diff options
Diffstat (limited to 'target')
| -rw-r--r-- | target/arm/cpu64.c | 48 | ||||
| -rw-r--r-- | target/arm/cpu_tcg.c | 7 | ||||
| -rw-r--r-- | target/arm/helper-mve.h | 142 | ||||
| -rw-r--r-- | target/arm/mve.decode | 297 | ||||
| -rw-r--r-- | target/arm/mve_helper.c | 650 | ||||
| -rw-r--r-- | target/arm/translate-mve.c | 277 | ||||
| -rw-r--r-- | target/arm/translate-neon.c | 6 | ||||
| -rw-r--r-- | target/arm/translate.h | 6 |
8 files changed, 1380 insertions, 53 deletions
diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index 2f0cbddab5..15245a60a8 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -841,10 +841,58 @@ static void aarch64_max_initfn(Object *obj) cpu_max_set_sve_max_vq, NULL, NULL); } +static void aarch64_a64fx_initfn(Object *obj) +{ + ARMCPU *cpu = ARM_CPU(obj); + + cpu->dtb_compatible = "arm,a64fx"; + set_feature(&cpu->env, ARM_FEATURE_V8); + set_feature(&cpu->env, ARM_FEATURE_NEON); + set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); + set_feature(&cpu->env, ARM_FEATURE_AARCH64); + set_feature(&cpu->env, ARM_FEATURE_EL2); + set_feature(&cpu->env, ARM_FEATURE_EL3); + set_feature(&cpu->env, ARM_FEATURE_PMU); + cpu->midr = 0x461f0010; + cpu->revidr = 0x00000000; + cpu->ctr = 0x86668006; + cpu->reset_sctlr = 0x30000180; + cpu->isar.id_aa64pfr0 = 0x0000000101111111; /* No RAS Extensions */ + cpu->isar.id_aa64pfr1 = 0x0000000000000000; + cpu->isar.id_aa64dfr0 = 0x0000000010305408; + cpu->isar.id_aa64dfr1 = 0x0000000000000000; + cpu->id_aa64afr0 = 0x0000000000000000; + cpu->id_aa64afr1 = 0x0000000000000000; + cpu->isar.id_aa64mmfr0 = 0x0000000000001122; + cpu->isar.id_aa64mmfr1 = 0x0000000011212100; + cpu->isar.id_aa64mmfr2 = 0x0000000000001011; + cpu->isar.id_aa64isar0 = 0x0000000010211120; + cpu->isar.id_aa64isar1 = 0x0000000000010001; + cpu->isar.id_aa64zfr0 = 0x0000000000000000; + cpu->clidr = 0x0000000080000023; + cpu->ccsidr[0] = 0x7007e01c; /* 64KB L1 dcache */ + cpu->ccsidr[1] = 0x2007e01c; /* 64KB L1 icache */ + cpu->ccsidr[2] = 0x70ffe07c; /* 8MB L2 cache */ + cpu->dcz_blocksize = 6; /* 256 bytes */ + cpu->gic_num_lrs = 4; + cpu->gic_vpribits = 5; + cpu->gic_vprebits = 5; + + /* Suppport of A64FX's vector length are 128,256 and 512bit only */ + aarch64_add_sve_properties(obj); + bitmap_zero(cpu->sve_vq_supported, ARM_MAX_VQ); + set_bit(0, cpu->sve_vq_supported); /* 128bit */ + set_bit(1, cpu->sve_vq_supported); /* 256bit */ + set_bit(3, cpu->sve_vq_supported); /* 512bit */ + + /* TODO: Add A64FX specific HPC extension registers */ +} + static const ARMCPUInfo aarch64_cpus[] = { { .name = "cortex-a57", .initfn = aarch64_a57_initfn }, { .name = "cortex-a53", .initfn = aarch64_a53_initfn }, { .name = "cortex-a72", .initfn = aarch64_a72_initfn }, + { .name = "a64fx", .initfn = aarch64_a64fx_initfn }, { .name = "max", .initfn = aarch64_max_initfn }, }; diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c index ed444bf436..33cc75af57 100644 --- a/target/arm/cpu_tcg.c +++ b/target/arm/cpu_tcg.c @@ -654,12 +654,9 @@ static void cortex_m55_initfn(Object *obj) cpu->revidr = 0; cpu->pmsav7_dregion = 16; cpu->sau_sregion = 8; - /* - * These are the MVFR* values for the FPU, no MVE configuration; - * we will update them later when we implement MVE - */ + /* These are the MVFR* values for the FPU + full MVE configuration */ cpu->isar.mvfr0 = 0x10110221; - cpu->isar.mvfr1 = 0x12100011; + cpu->isar.mvfr1 = 0x12100211; cpu->isar.mvfr2 = 0x00000040; cpu->isar.id_pfr0 = 0x20000030; cpu->isar.id_pfr1 = 0x00000230; diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index 3db9b15f12..76bd25006d 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -177,6 +177,16 @@ DEF_HELPER_FLAGS_3(mve_vminab, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vminah, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vminaw, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcvt_rm_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vcvt_rm_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vcvt_rm_ss, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vcvt_rm_us, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vcvtb_sh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcvtt_sh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcvtb_hs, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcvtt_hs, TCG_CALL_NO_WG, void, env, ptr, ptr) + DEF_HELPER_FLAGS_3(mve_vmovnbb, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vmovnbh, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vmovntb, TCG_CALL_NO_WG, void, env, ptr, ptr) @@ -410,6 +420,60 @@ DEF_HELPER_FLAGS_4(mve_vhcadd270b, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vhcadd270h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vhcadd270w, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vfaddh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vfadds, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_4(mve_vfsubh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vfsubs, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_4(mve_vfmulh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vfmuls, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_4(mve_vfabdh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vfabds, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_4(mve_vmaxnmh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vmaxnms, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_4(mve_vminnmh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vminnms, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_4(mve_vmaxnmah, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vmaxnmas, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_4(mve_vminnmah, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vminnmas, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_4(mve_vfcadd90h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vfcadd90s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_4(mve_vfcadd270h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vfcadd270s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_4(mve_vfmah, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vfmas, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_4(mve_vfmsh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vfmss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_4(mve_vcmul0h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmul0s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmul90h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmul90s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmul180h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmul180s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmul270h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmul270s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_4(mve_vcmla0h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmla0s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmla90h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmla90s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmla180h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmla180s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmla270h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmla270s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + DEF_HELPER_FLAGS_4(mve_vadd_scalarb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vadd_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vadd_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) @@ -560,6 +624,18 @@ DEF_HELPER_FLAGS_3(mve_vminavb, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vminavh, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vminavw, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxnmvh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxnmvs, TCG_CALL_NO_WG, i32, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vminnmvh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminnmvs, TCG_CALL_NO_WG, i32, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vmaxnmavh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxnmavs, TCG_CALL_NO_WG, i32, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vminnmavh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminnmavs, TCG_CALL_NO_WG, i32, env, ptr, i32) + DEF_HELPER_FLAGS_3(mve_vaddlv_s, TCG_CALL_NO_WG, i64, env, ptr, i64) DEF_HELPER_FLAGS_3(mve_vaddlv_u, TCG_CALL_NO_WG, i64, env, ptr, i64) @@ -746,3 +822,69 @@ DEF_HELPER_FLAGS_3(mve_vcmpgt_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vcmple_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vcmple_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vcmple_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vfcmpeqh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vfcmpeqs, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vfcmpneh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vfcmpnes, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vfcmpgeh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vfcmpges, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vfcmplth, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vfcmplts, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vfcmpgth, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vfcmpgts, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vfcmpleh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vfcmples, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vfcmpeq_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vfcmpeq_scalars, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vfcmpne_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vfcmpne_scalars, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vfcmpge_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vfcmpge_scalars, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vfcmplt_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vfcmplt_scalars, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vfcmpgt_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vfcmpgt_scalars, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vfcmple_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vfcmple_scalars, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vfadd_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vfadd_scalars, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vfsub_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vfsub_scalars, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vfmul_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vfmul_scalars, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vfma_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vfma_scalars, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vfmas_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vfmas_scalars, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vcvt_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vcvt_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vcvt_hs, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vcvt_hu, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vcvt_sf, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vcvt_uf, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vcvt_fs, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vcvt_fu, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vrint_rm_h, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vrint_rm_s, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vrintx_h, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vrintx_s, TCG_CALL_NO_WG, void, env, ptr, ptr) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index 8744681629..14a4f39802 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -26,6 +26,14 @@ # VQDMULL has size in bit 28: 0 for 16 bit, 1 for 32 bit %size_28 28:1 !function=plus_1 +# 2 operand fp insns have size in bit 20: 1 for 16 bit, 0 for 32 bit, +# like Neon FP insns. +%2op_fp_size 20:1 !function=neon_3same_fp_size +# VCADD is an exception, where bit 20 is 0 for 16 bit and 1 for 32 bit +%2op_fp_size_rev 20:1 !function=plus_1 +# FP scalars have size in bit 28, 1 for 16 bit, 0 for 32 bit +%2op_fp_scalar_size 28:1 !function=neon_3same_fp_size + # 1imm format immediate %imm_28_16_0 28:1 16:3 0:4 @@ -116,8 +124,34 @@ @vcmp_scalar .... .... .. size:2 qn:3 . .... .... .... rm:4 &vcmp_scalar \ mask=%mask_22_13 +@vcmp_fp .... .... .... qn:3 . .... .... .... .... &vcmp \ + qm=%qm size=%2op_fp_scalar_size mask=%mask_22_13 + +# Bit 28 is a 2op_fp_scalar_size bit, but we do not decode it in this +# format to avoid complicated overlapping-instruction-groups +@vcmp_fp_scalar .... .... .... qn:3 . .... .... .... rm:4 &vcmp_scalar \ + mask=%mask_22_13 + @vmaxv .... .... .... size:2 .. rda:4 .... .... .... &vmaxv qm=%qm +@2op_fp .... .... .... .... .... .... .... .... &2op \ + qd=%qd qn=%qn qm=%qm size=%2op_fp_size + +@2op_fp_size_rev .... .... .... .... .... .... .... .... &2op \ + qd=%qd qn=%qn qm=%qm size=%2op_fp_size_rev + +# 2-operand, but Qd and Qn share a field. Size is in bit 28, but we +# don't decode it in this format +@vmaxnma .... .... .... .... .... .... .... .... &2op \ + qd=%qd qn=%qd qm=%qm + +# Here also we don't decode the bit 28 size in the format to avoid +# awkward nested overlap groups +@vmaxnmv .... .... .... .... rda:4 .... .... .... &vmaxv qm=%qm + +@2op_fp_scalar .... .... .... .... .... .... .... rm:4 &2scalar \ + qd=%qd qn=%qn size=%2op_fp_scalar_size + # Vector loads and stores # Widening loads and narrowing stores: @@ -187,6 +221,10 @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op # The VSHLL T2 encoding is not a @2op pattern, but is here because it # overlaps what would be size=0b11 VMULH/VRMULH { + VCVTB_SH 111 0 1110 0 . 11 1111 ... 0 1110 0 0 . 0 ... 1 @1op_nosz + + VMAXNMA 111 0 1110 0 . 11 1111 ... 0 1110 1 0 . 0 ... 1 @vmaxnma size=2 + VSHLL_BS 111 0 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_b VSHLL_BS 111 0 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_h @@ -199,6 +237,10 @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op } { + VCVTB_HS 111 1 1110 0 . 11 1111 ... 0 1110 0 0 . 0 ... 1 @1op_nosz + + VMAXNMA 111 1 1110 0 . 11 1111 ... 0 1110 1 0 . 0 ... 1 @vmaxnma size=1 + VSHLL_BU 111 1 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_b VSHLL_BU 111 1 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_h @@ -209,6 +251,9 @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op } { + VCVTT_SH 111 0 1110 0 . 11 1111 ... 1 1110 0 0 . 0 ... 1 @1op_nosz + + VMINNMA 111 0 1110 0 . 11 1111 ... 1 1110 1 0 . 0 ... 1 @vmaxnma size=2 VSHLL_TS 111 0 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_b VSHLL_TS 111 0 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_h @@ -221,6 +266,9 @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op } { + VCVTT_HS 111 1 1110 0 . 11 1111 ... 1 1110 0 0 . 0 ... 1 @1op_nosz + + VMINNMA 111 1 1110 0 . 11 1111 ... 1 1110 1 0 . 0 ... 1 @vmaxnma size=1 VSHLL_TU 111 1 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_b VSHLL_TU 111 1 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_h @@ -274,15 +322,29 @@ VQSHL_U 111 1 1111 0 . .. ... 0 ... 0 0100 . 1 . 1 ... 0 @2op_rev VQRSHL_S 111 0 1111 0 . .. ... 0 ... 0 0101 . 1 . 1 ... 0 @2op_rev VQRSHL_U 111 1 1111 0 . .. ... 0 ... 0 0101 . 1 . 1 ... 0 @2op_rev -VQDMLADH 1110 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 0 @2op -VQDMLADHX 1110 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 0 @2op -VQRDMLADH 1110 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 1 @2op -VQRDMLADHX 1110 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 1 @2op +{ + VCMUL0 111 . 1110 0 . 11 ... 0 ... 0 1110 . 0 . 0 ... 0 @2op_sz28 + VQDMLADH 1110 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 0 @2op + VQDMLSDH 1111 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 0 @2op +} + +{ + VCMUL180 111 . 1110 0 . 11 ... 0 ... 1 1110 . 0 . 0 ... 0 @2op_sz28 + VQDMLADHX 111 0 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 0 @2op + VQDMLSDHX 111 1 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 0 @2op +} + +{ + VCMUL90 111 . 1110 0 . 11 ... 0 ... 0 1110 . 0 . 0 ... 1 @2op_sz28 + VQRDMLADH 111 0 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 1 @2op + VQRDMLSDH 111 1 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 1 @2op +} -VQDMLSDH 1111 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 0 @2op -VQDMLSDHX 1111 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 0 @2op -VQRDMLSDH 1111 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 1 @2op -VQRDMLSDHX 1111 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 1 @2op +{ + VCMUL270 111 . 1110 0 . 11 ... 0 ... 1 1110 . 0 . 0 ... 1 @2op_sz28 + VQRDMLADHX 111 0 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 1 @2op + VQRDMLSDHX 111 1 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 1 @2op +} VQDMULLB 111 . 1110 0 . 11 ... 0 ... 0 1111 . 0 . 0 ... 1 @2op_sz28 VQDMULLT 111 . 1110 0 . 11 ... 0 ... 1 1111 . 0 . 0 ... 1 @2op_sz28 @@ -351,8 +413,10 @@ VDUP 1110 1110 1 0 10 ... 0 .... 1011 . 0 0 1 0000 @vdup size=2 VIWDUP 1110 1110 0 . .. ... 1 ... 0 1111 . 110 ... . @viwdup } { - VDDUP 1110 1110 0 . .. ... 1 ... 1 1111 . 110 111 . @vidup - VDWDUP 1110 1110 0 . .. ... 1 ... 1 1111 . 110 ... . @viwdup + VCMPGT_fp_scalar 1110 1110 0 . 11 ... 1 ... 1 1111 0110 .... @vcmp_fp_scalar size=2 + VCMPLE_fp_scalar 1110 1110 0 . 11 ... 1 ... 1 1111 1110 .... @vcmp_fp_scalar size=2 + VDDUP 1110 1110 0 . .. ... 1 ... 1 1111 . 110 111 . @vidup + VDWDUP 1110 1110 0 . .. ... 1 ... 1 1111 . 110 ... . @viwdup } # multiply-add long dual accumulate @@ -398,25 +462,50 @@ VMLADAV_S 1110 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 1 @vmladav_nosz VMLADAV_U 1111 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 1 @vmladav_nosz { - VMAXV_S 1110 1110 1110 .. 10 .... 1111 0 0 . 0 ... 0 @vmaxv - VMINV_S 1110 1110 1110 .. 10 .... 1111 1 0 . 0 ... 0 @vmaxv - VMAXAV 1110 1110 1110 .. 00 .... 1111 0 0 . 0 ... 0 @vmaxv - VMINAV 1110 1110 1110 .. 00 .... 1111 1 0 . 0 ... 0 @vmaxv + [ + VMAXNMAV 1110 1110 1110 11 00 .... 1111 0 0 . 0 ... 0 @vmaxnmv size=2 + VMINNMAV 1110 1110 1110 11 00 .... 1111 1 0 . 0 ... 0 @vmaxnmv size=2 + VMAXNMV 1110 1110 1110 11 10 .... 1111 0 0 . 0 ... 0 @vmaxnmv size=2 + VMINNMV 1110 1110 1110 11 10 .... 1111 1 0 . 0 ... 0 @vmaxnmv size=2 + ] + [ + VMAXV_S 1110 1110 1110 .. 10 .... 1111 0 0 . 0 ... 0 @vmaxv + VMINV_S 1110 1110 1110 .. 10 .... 1111 1 0 . 0 ... 0 @vmaxv + VMAXAV 1110 1110 1110 .. 00 .... 1111 0 0 . 0 ... 0 @vmaxv + VMINAV 1110 1110 1110 .. 00 .... 1111 1 0 . 0 ... 0 @vmaxv + ] VMLADAV_S 1110 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 0 @vmladav_nosz VRMLALDAVH_S 1110 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz } { - VMAXV_U 1111 1110 1110 .. 10 .... 1111 0 0 . 0 ... 0 @vmaxv - VMINV_U 1111 1110 1110 .. 10 .... 1111 1 0 . 0 ... 0 @vmaxv + [ + VMAXNMAV 1111 1110 1110 11 00 .... 1111 0 0 . 0 ... 0 @vmaxnmv size=1 + VMINNMAV 1111 1110 1110 11 00 .... 1111 1 0 . 0 ... 0 @vmaxnmv size=1 + VMAXNMV 1111 1110 1110 11 10 .... 1111 0 0 . 0 ... 0 @vmaxnmv size=1 + VMINNMV 1111 1110 1110 11 10 .... 1111 1 0 . 0 ... 0 @vmaxnmv size=1 + ] + [ + VMAXV_U 1111 1110 1110 .. 10 .... 1111 0 0 . 0 ... 0 @vmaxv + VMINV_U 1111 1110 1110 .. 10 .... 1111 1 0 . 0 ... 0 @vmaxv + ] VMLADAV_U 1111 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 0 @vmladav_nosz VRMLALDAVH_U 1111 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz } # Scalar operations -VADD_scalar 1110 1110 0 . .. ... 1 ... 0 1111 . 100 .... @2scalar -VSUB_scalar 1110 1110 0 . .. ... 1 ... 1 1111 . 100 .... @2scalar +{ + VCMPEQ_fp_scalar 1110 1110 0 . 11 ... 1 ... 0 1111 0100 .... @vcmp_fp_scalar size=2 + VCMPNE_fp_scalar 1110 1110 0 . 11 ... 1 ... 0 1111 1100 .... @vcmp_fp_scalar size=2 + VADD_scalar 1110 1110 0 . .. ... 1 ... 0 1111 . 100 .... @2scalar +} + +{ + VCMPLT_fp_scalar 1110 1110 0 . 11 ... 1 ... 1 1111 1100 .... @vcmp_fp_scalar size=2 + VCMPGE_fp_scalar 1110 1110 0 . 11 ... 1 ... 1 1111 0100 .... @vcmp_fp_scalar size=2 + VSUB_scalar 1110 1110 0 . .. ... 1 ... 1 1111 . 100 .... @2scalar +} { VSHL_S_scalar 1110 1110 0 . 11 .. 01 ... 1 1110 0110 .... @shl_scalar @@ -434,10 +523,17 @@ VSUB_scalar 1110 1110 0 . .. ... 1 ... 1 1111 . 100 .... @2scalar VBRSR 1111 1110 0 . .. ... 1 ... 1 1110 . 110 .... @2scalar } -VHADD_S_scalar 1110 1110 0 . .. ... 0 ... 0 1111 . 100 .... @2scalar -VHADD_U_scalar 1111 1110 0 . .. ... 0 ... 0 1111 . 100 .... @2scalar -VHSUB_S_scalar 1110 1110 0 . .. ... 0 ... 1 1111 . 100 .... @2scalar -VHSUB_U_scalar 1111 1110 0 . .. ... 0 ... 1 1111 . 100 .... @2scalar +{ + VADD_fp_scalar 111 . 1110 0 . 11 ... 0 ... 0 1111 . 100 .... @2op_fp_scalar + VHADD_S_scalar 1110 1110 0 . .. ... 0 ... 0 1111 . 100 .... @2scalar + VHADD_U_scalar 1111 1110 0 . .. ... 0 ... 0 1111 . 100 .... @2scalar +} + +{ + VSUB_fp_scalar 111 . 1110 0 . 11 ... 0 ... 1 1111 . 100 .... @2op_fp_scalar + VHSUB_S_scalar 1110 1110 0 . .. ... 0 ... 1 1111 . 100 .... @2scalar + VHSUB_U_scalar 1111 1110 0 . .. ... 0 ... 1 1111 . 100 .... @2scalar +} { VQADD_S_scalar 1110 1110 0 . .. ... 0 ... 0 1111 . 110 .... @2scalar @@ -453,12 +549,23 @@ VHSUB_U_scalar 1111 1110 0 . .. ... 0 ... 1 1111 . 100 .... @2scalar size=%size_28 } -VQDMULH_scalar 1110 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar -VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar +{ + VMUL_fp_scalar 111 . 1110 0 . 11 ... 1 ... 0 1110 . 110 .... @2op_fp_scalar + VQDMULH_scalar 1110 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar + VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar +} -# The U bit (28) is don't-care because it does not affect the result -VMLA 111- 1110 0 . .. ... 1 ... 0 1110 . 100 .... @2scalar -VMLAS 111- 1110 0 . .. ... 1 ... 1 1110 . 100 .... @2scalar +{ + VFMA_scalar 111 . 1110 0 . 11 ... 1 ... 0 1110 . 100 .... @2op_fp_scalar + # The U bit (28) is don't-care because it does not affect the result + VMLA 111 - 1110 0 . .. ... 1 ... 0 1110 . 100 .... @2scalar +} + +{ + VFMAS_scalar 111 . 1110 0 . 11 ... 1 ... 1 1110 . 100 .... @2op_fp_scalar + # The U bit (28) is don't-care because it does not affect the result + VMLAS 111 - 1110 0 . .. ... 1 ... 1 1110 . 100 .... @2scalar +} VQRDMLAH 1110 1110 0 . .. ... 0 ... 0 1110 . 100 .... @2scalar VQRDMLASH 1110 1110 0 . .. ... 0 ... 1 1110 . 100 .... @2scalar @@ -591,27 +698,135 @@ VSHLC 111 0 1110 1 . 1 imm:5 ... 0 1111 1100 rdm:4 qd=%qd # Comparisons. We expand out the conditions which are split across # encodings T1, T2, T3 and the fc bits. These include VPT, which is # effectively "VCMP then VPST". A plain "VCMP" has a mask field of zero. -VCMPEQ 1111 1110 0 . .. ... 1 ... 0 1111 0 0 . 0 ... 0 @vcmp -VCMPNE 1111 1110 0 . .. ... 1 ... 0 1111 1 0 . 0 ... 0 @vcmp +{ + VCMPEQ_fp 111 . 1110 0 . 11 ... 1 ... 0 1111 0 0 . 0 ... 0 @vcmp_fp + VCMPEQ 111 1 1110 0 . .. ... 1 ... 0 1111 0 0 . 0 ... 0 @vcmp +} + +{ + VCMPNE_fp 111 . 1110 0 . 11 ... 1 ... 0 1111 1 0 . 0 ... 0 @vcmp_fp + VCMPNE 111 1 1110 0 . .. ... 1 ... 0 1111 1 0 . 0 ... 0 @vcmp +} + +{ + VCMPGE_fp 111 . 1110 0 . 11 ... 1 ... 1 1111 0 0 . 0 ... 0 @vcmp_fp + VCMPGE 111 1 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 0 @vcmp +} + +{ + VCMPLT_fp 111 . 1110 0 . 11 ... 1 ... 1 1111 1 0 . 0 ... 0 @vcmp_fp + VCMPLT 111 1 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 0 @vcmp +} + +{ + VCMPGT_fp 111 . 1110 0 . 11 ... 1 ... 1 1111 0 0 . 0 ... 1 @vcmp_fp + VCMPGT 111 1 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 1 @vcmp +} + +{ + VCMPLE_fp 111 . 1110 0 . 11 ... 1 ... 1 1111 1 0 . 0 ... 1 @vcmp_fp + VCMPLE 1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 1 @vcmp +} + { VPSEL 1111 1110 0 . 11 ... 1 ... 0 1111 . 0 . 0 ... 1 @2op_nosz VCMPCS 1111 1110 0 . .. ... 1 ... 0 1111 0 0 . 0 ... 1 @vcmp VCMPHI 1111 1110 0 . .. ... 1 ... 0 1111 1 0 . 0 ... 1 @vcmp } -VCMPGE 1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 0 @vcmp -VCMPLT 1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 0 @vcmp -VCMPGT 1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 1 @vcmp -VCMPLE 1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 1 @vcmp { - VPNOT 1111 1110 0 0 11 000 1 000 0 1111 0100 1101 - VPST 1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13 - VCMPEQ_scalar 1111 1110 0 . .. ... 1 ... 0 1111 0 1 0 0 .... @vcmp_scalar + VPNOT 1111 1110 0 0 11 000 1 000 0 1111 0100 1101 + VPST 1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13 + VCMPEQ_fp_scalar 1111 1110 0 . 11 ... 1 ... 0 1111 0100 .... @vcmp_fp_scalar size=1 + VCMPEQ_scalar 1111 1110 0 . .. ... 1 ... 0 1111 0100 .... @vcmp_scalar +} + +{ + VCMPNE_fp_scalar 1111 1110 0 . 11 ... 1 ... 0 1111 1100 .... @vcmp_fp_scalar size=1 + VCMPNE_scalar 1111 1110 0 . .. ... 1 ... 0 1111 1100 .... @vcmp_scalar +} + +{ + VCMPGT_fp_scalar 1111 1110 0 . 11 ... 1 ... 1 1111 0110 .... @vcmp_fp_scalar size=1 + VCMPGT_scalar 1111 1110 0 . .. ... 1 ... 1 1111 0110 .... @vcmp_scalar +} + +{ + VCMPLE_fp_scalar 1111 1110 0 . 11 ... 1 ... 1 1111 1110 .... @vcmp_fp_scalar size=1 + VCMPLE_scalar 1111 1110 0 . .. ... 1 ... 1 1111 1110 .... @vcmp_scalar +} + +{ + VCMPGE_fp_scalar 1111 1110 0 . 11 ... 1 ... 1 1111 0100 .... @vcmp_fp_scalar size=1 + VCMPGE_scalar 1111 1110 0 . .. ... 1 ... 1 1111 0100 .... @vcmp_scalar } -VCMPNE_scalar 1111 1110 0 . .. ... 1 ... 0 1111 1 1 0 0 .... @vcmp_scalar +{ + VCMPLT_fp_scalar 1111 1110 0 . 11 ... 1 ... 1 1111 1100 .... @vcmp_fp_scalar size=1 + VCMPLT_scalar 1111 1110 0 . .. ... 1 ... 1 1111 1100 .... @vcmp_scalar +} + VCMPCS_scalar 1111 1110 0 . .. ... 1 ... 0 1111 0 1 1 0 .... @vcmp_scalar VCMPHI_scalar 1111 1110 0 . .. ... 1 ... 0 1111 1 1 1 0 .... @vcmp_scalar -VCMPGE_scalar 1111 1110 0 . .. ... 1 ... 1 1111 0 1 0 0 .... @vcmp_scalar -VCMPLT_scalar 1111 1110 0 . .. ... 1 ... 1 1111 1 1 0 0 .... @vcmp_scalar -VCMPGT_scalar 1111 1110 0 . .. ... 1 ... 1 1111 0 1 1 0 .... @vcmp_scalar -VCMPLE_scalar 1111 1110 0 . .. ... 1 ... 1 1111 1 1 1 0 .... @vcmp_scalar + +# 2-operand FP +VADD_fp 1110 1111 0 . 0 . ... 0 ... 0 1101 . 1 . 0 ... 0 @2op_fp +VSUB_fp 1110 1111 0 . 1 . ... 0 ... 0 1101 . 1 . 0 ... 0 @2op_fp +VMUL_fp 1111 1111 0 . 0 . ... 0 ... 0 1101 . 1 . 1 ... 0 @2op_fp +VABD_fp 1111 1111 0 . 1 . ... 0 ... 0 1101 . 1 . 0 ... 0 @2op_fp + +VMAXNM 1111 1111 0 . 0 . ... 0 ... 0 1111 . 1 . 1 ... 0 @2op_fp +VMINNM 1111 1111 0 . 1 . ... 0 ... 0 1111 . 1 . 1 ... 0 @2op_fp + +VCADD90_fp 1111 1100 1 . 0 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev +VCADD270_fp 1111 1101 1 . 0 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev + +VFMA 1110 1111 0 . 0 . ... 0 ... 0 1100 . 1 . 1 ... 0 @2op_fp +VFMS 1110 1111 0 . 1 . ... 0 ... 0 1100 . 1 . 1 ... 0 @2op_fp + +VCMLA0 1111 110 00 . 1 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev +VCMLA90 1111 110 01 . 1 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev +VCMLA180 1111 110 10 . 1 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev +VCMLA270 1111 110 11 . 1 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev + +# floating-point <-> fixed-point conversions. Naming convention: +# VCVT_<from><to>, S = signed int, U = unsigned int, H = halfprec, F = singleprec +@vcvt .... .... .. 1 ..... .... .. 1 . .... .... &2shift \ + qd=%qd qm=%qm shift=%rshift_i5 size=2 +@vcvt_f16 .... .... .. 11 .... .... .. 0 . .... .... &2shift \ + qd=%qd qm=%qm shift=%rshift_i4 size=1 + +VCVT_SH_fixed 1110 1111 1 . ...... ... 0 11 . 0 01 . 1 ... 0 @vcvt_f16 +VCVT_UH_fixed 1111 1111 1 . ...... ... 0 11 . 0 01 . 1 ... 0 @vcvt_f16 + +VCVT_HS_fixed 1110 1111 1 . ...... ... 0 11 . 1 01 . 1 ... 0 @vcvt_f16 +VCVT_HU_fixed 1111 1111 1 . ...... ... 0 11 . 1 01 . 1 ... 0 @vcvt_f16 + +VCVT_SF_fixed 1110 1111 1 . ...... ... 0 11 . 0 01 . 1 ... 0 @vcvt +VCVT_UF_fixed 1111 1111 1 . ...... ... 0 11 . 0 01 . 1 ... 0 @vcvt + +VCVT_FS_fixed 1110 1111 1 . ...... ... 0 11 . 1 01 . 1 ... 0 @vcvt +VCVT_FU_fixed 1111 1111 1 . ...... ... 0 11 . 1 01 . 1 ... 0 @vcvt + +# VCVT between floating point and integer (halfprec and single); +# VCVT_<from><to>, S = signed int, U = unsigned int, F = float +VCVT_SF 1111 1111 1 . 11 .. 11 ... 0 011 00 1 . 0 ... 0 @1op +VCVT_UF 1111 1111 1 . 11 .. 11 ... 0 011 01 1 . 0 ... 0 @1op +VCVT_FS 1111 1111 1 . 11 .. 11 ... 0 011 10 1 . 0 ... 0 @1op +VCVT_FU 1111 1111 1 . 11 .. 11 ... 0 011 11 1 . 0 ... 0 @1op + +# VCVT from floating point to integer with specified rounding mode +VCVTAS 1111 1111 1 . 11 .. 11 ... 000 00 0 1 . 0 ... 0 @1op +VCVTAU 1111 1111 1 . 11 .. 11 ... 000 00 1 1 . 0 ... 0 @1op +VCVTNS 1111 1111 1 . 11 .. 11 ... 000 01 0 1 . 0 ... 0 @1op +VCVTNU 1111 1111 1 . 11 .. 11 ... 000 01 1 1 . 0 ... 0 @1op +VCVTPS 1111 1111 1 . 11 .. 11 ... 000 10 0 1 . 0 ... 0 @1op +VCVTPU 1111 1111 1 . 11 .. 11 ... 000 10 1 1 . 0 ... 0 @1op +VCVTMS 1111 1111 1 . 11 .. 11 ... 000 11 0 1 . 0 ... 0 @1op +VCVTMU 1111 1111 1 . 11 .. 11 ... 000 11 1 1 . 0 ... 0 @1op + +VRINTN 1111 1111 1 . 11 .. 10 ... 001 000 1 . 0 ... 0 @1op +VRINTX 1111 1111 1 . 11 .. 10 ... 001 001 1 . 0 ... 0 @1op +VRINTA 1111 1111 1 . 11 .. 10 ... 001 010 1 . 0 ... 0 @1op +VRINTZ 1111 1111 1 . 11 .. 10 ... 001 011 1 . 0 ... 0 @1op +VRINTM 1111 1111 1 . 11 .. 10 ... 001 101 1 . 0 ... 0 @1op +VRINTP 1111 1111 1 . 11 .. 10 ... 001 111 1 . 0 ... 0 @1op diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index c2826eb5f9..846962bf4c 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -25,6 +25,7 @@ #include "exec/cpu_ldst.h" #include "exec/exec-all.h" #include "tcg/tcg.h" +#include "fpu/softfloat.h" static uint16_t mve_eci_mask(CPUARMState *env) { @@ -2798,3 +2799,652 @@ DO_VMAXMINA(vmaxaw, 4, int32_t, uint32_t, DO_MAX) DO_VMAXMINA(vminab, 1, int8_t, uint8_t, DO_MIN) DO_VMAXMINA(vminah, 2, int16_t, uint16_t, DO_MIN) DO_VMAXMINA(vminaw, 4, int32_t, uint32_t, DO_MIN) + +/* + * 2-operand floating point. Note that if an element is partially + * predicated we must do the FP operation to update the non-predicated + * bytes, but we must be careful to avoid updating the FP exception + * state unless byte 0 of the element was unpredicated. + */ +#define DO_2OP_FP(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, \ + void *vd, void *vn, void *vm) \ + { \ + TYPE *d = vd, *n = vn, *m = vm; \ + TYPE r; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + float_status *fpst; \ + float_status scratch_fpst; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if ((mask & MAKE_64BIT_MASK(0, ESIZE)) == 0) { \ + continue; \ + } \ + fpst = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + if (!(mask & 1)) { \ + /* We need the result but without updating flags */ \ + scratch_fpst = *fpst; \ + fpst = &scratch_fpst; \ + } \ + r = FN(n[H##ESIZE(e)], m[H##ESIZE(e)], fpst); \ + mergemask(&d[H##ESIZE(e)], r, mask); \ + } \ + mve_advance_vpt(env); \ + } + +#define DO_2OP_FP_ALL(OP, FN) \ + DO_2OP_FP(OP##h, 2, float16, float16_##FN) \ + DO_2OP_FP(OP##s, 4, float32, float32_##FN) + +DO_2OP_FP_ALL(vfadd, add) +DO_2OP_FP_ALL(vfsub, sub) +DO_2OP_FP_ALL(vfmul, mul) + +static inline float16 float16_abd(float16 a, float16 b, float_status *s) +{ + return float16_abs(float16_sub(a, b, s)); +} + +static inline float32 float32_abd(float32 a, float32 b, float_status *s) +{ + return float32_abs(float32_sub(a, b, s)); +} + +DO_2OP_FP_ALL(vfabd, abd) +DO_2OP_FP_ALL(vmaxnm, maxnum) +DO_2OP_FP_ALL(vminnm, minnum) + +static inline float16 float16_maxnuma(float16 a, float16 b, float_status *s) +{ + return float16_maxnum(float16_abs(a), float16_abs(b), s); +} + +static inline float32 float32_maxnuma(float32 a, float32 b, float_status *s) +{ + return float32_maxnum(float32_abs(a), float32_abs(b), s); +} + +static inline float16 float16_minnuma(float16 a, float16 b, float_status *s) +{ + return float16_minnum(float16_abs(a), float16_abs(b), s); +} + +static inline float32 float32_minnuma(float32 a, float32 b, float_status *s) +{ + return float32_minnum(float32_abs(a), float32_abs(b), s); +} + +DO_2OP_FP_ALL(vmaxnma, maxnuma) +DO_2OP_FP_ALL(vminnma, minnuma) + +#define DO_VCADD_FP(OP, ESIZE, TYPE, FN0, FN1) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, \ + void *vd, void *vn, void *vm) \ + { \ + TYPE *d = vd, *n = vn, *m = vm; \ + TYPE r[16 / ESIZE]; \ + uint16_t tm, mask = mve_element_mask(env); \ + unsigned e; \ + float_status *fpst; \ + float_status scratch_fpst; \ + /* Calculate all results first to avoid overwriting inputs */ \ + for (e = 0, tm = mask; e < 16 / ESIZE; e++, tm >>= ESIZE) { \ + if ((tm & MAKE_64BIT_MASK(0, ESIZE)) == 0) { \ + r[e] = 0; \ + continue; \ + } \ + fpst = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + if (!(tm & 1)) { \ + /* We need the result but without updating flags */ \ + scratch_fpst = *fpst; \ + fpst = &scratch_fpst; \ + } \ + if (!(e & 1)) { \ + r[e] = FN0(n[H##ESIZE(e)], m[H##ESIZE(e + 1)], fpst); \ + } else { \ + r[e] = FN1(n[H##ESIZE(e)], m[H##ESIZE(e - 1)], fpst); \ + } \ + } \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + mergemask(&d[H##ESIZE(e)], r[e], mask); \ + } \ + mve_advance_vpt(env); \ + } + +DO_VCADD_FP(vfcadd90h, 2, float16, float16_sub, float16_add) +DO_VCADD_FP(vfcadd90s, 4, float32, float32_sub, float32_add) +DO_VCADD_FP(vfcadd270h, 2, float16, float16_add, float16_sub) +DO_VCADD_FP(vfcadd270s, 4, float32, float32_add, float32_sub) + +#define DO_VFMA(OP, ESIZE, TYPE, CHS) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, \ + void *vd, void *vn, void *vm) \ + { \ + TYPE *d = vd, *n = vn, *m = vm; \ + TYPE r; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + float_status *fpst; \ + float_status scratch_fpst; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if ((mask & MAKE_64BIT_MASK(0, ESIZE)) == 0) { \ + continue; \ + } \ + fpst = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + if (!(mask & 1)) { \ + /* We need the result but without updating flags */ \ + scratch_fpst = *fpst; \ + fpst = &scratch_fpst; \ + } \ + r = n[H##ESIZE(e)]; \ + if (CHS) { \ + r = TYPE##_chs(r); \ + } \ + r = TYPE##_muladd(r, m[H##ESIZE(e)], d[H##ESIZE(e)], \ + 0, fpst); \ + mergemask(&d[H##ESIZE(e)], r, mask); \ + } \ + mve_advance_vpt(env); \ + } + +DO_VFMA(vfmah, 2, float16, false) +DO_VFMA(vfmas, 4, float32, false) +DO_VFMA(vfmsh, 2, float16, true) +DO_VFMA(vfmss, 4, float32, true) + +#define DO_VCMLA(OP, ESIZE, TYPE, ROT, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, \ + void *vd, void *vn, void *vm) \ + { \ + TYPE *d = vd, *n = vn, *m = vm; \ + TYPE r0, r1, e1, e2, e3, e4; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + float_status *fpst0, *fpst1; \ + float_status scratch_fpst; \ + /* We loop through pairs of elements at a time */ \ + for (e = 0; e < 16 / ESIZE; e += 2, mask >>= ESIZE * 2) { \ + if ((mask & MAKE_64BIT_MASK(0, ESIZE * 2)) == 0) { \ + continue; \ + } \ + fpst0 = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + fpst1 = fpst0; \ + if (!(mask & 1)) { \ + scratch_fpst = *fpst0; \ + fpst0 = &scratch_fpst; \ + } \ + if (!(mask & (1 << ESIZE))) { \ + scratch_fpst = *fpst1; \ + fpst1 = &scratch_fpst; \ + } \ + switch (ROT) { \ + case 0: \ + e1 = m[H##ESIZE(e)]; \ + e2 = n[H##ESIZE(e)]; \ + e3 = m[H##ESIZE(e + 1)]; \ + e4 = n[H##ESIZE(e)]; \ + break; \ + case 1: \ + e1 = TYPE##_chs(m[H##ESIZE(e + 1)]); \ + e2 = n[H##ESIZE(e + 1)]; \ + e3 = m[H##ESIZE(e)]; \ + e4 = n[H##ESIZE(e + 1)]; \ + break; \ + case 2: \ + e1 = TYPE##_chs(m[H##ESIZE(e)]); \ + e2 = n[H##ESIZE(e)]; \ + e3 = TYPE##_chs(m[H##ESIZE(e + 1)]); \ + e4 = n[H##ESIZE(e)]; \ + break; \ + case 3: \ + e1 = m[H##ESIZE(e + 1)]; \ + e2 = n[H##ESIZE(e + 1)]; \ + e3 = TYPE##_chs(m[H##ESIZE(e)]); \ + e4 = n[H##ESIZE(e + 1)]; \ + break; \ + default: \ + g_assert_not_reached(); \ + } \ + r0 = FN(e2, e1, d[H##ESIZE(e)], fpst0); \ + r1 = FN(e4, e3, d[H##ESIZE(e + 1)], fpst1); \ + mergemask(&d[H##ESIZE(e)], r0, mask); \ + mergemask(&d[H##ESIZE(e + 1)], r1, mask >> ESIZE); \ + } \ + mve_advance_vpt(env); \ + } + +#define DO_VCMULH(N, M, D, S) float16_mul(N, M, S) +#define DO_VCMULS(N, M, D, S) float32_mul(N, M, S) + +#define DO_VCMLAH(N, M, D, S) float16_muladd(N, M, D, 0, S) +#define DO_VCMLAS(N, M, D, S) float32_muladd(N, M, D, 0, S) + +DO_VCMLA(vcmul0h, 2, float16, 0, DO_VCMULH) +DO_VCMLA(vcmul0s, 4, float32, 0, DO_VCMULS) +DO_VCMLA(vcmul90h, 2, float16, 1, DO_VCMULH) +DO_VCMLA(vcmul90s, 4, float32, 1, DO_VCMULS) +DO_VCMLA(vcmul180h, 2, float16, 2, DO_VCMULH) +DO_VCMLA(vcmul180s, 4, float32, 2, DO_VCMULS) +DO_VCMLA(vcmul270h, 2, float16, 3, DO_VCMULH) +DO_VCMLA(vcmul270s, 4, float32, 3, DO_VCMULS) + +DO_VCMLA(vcmla0h, 2, float16, 0, DO_VCMLAH) +DO_VCMLA(vcmla0s, 4, float32, 0, DO_VCMLAS) +DO_VCMLA(vcmla90h, 2, float16, 1, DO_VCMLAH) +DO_VCMLA(vcmla90s, 4, float32, 1, DO_VCMLAS) +DO_VCMLA(vcmla180h, 2, float16, 2, DO_VCMLAH) +DO_VCMLA(vcmla180s, 4, float32, 2, DO_VCMLAS) +DO_VCMLA(vcmla270h, 2, float16, 3, DO_VCMLAH) +DO_VCMLA(vcmla270s, 4, float32, 3, DO_VCMLAS) + +#define DO_2OP_FP_SCALAR(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, \ + void *vd, void *vn, uint32_t rm) \ + { \ + TYPE *d = vd, *n = vn; \ + TYPE r, m = rm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + float_status *fpst; \ + float_status scratch_fpst; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if ((mask & MAKE_64BIT_MASK(0, ESIZE)) == 0) { \ + continue; \ + } \ + fpst = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + if (!(mask & 1)) { \ + /* We need the result but without updating flags */ \ + scratch_fpst = *fpst; \ + fpst = &scratch_fpst; \ + } \ + r = FN(n[H##ESIZE(e)], m, fpst); \ + mergemask(&d[H##ESIZE(e)], r, mask); \ + } \ + mve_advance_vpt(env); \ + } + +#define DO_2OP_FP_SCALAR_ALL(OP, FN) \ + DO_2OP_FP_SCALAR(OP##h, 2, float16, float16_##FN) \ + DO_2OP_FP_SCALAR(OP##s, 4, float32, float32_##FN) + +DO_2OP_FP_SCALAR_ALL(vfadd_scalar, add) +DO_2OP_FP_SCALAR_ALL(vfsub_scalar, sub) +DO_2OP_FP_SCALAR_ALL(vfmul_scalar, mul) + +#define DO_2OP_FP_ACC_SCALAR(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, \ + void *vd, void *vn, uint32_t rm) \ + { \ + TYPE *d = vd, *n = vn; \ + TYPE r, m = rm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + float_status *fpst; \ + float_status scratch_fpst; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if ((mask & MAKE_64BIT_MASK(0, ESIZE)) == 0) { \ + continue; \ + } \ + fpst = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + if (!(mask & 1)) { \ + /* We need the result but without updating flags */ \ + scratch_fpst = *fpst; \ + fpst = &scratch_fpst; \ + } \ + r = FN(n[H##ESIZE(e)], m, d[H##ESIZE(e)], 0, fpst); \ + mergemask(&d[H##ESIZE(e)], r, mask); \ + } \ + mve_advance_vpt(env); \ + } + +/* VFMAS is vector * vector + scalar, so swap op2 and op3 */ +#define DO_VFMAS_SCALARH(N, M, D, F, S) float16_muladd(N, D, M, F, S) +#define DO_VFMAS_SCALARS(N, M, D, F, S) float32_muladd(N, D, M, F, S) + +/* VFMA is vector * scalar + vector */ +DO_2OP_FP_ACC_SCALAR(vfma_scalarh, 2, float16, float16_muladd) +DO_2OP_FP_ACC_SCALAR(vfma_scalars, 4, float32, float32_muladd) +DO_2OP_FP_ACC_SCALAR(vfmas_scalarh, 2, float16, DO_VFMAS_SCALARH) +DO_2OP_FP_ACC_SCALAR(vfmas_scalars, 4, float32, DO_VFMAS_SCALARS) + +/* Floating point max/min across vector. */ +#define DO_FP_VMAXMINV(OP, ESIZE, TYPE, ABS, FN) \ + uint32_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vm, \ + uint32_t ra_in) \ + { \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + TYPE *m = vm; \ + TYPE ra = (TYPE)ra_in; \ + float_status *fpst = (ESIZE == 2) ? \ + &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if (mask & 1) { \ + TYPE v = m[H##ESIZE(e)]; \ + if (TYPE##_is_signaling_nan(ra, fpst)) { \ + ra = TYPE##_silence_nan(ra, fpst); \ + float_raise(float_flag_invalid, fpst); \ + } \ + if (TYPE##_is_signaling_nan(v, fpst)) { \ + v = TYPE##_silence_nan(v, fpst); \ + float_raise(float_flag_invalid, fpst); \ + } \ + if (ABS) { \ + v = TYPE##_abs(v); \ + } \ + ra = FN(ra, v, fpst); \ + } \ + } \ + mve_advance_vpt(env); \ + return ra; \ + } \ + +#define NOP(X) (X) + +DO_FP_VMAXMINV(vmaxnmvh, 2, float16, false, float16_maxnum) +DO_FP_VMAXMINV(vmaxnmvs, 4, float32, false, float32_maxnum) +DO_FP_VMAXMINV(vminnmvh, 2, float16, false, float16_minnum) +DO_FP_VMAXMINV(vminnmvs, 4, float32, false, float32_minnum) +DO_FP_VMAXMINV(vmaxnmavh, 2, float16, true, float16_maxnum) +DO_FP_VMAXMINV(vmaxnmavs, 4, float32, true, float32_maxnum) +DO_FP_VMAXMINV(vminnmavh, 2, float16, true, float16_minnum) +DO_FP_VMAXMINV(vminnmavs, 4, float32, true, float32_minnum) + +/* FP compares; note that all comparisons signal InvalidOp for QNaNs */ +#define DO_VCMP_FP(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vn, void *vm) \ + { \ + TYPE *n = vn, *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + uint16_t eci_mask = mve_eci_mask(env); \ + uint16_t beatpred = 0; \ + uint16_t emask = MAKE_64BIT_MASK(0, ESIZE); \ + unsigned e; \ + float_status *fpst; \ + float_status scratch_fpst; \ + bool r; \ + for (e = 0; e < 16 / ESIZE; e++, emask <<= ESIZE) { \ + if ((mask & emask) == 0) { \ + continue; \ + } \ + fpst = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + if (!(mask & (1 << (e * ESIZE)))) { \ + /* We need the result but without updating flags */ \ + scratch_fpst = *fpst; \ + fpst = &scratch_fpst; \ + } \ + r = FN(n[H##ESIZE(e)], m[H##ESIZE(e)], fpst); \ + /* Comparison sets 0/1 bits for each byte in the element */ \ + beatpred |= r * emask; \ + } \ + beatpred &= mask; \ + env->v7m.vpr = (env->v7m.vpr & ~(uint32_t)eci_mask) | \ + (beatpred & eci_mask); \ + mve_advance_vpt(env); \ + } + +#define DO_VCMP_FP_SCALAR(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vn, \ + uint32_t rm) \ + { \ + TYPE *n = vn; \ + uint16_t mask = mve_element_mask(env); \ + uint16_t eci_mask = mve_eci_mask(env); \ + uint16_t beatpred = 0; \ + uint16_t emask = MAKE_64BIT_MASK(0, ESIZE); \ + unsigned e; \ + float_status *fpst; \ + float_status scratch_fpst; \ + bool r; \ + for (e = 0; e < 16 / ESIZE; e++, emask <<= ESIZE) { \ + if ((mask & emask) == 0) { \ + continue; \ + } \ + fpst = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + if (!(mask & (1 << (e * ESIZE)))) { \ + /* We need the result but without updating flags */ \ + scratch_fpst = *fpst; \ + fpst = &scratch_fpst; \ + } \ + r = FN(n[H##ESIZE(e)], (TYPE)rm, fpst); \ + /* Comparison sets 0/1 bits for each byte in the element */ \ + beatpred |= r * emask; \ + } \ + beatpred &= mask; \ + env->v7m.vpr = (env->v7m.vpr & ~(uint32_t)eci_mask) | \ + (beatpred & eci_mask); \ + mve_advance_vpt(env); \ + } + +#define DO_VCMP_FP_BOTH(VOP, SOP, ESIZE, TYPE, FN) \ + DO_VCMP_FP(VOP, ESIZE, TYPE, FN) \ + DO_VCMP_FP_SCALAR(SOP, ESIZE, TYPE, FN) + +/* + * Some care is needed here to get the correct result for the unordered case. + * Architecturally EQ, GE and GT are defined to be false for unordered, but + * the NE, LT and LE comparisons are defined as simple logical inverses of + * EQ, GE and GT and so they must return true for unordered. The softfloat + * comparison functions float*_{eq,le,lt} all return false for unordered. + */ +#define DO_GE16(X, Y, S) float16_le(Y, X, S) +#define DO_GE32(X, Y, S) float32_le(Y, X, S) +#define DO_GT16(X, Y, S) float16_lt(Y, X, S) +#define DO_GT32(X, Y, S) float32_lt(Y, X, S) + +DO_VCMP_FP_BOTH(vfcmpeqh, vfcmpeq_scalarh, 2, float16, float16_eq) +DO_VCMP_FP_BOTH(vfcmpeqs, vfcmpeq_scalars, 4, float32, float32_eq) + +DO_VCMP_FP_BOTH(vfcmpneh, vfcmpne_scalarh, 2, float16, !float16_eq) +DO_VCMP_FP_BOTH(vfcmpnes, vfcmpne_scalars, 4, float32, !float32_eq) + +DO_VCMP_FP_BOTH(vfcmpgeh, vfcmpge_scalarh, 2, float16, DO_GE16) +DO_VCMP_FP_BOTH(vfcmpges, vfcmpge_scalars, 4, float32, DO_GE32) + +DO_VCMP_FP_BOTH(vfcmplth, vfcmplt_scalarh, 2, float16, !DO_GE16) +DO_VCMP_FP_BOTH(vfcmplts, vfcmplt_scalars, 4, float32, !DO_GE32) + +DO_VCMP_FP_BOTH(vfcmpgth, vfcmpgt_scalarh, 2, float16, DO_GT16) +DO_VCMP_FP_BOTH(vfcmpgts, vfcmpgt_scalars, 4, float32, DO_GT32) + +DO_VCMP_FP_BOTH(vfcmpleh, vfcmple_scalarh, 2, float16, !DO_GT16) +DO_VCMP_FP_BOTH(vfcmples, vfcmple_scalars, 4, float32, !DO_GT32) + +#define DO_VCVT_FIXED(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, void *vm, \ + uint32_t shift) \ + { \ + TYPE *d = vd, *m = vm; \ + TYPE r; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + float_status *fpst; \ + float_status scratch_fpst; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if ((mask & MAKE_64BIT_MASK(0, ESIZE)) == 0) { \ + continue; \ + } \ + fpst = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + if (!(mask & 1)) { \ + /* We need the result but without updating flags */ \ + scratch_fpst = *fpst; \ + fpst = &scratch_fpst; \ + } \ + r = FN(m[H##ESIZE(e)], shift, fpst); \ + mergemask(&d[H##ESIZE(e)], r, mask); \ + } \ + mve_advance_vpt(env); \ + } + +DO_VCVT_FIXED(vcvt_sh, 2, int16_t, helper_vfp_shtoh) +DO_VCVT_FIXED(vcvt_uh, 2, uint16_t, helper_vfp_uhtoh) +DO_VCVT_FIXED(vcvt_hs, 2, int16_t, helper_vfp_toshh_round_to_zero) +DO_VCVT_FIXED(vcvt_hu, 2, uint16_t, helper_vfp_touhh_round_to_zero) +DO_VCVT_FIXED(vcvt_sf, 4, int32_t, helper_vfp_sltos) +DO_VCVT_FIXED(vcvt_uf, 4, uint32_t, helper_vfp_ultos) +DO_VCVT_FIXED(vcvt_fs, 4, int32_t, helper_vfp_tosls_round_to_zero) +DO_VCVT_FIXED(vcvt_fu, 4, uint32_t, helper_vfp_touls_round_to_zero) + +/* VCVT with specified rmode */ +#define DO_VCVT_RMODE(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, \ + void *vd, void *vm, uint32_t rmode) \ + { \ + TYPE *d = vd, *m = vm; \ + TYPE r; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + float_status *fpst; \ + float_status scratch_fpst; \ + float_status *base_fpst = (ESIZE == 2) ? \ + &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + uint32_t prev_rmode = get_float_rounding_mode(base_fpst); \ + set_float_rounding_mode(rmode, base_fpst); \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if ((mask & MAKE_64BIT_MASK(0, ESIZE)) == 0) { \ + continue; \ + } \ + fpst = base_fpst; \ + if (!(mask & 1)) { \ + /* We need the result but without updating flags */ \ + scratch_fpst = *fpst; \ + fpst = &scratch_fpst; \ + } \ + r = FN(m[H##ESIZE(e)], 0, fpst); \ + mergemask(&d[H##ESIZE(e)], r, mask); \ + } \ + set_float_rounding_mode(prev_rmode, base_fpst); \ + mve_advance_vpt(env); \ + } + +DO_VCVT_RMODE(vcvt_rm_sh, 2, uint16_t, helper_vfp_toshh) +DO_VCVT_RMODE(vcvt_rm_uh, 2, uint16_t, helper_vfp_touhh) +DO_VCVT_RMODE(vcvt_rm_ss, 4, uint32_t, helper_vfp_tosls) +DO_VCVT_RMODE(vcvt_rm_us, 4, uint32_t, helper_vfp_touls) + +#define DO_VRINT_RM_H(M, F, S) helper_rinth(M, S) +#define DO_VRINT_RM_S(M, F, S) helper_rints(M, S) + +DO_VCVT_RMODE(vrint_rm_h, 2, uint16_t, DO_VRINT_RM_H) +DO_VCVT_RMODE(vrint_rm_s, 4, uint32_t, DO_VRINT_RM_S) + +/* + * VCVT between halfprec and singleprec. As usual for halfprec + * conversions, FZ16 is ignored and AHP is observed. + */ +static void do_vcvt_sh(CPUARMState *env, void *vd, void *vm, int top) +{ + uint16_t *d = vd; + uint32_t *m = vm; + uint16_t r; + uint16_t mask = mve_element_mask(env); + bool ieee = !(env->vfp.xregs[ARM_VFP_FPSCR] & FPCR_AHP); + unsigned e; + float_status *fpst; + float_status scratch_fpst; + float_status *base_fpst = &env->vfp.standard_fp_status; + bool old_fz = get_flush_to_zero(base_fpst); + set_flush_to_zero(false, base_fpst); + for (e = 0; e < 16 / 4; e++, mask >>= 4) { + if ((mask & MAKE_64BIT_MASK(0, 4)) == 0) { + continue; + } + fpst = base_fpst; + if (!(mask & 1)) { + /* We need the result but without updating flags */ + scratch_fpst = *fpst; + fpst = &scratch_fpst; + } + r = float32_to_float16(m[H4(e)], ieee, fpst); + mergemask(&d[H2(e * 2 + top)], r, mask >> (top * 2)); + } + set_flush_to_zero(old_fz, base_fpst); + mve_advance_vpt(env); +} + +static void do_vcvt_hs(CPUARMState *env, void *vd, void *vm, int top) +{ + uint32_t *d = vd; + uint16_t *m = vm; + uint32_t r; + uint16_t mask = mve_element_mask(env); + bool ieee = !(env->vfp.xregs[ARM_VFP_FPSCR] & FPCR_AHP); + unsigned e; + float_status *fpst; + float_status scratch_fpst; + float_status *base_fpst = &env->vfp.standard_fp_status; + bool old_fiz = get_flush_inputs_to_zero(base_fpst); + set_flush_inputs_to_zero(false, base_fpst); + for (e = 0; e < 16 / 4; e++, mask >>= 4) { + if ((mask & MAKE_64BIT_MASK(0, 4)) == 0) { + continue; + } + fpst = base_fpst; + if (!(mask & (1 << (top * 2)))) { + /* We need the result but without updating flags */ + scratch_fpst = *fpst; + fpst = &scratch_fpst; + } + r = float16_to_float32(m[H2(e * 2 + top)], ieee, fpst); + mergemask(&d[H4(e)], r, mask); + } + set_flush_inputs_to_zero(old_fiz, base_fpst); + mve_advance_vpt(env); +} + +void HELPER(mve_vcvtb_sh)(CPUARMState *env, void *vd, void *vm) +{ + do_vcvt_sh(env, vd, vm, 0); +} +void HELPER(mve_vcvtt_sh)(CPUARMState *env, void *vd, void *vm) +{ + do_vcvt_sh(env, vd, vm, 1); +} +void HELPER(mve_vcvtb_hs)(CPUARMState *env, void *vd, void *vm) +{ + do_vcvt_hs(env, vd, vm, 0); +} +void HELPER(mve_vcvtt_hs)(CPUARMState *env, void *vd, void *vm) +{ + do_vcvt_hs(env, vd, vm, 1); +} + +#define DO_1OP_FP(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, void *vm) \ + { \ + TYPE *d = vd, *m = vm; \ + TYPE r; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + float_status *fpst; \ + float_status scratch_fpst; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if ((mask & MAKE_64BIT_MASK(0, ESIZE)) == 0) { \ + continue; \ + } \ + fpst = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + if (!(mask & 1)) { \ + /* We need the result but without updating flags */ \ + scratch_fpst = *fpst; \ + fpst = &scratch_fpst; \ + } \ + r = FN(m[H##ESIZE(e)], fpst); \ + mergemask(&d[H##ESIZE(e)], r, mask); \ + } \ + mve_advance_vpt(env); \ + } + +DO_1OP_FP(vrintx_h, 2, float16, float16_round_to_int) +DO_1OP_FP(vrintx_s, 4, float32, float32_round_to_int) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index 78229c44c6..2ed91577ec 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -49,6 +49,7 @@ typedef void MVEGenCmpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenScalarCmpFn(TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenVABAVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenDualAccOpFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); +typedef void MVEGenVCVTRmodeFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); /* Return the offset of a Qn register (same semantics as aa32_vfp_qreg()) */ static inline long mve_qreg_offset(unsigned reg) @@ -543,6 +544,148 @@ DO_1OP(VQNEG, vqneg) DO_1OP(VMAXA, vmaxa) DO_1OP(VMINA, vmina) +/* + * For simple float/int conversions we use the fixed-point + * conversion helpers with a zero shift count + */ +#define DO_VCVT(INSN, HFN, SFN) \ + static void gen_##INSN##h(TCGv_ptr env, TCGv_ptr qd, TCGv_ptr qm) \ + { \ + gen_helper_mve_##HFN(env, qd, qm, tcg_constant_i32(0)); \ + } \ + static void gen_##INSN##s(TCGv_ptr env, TCGv_ptr qd, TCGv_ptr qm) \ + { \ + gen_helper_mve_##SFN(env, qd, qm, tcg_constant_i32(0)); \ + } \ + static bool trans_##INSN(DisasContext *s, arg_1op *a) \ + { \ + static MVEGenOneOpFn * const fns[] = { \ + NULL, \ + gen_##INSN##h, \ + gen_##INSN##s, \ + NULL, \ + }; \ + if (!dc_isar_feature(aa32_mve_fp, s)) { \ + return false; \ + } \ + return do_1op(s, a, fns[a->size]); \ + } + +DO_VCVT(VCVT_SF, vcvt_sh, vcvt_sf) +DO_VCVT(VCVT_UF, vcvt_uh, vcvt_uf) +DO_VCVT(VCVT_FS, vcvt_hs, vcvt_fs) +DO_VCVT(VCVT_FU, vcvt_hu, vcvt_fu) + +static bool do_vcvt_rmode(DisasContext *s, arg_1op *a, + enum arm_fprounding rmode, bool u) +{ + /* + * Handle VCVT fp to int with specified rounding mode. + * This is a 1op fn but we must pass the rounding mode as + * an immediate to the helper. + */ + TCGv_ptr qd, qm; + static MVEGenVCVTRmodeFn * const fns[4][2] = { + { NULL, NULL }, + { gen_helper_mve_vcvt_rm_sh, gen_helper_mve_vcvt_rm_uh }, + { gen_helper_mve_vcvt_rm_ss, gen_helper_mve_vcvt_rm_us }, + { NULL, NULL }, + }; + MVEGenVCVTRmodeFn *fn = fns[a->size][u]; + + if (!dc_isar_feature(aa32_mve_fp, s) || + !mve_check_qreg_bank(s, a->qd | a->qm) || + !fn) { + return false; + } + + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qd = mve_qreg_ptr(a->qd); + qm = mve_qreg_ptr(a->qm); + fn(cpu_env, qd, qm, tcg_constant_i32(arm_rmode_to_sf(rmode))); + tcg_temp_free_ptr(qd); + tcg_temp_free_ptr(qm); + mve_update_eci(s); + return true; +} + +#define DO_VCVT_RMODE(INSN, RMODE, U) \ + static bool trans_##INSN(DisasContext *s, arg_1op *a) \ + { \ + return do_vcvt_rmode(s, a, RMODE, U); \ + } \ + +DO_VCVT_RMODE(VCVTAS, FPROUNDING_TIEAWAY, false) +DO_VCVT_RMODE(VCVTAU, FPROUNDING_TIEAWAY, true) +DO_VCVT_RMODE(VCVTNS, FPROUNDING_TIEEVEN, false) +DO_VCVT_RMODE(VCVTNU, FPROUNDING_TIEEVEN, true) +DO_VCVT_RMODE(VCVTPS, FPROUNDING_POSINF, false) +DO_VCVT_RMODE(VCVTPU, FPROUNDING_POSINF, true) +DO_VCVT_RMODE(VCVTMS, FPROUNDING_NEGINF, false) +DO_VCVT_RMODE(VCVTMU, FPROUNDING_NEGINF, true) + +#define DO_VCVT_SH(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_1op *a) \ + { \ + if (!dc_isar_feature(aa32_mve_fp, s)) { \ + return false; \ + } \ + return do_1op(s, a, gen_helper_mve_##FN); \ + } \ + +DO_VCVT_SH(VCVTB_SH, vcvtb_sh) +DO_VCVT_SH(VCVTT_SH, vcvtt_sh) +DO_VCVT_SH(VCVTB_HS, vcvtb_hs) +DO_VCVT_SH(VCVTT_HS, vcvtt_hs) + +#define DO_VRINT(INSN, RMODE) \ + static void gen_##INSN##h(TCGv_ptr env, TCGv_ptr qd, TCGv_ptr qm) \ + { \ + gen_helper_mve_vrint_rm_h(env, qd, qm, \ + tcg_constant_i32(arm_rmode_to_sf(RMODE))); \ + } \ + static void gen_##INSN##s(TCGv_ptr env, TCGv_ptr qd, TCGv_ptr qm) \ + { \ + gen_helper_mve_vrint_rm_s(env, qd, qm, \ + tcg_constant_i32(arm_rmode_to_sf(RMODE))); \ + } \ + static bool trans_##INSN(DisasContext *s, arg_1op *a) \ + { \ + static MVEGenOneOpFn * const fns[] = { \ + NULL, \ + gen_##INSN##h, \ + gen_##INSN##s, \ + NULL, \ + }; \ + if (!dc_isar_feature(aa32_mve_fp, s)) { \ + return false; \ + } \ + return do_1op(s, a, fns[a->size]); \ + } + +DO_VRINT(VRINTN, FPROUNDING_TIEEVEN) +DO_VRINT(VRINTA, FPROUNDING_TIEAWAY) +DO_VRINT(VRINTZ, FPROUNDING_ZERO) +DO_VRINT(VRINTM, FPROUNDING_NEGINF) +DO_VRINT(VRINTP, FPROUNDING_POSINF) + +static bool trans_VRINTX(DisasContext *s, arg_1op *a) +{ + static MVEGenOneOpFn * const fns[] = { + NULL, + gen_helper_mve_vrintx_h, + gen_helper_mve_vrintx_s, + NULL, + }; + if (!dc_isar_feature(aa32_mve_fp, s)) { + return false; + } + return do_1op(s, a, fns[a->size]); +} + /* Narrowing moves: only size 0 and 1 are valid */ #define DO_VMOVN(INSN, FN) \ static bool trans_##INSN(DisasContext *s, arg_1op *a) \ @@ -831,6 +974,42 @@ static bool trans_VSBCI(DisasContext *s, arg_2op *a) return do_2op(s, a, gen_helper_mve_vsbci); } +#define DO_2OP_FP(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_2op *a) \ + { \ + static MVEGenTwoOpFn * const fns[] = { \ + NULL, \ + gen_helper_mve_##FN##h, \ + gen_helper_mve_##FN##s, \ + NULL, \ + }; \ + if (!dc_isar_feature(aa32_mve_fp, s)) { \ + return false; \ + } \ + return do_2op(s, a, fns[a->size]); \ + } + +DO_2OP_FP(VADD_fp, vfadd) +DO_2OP_FP(VSUB_fp, vfsub) +DO_2OP_FP(VMUL_fp, vfmul) +DO_2OP_FP(VABD_fp, vfabd) +DO_2OP_FP(VMAXNM, vmaxnm) +DO_2OP_FP(VMINNM, vminnm) +DO_2OP_FP(VCADD90_fp, vfcadd90) +DO_2OP_FP(VCADD270_fp, vfcadd270) +DO_2OP_FP(VFMA, vfma) +DO_2OP_FP(VFMS, vfms) +DO_2OP_FP(VCMUL0, vcmul0) +DO_2OP_FP(VCMUL90, vcmul90) +DO_2OP_FP(VCMUL180, vcmul180) +DO_2OP_FP(VCMUL270, vcmul270) +DO_2OP_FP(VCMLA0, vcmla0) +DO_2OP_FP(VCMLA90, vcmla90) +DO_2OP_FP(VCMLA180, vcmla180) +DO_2OP_FP(VCMLA270, vcmla270) +DO_2OP_FP(VMAXNMA, vmaxnma) +DO_2OP_FP(VMINNMA, vminnma) + static bool do_2op_scalar(DisasContext *s, arg_2scalar *a, MVEGenTwoOpScalarFn fn) { @@ -861,7 +1040,7 @@ static bool do_2op_scalar(DisasContext *s, arg_2scalar *a, return true; } -#define DO_2OP_SCALAR(INSN, FN) \ +#define DO_2OP_SCALAR(INSN, FN) \ static bool trans_##INSN(DisasContext *s, arg_2scalar *a) \ { \ static MVEGenTwoOpScalarFn * const fns[] = { \ @@ -924,6 +1103,28 @@ static bool trans_VQDMULLT_scalar(DisasContext *s, arg_2scalar *a) return do_2op_scalar(s, a, fns[a->size]); } + +#define DO_2OP_FP_SCALAR(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_2scalar *a) \ + { \ + static MVEGenTwoOpScalarFn * const fns[] = { \ + NULL, \ + gen_helper_mve_##FN##h, \ + gen_helper_mve_##FN##s, \ + NULL, \ + }; \ + if (!dc_isar_feature(aa32_mve_fp, s)) { \ + return false; \ + } \ + return do_2op_scalar(s, a, fns[a->size]); \ + } + +DO_2OP_FP_SCALAR(VADD_fp_scalar, vfadd_scalar) +DO_2OP_FP_SCALAR(VSUB_fp_scalar, vfsub_scalar) +DO_2OP_FP_SCALAR(VMUL_fp_scalar, vfmul_scalar) +DO_2OP_FP_SCALAR(VFMA_scalar, vfma_scalar) +DO_2OP_FP_SCALAR(VFMAS_scalar, vfmas_scalar) + static bool do_long_dual_acc(DisasContext *s, arg_vmlaldav *a, MVEGenLongDualAccOpFn *fn) { @@ -1381,6 +1582,24 @@ DO_2SHIFT(VRSHRI_U, vrshli_u, true) DO_2SHIFT(VSRI, vsri, false) DO_2SHIFT(VSLI, vsli, false) +#define DO_2SHIFT_FP(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_2shift *a) \ + { \ + if (!dc_isar_feature(aa32_mve_fp, s)) { \ + return false; \ + } \ + return do_2shift(s, a, gen_helper_mve_##FN, false); \ + } + +DO_2SHIFT_FP(VCVT_SH_fixed, vcvt_sh) +DO_2SHIFT_FP(VCVT_UH_fixed, vcvt_uh) +DO_2SHIFT_FP(VCVT_HS_fixed, vcvt_hs) +DO_2SHIFT_FP(VCVT_HU_fixed, vcvt_hu) +DO_2SHIFT_FP(VCVT_SF_fixed, vcvt_sf) +DO_2SHIFT_FP(VCVT_UF_fixed, vcvt_uf) +DO_2SHIFT_FP(VCVT_FS_fixed, vcvt_fs) +DO_2SHIFT_FP(VCVT_FU_fixed, vcvt_fu) + static bool do_2shift_scalar(DisasContext *s, arg_shl_scalar *a, MVEGenTwoOpShiftFn *fn) { @@ -1700,6 +1919,42 @@ DO_VCMP(VCMPLT, vcmplt) DO_VCMP(VCMPGT, vcmpgt) DO_VCMP(VCMPLE, vcmple) +#define DO_VCMP_FP(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_vcmp *a) \ + { \ + static MVEGenCmpFn * const fns[] = { \ + NULL, \ + gen_helper_mve_##FN##h, \ + gen_helper_mve_##FN##s, \ + NULL, \ + }; \ + if (!dc_isar_feature(aa32_mve_fp, s)) { \ + return false; \ + } \ + return do_vcmp(s, a, fns[a->size]); \ + } \ + static bool trans_##INSN##_scalar(DisasContext *s, \ + arg_vcmp_scalar *a) \ + { \ + static MVEGenScalarCmpFn * const fns[] = { \ + NULL, \ + gen_helper_mve_##FN##_scalarh, \ + gen_helper_mve_##FN##_scalars, \ + NULL, \ + }; \ + if (!dc_isar_feature(aa32_mve_fp, s)) { \ + return false; \ + } \ + return do_vcmp_scalar(s, a, fns[a->size]); \ + } + +DO_VCMP_FP(VCMPEQ_fp, vfcmpeq) +DO_VCMP_FP(VCMPNE_fp, vfcmpne) +DO_VCMP_FP(VCMPGE_fp, vfcmpge) +DO_VCMP_FP(VCMPLT_fp, vfcmplt) +DO_VCMP_FP(VCMPGT_fp, vfcmpgt) +DO_VCMP_FP(VCMPLE_fp, vfcmple) + static bool do_vmaxv(DisasContext *s, arg_vmaxv *a, MVEGenVADDVFn fn) { /* @@ -1748,6 +2003,26 @@ DO_VMAXV(VMINV_S, vminvs) DO_VMAXV(VMINV_U, vminvu) DO_VMAXV(VMINAV, vminav) +#define DO_VMAXV_FP(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_vmaxv *a) \ + { \ + static MVEGenVADDVFn * const fns[] = { \ + NULL, \ + gen_helper_mve_##FN##h, \ + gen_helper_mve_##FN##s, \ + NULL, \ + }; \ + if (!dc_isar_feature(aa32_mve_fp, s)) { \ + return false; \ + } \ + return do_vmaxv(s, a, fns[a->size]); \ + } + +DO_VMAXV_FP(VMAXNMV, vmaxnmv) +DO_VMAXV_FP(VMINNMV, vminnmv) +DO_VMAXV_FP(VMAXNMAV, vmaxnmav) +DO_VMAXV_FP(VMINNMAV, vminnmav) + static bool do_vabav(DisasContext *s, arg_vabav *a, MVEGenVABAVFn *fn) { /* Absolute difference accumulated across vector */ diff --git a/target/arm/translate-neon.c b/target/arm/translate-neon.c index c53ab20fa4..dd43de558e 100644 --- a/target/arm/translate-neon.c +++ b/target/arm/translate-neon.c @@ -28,12 +28,6 @@ #include "translate.h" #include "translate-a32.h" -static inline int neon_3same_fp_size(DisasContext *s, int x) -{ - /* Convert 0==fp32, 1==fp16 into a MO_* value */ - return MO_32 - x; -} - /* Include the generated Neon decoder */ #include "decode-neon-dp.c.inc" #include "decode-neon-ls.c.inc" diff --git a/target/arm/translate.h b/target/arm/translate.h index 241596c5bd..8636c20c3b 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -181,6 +181,12 @@ static inline int rsub_8(DisasContext *s, int x) return 8 - x; } +static inline int neon_3same_fp_size(DisasContext *s, int x) +{ + /* Convert 0==fp32, 1==fp16 into a MO_* value */ + return MO_32 - x; +} + static inline int arm_dc_feature(DisasContext *dc, int feature) { return (dc->features & (1ULL << feature)) != 0; |