[GPU] Add k prefix to texture load group size constants
This commit is contained in:
parent
8f06ba6f7d
commit
2f0a884438
|
@ -22,8 +22,8 @@
|
|||
// 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
|
||||
#define kXeTextureLoadGroupSizeX 4
|
||||
#define kXeTextureLoadGroupSizeY 32
|
||||
|
||||
xesl_cbuffer_begin(xe_texture_load_constants, set=2, binding=0, b0, space0)
|
||||
uint xe_texture_load_is_tiled_3d_endian_scale;
|
||||
|
|
|
@ -15,8 +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(XeTextureLoadGroupSizeX,
|
||||
XeTextureLoadGroupSizeY, 1)
|
||||
xesl_entry_bindings_end_local_size(kXeTextureLoadGroupSizeX,
|
||||
kXeTextureLoadGroupSizeY, 1)
|
||||
xesl_input_global_invocation_id
|
||||
xesl_entry_signature_end
|
||||
// 1 thread = 2 blocks.
|
||||
|
|
|
@ -15,8 +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(XeTextureLoadGroupSizeX,
|
||||
XeTextureLoadGroupSizeY, 1)
|
||||
xesl_entry_bindings_end_local_size(kXeTextureLoadGroupSizeX,
|
||||
kXeTextureLoadGroupSizeY, 1)
|
||||
xesl_input_global_invocation_id
|
||||
xesl_entry_signature_end
|
||||
// 1 thread = 16 blocks passed through an externally provided
|
||||
|
|
|
@ -15,8 +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(XeTextureLoadGroupSizeX,
|
||||
XeTextureLoadGroupSizeY, 1)
|
||||
xesl_entry_bindings_end_local_size(kXeTextureLoadGroupSizeX,
|
||||
kXeTextureLoadGroupSizeY, 1)
|
||||
xesl_input_global_invocation_id
|
||||
xesl_entry_signature_end
|
||||
// 1 thread = 8 blocks passed through an externally provided
|
||||
|
|
|
@ -15,8 +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(XeTextureLoadGroupSizeX,
|
||||
XeTextureLoadGroupSizeY, 1)
|
||||
xesl_entry_bindings_end_local_size(kXeTextureLoadGroupSizeX,
|
||||
kXeTextureLoadGroupSizeY, 1)
|
||||
xesl_input_global_invocation_id
|
||||
xesl_entry_signature_end
|
||||
// 1 thread = 8 packed 32-bit texels with the externally provided uint4 -> 2x
|
||||
|
|
|
@ -15,8 +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(XeTextureLoadGroupSizeX,
|
||||
XeTextureLoadGroupSizeY, 1)
|
||||
xesl_entry_bindings_end_local_size(kXeTextureLoadGroupSizeX,
|
||||
kXeTextureLoadGroupSizeY, 1)
|
||||
xesl_input_global_invocation_id
|
||||
xesl_entry_signature_end
|
||||
// 1 thread = 4 blocks passed through an externally provided
|
||||
|
|
|
@ -15,8 +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(XeTextureLoadGroupSizeX,
|
||||
XeTextureLoadGroupSizeY, 1)
|
||||
xesl_entry_bindings_end_local_size(kXeTextureLoadGroupSizeX,
|
||||
kXeTextureLoadGroupSizeY, 1)
|
||||
xesl_input_global_invocation_id
|
||||
xesl_entry_signature_end
|
||||
// 1 thread = 16 blocks.
|
||||
|
|
|
@ -30,8 +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(XeTextureLoadGroupSizeX,
|
||||
XeTextureLoadGroupSizeY, 1)
|
||||
xesl_entry_bindings_end_local_size(kXeTextureLoadGroupSizeX,
|
||||
kXeTextureLoadGroupSizeY, 1)
|
||||
xesl_input_global_invocation_id
|
||||
xesl_entry_signature_end
|
||||
// 1 thread = 4 CTX1 blocks to 16x4 R8G8 texels.
|
||||
|
|
|
@ -16,8 +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(XeTextureLoadGroupSizeX,
|
||||
XeTextureLoadGroupSizeY, 1)
|
||||
xesl_entry_bindings_end_local_size(kXeTextureLoadGroupSizeX,
|
||||
kXeTextureLoadGroupSizeY, 1)
|
||||
xesl_input_global_invocation_id
|
||||
xesl_entry_signature_end
|
||||
// 1 thread = 2 DXN blocks to 8x4 R8G8 texels.
|
||||
|
|
|
@ -16,8 +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(XeTextureLoadGroupSizeX,
|
||||
XeTextureLoadGroupSizeY, 1)
|
||||
xesl_entry_bindings_end_local_size(kXeTextureLoadGroupSizeX,
|
||||
kXeTextureLoadGroupSizeY, 1)
|
||||
xesl_input_global_invocation_id
|
||||
xesl_entry_signature_end
|
||||
// 1 thread = 4 DXT1 blocks to 16x4 R8G8B8A8 texels.
|
||||
|
|
|
@ -16,8 +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(XeTextureLoadGroupSizeX,
|
||||
XeTextureLoadGroupSizeY, 1)
|
||||
xesl_entry_bindings_end_local_size(kXeTextureLoadGroupSizeX,
|
||||
kXeTextureLoadGroupSizeY, 1)
|
||||
xesl_input_global_invocation_id
|
||||
xesl_entry_signature_end
|
||||
// 1 thread = 2 DXT3 blocks to 8x4 R8G8B8A8 texels.
|
||||
|
|
|
@ -16,8 +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(XeTextureLoadGroupSizeX,
|
||||
XeTextureLoadGroupSizeY, 1)
|
||||
xesl_entry_bindings_end_local_size(kXeTextureLoadGroupSizeX,
|
||||
kXeTextureLoadGroupSizeY, 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
|
||||
|
|
|
@ -15,8 +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(XeTextureLoadGroupSizeX,
|
||||
XeTextureLoadGroupSizeY, 1)
|
||||
xesl_entry_bindings_end_local_size(kXeTextureLoadGroupSizeX,
|
||||
kXeTextureLoadGroupSizeY, 1)
|
||||
xesl_input_global_invocation_id
|
||||
xesl_entry_signature_end
|
||||
// 1 thread = 4 DXT3A-as-1111 blocks to 16x4 16bpp texels passed through an
|
||||
|
|
|
@ -16,8 +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(XeTextureLoadGroupSizeX,
|
||||
XeTextureLoadGroupSizeY, 1)
|
||||
xesl_entry_bindings_end_local_size(kXeTextureLoadGroupSizeX,
|
||||
kXeTextureLoadGroupSizeY, 1)
|
||||
xesl_input_global_invocation_id
|
||||
xesl_entry_signature_end
|
||||
// 1 thread = 2 DXT5 blocks to 8x4 R8G8B8A8 texels.
|
||||
|
|
|
@ -16,8 +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(XeTextureLoadGroupSizeX,
|
||||
XeTextureLoadGroupSizeY, 1)
|
||||
xesl_entry_bindings_end_local_size(kXeTextureLoadGroupSizeX,
|
||||
kXeTextureLoadGroupSizeY, 1)
|
||||
xesl_input_global_invocation_id
|
||||
xesl_entry_signature_end
|
||||
// 1 thread = 4 DXT5A blocks to 16x4 R8 texels.
|
||||
|
|
Loading…
Reference in New Issue