diff --git a/target/arm/helper.h b/target/arm/helper.h index f345087ddb..9a89c9cea7 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -334,6 +334,14 @@ DEF_HELPER_FLAGS_5(neon_uqshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(neon_uqshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(neon_uqshl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(neon_uqshl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_sqrshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_sqrshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_sqrshl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_sqrshl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_uqrshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_uqrshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_uqrshl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_uqrshl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_srshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_srshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c index 63c3ec2e73..6dc96269d5 100644 --- a/target/arm/tcg/gengvec.c +++ b/target/arm/tcg/gengvec.c @@ -1264,6 +1264,30 @@ void gen_neon_uqshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, opr_sz, max_sz, 0, fns[vece]); } +void gen_neon_sqrshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static gen_helper_gvec_3_ptr * const fns[] = { + gen_helper_neon_sqrshl_b, gen_helper_neon_sqrshl_h, + gen_helper_neon_sqrshl_s, gen_helper_neon_sqrshl_d, + }; + tcg_debug_assert(vece <= MO_64); + tcg_gen_gvec_3_ptr(rd_ofs, rn_ofs, rm_ofs, tcg_env, + opr_sz, max_sz, 0, fns[vece]); +} + +void gen_neon_uqrshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static gen_helper_gvec_3_ptr * const fns[] = { + gen_helper_neon_uqrshl_b, gen_helper_neon_uqrshl_h, + gen_helper_neon_uqrshl_s, gen_helper_neon_uqrshl_d, + }; + tcg_debug_assert(vece <= MO_64); + tcg_gen_gvec_3_ptr(rd_ofs, rn_ofs, rm_ofs, tcg_env, + opr_sz, max_sz, 0, fns[vece]); +} + void gen_uqadd_bhs(TCGv_i64 res, TCGv_i64 qc, TCGv_i64 a, TCGv_i64 b, MemOp esz) { uint64_t max = MAKE_64BIT_MASK(0, 8 << esz); diff --git a/target/arm/tcg/neon-dp.decode b/target/arm/tcg/neon-dp.decode index 6d4996b8d8..788578c8fa 100644 --- a/target/arm/tcg/neon-dp.decode +++ b/target/arm/tcg/neon-dp.decode @@ -102,25 +102,12 @@ VCGE_U_3s 1111 001 1 0 . .. .... .... 0011 . . . 1 .... @3same VSHL_S_3s 1111 001 0 0 . .. .... .... 0100 . . . 0 .... @3same_rev VSHL_U_3s 1111 001 1 0 . .. .... .... 0100 . . . 0 .... @3same_rev - -# Insns operating on 64-bit elements (size!=0b11 handled elsewhere) -# The _rev suffix indicates that Vn and Vm are reversed (as explained -# by the comment for the @3same_rev format). -@3same_64_rev .... ... . . . 11 .... .... .... . q:1 . . .... \ - &3same vm=%vn_dp vn=%vm_dp vd=%vd_dp size=3 - VQSHL_S_3s 1111 001 0 0 . .. .... .... 0100 . . . 1 .... @3same_rev VQSHL_U_3s 1111 001 1 0 . .. .... .... 0100 . . . 1 .... @3same_rev VRSHL_S_3s 1111 001 0 0 . .. .... .... 0101 . . . 0 .... @3same_rev VRSHL_U_3s 1111 001 1 0 . .. .... .... 0101 . . . 0 .... @3same_rev -{ - VQRSHL_S64_3s 1111 001 0 0 . .. .... .... 0101 . . . 1 .... @3same_64_rev - VQRSHL_S_3s 1111 001 0 0 . .. .... .... 0101 . . . 1 .... @3same_rev -} -{ - VQRSHL_U64_3s 1111 001 1 0 . .. .... .... 0101 . . . 1 .... @3same_64_rev - VQRSHL_U_3s 1111 001 1 0 . .. .... .... 0101 . . . 1 .... @3same_rev -} +VQRSHL_S_3s 1111 001 0 0 . .. .... .... 0101 . . . 1 .... @3same_rev +VQRSHL_U_3s 1111 001 1 0 . .. .... .... 0101 . . . 1 .... @3same_rev VMAX_S_3s 1111 001 0 0 . .. .... .... 0110 . . . 0 .... @3same VMAX_U_3s 1111 001 1 0 . .. .... .... 0110 . . . 0 .... @3same diff --git a/target/arm/tcg/neon_helper.c b/target/arm/tcg/neon_helper.c index 88301f0dcb..b29a7c725f 100644 --- a/target/arm/tcg/neon_helper.c +++ b/target/arm/tcg/neon_helper.c @@ -435,11 +435,23 @@ uint64_t HELPER(neon_qshlu_s64)(CPUARMState *env, uint64_t val, uint64_t shift) #define NEON_FN(dest, src1, src2) \ (dest = do_uqrshl_bhs(src1, (int8_t)src2, 8, true, env->vfp.qc)) NEON_VOP_ENV(qrshl_u8, neon_u8, 4) +NEON_GVEC_VOP2_ENV(neon_uqrshl_b, uint8_t) #undef NEON_FN #define NEON_FN(dest, src1, src2) \ (dest = do_uqrshl_bhs(src1, (int8_t)src2, 16, true, env->vfp.qc)) NEON_VOP_ENV(qrshl_u16, neon_u16, 2) +NEON_GVEC_VOP2_ENV(neon_uqrshl_h, uint16_t) +#undef NEON_FN + +#define NEON_FN(dest, src1, src2) \ + (dest = do_uqrshl_bhs(src1, (int8_t)src2, 32, true, env->vfp.qc)) +NEON_GVEC_VOP2_ENV(neon_uqrshl_s, uint32_t) +#undef NEON_FN + +#define NEON_FN(dest, src1, src2) \ + (dest = do_uqrshl_d(src1, (int8_t)src2, true, env->vfp.qc)) +NEON_GVEC_VOP2_ENV(neon_uqrshl_d, uint64_t) #undef NEON_FN uint32_t HELPER(neon_qrshl_u32)(CPUARMState *env, uint32_t val, uint32_t shift) @@ -455,11 +467,23 @@ uint64_t HELPER(neon_qrshl_u64)(CPUARMState *env, uint64_t val, uint64_t shift) #define NEON_FN(dest, src1, src2) \ (dest = do_sqrshl_bhs(src1, (int8_t)src2, 8, true, env->vfp.qc)) NEON_VOP_ENV(qrshl_s8, neon_s8, 4) +NEON_GVEC_VOP2_ENV(neon_sqrshl_b, int8_t) #undef NEON_FN #define NEON_FN(dest, src1, src2) \ (dest = do_sqrshl_bhs(src1, (int8_t)src2, 16, true, env->vfp.qc)) NEON_VOP_ENV(qrshl_s16, neon_s16, 2) +NEON_GVEC_VOP2_ENV(neon_sqrshl_h, int16_t) +#undef NEON_FN + +#define NEON_FN(dest, src1, src2) \ + (dest = do_sqrshl_bhs(src1, (int8_t)src2, 32, true, env->vfp.qc)) +NEON_GVEC_VOP2_ENV(neon_sqrshl_s, int32_t) +#undef NEON_FN + +#define NEON_FN(dest, src1, src2) \ + (dest = do_sqrshl_d(src1, (int8_t)src2, true, env->vfp.qc)) +NEON_GVEC_VOP2_ENV(neon_sqrshl_d, int64_t) #undef NEON_FN uint32_t HELPER(neon_qrshl_s32)(CPUARMState *env, uint32_t val, uint32_t shift) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 97bd69eb3f..b9d577f620 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -10968,6 +10968,13 @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) } switch (opcode) { + case 0x0b: /* SQRSHL, UQRSHL */ + if (u) { + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_neon_uqrshl, size); + } else { + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_neon_sqrshl, size); + } + return; case 0x0c: /* SMAX, UMAX */ if (u) { gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_umax, size); @@ -11103,16 +11110,6 @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) genfn = fns[size][u]; break; } - case 0xb: /* SQRSHL, UQRSHL */ - { - static NeonGenTwoOpEnvFn * const fns[3][2] = { - { gen_helper_neon_qrshl_s8, gen_helper_neon_qrshl_u8 }, - { gen_helper_neon_qrshl_s16, gen_helper_neon_qrshl_u16 }, - { gen_helper_neon_qrshl_s32, gen_helper_neon_qrshl_u32 }, - }; - genenvfn = fns[size][u]; - break; - } default: g_assert_not_reached(); } diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c index a3eec47092..5f1576393e 100644 --- a/target/arm/tcg/translate-neon.c +++ b/target/arm/tcg/translate-neon.c @@ -798,6 +798,8 @@ DO_3SAME(VRSHL_S, gen_gvec_srshl) DO_3SAME(VRSHL_U, gen_gvec_urshl) DO_3SAME(VQSHL_S, gen_neon_sqshl) DO_3SAME(VQSHL_U, gen_neon_uqshl) +DO_3SAME(VQRSHL_S, gen_neon_sqrshl) +DO_3SAME(VQRSHL_U, gen_neon_uqrshl) /* These insns are all gvec_bitsel but with the inputs in various orders. */ #define DO_3SAME_BITSEL(INSN, O1, O2, O3) \ @@ -916,26 +918,6 @@ DO_SHA2(SHA256H, gen_helper_crypto_sha256h) DO_SHA2(SHA256H2, gen_helper_crypto_sha256h2) DO_SHA2(SHA256SU1, gen_helper_crypto_sha256su1) -#define DO_3SAME_64(INSN, FUNC) \ - static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ - uint32_t rn_ofs, uint32_t rm_ofs, \ - uint32_t oprsz, uint32_t maxsz) \ - { \ - static const GVecGen3 op = { .fni8 = FUNC }; \ - tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, &op); \ - } \ - DO_3SAME(INSN, gen_##INSN##_3s) - -#define DO_3SAME_64_ENV(INSN, FUNC) \ - static void gen_##INSN##_elt(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m) \ - { \ - FUNC(d, tcg_env, n, m); \ - } \ - DO_3SAME_64(INSN, gen_##INSN##_elt) - -DO_3SAME_64_ENV(VQRSHL_S64, gen_helper_neon_qrshl_s64) -DO_3SAME_64_ENV(VQRSHL_U64, gen_helper_neon_qrshl_u64) - #define DO_3SAME_32(INSN, FUNC) \ static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ uint32_t rn_ofs, uint32_t rm_ofs, \ @@ -969,30 +951,6 @@ DO_3SAME_64_ENV(VQRSHL_U64, gen_helper_neon_qrshl_u64) FUNC(d, tcg_env, n, m); \ } -#define DO_3SAME_32_ENV(INSN, FUNC) \ - WRAP_ENV_FN(gen_##INSN##_tramp8, gen_helper_neon_##FUNC##8); \ - WRAP_ENV_FN(gen_##INSN##_tramp16, gen_helper_neon_##FUNC##16); \ - WRAP_ENV_FN(gen_##INSN##_tramp32, gen_helper_neon_##FUNC##32); \ - static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ - uint32_t rn_ofs, uint32_t rm_ofs, \ - uint32_t oprsz, uint32_t maxsz) \ - { \ - static const GVecGen3 ops[4] = { \ - { .fni4 = gen_##INSN##_tramp8 }, \ - { .fni4 = gen_##INSN##_tramp16 }, \ - { .fni4 = gen_##INSN##_tramp32 }, \ - { 0 }, \ - }; \ - tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, &ops[vece]); \ - } \ - static bool trans_##INSN##_3s(DisasContext *s, arg_3same *a) \ - { \ - if (a->size > 2) { \ - return false; \ - } \ - return do_3same(s, a, gen_##INSN##_3s); \ - } - DO_3SAME_32(VHADD_S, hadd_s) DO_3SAME_32(VHADD_U, hadd_u) DO_3SAME_32(VHSUB_S, hsub_s) @@ -1000,9 +958,6 @@ DO_3SAME_32(VHSUB_U, hsub_u) DO_3SAME_32(VRHADD_S, rhadd_s) DO_3SAME_32(VRHADD_U, rhadd_u) -DO_3SAME_32_ENV(VQRSHL_S, qrshl_s) -DO_3SAME_32_ENV(VQRSHL_U, qrshl_u) - #define DO_3SAME_VQDMULH(INSN, FUNC) \ WRAP_ENV_FN(gen_##INSN##_tramp16, gen_helper_neon_##FUNC##_s16); \ WRAP_ENV_FN(gen_##INSN##_tramp32, gen_helper_neon_##FUNC##_s32); \ diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index 6c6d4d49e7..048cb45ebe 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -467,6 +467,10 @@ void gen_neon_sqshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); void gen_neon_uqshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_neon_sqrshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_neon_uqrshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); void gen_cmtst_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); void gen_ushl_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b);