000, 0x00040047, - 0x00000024, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000017, 0x0000000B, 0x00000004, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, 0x00040017, 0x00000012, 0x0000000C, 0x00000002, @@ -441,7 +441,7 @@ const uint32_t texture_load_64bpb_scaled_cs[] = { 0x000007DD, 0x00000017, 0x0003001E, 0x000007B5, 0x000007DD, 0x00040020, 0x00000A32, 0x00000002, 0x000007B5, 0x0004003B, 0x00000A32, 0x0000107A, 0x00000002, 0x00040020, 0x00000294, 0x00000002, 0x00000017, 0x0006002C, - 0x00000014, 0x00000024, 0x00000A22, 0x00000A6A, 0x00000A0D, 0x0005002C, + 0x00000014, 0x00000BC3, 0x00000A16, 0x00000A6A, 0x00000A0D, 0x0005002C, 0x00000011, 0x0000074E, 0x00000A13, 0x00000A13, 0x0004002B, 0x0000000B, 0x00000A25, 0x00000009, 0x0004002B, 0x0000000B, 0x00000A28, 0x0000000A, 0x0007002C, 0x00000017, 0x000009CE, 0x000008A6, 0x000008A6, 0x000008A6, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_8bpb_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_8bpb_cs.h index ba21280eb..3e3fa36bc 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_8bpb_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_8bpb_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 2 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -92,7 +92,7 @@ %4218 = OpVariable %_ptr_Uniform__struct_1960 Uniform %_ptr_Uniform_v2uint = OpTypePointer Uniform %v2uint %_ptr_Uniform_v4uint = OpTypePointer Uniform %v4uint -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_2 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %uint_8 = OpConstant %uint 8 %5663 = OpFunction %void None %1282 %15110 = OpLabel @@ -293,7 +293,7 @@ const uint32_t texture_load_8bpb_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000002, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -311,7 +311,7 @@ const uint32_t texture_load_8bpb_cs[] = { 0x00000018, 0x00050048, 0x000007A8, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007A8, 0x00000003, 0x00040047, 0x0000107A, 0x00000022, 0x00000001, 0x00040047, 0x0000107A, 0x00000021, 0x00000000, 0x00040047, - 0x00000BB1, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, 0x00040017, 0x00000012, 0x0000000C, 0x00000002, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000016, 0x0000000C, 0x00000003, @@ -349,7 +349,7 @@ const uint32_t texture_load_8bpb_cs[] = { 0x00000011, 0x0003001E, 0x000007A8, 0x000007D6, 0x00040020, 0x00000A25, 0x00000002, 0x000007A8, 0x0004003B, 0x00000A25, 0x0000107A, 0x00000002, 0x00040020, 0x0000028E, 0x00000002, 0x00000011, 0x00040020, 0x00000294, - 0x00000002, 0x00000017, 0x0006002C, 0x00000014, 0x00000BB1, 0x00000A10, + 0x00000002, 0x00000017, 0x0006002C, 0x00000014, 0x00000BC3, 0x00000A16, 0x00000A6A, 0x00000A0D, 0x0004002B, 0x0000000B, 0x00000A22, 0x00000008, 0x00050036, 0x00000008, 0x0000161F, 0x00000000, 0x00000502, 0x000200F8, 0x00003B06, 0x000300F7, 0x00004C7A, 0x00000000, 0x000300FB, 0x00000A0A, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_8bpb_scaled_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_8bpb_scaled_cs.h index e05d9dde7..87dd07691 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_8bpb_scaled_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_8bpb_scaled_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 2 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -93,7 +93,7 @@ %4218 = OpVariable %_ptr_Uniform__struct_1960 Uniform %_ptr_Uniform_v2uint = OpTypePointer Uniform %v2uint %_ptr_Uniform_v4uint = OpTypePointer Uniform %v4uint -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_2 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %1870 = OpConstantComposite %v2uint %uint_3 %uint_3 %uint_8 = OpConstant %uint 8 %5663 = OpFunction %void None %1282 @@ -331,7 +331,7 @@ const uint32_t texture_load_8bpb_scaled_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000002, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -349,7 +349,7 @@ const uint32_t texture_load_8bpb_scaled_cs[] = { 0x00000018, 0x00050048, 0x000007A8, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007A8, 0x00000003, 0x00040047, 0x0000107A, 0x00000022, 0x00000001, 0x00040047, 0x0000107A, 0x00000021, 0x00000000, 0x00040047, - 0x00000BB1, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, 0x00040017, 0x00000012, 0x0000000C, 0x00000002, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000016, 0x0000000C, 0x00000003, @@ -388,7 +388,7 @@ const uint32_t texture_load_8bpb_scaled_cs[] = { 0x0003001E, 0x000007A8, 0x000007D6, 0x00040020, 0x00000A25, 0x00000002, 0x000007A8, 0x0004003B, 0x00000A25, 0x0000107A, 0x00000002, 0x00040020, 0x0000028E, 0x00000002, 0x00000011, 0x00040020, 0x00000294, 0x00000002, - 0x00000017, 0x0006002C, 0x00000014, 0x00000BB1, 0x00000A10, 0x00000A6A, + 0x00000017, 0x0006002C, 0x00000014, 0x00000BC3, 0x00000A16, 0x00000A6A, 0x00000A0D, 0x0005002C, 0x00000011, 0x0000074E, 0x00000A13, 0x00000A13, 0x0004002B, 0x0000000B, 0x00000A22, 0x00000008, 0x00050036, 0x00000008, 0x0000161F, 0x00000000, 0x00000502, 0x000200F8, 0x00003B06, 0x000300F7, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_ctx1_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_ctx1_cs.h index 9763a89c1..38e5e9fcc 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_ctx1_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_ctx1_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 8 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -101,7 +101,7 @@ %_ptr_Uniform__struct_1973 = OpTypePointer Uniform %_struct_1973 %5134 = OpVariable %_ptr_Uniform__struct_1973 Uniform %uint_32 = OpConstant %uint 32 -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_8 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %10264 = OpUndef %v4uint %uint_9 = OpConstant %uint 9 %uint_10 = OpConstant %uint 10 @@ -978,7 +978,7 @@ const uint32_t texture_load_ctx1_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000008, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -996,7 +996,7 @@ const uint32_t texture_load_ctx1_cs[] = { 0x00000019, 0x00050048, 0x000007B5, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007B5, 0x00000003, 0x00040047, 0x0000140E, 0x00000022, 0x00000000, 0x00040047, 0x0000140E, 0x00000021, 0x00000000, 0x00040047, - 0x00000024, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000017, 0x0000000B, 0x00000004, 0x00040017, 0x00000011, 0x0000000B, 0x00000002, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, @@ -1041,7 +1041,7 @@ const uint32_t texture_load_ctx1_cs[] = { 0x00FF0000, 0x0003001D, 0x000007DD, 0x00000017, 0x0003001E, 0x000007B5, 0x000007DD, 0x00040020, 0x00000A32, 0x00000002, 0x000007B5, 0x0004003B, 0x00000A32, 0x0000140E, 0x00000002, 0x0004002B, 0x0000000B, 0x00000A6A, - 0x00000020, 0x0006002C, 0x00000014, 0x00000024, 0x00000A22, 0x00000A6A, + 0x00000020, 0x0006002C, 0x00000014, 0x00000BC3, 0x00000A16, 0x00000A6A, 0x00000A0D, 0x00030001, 0x00000017, 0x00002818, 0x0004002B, 0x0000000B, 0x00000A25, 0x00000009, 0x0004002B, 0x0000000B, 0x00000A28, 0x0000000A, 0x0007002C, 0x00000017, 0x000009CE, 0x000008A6, 0x000008A6, 0x000008A6, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_dxn_rg8_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_dxn_rg8_cs.h index 83a59a9f0..4da02a1c5 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_dxn_rg8_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_dxn_rg8_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 16 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -108,7 +108,7 @@ %5134 = OpVariable %_ptr_Uniform__struct_1973 Uniform %uint_12 = OpConstant %uint 12 %uint_32 = OpConstant %uint 32 -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_16 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %uint_10 = OpConstant %uint 10 %uint_11 = OpConstant %uint 11 %2510 = OpConstantComposite %v4uint %uint_16711935 %uint_16711935 %uint_16711935 %uint_16711935 @@ -2596,7 +2596,7 @@ const uint32_t texture_load_dxn_rg8_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000010, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -2614,7 +2614,7 @@ const uint32_t texture_load_dxn_rg8_cs[] = { 0x00000019, 0x00050048, 0x000007B5, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007B5, 0x00000003, 0x00040047, 0x0000140E, 0x00000022, 0x00000000, 0x00040047, 0x0000140E, 0x00000021, 0x00000000, 0x00040047, - 0x0000006C, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000011, 0x0000000B, 0x00000002, 0x00040017, 0x00000017, 0x0000000B, 0x00000004, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, @@ -2664,7 +2664,7 @@ const uint32_t texture_load_dxn_rg8_cs[] = { 0x000007DD, 0x00040020, 0x00000A33, 0x00000002, 0x000007B5, 0x0004003B, 0x00000A33, 0x0000140E, 0x00000002, 0x0004002B, 0x0000000B, 0x00000A2E, 0x0000000C, 0x0004002B, 0x0000000B, 0x00000A6A, 0x00000020, 0x0006002C, - 0x00000014, 0x0000006C, 0x00000A3A, 0x00000A6A, 0x00000A0D, 0x0004002B, + 0x00000014, 0x00000BC3, 0x00000A16, 0x00000A6A, 0x00000A0D, 0x0004002B, 0x0000000B, 0x00000A28, 0x0000000A, 0x0004002B, 0x0000000B, 0x00000A2B, 0x0000000B, 0x0007002C, 0x00000017, 0x000009CE, 0x000008A6, 0x000008A6, 0x000008A6, 0x000008A6, 0x0007002C, 0x00000017, 0x0000013D, 0x00000A22, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_dxt1_rgba8_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_dxt1_rgba8_cs.h index deca30b20..cddebadde 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_dxt1_rgba8_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_dxt1_rgba8_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 8 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -112,7 +112,7 @@ %_ptr_Uniform__struct_1973 = OpTypePointer Uniform %_struct_1973 %5134 = OpVariable %_ptr_Uniform__struct_1973 Uniform %uint_32 = OpConstant %uint 32 -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_8 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %2510 = OpConstantComposite %v4uint %uint_16711935 %uint_16711935 %uint_16711935 %uint_16711935 %317 = OpConstantComposite %v4uint %uint_8 %uint_8 %uint_8 %uint_8 %1838 = OpConstantComposite %v4uint %uint_4278255360 %uint_4278255360 %uint_4278255360 %uint_4278255360 @@ -815,7 +815,7 @@ const uint32_t texture_load_dxt1_rgba8_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000008, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -833,7 +833,7 @@ const uint32_t texture_load_dxt1_rgba8_cs[] = { 0x00000019, 0x00050048, 0x000007B5, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007B5, 0x00000003, 0x00040047, 0x0000140E, 0x00000022, 0x00000000, 0x00040047, 0x0000140E, 0x00000021, 0x00000000, 0x00040047, - 0x00000024, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000011, 0x0000000B, 0x00000002, 0x00040017, 0x00000017, 0x0000000B, 0x00000004, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, @@ -886,7 +886,7 @@ const uint32_t texture_load_dxt1_rgba8_cs[] = { 0x0003001D, 0x000007DD, 0x00000017, 0x0003001E, 0x000007B5, 0x000007DD, 0x00040020, 0x00000A33, 0x00000002, 0x000007B5, 0x0004003B, 0x00000A33, 0x0000140E, 0x00000002, 0x0004002B, 0x0000000B, 0x00000A6A, 0x00000020, - 0x0006002C, 0x00000014, 0x00000024, 0x00000A22, 0x00000A6A, 0x00000A0D, + 0x0006002C, 0x00000014, 0x00000BC3, 0x00000A16, 0x00000A6A, 0x00000A0D, 0x0007002C, 0x00000017, 0x000009CE, 0x000008A6, 0x000008A6, 0x000008A6, 0x000008A6, 0x0007002C, 0x00000017, 0x0000013D, 0x00000A22, 0x00000A22, 0x00000A22, 0x00000A22, 0x0007002C, 0x00000017, 0x0000072E, 0x000005FD, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_dxt3_rgba8_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_dxt3_rgba8_cs.h index 2267c600c..b21609b2e 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_dxt3_rgba8_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_dxt3_rgba8_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 16 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -115,7 +115,7 @@ %uint_28 = OpConstant %uint 28 %1133 = OpConstantComposite %v4uint %uint_16 %uint_20 %uint_24 %uint_28 %uint_32 = OpConstant %uint 32 -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_16 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %uint_11 = OpConstant %uint 11 %2510 = OpConstantComposite %v4uint %uint_16711935 %uint_16711935 %uint_16711935 %uint_16711935 %317 = OpConstantComposite %v4uint %uint_8 %uint_8 %uint_8 %uint_8 @@ -740,7 +740,7 @@ const uint32_t texture_load_dxt3_rgba8_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000010, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -758,7 +758,7 @@ const uint32_t texture_load_dxt3_rgba8_cs[] = { 0x00000019, 0x00050048, 0x000007B5, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007B5, 0x00000003, 0x00040047, 0x0000140E, 0x00000022, 0x00000000, 0x00040047, 0x0000140E, 0x00000021, 0x00000000, 0x00040047, - 0x0000006C, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000011, 0x0000000B, 0x00000002, 0x00040017, 0x00000017, 0x0000000B, 0x00000004, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, @@ -813,8 +813,8 @@ const uint32_t texture_load_dxt3_rgba8_cs[] = { 0x000006A9, 0x11000000, 0x0004002B, 0x0000000B, 0x00000A52, 0x00000018, 0x0004002B, 0x0000000B, 0x00000A5E, 0x0000001C, 0x0007002C, 0x00000017, 0x0000046D, 0x00000A3A, 0x00000A46, 0x00000A52, 0x00000A5E, 0x0004002B, - 0x0000000B, 0x00000A6A, 0x00000020, 0x0006002C, 0x00000014, 0x0000006C, - 0x00000A3A, 0x00000A6A, 0x00000A0D, 0x0004002B, 0x0000000B, 0x00000A2B, + 0x0000000B, 0x00000A6A, 0x00000020, 0x0006002C, 0x00000014, 0x00000BC3, + 0x00000A16, 0x00000A6A, 0x00000A0D, 0x0004002B, 0x0000000B, 0x00000A2B, 0x0000000B, 0x0007002C, 0x00000017, 0x000009CE, 0x000008A6, 0x000008A6, 0x000008A6, 0x000008A6, 0x0007002C, 0x00000017, 0x0000013D, 0x00000A22, 0x00000A22, 0x00000A22, 0x00000A22, 0x0007002C, 0x00000017, 0x0000072E, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_dxt3a_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_dxt3a_cs.h index 5abc8cf69..7a4c1d3e3 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_dxt3a_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_dxt3a_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 8 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -99,7 +99,7 @@ %_ptr_Uniform__struct_1973 = OpTypePointer Uniform %_struct_1973 %5134 = OpVariable %_ptr_Uniform__struct_1973 Uniform %uint_32 = OpConstant %uint 32 -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_8 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %uint_9 = OpConstant %uint 9 %uint_10 = OpConstant %uint 10 %2510 = OpConstantComposite %v4uint %uint_16711935 %uint_16711935 %uint_16711935 %uint_16711935 @@ -460,7 +460,7 @@ const uint32_t texture_load_dxt3a_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000008, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -478,7 +478,7 @@ const uint32_t texture_load_dxt3a_cs[] = { 0x00000019, 0x00050048, 0x000007B5, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007B5, 0x00000003, 0x00040047, 0x0000140E, 0x00000022, 0x00000000, 0x00040047, 0x0000140E, 0x00000021, 0x00000000, 0x00040047, - 0x00000024, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000017, 0x0000000B, 0x00000004, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, 0x00040017, 0x00000012, 0x0000000C, 0x00000002, @@ -521,7 +521,7 @@ const uint32_t texture_load_dxt3a_cs[] = { 0x00000002, 0x00000017, 0x0003001D, 0x000007DD, 0x00000017, 0x0003001E, 0x000007B5, 0x000007DD, 0x00040020, 0x00000A32, 0x00000002, 0x000007B5, 0x0004003B, 0x00000A32, 0x0000140E, 0x00000002, 0x0004002B, 0x0000000B, - 0x00000A6A, 0x00000020, 0x0006002C, 0x00000014, 0x00000024, 0x00000A22, + 0x00000A6A, 0x00000020, 0x0006002C, 0x00000014, 0x00000BC3, 0x00000A16, 0x00000A6A, 0x00000A0D, 0x0004002B, 0x0000000B, 0x00000A25, 0x00000009, 0x0004002B, 0x0000000B, 0x00000A28, 0x0000000A, 0x0007002C, 0x00000017, 0x000009CE, 0x000008A6, 0x000008A6, 0x000008A6, 0x000008A6, 0x0007002C, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_dxt3aas1111_argb4_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_dxt3aas1111_argb4_cs.h index df070fd18..48f942d70 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_dxt3aas1111_argb4_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_dxt3aas1111_argb4_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 8 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -113,7 +113,7 @@ %_ptr_Uniform__struct_1973 = OpTypePointer Uniform %_struct_1973 %5134 = OpVariable %_ptr_Uniform__struct_1973 Uniform %uint_32 = OpConstant %uint 32 -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_8 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %2510 = OpConstantComposite %v4uint %uint_16711935 %uint_16711935 %uint_16711935 %uint_16711935 %317 = OpConstantComposite %v4uint %uint_8 %uint_8 %uint_8 %uint_8 %1838 = OpConstantComposite %v4uint %uint_4278255360 %uint_4278255360 %uint_4278255360 %uint_4278255360 @@ -711,7 +711,7 @@ const uint32_t texture_load_dxt3aas1111_argb4_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000008, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -729,7 +729,7 @@ const uint32_t texture_load_dxt3aas1111_argb4_cs[] = { 0x00000019, 0x00050048, 0x000007B5, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007B5, 0x00000003, 0x00040047, 0x0000140E, 0x00000022, 0x00000000, 0x00040047, 0x0000140E, 0x00000021, 0x00000000, 0x00040047, - 0x00000024, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000011, 0x0000000B, 0x00000002, 0x00040017, 0x00000017, 0x0000000B, 0x00000004, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, @@ -786,7 +786,7 @@ const uint32_t texture_load_dxt3aas1111_argb4_cs[] = { 0x00000017, 0x0003001E, 0x000007B5, 0x000007DD, 0x00040020, 0x00000A33, 0x00000002, 0x000007B5, 0x0004003B, 0x00000A33, 0x0000140E, 0x00000002, 0x0004002B, 0x0000000B, 0x00000A6A, 0x00000020, 0x0006002C, 0x00000014, - 0x00000024, 0x00000A22, 0x00000A6A, 0x00000A0D, 0x0007002C, 0x00000017, + 0x00000BC3, 0x00000A16, 0x00000A6A, 0x00000A0D, 0x0007002C, 0x00000017, 0x000009CE, 0x000008A6, 0x000008A6, 0x000008A6, 0x000008A6, 0x0007002C, 0x00000017, 0x0000013D, 0x00000A22, 0x00000A22, 0x00000A22, 0x00000A22, 0x0007002C, 0x00000017, 0x0000072E, 0x000005FD, 0x000005FD, 0x000005FD, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_dxt3aas1111_bgra4_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_dxt3aas1111_bgra4_cs.h index c4c0775f6..31e1fef24 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_dxt3aas1111_bgra4_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_dxt3aas1111_bgra4_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 8 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -113,7 +113,7 @@ %_ptr_Uniform__struct_1973 = OpTypePointer Uniform %_struct_1973 %5134 = OpVariable %_ptr_Uniform__struct_1973 Uniform %uint_32 = OpConstant %uint 32 -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_8 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %2510 = OpConstantComposite %v4uint %uint_16711935 %uint_16711935 %uint_16711935 %uint_16711935 %317 = OpConstantComposite %v4uint %uint_8 %uint_8 %uint_8 %uint_8 %1838 = OpConstantComposite %v4uint %uint_4278255360 %uint_4278255360 %uint_4278255360 %uint_4278255360 @@ -711,7 +711,7 @@ const uint32_t texture_load_dxt3aas1111_bgra4_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000008, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -729,7 +729,7 @@ const uint32_t texture_load_dxt3aas1111_bgra4_cs[] = { 0x00000019, 0x00050048, 0x000007B5, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007B5, 0x00000003, 0x00040047, 0x0000140E, 0x00000022, 0x00000000, 0x00040047, 0x0000140E, 0x00000021, 0x00000000, 0x00040047, - 0x00000024, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000011, 0x0000000B, 0x00000002, 0x00040017, 0x00000017, 0x0000000B, 0x00000004, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, @@ -786,7 +786,7 @@ const uint32_t texture_load_dxt3aas1111_bgra4_cs[] = { 0x00000017, 0x0003001E, 0x000007B5, 0x000007DD, 0x00040020, 0x00000A33, 0x00000002, 0x000007B5, 0x0004003B, 0x00000A33, 0x0000140E, 0x00000002, 0x0004002B, 0x0000000B, 0x00000A6A, 0x00000020, 0x0006002C, 0x00000014, - 0x00000024, 0x00000A22, 0x00000A6A, 0x00000A0D, 0x0007002C, 0x00000017, + 0x00000BC3, 0x00000A16, 0x00000A6A, 0x00000A0D, 0x0007002C, 0x00000017, 0x000009CE, 0x000008A6, 0x000008A6, 0x000008A6, 0x000008A6, 0x0007002C, 0x00000017, 0x0000013D, 0x00000A22, 0x00000A22, 0x00000A22, 0x00000A22, 0x0007002C, 0x00000017, 0x0000072E, 0x000005FD, 0x000005FD, 0x000005FD, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_dxt5_rgba8_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_dxt5_rgba8_cs.h index c54c37caf..6aa53f01e 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_dxt5_rgba8_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_dxt5_rgba8_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 16 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -124,7 +124,7 @@ %413 = OpConstantComposite %v4uint %uint_24 %uint_16 %uint_8 %uint_0 %uint_4278190080 = OpConstant %uint 4278190080 %uint_32 = OpConstant %uint 32 -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_16 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %uint_11 = OpConstant %uint 11 %2510 = OpConstantComposite %v4uint %uint_16711935 %uint_16711935 %uint_16711935 %uint_16711935 %317 = OpConstantComposite %v4uint %uint_8 %uint_8 %uint_8 %uint_8 @@ -1843,7 +1843,7 @@ const uint32_t texture_load_dxt5_rgba8_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000010, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -1861,7 +1861,7 @@ const uint32_t texture_load_dxt5_rgba8_cs[] = { 0x00000019, 0x00050048, 0x000007B5, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007B5, 0x00000003, 0x00040047, 0x0000140E, 0x00000022, 0x00000000, 0x00040047, 0x0000140E, 0x00000021, 0x00000000, 0x00040047, - 0x0000006C, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000011, 0x0000000B, 0x00000002, 0x00040017, 0x00000017, 0x0000000B, 0x00000004, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, @@ -1922,7 +1922,7 @@ const uint32_t texture_load_dxt5_rgba8_cs[] = { 0x0004003B, 0x00000A33, 0x0000140E, 0x00000002, 0x0007002C, 0x00000017, 0x0000019D, 0x00000A52, 0x00000A3A, 0x00000A22, 0x00000A0A, 0x0004002B, 0x0000000B, 0x00000580, 0xFF000000, 0x0004002B, 0x0000000B, 0x00000A6A, - 0x00000020, 0x0006002C, 0x00000014, 0x0000006C, 0x00000A3A, 0x00000A6A, + 0x00000020, 0x0006002C, 0x00000014, 0x00000BC3, 0x00000A16, 0x00000A6A, 0x00000A0D, 0x0004002B, 0x0000000B, 0x00000A2B, 0x0000000B, 0x0007002C, 0x00000017, 0x000009CE, 0x000008A6, 0x000008A6, 0x000008A6, 0x000008A6, 0x0007002C, 0x00000017, 0x0000013D, 0x00000A22, 0x00000A22, 0x00000A22, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_dxt5a_r8_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_dxt5a_r8_cs.h index 293c94e34..624ad0165 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_dxt5a_r8_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_dxt5a_r8_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 8 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -111,7 +111,7 @@ %5134 = OpVariable %_ptr_Uniform__struct_1973 Uniform %uint_12 = OpConstant %uint 12 %uint_32 = OpConstant %uint 32 -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_8 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %2510 = OpConstantComposite %v4uint %uint_16711935 %uint_16711935 %uint_16711935 %uint_16711935 %317 = OpConstantComposite %v4uint %uint_8 %uint_8 %uint_8 %uint_8 %1838 = OpConstantComposite %v4uint %uint_4278255360 %uint_4278255360 %uint_4278255360 %uint_4278255360 @@ -2594,7 +2594,7 @@ const uint32_t texture_load_dxt5a_r8_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000008, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -2612,7 +2612,7 @@ const uint32_t texture_load_dxt5a_r8_cs[] = { 0x00000019, 0x00050048, 0x000007B5, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007B5, 0x00000003, 0x00040047, 0x0000140E, 0x00000022, 0x00000000, 0x00040047, 0x0000140E, 0x00000021, 0x00000000, 0x00040047, - 0x00000024, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000011, 0x0000000B, 0x00000002, 0x00040017, 0x00000017, 0x0000000B, 0x00000004, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, @@ -2664,7 +2664,7 @@ const uint32_t texture_load_dxt5a_r8_cs[] = { 0x000007DD, 0x00040020, 0x00000A32, 0x00000002, 0x000007B5, 0x0004003B, 0x00000A32, 0x0000140E, 0x00000002, 0x0004002B, 0x0000000B, 0x00000A2E, 0x0000000C, 0x0004002B, 0x0000000B, 0x00000A6A, 0x00000020, 0x0006002C, - 0x00000014, 0x00000024, 0x00000A22, 0x00000A6A, 0x00000A0D, 0x0007002C, + 0x00000014, 0x00000BC3, 0x00000A16, 0x00000A6A, 0x00000A0D, 0x0007002C, 0x00000017, 0x000009CE, 0x000008A6, 0x000008A6, 0x000008A6, 0x000008A6, 0x0007002C, 0x00000017, 0x0000013D, 0x00000A22, 0x00000A22, 0x00000A22, 0x00000A22, 0x0007002C, 0x00000017, 0x0000072E, 0x000005FD, 0x000005FD, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r16_snorm_float_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r16_snorm_float_cs.h index 221d7a916..848e409b5 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r16_snorm_float_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r16_snorm_float_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 2 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -100,7 +100,7 @@ %_ptr_Uniform__struct_1973 = OpTypePointer Uniform %_struct_1973 %4218 = OpVariable %_ptr_Uniform__struct_1973 Uniform %_ptr_Uniform_v4uint = OpTypePointer Uniform %v4uint -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_2 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %2510 = OpConstantComposite %v4uint %uint_16711935 %uint_16711935 %uint_16711935 %uint_16711935 %317 = OpConstantComposite %v4uint %uint_8 %uint_8 %uint_8 %uint_8 %1838 = OpConstantComposite %v4uint %uint_4278255360 %uint_4278255360 %uint_4278255360 %uint_4278255360 @@ -383,7 +383,7 @@ const uint32_t texture_load_r16_snorm_float_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000002, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -401,7 +401,7 @@ const uint32_t texture_load_r16_snorm_float_cs[] = { 0x00000018, 0x00050048, 0x000007B5, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007B5, 0x00000003, 0x00040047, 0x0000107A, 0x00000022, 0x00000001, 0x00040047, 0x0000107A, 0x00000021, 0x00000000, 0x00040047, - 0x00000BB1, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000017, 0x0000000B, 0x00000004, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, 0x00040017, 0x00000012, 0x0000000C, 0x00000002, @@ -445,7 +445,7 @@ const uint32_t texture_load_r16_snorm_float_cs[] = { 0x0003001D, 0x000007DD, 0x00000017, 0x0003001E, 0x000007B5, 0x000007DD, 0x00040020, 0x00000A32, 0x00000002, 0x000007B5, 0x0004003B, 0x00000A32, 0x0000107A, 0x00000002, 0x00040020, 0x00000294, 0x00000002, 0x00000017, - 0x0006002C, 0x00000014, 0x00000BB1, 0x00000A10, 0x00000A6A, 0x00000A0D, + 0x0006002C, 0x00000014, 0x00000BC3, 0x00000A16, 0x00000A6A, 0x00000A0D, 0x0007002C, 0x00000017, 0x000009CE, 0x000008A6, 0x000008A6, 0x000008A6, 0x000008A6, 0x0007002C, 0x00000017, 0x0000013D, 0x00000A22, 0x00000A22, 0x00000A22, 0x00000A22, 0x0007002C, 0x00000017, 0x0000072E, 0x000005FD, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r16_snorm_float_scaled_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r16_snorm_float_scaled_cs.h index cc0f5a113..ef4d4ddc8 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r16_snorm_float_scaled_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r16_snorm_float_scaled_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 2 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -102,7 +102,7 @@ %_ptr_Uniform__struct_1973 = OpTypePointer Uniform %_struct_1973 %4218 = OpVariable %_ptr_Uniform__struct_1973 Uniform %_ptr_Uniform_v4uint = OpTypePointer Uniform %v4uint -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_2 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %1870 = OpConstantComposite %v2uint %uint_3 %uint_3 %2510 = OpConstantComposite %v4uint %uint_16711935 %uint_16711935 %uint_16711935 %uint_16711935 %317 = OpConstantComposite %v4uint %uint_8 %uint_8 %uint_8 %uint_8 @@ -422,7 +422,7 @@ const uint32_t texture_load_r16_snorm_float_scaled_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000002, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -440,7 +440,7 @@ const uint32_t texture_load_r16_snorm_float_scaled_cs[] = { 0x00000018, 0x00050048, 0x000007B5, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007B5, 0x00000003, 0x00040047, 0x0000107A, 0x00000022, 0x00000001, 0x00040047, 0x0000107A, 0x00000021, 0x00000000, 0x00040047, - 0x00000BB1, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000017, 0x0000000B, 0x00000004, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, 0x00040017, 0x00000012, 0x0000000C, 0x00000002, @@ -485,8 +485,8 @@ const uint32_t texture_load_r16_snorm_float_scaled_cs[] = { 0x00000A31, 0x0000140E, 0x00000002, 0x0003001D, 0x000007DD, 0x00000017, 0x0003001E, 0x000007B5, 0x000007DD, 0x00040020, 0x00000A32, 0x00000002, 0x000007B5, 0x0004003B, 0x00000A32, 0x0000107A, 0x00000002, 0x00040020, - 0x00000294, 0x00000002, 0x00000017, 0x0006002C, 0x00000014, 0x00000BB1, - 0x00000A10, 0x00000A6A, 0x00000A0D, 0x0005002C, 0x00000011, 0x0000074E, + 0x00000294, 0x00000002, 0x00000017, 0x0006002C, 0x00000014, 0x00000BC3, + 0x00000A16, 0x00000A6A, 0x00000A0D, 0x0005002C, 0x00000011, 0x0000074E, 0x00000A13, 0x00000A13, 0x0007002C, 0x00000017, 0x000009CE, 0x000008A6, 0x000008A6, 0x000008A6, 0x000008A6, 0x0007002C, 0x00000017, 0x0000013D, 0x00000A22, 0x00000A22, 0x00000A22, 0x00000A22, 0x0007002C, 0x00000017, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r16_unorm_float_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r16_unorm_float_cs.h index 7ebd50e48..20fd03316 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r16_unorm_float_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r16_unorm_float_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 2 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -99,7 +99,7 @@ %_ptr_Uniform__struct_1973 = OpTypePointer Uniform %_struct_1973 %4218 = OpVariable %_ptr_Uniform__struct_1973 Uniform %_ptr_Uniform_v4uint = OpTypePointer Uniform %v4uint -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_2 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %2510 = OpConstantComposite %v4uint %uint_16711935 %uint_16711935 %uint_16711935 %uint_16711935 %317 = OpConstantComposite %v4uint %uint_8 %uint_8 %uint_8 %uint_8 %1838 = OpConstantComposite %v4uint %uint_4278255360 %uint_4278255360 %uint_4278255360 %uint_4278255360 @@ -374,7 +374,7 @@ const uint32_t texture_load_r16_unorm_float_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000002, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -392,7 +392,7 @@ const uint32_t texture_load_r16_unorm_float_cs[] = { 0x00000018, 0x00050048, 0x000007B5, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007B5, 0x00000003, 0x00040047, 0x0000107A, 0x00000022, 0x00000001, 0x00040047, 0x0000107A, 0x00000021, 0x00000000, 0x00040047, - 0x00000BB1, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000017, 0x0000000B, 0x00000004, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, 0x00040017, 0x00000012, 0x0000000C, 0x00000002, @@ -435,7 +435,7 @@ const uint32_t texture_load_r16_unorm_float_cs[] = { 0x000007DD, 0x00000017, 0x0003001E, 0x000007B5, 0x000007DD, 0x00040020, 0x00000A32, 0x00000002, 0x000007B5, 0x0004003B, 0x00000A32, 0x0000107A, 0x00000002, 0x00040020, 0x00000294, 0x00000002, 0x00000017, 0x0006002C, - 0x00000014, 0x00000BB1, 0x00000A10, 0x00000A6A, 0x00000A0D, 0x0007002C, + 0x00000014, 0x00000BC3, 0x00000A16, 0x00000A6A, 0x00000A0D, 0x0007002C, 0x00000017, 0x000009CE, 0x000008A6, 0x000008A6, 0x000008A6, 0x000008A6, 0x0007002C, 0x00000017, 0x0000013D, 0x00000A22, 0x00000A22, 0x00000A22, 0x00000A22, 0x0007002C, 0x00000017, 0x0000072E, 0x000005FD, 0x000005FD, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r16_unorm_float_scaled_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r16_unorm_float_scaled_cs.h index 44422dc3d..60ac24580 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r16_unorm_float_scaled_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r16_unorm_float_scaled_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 2 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -101,7 +101,7 @@ %_ptr_Uniform__struct_1973 = OpTypePointer Uniform %_struct_1973 %4218 = OpVariable %_ptr_Uniform__struct_1973 Uniform %_ptr_Uniform_v4uint = OpTypePointer Uniform %v4uint -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_2 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %1870 = OpConstantComposite %v2uint %uint_3 %uint_3 %2510 = OpConstantComposite %v4uint %uint_16711935 %uint_16711935 %uint_16711935 %uint_16711935 %317 = OpConstantComposite %v4uint %uint_8 %uint_8 %uint_8 %uint_8 @@ -413,7 +413,7 @@ const uint32_t texture_load_r16_unorm_float_scaled_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000002, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -431,7 +431,7 @@ const uint32_t texture_load_r16_unorm_float_scaled_cs[] = { 0x00000018, 0x00050048, 0x000007B5, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007B5, 0x00000003, 0x00040047, 0x0000107A, 0x00000022, 0x00000001, 0x00040047, 0x0000107A, 0x00000021, 0x00000000, 0x00040047, - 0x00000BB1, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000017, 0x0000000B, 0x00000004, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, 0x00040017, 0x00000012, 0x0000000C, 0x00000002, @@ -475,7 +475,7 @@ const uint32_t texture_load_r16_unorm_float_scaled_cs[] = { 0x0000140E, 0x00000002, 0x0003001D, 0x000007DD, 0x00000017, 0x0003001E, 0x000007B5, 0x000007DD, 0x00040020, 0x00000A32, 0x00000002, 0x000007B5, 0x0004003B, 0x00000A32, 0x0000107A, 0x00000002, 0x00040020, 0x00000294, - 0x00000002, 0x00000017, 0x0006002C, 0x00000014, 0x00000BB1, 0x00000A10, + 0x00000002, 0x00000017, 0x0006002C, 0x00000014, 0x00000BC3, 0x00000A16, 0x00000A6A, 0x00000A0D, 0x0005002C, 0x00000011, 0x0000074E, 0x00000A13, 0x00000A13, 0x0007002C, 0x00000017, 0x000009CE, 0x000008A6, 0x000008A6, 0x000008A6, 0x000008A6, 0x0007002C, 0x00000017, 0x0000013D, 0x00000A22, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r4g4b4a4_a4r4g4b4_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r4g4b4a4_a4r4g4b4_cs.h index ba0d08895..022abf5f8 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r4g4b4a4_a4r4g4b4_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r4g4b4a4_a4r4g4b4_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 2 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -96,7 +96,7 @@ %_ptr_Uniform__struct_1973 = OpTypePointer Uniform %_struct_1973 %4218 = OpVariable %_ptr_Uniform__struct_1973 Uniform %_ptr_Uniform_v4uint = OpTypePointer Uniform %v4uint -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_2 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %2510 = OpConstantComposite %v4uint %uint_16711935 %uint_16711935 %uint_16711935 %uint_16711935 %317 = OpConstantComposite %v4uint %uint_8 %uint_8 %uint_8 %uint_8 %1838 = OpConstantComposite %v4uint %uint_4278255360 %uint_4278255360 %uint_4278255360 %uint_4278255360 @@ -338,7 +338,7 @@ const uint32_t texture_load_r4g4b4a4_a4r4g4b4_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000002, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -356,7 +356,7 @@ const uint32_t texture_load_r4g4b4a4_a4r4g4b4_cs[] = { 0x00000018, 0x00050048, 0x000007B5, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007B5, 0x00000003, 0x00040047, 0x0000107A, 0x00000022, 0x00000001, 0x00040047, 0x0000107A, 0x00000021, 0x00000000, 0x00040047, - 0x00000BB1, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000017, 0x0000000B, 0x00000004, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, 0x00040017, 0x00000012, 0x0000000C, 0x00000002, @@ -397,7 +397,7 @@ const uint32_t texture_load_r4g4b4a4_a4r4g4b4_cs[] = { 0x0003001D, 0x000007DD, 0x00000017, 0x0003001E, 0x000007B5, 0x000007DD, 0x00040020, 0x00000A32, 0x00000002, 0x000007B5, 0x0004003B, 0x00000A32, 0x0000107A, 0x00000002, 0x00040020, 0x00000294, 0x00000002, 0x00000017, - 0x0006002C, 0x00000014, 0x00000BB1, 0x00000A10, 0x00000A6A, 0x00000A0D, + 0x0006002C, 0x00000014, 0x00000BC3, 0x00000A16, 0x00000A6A, 0x00000A0D, 0x0007002C, 0x00000017, 0x000009CE, 0x000008A6, 0x000008A6, 0x000008A6, 0x000008A6, 0x0007002C, 0x00000017, 0x0000013D, 0x00000A22, 0x00000A22, 0x00000A22, 0x00000A22, 0x0007002C, 0x00000017, 0x0000072E, 0x000005FD, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r4g4b4a4_a4r4g4b4_scaled_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r4g4b4a4_a4r4g4b4_scaled_cs.h index 799d9ba2f..8719b9439 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r4g4b4a4_a4r4g4b4_scaled_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r4g4b4a4_a4r4g4b4_scaled_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 2 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -98,7 +98,7 @@ %_ptr_Uniform__struct_1973 = OpTypePointer Uniform %_struct_1973 %4218 = OpVariable %_ptr_Uniform__struct_1973 Uniform %_ptr_Uniform_v4uint = OpTypePointer Uniform %v4uint -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_2 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %1870 = OpConstantComposite %v2uint %uint_3 %uint_3 %2510 = OpConstantComposite %v4uint %uint_16711935 %uint_16711935 %uint_16711935 %uint_16711935 %317 = OpConstantComposite %v4uint %uint_8 %uint_8 %uint_8 %uint_8 @@ -377,7 +377,7 @@ const uint32_t texture_load_r4g4b4a4_a4r4g4b4_scaled_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000002, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -395,7 +395,7 @@ const uint32_t texture_load_r4g4b4a4_a4r4g4b4_scaled_cs[] = { 0x00000018, 0x00050048, 0x000007B5, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007B5, 0x00000003, 0x00040047, 0x0000107A, 0x00000022, 0x00000001, 0x00040047, 0x0000107A, 0x00000021, 0x00000000, 0x00040047, - 0x00000BB1, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000017, 0x0000000B, 0x00000004, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, 0x00040017, 0x00000012, 0x0000000C, 0x00000002, @@ -437,8 +437,8 @@ const uint32_t texture_load_r4g4b4a4_a4r4g4b4_scaled_cs[] = { 0x00000A31, 0x0000140E, 0x00000002, 0x0003001D, 0x000007DD, 0x00000017, 0x0003001E, 0x000007B5, 0x000007DD, 0x00040020, 0x00000A32, 0x00000002, 0x000007B5, 0x0004003B, 0x00000A32, 0x0000107A, 0x00000002, 0x00040020, - 0x00000294, 0x00000002, 0x00000017, 0x0006002C, 0x00000014, 0x00000BB1, - 0x00000A10, 0x00000A6A, 0x00000A0D, 0x0005002C, 0x00000011, 0x0000074E, + 0x00000294, 0x00000002, 0x00000017, 0x0006002C, 0x00000014, 0x00000BC3, + 0x00000A16, 0x00000A6A, 0x00000A0D, 0x0005002C, 0x00000011, 0x0000074E, 0x00000A13, 0x00000A13, 0x0007002C, 0x00000017, 0x000009CE, 0x000008A6, 0x000008A6, 0x000008A6, 0x000008A6, 0x0007002C, 0x00000017, 0x0000013D, 0x00000A22, 0x00000A22, 0x00000A22, 0x00000A22, 0x0007002C, 0x00000017, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r4g4b4a4_b4g4r4a4_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r4g4b4a4_b4g4r4a4_cs.h index 4bea3de3a..19e0a3112 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r4g4b4a4_b4g4r4a4_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r4g4b4a4_b4g4r4a4_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 2 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -96,7 +96,7 @@ %_ptr_Uniform__struct_1973 = OpTypePointer Uniform %_struct_1973 %4218 = OpVariable %_ptr_Uniform__struct_1973 Uniform %_ptr_Uniform_v4uint = OpTypePointer Uniform %v4uint -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_2 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %2510 = OpConstantComposite %v4uint %uint_16711935 %uint_16711935 %uint_16711935 %uint_16711935 %317 = OpConstantComposite %v4uint %uint_8 %uint_8 %uint_8 %uint_8 %1838 = OpConstantComposite %v4uint %uint_4278255360 %uint_4278255360 %uint_4278255360 %uint_4278255360 @@ -341,7 +341,7 @@ const uint32_t texture_load_r4g4b4a4_b4g4r4a4_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000002, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -359,7 +359,7 @@ const uint32_t texture_load_r4g4b4a4_b4g4r4a4_cs[] = { 0x00000018, 0x00050048, 0x000007B5, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007B5, 0x00000003, 0x00040047, 0x0000107A, 0x00000022, 0x00000001, 0x00040047, 0x0000107A, 0x00000021, 0x00000000, 0x00040047, - 0x00000BB1, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000017, 0x0000000B, 0x00000004, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, 0x00040017, 0x00000012, 0x0000000C, 0x00000002, @@ -400,7 +400,7 @@ const uint32_t texture_load_r4g4b4a4_b4g4r4a4_cs[] = { 0x0003001D, 0x000007DD, 0x00000017, 0x0003001E, 0x000007B5, 0x000007DD, 0x00040020, 0x00000A32, 0x00000002, 0x000007B5, 0x0004003B, 0x00000A32, 0x0000107A, 0x00000002, 0x00040020, 0x00000294, 0x00000002, 0x00000017, - 0x0006002C, 0x00000014, 0x00000BB1, 0x00000A10, 0x00000A6A, 0x00000A0D, + 0x0006002C, 0x00000014, 0x00000BC3, 0x00000A16, 0x00000A6A, 0x00000A0D, 0x0007002C, 0x00000017, 0x000009CE, 0x000008A6, 0x000008A6, 0x000008A6, 0x000008A6, 0x0007002C, 0x00000017, 0x0000013D, 0x00000A22, 0x00000A22, 0x00000A22, 0x00000A22, 0x0007002C, 0x00000017, 0x0000072E, 0x000005FD, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r4g4b4a4_b4g4r4a4_scaled_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r4g4b4a4_b4g4r4a4_scaled_cs.h index 57368dbe1..440330930 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r4g4b4a4_b4g4r4a4_scaled_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r4g4b4a4_b4g4r4a4_scaled_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 2 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -98,7 +98,7 @@ %_ptr_Uniform__struct_1973 = OpTypePointer Uniform %_struct_1973 %4218 = OpVariable %_ptr_Uniform__struct_1973 Uniform %_ptr_Uniform_v4uint = OpTypePointer Uniform %v4uint -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_2 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %1870 = OpConstantComposite %v2uint %uint_3 %uint_3 %2510 = OpConstantComposite %v4uint %uint_16711935 %uint_16711935 %uint_16711935 %uint_16711935 %317 = OpConstantComposite %v4uint %uint_8 %uint_8 %uint_8 %uint_8 @@ -380,7 +380,7 @@ const uint32_t texture_load_r4g4b4a4_b4g4r4a4_scaled_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000002, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -398,7 +398,7 @@ const uint32_t texture_load_r4g4b4a4_b4g4r4a4_scaled_cs[] = { 0x00000018, 0x00050048, 0x000007B5, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007B5, 0x00000003, 0x00040047, 0x0000107A, 0x00000022, 0x00000001, 0x00040047, 0x0000107A, 0x00000021, 0x00000000, 0x00040047, - 0x00000BB1, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000017, 0x0000000B, 0x00000004, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, 0x00040017, 0x00000012, 0x0000000C, 0x00000002, @@ -440,8 +440,8 @@ const uint32_t texture_load_r4g4b4a4_b4g4r4a4_scaled_cs[] = { 0x00000A31, 0x0000140E, 0x00000002, 0x0003001D, 0x000007DD, 0x00000017, 0x0003001E, 0x000007B5, 0x000007DD, 0x00040020, 0x00000A32, 0x00000002, 0x000007B5, 0x0004003B, 0x00000A32, 0x0000107A, 0x00000002, 0x00040020, - 0x00000294, 0x00000002, 0x00000017, 0x0006002C, 0x00000014, 0x00000BB1, - 0x00000A10, 0x00000A6A, 0x00000A0D, 0x0005002C, 0x00000011, 0x0000074E, + 0x00000294, 0x00000002, 0x00000017, 0x0006002C, 0x00000014, 0x00000BC3, + 0x00000A16, 0x00000A6A, 0x00000A0D, 0x0005002C, 0x00000011, 0x0000074E, 0x00000A13, 0x00000A13, 0x0007002C, 0x00000017, 0x000009CE, 0x000008A6, 0x000008A6, 0x000008A6, 0x000008A6, 0x0007002C, 0x00000017, 0x0000013D, 0x00000A22, 0x00000A22, 0x00000A22, 0x00000A22, 0x0007002C, 0x00000017, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r5g5b5a1_b5g5r5a1_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r5g5b5a1_b5g5r5a1_cs.h index 8db988351..f3c32a6b2 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r5g5b5a1_b5g5r5a1_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r5g5b5a1_b5g5r5a1_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 2 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -97,7 +97,7 @@ %_ptr_Uniform__struct_1973 = OpTypePointer Uniform %_struct_1973 %4218 = OpVariable %_ptr_Uniform__struct_1973 Uniform %_ptr_Uniform_v4uint = OpTypePointer Uniform %v4uint -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_2 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %2510 = OpConstantComposite %v4uint %uint_16711935 %uint_16711935 %uint_16711935 %uint_16711935 %317 = OpConstantComposite %v4uint %uint_8 %uint_8 %uint_8 %uint_8 %1838 = OpConstantComposite %v4uint %uint_4278255360 %uint_4278255360 %uint_4278255360 %uint_4278255360 @@ -343,7 +343,7 @@ const uint32_t texture_load_r5g5b5a1_b5g5r5a1_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000002, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -361,7 +361,7 @@ const uint32_t texture_load_r5g5b5a1_b5g5r5a1_cs[] = { 0x00000018, 0x00050048, 0x000007B5, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007B5, 0x00000003, 0x00040047, 0x0000107A, 0x00000022, 0x00000001, 0x00040047, 0x0000107A, 0x00000021, 0x00000000, 0x00040047, - 0x00000BB1, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000017, 0x0000000B, 0x00000004, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, 0x00040017, 0x00000012, 0x0000000C, 0x00000002, @@ -403,7 +403,7 @@ const uint32_t texture_load_r5g5b5a1_b5g5r5a1_cs[] = { 0x00000017, 0x0003001E, 0x000007B5, 0x000007DD, 0x00040020, 0x00000A32, 0x00000002, 0x000007B5, 0x0004003B, 0x00000A32, 0x0000107A, 0x00000002, 0x00040020, 0x00000294, 0x00000002, 0x00000017, 0x0006002C, 0x00000014, - 0x00000BB1, 0x00000A10, 0x00000A6A, 0x00000A0D, 0x0007002C, 0x00000017, + 0x00000BC3, 0x00000A16, 0x00000A6A, 0x00000A0D, 0x0007002C, 0x00000017, 0x000009CE, 0x000008A6, 0x000008A6, 0x000008A6, 0x000008A6, 0x0007002C, 0x00000017, 0x0000013D, 0x00000A22, 0x00000A22, 0x00000A22, 0x00000A22, 0x0007002C, 0x00000017, 0x0000072E, 0x000005FD, 0x000005FD, 0x000005FD, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r5g5b5a1_b5g5r5a1_scaled_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r5g5b5a1_b5g5r5a1_scaled_cs.h index 50fe01671..aa4259148 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r5g5b5a1_b5g5r5a1_scaled_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r5g5b5a1_b5g5r5a1_scaled_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 2 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -99,7 +99,7 @@ %_ptr_Uniform__struct_1973 = OpTypePointer Uniform %_struct_1973 %4218 = OpVariable %_ptr_Uniform__struct_1973 Uniform %_ptr_Uniform_v4uint = OpTypePointer Uniform %v4uint -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_2 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %1870 = OpConstantComposite %v2uint %uint_3 %uint_3 %2510 = OpConstantComposite %v4uint %uint_16711935 %uint_16711935 %uint_16711935 %uint_16711935 %317 = OpConstantComposite %v4uint %uint_8 %uint_8 %uint_8 %uint_8 @@ -382,7 +382,7 @@ const uint32_t texture_load_r5g5b5a1_b5g5r5a1_scaled_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000002, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -400,7 +400,7 @@ const uint32_t texture_load_r5g5b5a1_b5g5r5a1_scaled_cs[] = { 0x00000018, 0x00050048, 0x000007B5, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007B5, 0x00000003, 0x00040047, 0x0000107A, 0x00000022, 0x00000001, 0x00040047, 0x0000107A, 0x00000021, 0x00000000, 0x00040047, - 0x00000BB1, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000017, 0x0000000B, 0x00000004, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, 0x00040017, 0x00000012, 0x0000000C, 0x00000002, @@ -443,7 +443,7 @@ const uint32_t texture_load_r5g5b5a1_b5g5r5a1_scaled_cs[] = { 0x00000002, 0x0003001D, 0x000007DD, 0x00000017, 0x0003001E, 0x000007B5, 0x000007DD, 0x00040020, 0x00000A32, 0x00000002, 0x000007B5, 0x0004003B, 0x00000A32, 0x0000107A, 0x00000002, 0x00040020, 0x00000294, 0x00000002, - 0x00000017, 0x0006002C, 0x00000014, 0x00000BB1, 0x00000A10, 0x00000A6A, + 0x00000017, 0x0006002C, 0x00000014, 0x00000BC3, 0x00000A16, 0x00000A6A, 0x00000A0D, 0x0005002C, 0x00000011, 0x0000074E, 0x00000A13, 0x00000A13, 0x0007002C, 0x00000017, 0x000009CE, 0x000008A6, 0x000008A6, 0x000008A6, 0x000008A6, 0x0007002C, 0x00000017, 0x0000013D, 0x00000A22, 0x00000A22, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r5g5b6_b5g6r5_swizzle_rbga_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r5g5b6_b5g6r5_swizzle_rbga_cs.h index d0df4e2a2..68ab4ba7e 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r5g5b6_b5g6r5_swizzle_rbga_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r5g5b6_b5g6r5_swizzle_rbga_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 2 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -96,7 +96,7 @@ %_ptr_Uniform__struct_1973 = OpTypePointer Uniform %_struct_1973 %4218 = OpVariable %_ptr_Uniform__struct_1973 Uniform %_ptr_Uniform_v4uint = OpTypePointer Uniform %v4uint -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_2 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %2510 = OpConstantComposite %v4uint %uint_16711935 %uint_16711935 %uint_16711935 %uint_16711935 %317 = OpConstantComposite %v4uint %uint_8 %uint_8 %uint_8 %uint_8 %1838 = OpConstantComposite %v4uint %uint_4278255360 %uint_4278255360 %uint_4278255360 %uint_4278255360 @@ -338,7 +338,7 @@ const uint32_t texture_load_r5g5b6_b5g6r5_swizzle_rbga_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000002, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -356,7 +356,7 @@ const uint32_t texture_load_r5g5b6_b5g6r5_swizzle_rbga_cs[] = { 0x00000018, 0x00050048, 0x000007B5, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007B5, 0x00000003, 0x00040047, 0x0000107A, 0x00000022, 0x00000001, 0x00040047, 0x0000107A, 0x00000021, 0x00000000, 0x00040047, - 0x00000BB1, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000017, 0x0000000B, 0x00000004, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, 0x00040017, 0x00000012, 0x0000000C, 0x00000002, @@ -397,7 +397,7 @@ const uint32_t texture_load_r5g5b6_b5g6r5_swizzle_rbga_cs[] = { 0x0003001D, 0x000007DD, 0x00000017, 0x0003001E, 0x000007B5, 0x000007DD, 0x00040020, 0x00000A32, 0x00000002, 0x000007B5, 0x0004003B, 0x00000A32, 0x0000107A, 0x00000002, 0x00040020, 0x00000294, 0x00000002, 0x00000017, - 0x0006002C, 0x00000014, 0x00000BB1, 0x00000A10, 0x00000A6A, 0x00000A0D, + 0x0006002C, 0x00000014, 0x00000BC3, 0x00000A16, 0x00000A6A, 0x00000A0D, 0x0007002C, 0x00000017, 0x000009CE, 0x000008A6, 0x000008A6, 0x000008A6, 0x000008A6, 0x0007002C, 0x00000017, 0x0000013D, 0x00000A22, 0x00000A22, 0x00000A22, 0x00000A22, 0x0007002C, 0x00000017, 0x0000072E, 0x000005FD, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r5g5b6_b5g6r5_swizzle_rbga_scaled_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r5g5b6_b5g6r5_swizzle_rbga_scaled_cs.h index c5d8f8bdb..2d324ed74 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r5g5b6_b5g6r5_swizzle_rbga_scaled_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r5g5b6_b5g6r5_swizzle_rbga_scaled_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 2 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -98,7 +98,7 @@ %_ptr_Uniform__struct_1973 = OpTypePointer Uniform %_struct_1973 %4218 = OpVariable %_ptr_Uniform__struct_1973 Uniform %_ptr_Uniform_v4uint = OpTypePointer Uniform %v4uint -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_2 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %1870 = OpConstantComposite %v2uint %uint_3 %uint_3 %2510 = OpConstantComposite %v4uint %uint_16711935 %uint_16711935 %uint_16711935 %uint_16711935 %317 = OpConstantComposite %v4uint %uint_8 %uint_8 %uint_8 %uint_8 @@ -377,7 +377,7 @@ const uint32_t texture_load_r5g5b6_b5g6r5_swizzle_rbga_scaled_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000002, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -395,7 +395,7 @@ const uint32_t texture_load_r5g5b6_b5g6r5_swizzle_rbga_scaled_cs[] = { 0x00000018, 0x00050048, 0x000007B5, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007B5, 0x00000003, 0x00040047, 0x0000107A, 0x00000022, 0x00000001, 0x00040047, 0x0000107A, 0x00000021, 0x00000000, 0x00040047, - 0x00000BB1, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000017, 0x0000000B, 0x00000004, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, 0x00040017, 0x00000012, 0x0000000C, 0x00000002, @@ -437,8 +437,8 @@ const uint32_t texture_load_r5g5b6_b5g6r5_swizzle_rbga_scaled_cs[] = { 0x00000A31, 0x0000140E, 0x00000002, 0x0003001D, 0x000007DD, 0x00000017, 0x0003001E, 0x000007B5, 0x000007DD, 0x00040020, 0x00000A32, 0x00000002, 0x000007B5, 0x0004003B, 0x00000A32, 0x0000107A, 0x00000002, 0x00040020, - 0x00000294, 0x00000002, 0x00000017, 0x0006002C, 0x00000014, 0x00000BB1, - 0x00000A10, 0x00000A6A, 0x00000A0D, 0x0005002C, 0x00000011, 0x0000074E, + 0x00000294, 0x00000002, 0x00000017, 0x0006002C, 0x00000014, 0x00000BC3, + 0x00000A16, 0x00000A6A, 0x00000A0D, 0x0005002C, 0x00000011, 0x0000074E, 0x00000A13, 0x00000A13, 0x0007002C, 0x00000017, 0x000009CE, 0x000008A6, 0x000008A6, 0x000008A6, 0x000008A6, 0x0007002C, 0x00000017, 0x0000013D, 0x00000A22, 0x00000A22, 0x00000A22, 0x00000A22, 0x0007002C, 0x00000017, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r5g6b5_b5g6r5_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r5g6b5_b5g6r5_cs.h index ae5082f7e..8017f60e8 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r5g6b5_b5g6r5_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r5g6b5_b5g6r5_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 2 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -97,7 +97,7 @@ %_ptr_Uniform__struct_1973 = OpTypePointer Uniform %_struct_1973 %4218 = OpVariable %_ptr_Uniform__struct_1973 Uniform %_ptr_Uniform_v4uint = OpTypePointer Uniform %v4uint -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_2 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %2510 = OpConstantComposite %v4uint %uint_16711935 %uint_16711935 %uint_16711935 %uint_16711935 %317 = OpConstantComposite %v4uint %uint_8 %uint_8 %uint_8 %uint_8 %1838 = OpConstantComposite %v4uint %uint_4278255360 %uint_4278255360 %uint_4278255360 %uint_4278255360 @@ -343,7 +343,7 @@ const uint32_t texture_load_r5g6b5_b5g6r5_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000002, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -361,7 +361,7 @@ const uint32_t texture_load_r5g6b5_b5g6r5_cs[] = { 0x00000018, 0x00050048, 0x000007B5, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007B5, 0x00000003, 0x00040047, 0x0000107A, 0x00000022, 0x00000001, 0x00040047, 0x0000107A, 0x00000021, 0x00000000, 0x00040047, - 0x00000BB1, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000017, 0x0000000B, 0x00000004, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, 0x00040017, 0x00000012, 0x0000000C, 0x00000002, @@ -403,7 +403,7 @@ const uint32_t texture_load_r5g6b5_b5g6r5_cs[] = { 0x00000017, 0x0003001E, 0x000007B5, 0x000007DD, 0x00040020, 0x00000A32, 0x00000002, 0x000007B5, 0x0004003B, 0x00000A32, 0x0000107A, 0x00000002, 0x00040020, 0x00000294, 0x00000002, 0x00000017, 0x0006002C, 0x00000014, - 0x00000BB1, 0x00000A10, 0x00000A6A, 0x00000A0D, 0x0007002C, 0x00000017, + 0x00000BC3, 0x00000A16, 0x00000A6A, 0x00000A0D, 0x0007002C, 0x00000017, 0x000009CE, 0x000008A6, 0x000008A6, 0x000008A6, 0x000008A6, 0x0007002C, 0x00000017, 0x0000013D, 0x00000A22, 0x00000A22, 0x00000A22, 0x00000A22, 0x0007002C, 0x00000017, 0x0000072E, 0x000005FD, 0x000005FD, 0x000005FD, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r5g6b5_b5g6r5_scaled_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r5g6b5_b5g6r5_scaled_cs.h index e3119a1a8..edf6dcf17 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r5g6b5_b5g6r5_scaled_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_r5g6b5_b5g6r5_scaled_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 2 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -99,7 +99,7 @@ %_ptr_Uniform__struct_1973 = OpTypePointer Uniform %_struct_1973 %4218 = OpVariable %_ptr_Uniform__struct_1973 Uniform %_ptr_Uniform_v4uint = OpTypePointer Uniform %v4uint -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_2 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %1870 = OpConstantComposite %v2uint %uint_3 %uint_3 %2510 = OpConstantComposite %v4uint %uint_16711935 %uint_16711935 %uint_16711935 %uint_16711935 %317 = OpConstantComposite %v4uint %uint_8 %uint_8 %uint_8 %uint_8 @@ -382,7 +382,7 @@ const uint32_t texture_load_r5g6b5_b5g6r5_scaled_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000002, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -400,7 +400,7 @@ const uint32_t texture_load_r5g6b5_b5g6r5_scaled_cs[] = { 0x00000018, 0x00050048, 0x000007B5, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007B5, 0x00000003, 0x00040047, 0x0000107A, 0x00000022, 0x00000001, 0x00040047, 0x0000107A, 0x00000021, 0x00000000, 0x00040047, - 0x00000BB1, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000017, 0x0000000B, 0x00000004, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, 0x00040017, 0x00000012, 0x0000000C, 0x00000002, @@ -443,7 +443,7 @@ const uint32_t texture_load_r5g6b5_b5g6r5_scaled_cs[] = { 0x00000002, 0x0003001D, 0x000007DD, 0x00000017, 0x0003001E, 0x000007B5, 0x000007DD, 0x00040020, 0x00000A32, 0x00000002, 0x000007B5, 0x0004003B, 0x00000A32, 0x0000107A, 0x00000002, 0x00040020, 0x00000294, 0x00000002, - 0x00000017, 0x0006002C, 0x00000014, 0x00000BB1, 0x00000A10, 0x00000A6A, + 0x00000017, 0x0006002C, 0x00000014, 0x00000BC3, 0x00000A16, 0x00000A6A, 0x00000A0D, 0x0005002C, 0x00000011, 0x0000074E, 0x00000A13, 0x00000A13, 0x0007002C, 0x00000017, 0x000009CE, 0x000008A6, 0x000008A6, 0x000008A6, 0x000008A6, 0x0007002C, 0x00000017, 0x0000013D, 0x00000A22, 0x00000A22, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_rgba16_snorm_float_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_rgba16_snorm_float_cs.h index c33cb5293..fa6d8f5cf 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_rgba16_snorm_float_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_rgba16_snorm_float_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 8 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -99,7 +99,7 @@ %_ptr_Uniform__struct_1973 = OpTypePointer Uniform %_struct_1973 %4218 = OpVariable %_ptr_Uniform__struct_1973 Uniform %_ptr_Uniform_v4uint = OpTypePointer Uniform %v4uint -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_8 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %uint_9 = OpConstant %uint 9 %uint_10 = OpConstant %uint 10 %2510 = OpConstantComposite %v4uint %uint_16711935 %uint_16711935 %uint_16711935 %uint_16711935 @@ -406,7 +406,7 @@ const uint32_t texture_load_rgba16_snorm_float_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000008, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -424,7 +424,7 @@ const uint32_t texture_load_rgba16_snorm_float_cs[] = { 0x00000018, 0x00050048, 0x000007B5, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007B5, 0x00000003, 0x00040047, 0x0000107A, 0x00000022, 0x00000001, 0x00040047, 0x0000107A, 0x00000021, 0x00000000, 0x00040047, - 0x00000024, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000017, 0x0000000B, 0x00000004, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, 0x00040017, 0x00000012, 0x0000000C, 0x00000002, @@ -467,7 +467,7 @@ const uint32_t texture_load_rgba16_snorm_float_cs[] = { 0x0000140E, 0x00000002, 0x0003001D, 0x000007DD, 0x00000017, 0x0003001E, 0x000007B5, 0x000007DD, 0x00040020, 0x00000A32, 0x00000002, 0x000007B5, 0x0004003B, 0x00000A32, 0x0000107A, 0x00000002, 0x00040020, 0x00000294, - 0x00000002, 0x00000017, 0x0006002C, 0x00000014, 0x00000024, 0x00000A22, + 0x00000002, 0x00000017, 0x0006002C, 0x00000014, 0x00000BC3, 0x00000A16, 0x00000A6A, 0x00000A0D, 0x0004002B, 0x0000000B, 0x00000A25, 0x00000009, 0x0004002B, 0x0000000B, 0x00000A28, 0x0000000A, 0x0007002C, 0x00000017, 0x000009CE, 0x000008A6, 0x000008A6, 0x000008A6, 0x000008A6, 0x0007002C, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_rgba16_snorm_float_scaled_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_rgba16_snorm_float_scaled_cs.h index e5e2f3919..b31f50daf 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_rgba16_snorm_float_scaled_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_rgba16_snorm_float_scaled_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 8 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -101,7 +101,7 @@ %_ptr_Uniform__struct_1973 = OpTypePointer Uniform %_struct_1973 %4218 = OpVariable %_ptr_Uniform__struct_1973 Uniform %_ptr_Uniform_v4uint = OpTypePointer Uniform %v4uint -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_8 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %1870 = OpConstantComposite %v2uint %uint_3 %uint_3 %uint_9 = OpConstant %uint 9 %uint_10 = OpConstant %uint 10 @@ -445,7 +445,7 @@ const uint32_t texture_load_rgba16_snorm_float_scaled_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000008, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -463,7 +463,7 @@ const uint32_t texture_load_rgba16_snorm_float_scaled_cs[] = { 0x00000018, 0x00050048, 0x000007B5, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007B5, 0x00000003, 0x00040047, 0x0000107A, 0x00000022, 0x00000001, 0x00040047, 0x0000107A, 0x00000021, 0x00000000, 0x00040047, - 0x00000024, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000017, 0x0000000B, 0x00000004, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, 0x00040017, 0x00000012, 0x0000000C, 0x00000002, @@ -508,7 +508,7 @@ const uint32_t texture_load_rgba16_snorm_float_scaled_cs[] = { 0x000007DD, 0x00000017, 0x0003001E, 0x000007B5, 0x000007DD, 0x00040020, 0x00000A32, 0x00000002, 0x000007B5, 0x0004003B, 0x00000A32, 0x0000107A, 0x00000002, 0x00040020, 0x00000294, 0x00000002, 0x00000017, 0x0006002C, - 0x00000014, 0x00000024, 0x00000A22, 0x00000A6A, 0x00000A0D, 0x0005002C, + 0x00000014, 0x00000BC3, 0x00000A16, 0x00000A6A, 0x00000A0D, 0x0005002C, 0x00000011, 0x0000074E, 0x00000A13, 0x00000A13, 0x0004002B, 0x0000000B, 0x00000A25, 0x00000009, 0x0004002B, 0x0000000B, 0x00000A28, 0x0000000A, 0x0007002C, 0x00000017, 0x000009CE, 0x000008A6, 0x000008A6, 0x000008A6, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_rgba16_unorm_float_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_rgba16_unorm_float_cs.h index 760706d7e..a78af2e24 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_rgba16_unorm_float_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_rgba16_unorm_float_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 8 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -97,7 +97,7 @@ %_ptr_Uniform__struct_1973 = OpTypePointer Uniform %_struct_1973 %4218 = OpVariable %_ptr_Uniform__struct_1973 Uniform %_ptr_Uniform_v4uint = OpTypePointer Uniform %v4uint -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_8 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %uint_9 = OpConstant %uint 9 %uint_10 = OpConstant %uint 10 %2510 = OpConstantComposite %v4uint %uint_16711935 %uint_16711935 %uint_16711935 %uint_16711935 @@ -396,7 +396,7 @@ const uint32_t texture_load_rgba16_unorm_float_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000008, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -414,7 +414,7 @@ const uint32_t texture_load_rgba16_unorm_float_cs[] = { 0x00000018, 0x00050048, 0x000007B5, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007B5, 0x00000003, 0x00040047, 0x0000107A, 0x00000022, 0x00000001, 0x00040047, 0x0000107A, 0x00000021, 0x00000000, 0x00040047, - 0x00000024, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000017, 0x0000000B, 0x00000004, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, 0x00040017, 0x00000012, 0x0000000C, 0x00000002, @@ -455,8 +455,8 @@ const uint32_t texture_load_rgba16_unorm_float_cs[] = { 0x00000A31, 0x0000140E, 0x00000002, 0x0003001D, 0x000007DD, 0x00000017, 0x0003001E, 0x000007B5, 0x000007DD, 0x00040020, 0x00000A32, 0x00000002, 0x000007B5, 0x0004003B, 0x00000A32, 0x0000107A, 0x00000002, 0x00040020, - 0x00000294, 0x00000002, 0x00000017, 0x0006002C, 0x00000014, 0x00000024, - 0x00000A22, 0x00000A6A, 0x00000A0D, 0x0004002B, 0x0000000B, 0x00000A25, + 0x00000294, 0x00000002, 0x00000017, 0x0006002C, 0x00000014, 0x00000BC3, + 0x00000A16, 0x00000A6A, 0x00000A0D, 0x0004002B, 0x0000000B, 0x00000A25, 0x00000009, 0x0004002B, 0x0000000B, 0x00000A28, 0x0000000A, 0x0007002C, 0x00000017, 0x000009CE, 0x000008A6, 0x000008A6, 0x000008A6, 0x000008A6, 0x0007002C, 0x00000017, 0x0000013D, 0x00000A22, 0x00000A22, 0x00000A22, diff --git a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_rgba16_unorm_float_scaled_cs.h b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_rgba16_unorm_float_scaled_cs.h index fdc8c9614..0691d084c 100644 --- a/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_rgba16_unorm_float_scaled_cs.h +++ b/src/xenia/gpu/shaders/bytecode/vulkan_spirv/texture_load_rgba16_unorm_float_scaled_cs.h @@ -9,7 +9,7 @@ %1 = OpExtInstImport "GLSL.std.450" OpMemoryModel Logical GLSL450 OpEntryPoint GLCompute %5663 "main" %gl_GlobalInvocationID - OpExecutionMode %5663 LocalSize 8 32 1 + OpExecutionMode %5663 LocalSize 4 32 1 OpMemberDecorate %_struct_1161 0 Offset 0 OpMemberDecorate %_struct_1161 1 Offset 4 OpMemberDecorate %_struct_1161 2 Offset 8 @@ -99,7 +99,7 @@ %_ptr_Uniform__struct_1973 = OpTypePointer Uniform %_struct_1973 %4218 = OpVariable %_ptr_Uniform__struct_1973 Uniform %_ptr_Uniform_v4uint = OpTypePointer Uniform %v4uint -%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_8 %uint_32 %uint_1 +%gl_WorkGroupSize = OpConstantComposite %v3uint %uint_4 %uint_32 %uint_1 %1870 = OpConstantComposite %v2uint %uint_3 %uint_3 %uint_9 = OpConstant %uint 9 %uint_10 = OpConstant %uint 10 @@ -435,7 +435,7 @@ const uint32_t texture_load_rgba16_unorm_float_scaled_cs[] = { 0x00000001, 0x0006000B, 0x00000001, 0x4C534C47, 0x6474732E, 0x3035342E, 0x00000000, 0x0003000E, 0x00000000, 0x00000001, 0x0006000F, 0x00000005, 0x0000161F, 0x6E69616D, 0x00000000, 0x00000F48, 0x00060010, 0x0000161F, - 0x00000011, 0x00000008, 0x00000020, 0x00000001, 0x00050048, 0x00000489, + 0x00000011, 0x00000004, 0x00000020, 0x00000001, 0x00050048, 0x00000489, 0x00000000, 0x00000023, 0x00000000, 0x00050048, 0x00000489, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x00000489, 0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x00000489, 0x00000003, 0x00000023, 0x0000000C, @@ -453,7 +453,7 @@ const uint32_t texture_load_rgba16_unorm_float_scaled_cs[] = { 0x00000018, 0x00050048, 0x000007B5, 0x00000000, 0x00000023, 0x00000000, 0x00030047, 0x000007B5, 0x00000003, 0x00040047, 0x0000107A, 0x00000022, 0x00000001, 0x00040047, 0x0000107A, 0x00000021, 0x00000000, 0x00040047, - 0x00000024, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, + 0x00000BC3, 0x0000000B, 0x00000019, 0x00020013, 0x00000008, 0x00030021, 0x00000502, 0x00000008, 0x00040015, 0x0000000B, 0x00000020, 0x00000000, 0x00040017, 0x00000017, 0x0000000B, 0x00000004, 0x00040015, 0x0000000C, 0x00000020, 0x00000001, 0x00040017, 0x00000012, 0x0000000C, 0x00000002, @@ -496,7 +496,7 @@ const uint32_t texture_load_rgba16_unorm_float_scaled_cs[] = { 0x0003001D, 0x000007DD, 0x00000017, 0x0003001E, 0x000007B5, 0x000007DD, 0x00040020, 0x00000A32, 0x00000002, 0x000007B5, 0x0004003B, 0x00000A32, 0x0000107A, 0x00000002, 0x00040020, 0x00000294, 0x00000002, 0x00000017, - 0x0006002C, 0x00000014, 0x00000024, 0x00000A22, 0x00000A6A, 0x00000A0D, + 0x0006002C, 0x00000014, 0x00000BC3, 0x00000A16, 0x00000A6A, 0x00000A0D, 0x0005002C, 0x00000011, 0x0000074E, 0x00000A13, 0x00000A13, 0x0004002B, 0x0000000B, 0x00000A25, 0x00000009, 0x0004002B, 0x0000000B, 0x00000A28, 0x0000000A, 0x0007002C, 0x00000017, 0x000009CE, 0x000008A6, 0x000008A6, diff --git a/src/xenia/gpu/shaders/texture_load.xesli b/src/xenia/gpu/shaders/texture_load.xesli index 92c50cc4e..036bc8117 100644 --- a/src/xenia/gpu/shaders/texture_load.xesli +++ b/src/xenia/gpu/shaders/texture_load.xesli @@ -13,6 +13,18 @@ #include "endian.xesli" #include "texture_address.xesli" +// 128 threads per group (the maximum wave size supported by DXIL and SPIR-V, +// and the minimum required number of threads per group on Vulkan), laid out as +// 4x32 (32 texels along Y per group - one guest tile) - starting with 64x32 +// blocks (2x1 guest tiles) per group for 8bpb / 16bpb, and smaller for larger +// block sizes. Since the mip tail is packed in 32x / x32 storage, there's no +// need for the Y group size smaller than 32 - 8x16, for instance, would result +// in 128x16 blocks per group for 8bpb / 16bpb, and for a 32x32 mip tail, there +// would be two groups rather than one, for a total of 128x32 blocks - 75% of +// the work will be wasted rather than 50% with one 64x32-block group. +#define XeTextureLoadGroupSizeX 4 +#define XeTextureLoadGroupSizeY 32 + xesl_cbuffer_begin(xe_texture_load_constants, set=2, binding=0, b0, space0) uint xe_texture_load_is_tiled_3d_endian_scale; // Base offset in bytes, resolution-scaled. diff --git a/src/xenia/gpu/shaders/texture_load_128bpb.xesli b/src/xenia/gpu/shaders/texture_load_128bpb.xesli index e26e7d9b7..c98c03605 100644 --- a/src/xenia/gpu/shaders/texture_load_128bpb.xesli +++ b/src/xenia/gpu/shaders/texture_load_128bpb.xesli @@ -15,7 +15,8 @@ xesl_entry xesl_entry_binding_next xesl_typedStorageBuffer(xesl_uint4, xe_texture_load_source, set=1, binding=0, t0, space0) -xesl_entry_bindings_end_local_size(16, 32, 1) +xesl_entry_bindings_end_local_size(XeTextureLoadGroupSizeX, + XeTextureLoadGroupSizeY, 1) xesl_input_global_invocation_id xesl_entry_signature_end // 1 thread = 2 blocks. diff --git a/src/xenia/gpu/shaders/texture_load_16bpb.xesli b/src/xenia/gpu/shaders/texture_load_16bpb.xesli index 4dbcc08bb..5cdb3207f 100644 --- a/src/xenia/gpu/shaders/texture_load_16bpb.xesli +++ b/src/xenia/gpu/shaders/texture_load_16bpb.xesli @@ -15,7 +15,8 @@ xesl_entry xesl_entry_binding_next xesl_typedStorageBuffer(xesl_uint4, xe_texture_load_source, set=1, binding=0, t0, space0) -xesl_entry_bindings_end_local_size(2, 32, 1) +xesl_entry_bindings_end_local_size(XeTextureLoadGroupSizeX, + XeTextureLoadGroupSizeY, 1) xesl_input_global_invocation_id xesl_entry_signature_end // 1 thread = 16 blocks passed through an externally provided diff --git a/src/xenia/gpu/shaders/texture_load_32bpb.xesli b/src/xenia/gpu/shaders/texture_load_32bpb.xesli index 27b479ee1..d56168ded 100644 --- a/src/xenia/gpu/shaders/texture_load_32bpb.xesli +++ b/src/xenia/gpu/shaders/texture_load_32bpb.xesli @@ -15,7 +15,8 @@ xesl_entry xesl_entry_binding_next xesl_typedStorageBuffer(xesl_uint4, xe_texture_load_source, set=1, binding=0, t0, space0) -xesl_entry_bindings_end_local_size(4, 32, 1) +xesl_entry_bindings_end_local_size(XeTextureLoadGroupSizeX, + XeTextureLoadGroupSizeY, 1) xesl_input_global_invocation_id xesl_entry_signature_end // 1 thread = 8 blocks passed through an externally provided diff --git a/src/xenia/gpu/shaders/texture_load_32bpb_64bpb.xesli b/src/xenia/gpu/shaders/texture_load_32bpb_64bpb.xesli index cc960acfd..a48dce4a8 100644 --- a/src/xenia/gpu/shaders/texture_load_32bpb_64bpb.xesli +++ b/src/xenia/gpu/shaders/texture_load_32bpb_64bpb.xesli @@ -15,7 +15,8 @@ xesl_entry xesl_entry_binding_next xesl_typedStorageBuffer(xesl_uint4, xe_texture_load_source, set=1, binding=0, t0, space0) -xesl_entry_bindings_end_local_size(4, 32, 1) +xesl_entry_bindings_end_local_size(XeTextureLoadGroupSizeX, + XeTextureLoadGroupSizeY, 1) xesl_input_global_invocation_id xesl_entry_signature_end // 1 thread = 8 packed 32-bit texels with the externally provided uint4 -> 2x diff --git a/src/xenia/gpu/shaders/texture_load_64bpb.xesli b/src/xenia/gpu/shaders/texture_load_64bpb.xesli index f167c4eb8..55ed8e3dd 100644 --- a/src/xenia/gpu/shaders/texture_load_64bpb.xesli +++ b/src/xenia/gpu/shaders/texture_load_64bpb.xesli @@ -15,7 +15,8 @@ xesl_entry xesl_entry_binding_next xesl_typedStorageBuffer(xesl_uint4, xe_texture_load_source, set=1, binding=0, t0, space0) -xesl_entry_bindings_end_local_size(8, 32, 1) +xesl_entry_bindings_end_local_size(XeTextureLoadGroupSizeX, + XeTextureLoadGroupSizeY, 1) xesl_input_global_invocation_id xesl_entry_signature_end // 1 thread = 4 blocks passed through an externally provided diff --git a/src/xenia/gpu/shaders/texture_load_8bpb.xesli b/src/xenia/gpu/shaders/texture_load_8bpb.xesli index ecc60afdc..dcb6cab05 100644 --- a/src/xenia/gpu/shaders/texture_load_8bpb.xesli +++ b/src/xenia/gpu/shaders/texture_load_8bpb.xesli @@ -15,7 +15,8 @@ xesl_entry xesl_entry_binding_next xesl_typedStorageBuffer(xesl_uint2, xe_texture_load_source, set=1, binding=0, t0, space0) -xesl_entry_bindings_end_local_size(2, 32, 1) +xesl_entry_bindings_end_local_size(XeTextureLoadGroupSizeX, + XeTextureLoadGroupSizeY, 1) xesl_input_global_invocation_id xesl_entry_signature_end // 1 thread = 16 blocks. diff --git a/src/xenia/gpu/shaders/texture_load_ctx1.cs.xesl b/src/xenia/gpu/shaders/texture_load_ctx1.cs.xesl index 6aa92ed37..81e07ae1e 100644 --- a/src/xenia/gpu/shaders/texture_load_ctx1.cs.xesl +++ b/src/xenia/gpu/shaders/texture_load_ctx1.cs.xesl @@ -30,7 +30,8 @@ xesl_entry xesl_entry_binding_next xesl_typedStorageBuffer(xesl_uint4, xe_texture_load_source, set=1, binding=0, t0, space0) -xesl_entry_bindings_end_local_size(8, 32, 1) +xesl_entry_bindings_end_local_size(XeTextureLoadGroupSizeX, + XeTextureLoadGroupSizeY, 1) xesl_input_global_invocation_id xesl_entry_signature_end // 1 thread = 4 CTX1 blocks to 16x4 R8G8 texels. diff --git a/src/xenia/gpu/shaders/texture_load_dxn_rg8.cs.xesl b/src/xenia/gpu/shaders/texture_load_dxn_rg8.cs.xesl index b89681973..465fe8719 100644 --- a/src/xenia/gpu/shaders/texture_load_dxn_rg8.cs.xesl +++ b/src/xenia/gpu/shaders/texture_load_dxn_rg8.cs.xesl @@ -16,7 +16,8 @@ xesl_entry xesl_entry_binding_next xesl_typedStorageBuffer(xesl_uint4, xe_texture_load_source, set=1, binding=0, t0, space0) -xesl_entry_bindings_end_local_size(16, 32, 1) +xesl_entry_bindings_end_local_size(XeTextureLoadGroupSizeX, + XeTextureLoadGroupSizeY, 1) xesl_input_global_invocation_id xesl_entry_signature_end // 1 thread = 2 DXN blocks to 8x4 R8G8 texels. diff --git a/src/xenia/gpu/shaders/texture_load_dxt1_rgba8.cs.xesl b/src/xenia/gpu/shaders/texture_load_dxt1_rgba8.cs.xesl index 2829666d0..4ace2fc19 100644 --- a/src/xenia/gpu/shaders/texture_load_dxt1_rgba8.cs.xesl +++ b/src/xenia/gpu/shaders/texture_load_dxt1_rgba8.cs.xesl @@ -16,7 +16,8 @@ xesl_entry xesl_entry_binding_next xesl_typedStorageBuffer(xesl_uint4, xe_texture_load_source, set=1, binding=0, t0, space0) -xesl_entry_bindings_end_local_size(8, 32, 1) +xesl_entry_bindings_end_local_size(XeTextureLoadGroupSizeX, + XeTextureLoadGroupSizeY, 1) xesl_input_global_invocation_id xesl_entry_signature_end // 1 thread = 4 DXT1 blocks to 16x4 R8G8B8A8 texels. diff --git a/src/xenia/gpu/shaders/texture_load_dxt3_rgba8.cs.xesl b/src/xenia/gpu/shaders/texture_load_dxt3_rgba8.cs.xesl index fe8cf4f32..1e6dfd435 100644 --- a/src/xenia/gpu/shaders/texture_load_dxt3_rgba8.cs.xesl +++ b/src/xenia/gpu/shaders/texture_load_dxt3_rgba8.cs.xesl @@ -16,7 +16,8 @@ xesl_entry xesl_entry_binding_next xesl_typedStorageBuffer(xesl_uint4, xe_texture_load_source, set=1, binding=0, t0, space0) -xesl_entry_bindings_end_local_size(16, 32, 1) +xesl_entry_bindings_end_local_size(XeTextureLoadGroupSizeX, + XeTextureLoadGroupSizeY, 1) xesl_input_global_invocation_id xesl_entry_signature_end // 1 thread = 2 DXT3 blocks to 8x4 R8G8B8A8 texels. diff --git a/src/xenia/gpu/shaders/texture_load_dxt3a.cs.xesl b/src/xenia/gpu/shaders/texture_load_dxt3a.cs.xesl index ced671884..a735b6af0 100644 --- a/src/xenia/gpu/shaders/texture_load_dxt3a.cs.xesl +++ b/src/xenia/gpu/shaders/texture_load_dxt3a.cs.xesl @@ -16,7 +16,8 @@ xesl_entry xesl_entry_binding_next xesl_typedStorageBuffer(xesl_uint4, xe_texture_load_source, set=1, binding=0, t0, space0) -xesl_entry_bindings_end_local_size(8, 32, 1) +xesl_entry_bindings_end_local_size(XeTextureLoadGroupSizeX, + XeTextureLoadGroupSizeY, 1) xesl_input_global_invocation_id xesl_entry_signature_end // 1 thread = 4 DXT3A blocks to 16x4 R8 texels (no need to convert to DXT3 diff --git a/src/xenia/gpu/shaders/texture_load_dxt3aas1111.xesli b/src/xenia/gpu/shaders/texture_load_dxt3aas1111.xesli index 3ce036013..607b8e55f 100644 --- a/src/xenia/gpu/shaders/texture_load_dxt3aas1111.xesli +++ b/src/xenia/gpu/shaders/texture_load_dxt3aas1111.xesli @@ -15,7 +15,8 @@ xesl_entry xesl_entry_binding_next xesl_typedStorageBuffer(xesl_uint4, xe_texture_load_source, set=1, binding=0, t0, space0) -xesl_entry_bindings_end_local_size(8, 32, 1) +xesl_entry_bindings_end_local_size(XeTextureLoadGroupSizeX, + XeTextureLoadGroupSizeY, 1) xesl_input_global_invocation_id xesl_entry_signature_end // 1 thread = 4 DXT3A-as-1111 blocks to 16x4 16bpp texels passed through an diff --git a/src/xenia/gpu/shaders/texture_load_dxt5_rgba8.cs.xesl b/src/xenia/gpu/shaders/texture_load_dxt5_rgba8.cs.xesl index 58df86f9a..63473faf1 100644 --- a/src/xenia/gpu/shaders/texture_load_dxt5_rgba8.cs.xesl +++ b/src/xenia/gpu/shaders/texture_load_dxt5_rgba8.cs.xesl @@ -16,7 +16,8 @@ xesl_entry xesl_entry_binding_next xesl_typedStorageBuffer(xesl_uint4, xe_texture_load_source, set=1, binding=0, t0, space0) -xesl_entry_bindings_end_local_size(16, 32, 1) +xesl_entry_bindings_end_local_size(XeTextureLoadGroupSizeX, + XeTextureLoadGroupSizeY, 1) xesl_input_global_invocation_id xesl_entry_signature_end // 1 thread = 2 DXT5 blocks to 8x4 R8G8B8A8 texels. diff --git a/src/xenia/gpu/shaders/texture_load_dxt5a_r8.cs.xesl b/src/xenia/gpu/shaders/texture_load_dxt5a_r8.cs.xesl index e0df0f980..e6f4afa14 100644 --- a/src/xenia/gpu/shaders/texture_load_dxt5a_r8.cs.xesl +++ b/src/xenia/gpu/shaders/texture_load_dxt5a_r8.cs.xesl @@ -16,7 +16,8 @@ xesl_entry xesl_entry_binding_next xesl_typedStorageBuffer(xesl_uint4, xe_texture_load_source, set=1, binding=0, t0, space0) -xesl_entry_bindings_end_local_size(8, 32, 1) +xesl_entry_bindings_end_local_size(XeTextureLoadGroupSizeX, + XeTextureLoadGroupSizeY, 1) xesl_input_global_invocation_id xesl_entry_signature_end // 1 thread = 4 DXT5A blocks to 16x4 R8 texels. diff --git a/src/xenia/ui/shaders/xesl.xesli b/src/xenia/ui/shaders/xesl.xesli index cf856e094..0b50bd162 100644 --- a/src/xenia/ui/shaders/xesl.xesli +++ b/src/xenia/ui/shaders/xesl.xesli @@ -103,6 +103,16 @@ // HLSL linkage. // Both binding and signature entry names may be placed in the global scope in // the target language, make sure they don't collide with anything there. +// +// In compute shaders, the total group size must not exceed 128 threads (unless +// the shader is used with the appropriate conditionals), as that's the minimum +// maxComputeWorkGroupInvocations requirement on Vulkan. 128 threads exactly is +// the recommended group size overall, especially for shaders not using the +// group functionality, as it's the maximum wave size supported by DXIL and +// SPIR-V wave operations, and there are PowerVR GPUs with 128-lane waves, so +// it provides balance between wave utilization and excess thread (and, on GPUs +// with smaller waves, wave) count if the size of the actual work domain is not +// aligned to the group size. #if XESL_LANGUAGE_GLSL #define xesl_entry_bindings_end_local_size(x, y, z) \ layout(local_size_x=(x), local_size_y=(y), local_size_z=(z)) in;