Instead of passing env and leaving it up to the helper to get the right fpstatus we pass it explicitly. There was already a get_fpstatus helper for neon for the 32 bit code. We also add an get_ahp_flag() for passing the state of the alternative FP16 format flag. This leaves scope for later tracking the AHP state in translation flags.
Signed-off-by: Alex Bennée <alex.ben...@linaro.org> --- target/arm/helper.c | 58 ++++++++++++------------------- target/arm/helper.h | 12 +++---- target/arm/translate-a64.c | 38 +++++++++++++++++---- target/arm/translate.c | 70 +++++++++++++++++++++++++++++--------- target/arm/translate.h | 15 ++++++++ 5 files changed, 128 insertions(+), 65 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index 0fef5d4d06..4dd28bb70c 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -11457,64 +11457,50 @@ uint32_t HELPER(set_neon_rmode)(uint32_t rmode, CPUARMState *env) } /* Half precision conversions. */ -static float32 do_fcvt_f16_to_f32(uint32_t a, CPUARMState *env, float_status *s) +static float32 do_fcvt_f16_to_f32(float16 a, float_status *s, bool ahp) { - int ieee = (env->vfp.xregs[ARM_VFP_FPSCR] & (1 << 26)) == 0; - float32 r = float16_to_float32(make_float16(a), ieee, s); - if (ieee) { - return float32_maybe_silence_nan(r, s); - } - return r; + return float16_to_float32(a, !ahp, s); } -static uint32_t do_fcvt_f32_to_f16(float32 a, CPUARMState *env, float_status *s) +static float16 do_fcvt_f32_to_f16(float32 a, float_status *s, bool ahp) { - int ieee = (env->vfp.xregs[ARM_VFP_FPSCR] & (1 << 26)) == 0; - float16 r = float32_to_float16(a, ieee, s); - if (ieee) { - r = float16_maybe_silence_nan(r, s); - } - return float16_val(r); + return float32_to_float16(a, !ahp, s); } -float32 HELPER(neon_fcvt_f16_to_f32)(uint32_t a, CPUARMState *env) +float32 HELPER(neon_fcvt_f16_to_f32)(float16 a, void *fpstp, uint32_t ahp_mode) { - return do_fcvt_f16_to_f32(a, env, &env->vfp.standard_fp_status); + float_status *fpst = fpstp; + return do_fcvt_f16_to_f32(a, fpst, ahp_mode); } -uint32_t HELPER(neon_fcvt_f32_to_f16)(float32 a, CPUARMState *env) +float16 HELPER(neon_fcvt_f32_to_f16)(float32 a, void *fpstp, uint32_t ahp_mode) { - return do_fcvt_f32_to_f16(a, env, &env->vfp.standard_fp_status); + float_status *fpst = fpstp; + return do_fcvt_f32_to_f16(a, fpst, ahp_mode); } -float32 HELPER(vfp_fcvt_f16_to_f32)(uint32_t a, CPUARMState *env) +float32 HELPER(vfp_fcvt_f16_to_f32)(float16 a, void *fpstp, uint32_t ahp_mode) { - return do_fcvt_f16_to_f32(a, env, &env->vfp.fp_status); + float_status *fpst = fpstp; + return do_fcvt_f16_to_f32(a, fpst, ahp_mode); } -uint32_t HELPER(vfp_fcvt_f32_to_f16)(float32 a, CPUARMState *env) +float16 HELPER(vfp_fcvt_f32_to_f16)(float32 a, void *fpstp, uint32_t ahp_mode) { - return do_fcvt_f32_to_f16(a, env, &env->vfp.fp_status); + float_status *fpst = fpstp; + return do_fcvt_f32_to_f16(a, fpst, ahp_mode); } -float64 HELPER(vfp_fcvt_f16_to_f64)(uint32_t a, CPUARMState *env) +float64 HELPER(vfp_fcvt_f16_to_f64)(float16 a, void *fpstp, uint32_t ahp_mode) { - int ieee = (env->vfp.xregs[ARM_VFP_FPSCR] & (1 << 26)) == 0; - float64 r = float16_to_float64(make_float16(a), ieee, &env->vfp.fp_status); - if (ieee) { - return float64_maybe_silence_nan(r, &env->vfp.fp_status); - } - return r; + float_status *fpst = fpstp; + return float16_to_float64(a, !ahp_mode, fpst); } -uint32_t HELPER(vfp_fcvt_f64_to_f16)(float64 a, CPUARMState *env) +float16 HELPER(vfp_fcvt_f64_to_f16)(float64 a, void *fpstp, uint32_t ahp_mode) { - int ieee = (env->vfp.xregs[ARM_VFP_FPSCR] & (1 << 26)) == 0; - float16 r = float64_to_float16(a, ieee, &env->vfp.fp_status); - if (ieee) { - r = float16_maybe_silence_nan(r, &env->vfp.fp_status); - } - return float16_val(r); + float_status *fpst = fpstp; + return float64_to_float16(a, !ahp_mode, fpst); } #define float32_two make_float32(0x40000000) diff --git a/target/arm/helper.h b/target/arm/helper.h index 34e8cc8904..288480a0e7 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -181,12 +181,12 @@ DEF_HELPER_3(vfp_ultoh, f16, i32, i32, ptr) DEF_HELPER_FLAGS_2(set_rmode, TCG_CALL_NO_RWG, i32, i32, ptr) DEF_HELPER_FLAGS_2(set_neon_rmode, TCG_CALL_NO_RWG, i32, i32, env) -DEF_HELPER_2(vfp_fcvt_f16_to_f32, f32, i32, env) -DEF_HELPER_2(vfp_fcvt_f32_to_f16, i32, f32, env) -DEF_HELPER_2(neon_fcvt_f16_to_f32, f32, i32, env) -DEF_HELPER_2(neon_fcvt_f32_to_f16, i32, f32, env) -DEF_HELPER_FLAGS_2(vfp_fcvt_f16_to_f64, TCG_CALL_NO_RWG, f64, i32, env) -DEF_HELPER_FLAGS_2(vfp_fcvt_f64_to_f16, TCG_CALL_NO_RWG, i32, f64, env) +DEF_HELPER_3(vfp_fcvt_f16_to_f32, f32, f16, ptr, i32) +DEF_HELPER_3(vfp_fcvt_f32_to_f16, f16, f32, ptr, i32) +DEF_HELPER_3(neon_fcvt_f16_to_f32, f32, f16, ptr, i32) +DEF_HELPER_3(neon_fcvt_f32_to_f16, f16, f32, ptr, i32) +DEF_HELPER_FLAGS_3(vfp_fcvt_f16_to_f64, TCG_CALL_NO_RWG, f64, f16, ptr, i32) +DEF_HELPER_FLAGS_3(vfp_fcvt_f64_to_f16, TCG_CALL_NO_RWG, f16, f64, ptr, i32) DEF_HELPER_4(vfp_muladdd, f64, f64, f64, f64, ptr) DEF_HELPER_4(vfp_muladds, f32, f32, f32, f32, ptr) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index 6d49f30b4a..00a7c63240 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -4830,10 +4830,15 @@ static void handle_fp_fcvt(DisasContext *s, int opcode, } else { /* Single to half */ TCGv_i32 tcg_rd = tcg_temp_new_i32(); - gen_helper_vfp_fcvt_f32_to_f16(tcg_rd, tcg_rn, cpu_env); + TCGv_i32 ahp = get_ahp_flag(); + TCGv_ptr fpst = get_fpstatus_ptr(true); + + gen_helper_vfp_fcvt_f32_to_f16(tcg_rd, tcg_rn, fpst, ahp); /* write_fp_sreg is OK here because top half of tcg_rd is zero */ write_fp_sreg(s, rd, tcg_rd); tcg_temp_free_i32(tcg_rd); + tcg_temp_free_i32(ahp); + tcg_temp_free_ptr(fpst); } tcg_temp_free_i32(tcg_rn); break; @@ -4846,9 +4851,13 @@ static void handle_fp_fcvt(DisasContext *s, int opcode, /* Double to single */ gen_helper_vfp_fcvtsd(tcg_rd, tcg_rn, cpu_env); } else { + TCGv_ptr fpst = get_fpstatus_ptr(true); + TCGv_i32 ahp = get_ahp_flag(); /* Double to half */ - gen_helper_vfp_fcvt_f64_to_f16(tcg_rd, tcg_rn, cpu_env); + gen_helper_vfp_fcvt_f64_to_f16(tcg_rd, tcg_rn, fpst, ahp); /* write_fp_sreg is OK here because top half of tcg_rd is zero */ + tcg_temp_free_ptr(fpst); + tcg_temp_free_i32(ahp); } write_fp_sreg(s, rd, tcg_rd); tcg_temp_free_i32(tcg_rd); @@ -4858,17 +4867,21 @@ static void handle_fp_fcvt(DisasContext *s, int opcode, case 0x3: { TCGv_i32 tcg_rn = read_fp_sreg(s, rn); + TCGv_ptr tcg_fpst = get_fpstatus_ptr(true); + TCGv_i32 tcg_ahp = get_ahp_flag(); tcg_gen_ext16u_i32(tcg_rn, tcg_rn); if (dtype == 0) { /* Half to single */ TCGv_i32 tcg_rd = tcg_temp_new_i32(); - gen_helper_vfp_fcvt_f16_to_f32(tcg_rd, tcg_rn, cpu_env); + gen_helper_vfp_fcvt_f16_to_f32(tcg_rd, tcg_rn, tcg_fpst, tcg_ahp); write_fp_sreg(s, rd, tcg_rd); + tcg_temp_free_ptr(tcg_fpst); + tcg_temp_free_i32(tcg_ahp); tcg_temp_free_i32(tcg_rd); } else { /* Half to double */ TCGv_i64 tcg_rd = tcg_temp_new_i64(); - gen_helper_vfp_fcvt_f16_to_f64(tcg_rd, tcg_rn, cpu_env); + gen_helper_vfp_fcvt_f16_to_f64(tcg_rd, tcg_rn, tcg_fpst, tcg_ahp); write_fp_dreg(s, rd, tcg_rd); tcg_temp_free_i64(tcg_rd); } @@ -8487,12 +8500,17 @@ static void handle_2misc_narrow(DisasContext *s, bool scalar, } else { TCGv_i32 tcg_lo = tcg_temp_new_i32(); TCGv_i32 tcg_hi = tcg_temp_new_i32(); + TCGv_ptr fpst = get_fpstatus_ptr(true); + TCGv_i32 ahp = get_ahp_flag(); + tcg_gen_extr_i64_i32(tcg_lo, tcg_hi, tcg_op); - gen_helper_vfp_fcvt_f32_to_f16(tcg_lo, tcg_lo, cpu_env); - gen_helper_vfp_fcvt_f32_to_f16(tcg_hi, tcg_hi, cpu_env); + gen_helper_vfp_fcvt_f32_to_f16(tcg_lo, tcg_lo, fpst, ahp); + gen_helper_vfp_fcvt_f32_to_f16(tcg_hi, tcg_hi, fpst, ahp); tcg_gen_deposit_i32(tcg_res[pass], tcg_lo, tcg_hi, 16, 16); tcg_temp_free_i32(tcg_lo); tcg_temp_free_i32(tcg_hi); + tcg_temp_free_ptr(fpst); + tcg_temp_free_i32(ahp); } break; case 0x56: /* FCVTXN, FCVTXN2 */ @@ -10987,18 +11005,24 @@ static void handle_2misc_widening(DisasContext *s, int opcode, bool is_q, /* 16 -> 32 bit fp conversion */ int srcelt = is_q ? 4 : 0; TCGv_i32 tcg_res[4]; + TCGv_ptr fpst = get_fpstatus_ptr(true); + TCGv_i32 ahp = get_ahp_flag(); + for (pass = 0; pass < 4; pass++) { tcg_res[pass] = tcg_temp_new_i32(); read_vec_element_i32(s, tcg_res[pass], rn, srcelt + pass, MO_16); gen_helper_vfp_fcvt_f16_to_f32(tcg_res[pass], tcg_res[pass], - cpu_env); + fpst, ahp); } for (pass = 0; pass < 4; pass++) { write_vec_element_i32(s, tcg_res[pass], rd, pass, MO_32); tcg_temp_free_i32(tcg_res[pass]); } + + tcg_temp_free_ptr(fpst); + tcg_temp_free_i32(ahp); } } diff --git a/target/arm/translate.c b/target/arm/translate.c index ad208867a7..5eab9d585a 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -3824,53 +3824,75 @@ static int disas_vfp_insn(DisasContext *s, uint32_t insn) gen_vfp_sqrt(dp); break; case 4: /* vcvtb.f32.f16, vcvtb.f64.f16 */ + { + TCGv_ptr fpst = get_fpstatus_ptr(false); + TCGv_i32 ahp_mode = get_ahp_flag(); tmp = gen_vfp_mrs(); tcg_gen_ext16u_i32(tmp, tmp); if (dp) { gen_helper_vfp_fcvt_f16_to_f64(cpu_F0d, tmp, - cpu_env); + fpst, ahp_mode); } else { gen_helper_vfp_fcvt_f16_to_f32(cpu_F0s, tmp, - cpu_env); + fpst, ahp_mode); } + tcg_temp_free_i32(ahp_mode); + tcg_temp_free_ptr(fpst); tcg_temp_free_i32(tmp); break; + } case 5: /* vcvtt.f32.f16, vcvtt.f64.f16 */ + { + TCGv_ptr fpst = get_fpstatus_ptr(false); + TCGv_i32 ahp = get_ahp_flag(); tmp = gen_vfp_mrs(); tcg_gen_shri_i32(tmp, tmp, 16); if (dp) { gen_helper_vfp_fcvt_f16_to_f64(cpu_F0d, tmp, - cpu_env); + fpst, ahp); } else { gen_helper_vfp_fcvt_f16_to_f32(cpu_F0s, tmp, - cpu_env); + fpst, ahp); } tcg_temp_free_i32(tmp); + tcg_temp_free_i32(ahp); + tcg_temp_free_ptr(fpst); break; + } case 6: /* vcvtb.f16.f32, vcvtb.f16.f64 */ + { + TCGv_ptr fpst = get_fpstatus_ptr(false); + TCGv_i32 ahp = get_ahp_flag(); tmp = tcg_temp_new_i32(); + if (dp) { gen_helper_vfp_fcvt_f64_to_f16(tmp, cpu_F0d, - cpu_env); + fpst, ahp); } else { gen_helper_vfp_fcvt_f32_to_f16(tmp, cpu_F0s, - cpu_env); + fpst, ahp); } gen_mov_F0_vreg(0, rd); tmp2 = gen_vfp_mrs(); tcg_gen_andi_i32(tmp2, tmp2, 0xffff0000); tcg_gen_or_i32(tmp, tmp, tmp2); tcg_temp_free_i32(tmp2); + tcg_temp_free_i32(ahp); + tcg_temp_free_ptr(fpst); gen_vfp_msr(tmp); break; + } case 7: /* vcvtt.f16.f32, vcvtt.f16.f64 */ + { + TCGv_ptr fpst = get_fpstatus_ptr(true); + TCGv_i32 ahp = get_ahp_flag(); tmp = tcg_temp_new_i32(); if (dp) { gen_helper_vfp_fcvt_f64_to_f16(tmp, cpu_F0d, - cpu_env); + fpst, ahp); } else { gen_helper_vfp_fcvt_f32_to_f16(tmp, cpu_F0s, - cpu_env); + fpst, ahp); } tcg_gen_shli_i32(tmp, tmp, 16); gen_mov_F0_vreg(0, rd); @@ -3880,6 +3902,7 @@ static int disas_vfp_insn(DisasContext *s, uint32_t insn) tcg_temp_free_i32(tmp2); gen_vfp_msr(tmp); break; + } case 8: /* cmp */ gen_vfp_cmp(dp); break; @@ -7222,53 +7245,68 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } break; case NEON_2RM_VCVT_F16_F32: + { + TCGv_ptr fpst; + TCGv_i32 ahp; + if (!arm_dc_feature(s, ARM_FEATURE_VFP_FP16) || q || (rm & 1)) { return 1; } tmp = tcg_temp_new_i32(); tmp2 = tcg_temp_new_i32(); + fpst = get_fpstatus_ptr(true); + ahp = get_ahp_flag(); tcg_gen_ld_f32(cpu_F0s, cpu_env, neon_reg_offset(rm, 0)); - gen_helper_neon_fcvt_f32_to_f16(tmp, cpu_F0s, cpu_env); + gen_helper_neon_fcvt_f32_to_f16(tmp, cpu_F0s, fpst, ahp); tcg_gen_ld_f32(cpu_F0s, cpu_env, neon_reg_offset(rm, 1)); - gen_helper_neon_fcvt_f32_to_f16(tmp2, cpu_F0s, cpu_env); + gen_helper_neon_fcvt_f32_to_f16(tmp2, cpu_F0s, fpst, ahp); tcg_gen_shli_i32(tmp2, tmp2, 16); tcg_gen_or_i32(tmp2, tmp2, tmp); tcg_gen_ld_f32(cpu_F0s, cpu_env, neon_reg_offset(rm, 2)); - gen_helper_neon_fcvt_f32_to_f16(tmp, cpu_F0s, cpu_env); + gen_helper_neon_fcvt_f32_to_f16(tmp, cpu_F0s, fpst, ahp); tcg_gen_ld_f32(cpu_F0s, cpu_env, neon_reg_offset(rm, 3)); neon_store_reg(rd, 0, tmp2); tmp2 = tcg_temp_new_i32(); - gen_helper_neon_fcvt_f32_to_f16(tmp2, cpu_F0s, cpu_env); + gen_helper_neon_fcvt_f32_to_f16(tmp2, cpu_F0s, fpst, ahp); tcg_gen_shli_i32(tmp2, tmp2, 16); tcg_gen_or_i32(tmp2, tmp2, tmp); neon_store_reg(rd, 1, tmp2); tcg_temp_free_i32(tmp); + tcg_temp_free_i32(ahp); + tcg_temp_free_ptr(fpst); break; + } case NEON_2RM_VCVT_F32_F16: + { + TCGv_ptr fpst; + TCGv_i32 ahp; if (!arm_dc_feature(s, ARM_FEATURE_VFP_FP16) || q || (rd & 1)) { return 1; } + fpst = get_fpstatus_ptr(true); + ahp = get_ahp_flag(); tmp3 = tcg_temp_new_i32(); tmp = neon_load_reg(rm, 0); tmp2 = neon_load_reg(rm, 1); tcg_gen_ext16u_i32(tmp3, tmp); - gen_helper_neon_fcvt_f16_to_f32(cpu_F0s, tmp3, cpu_env); + gen_helper_neon_fcvt_f16_to_f32(cpu_F0s, tmp3, fpst, ahp); tcg_gen_st_f32(cpu_F0s, cpu_env, neon_reg_offset(rd, 0)); tcg_gen_shri_i32(tmp3, tmp, 16); - gen_helper_neon_fcvt_f16_to_f32(cpu_F0s, tmp3, cpu_env); + gen_helper_neon_fcvt_f16_to_f32(cpu_F0s, tmp3, fpst, ahp); tcg_gen_st_f32(cpu_F0s, cpu_env, neon_reg_offset(rd, 1)); tcg_temp_free_i32(tmp); tcg_gen_ext16u_i32(tmp3, tmp2); - gen_helper_neon_fcvt_f16_to_f32(cpu_F0s, tmp3, cpu_env); + gen_helper_neon_fcvt_f16_to_f32(cpu_F0s, tmp3, fpst, ahp); tcg_gen_st_f32(cpu_F0s, cpu_env, neon_reg_offset(rd, 2)); tcg_gen_shri_i32(tmp3, tmp2, 16); - gen_helper_neon_fcvt_f16_to_f32(cpu_F0s, tmp3, cpu_env); + gen_helper_neon_fcvt_f16_to_f32(cpu_F0s, tmp3, fpst, ahp); tcg_gen_st_f32(cpu_F0s, cpu_env, neon_reg_offset(rd, 3)); tcg_temp_free_i32(tmp2); tcg_temp_free_i32(tmp3); break; + } case NEON_2RM_AESE: case NEON_2RM_AESMC: if (!arm_dc_feature(s, ARM_FEATURE_V8_AES) || ((rm | rd) & 1)) { diff --git a/target/arm/translate.h b/target/arm/translate.h index 4428c98e2e..41d0b8cd9a 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -177,4 +177,19 @@ void arm_free_cc(DisasCompare *cmp); void arm_jump_cc(DisasCompare *cmp, TCGLabel *label); void arm_gen_test_cc(int cc, TCGLabel *label); +/* Return state of Alternate Half-precision flag, caller frees result */ +static inline TCGv_i32 get_ahp_flag(void) +{ + TCGv_i32 fpscr = tcg_temp_new_i32(); + TCGv_i32 ahp_mode = tcg_temp_new_i32(); + + tcg_gen_ld_i32(fpscr, cpu_env, offsetof(CPUARMState, + vfp.xregs[ARM_VFP_FPSCR])); + tcg_gen_extract_i32(ahp_mode, fpscr, 26, 1); + + tcg_temp_free_i32(fpscr); + + return ahp_mode; +} + #endif /* TARGET_ARM_TRANSLATE_H */ -- 2.17.0