From c994c84d384b87cd862d12f6b9db4bcfd42b5a7b Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Fri, 4 Jul 2025 08:19:34 -0600 Subject: [PATCH] target/arm: Introduce FPST_ZA, FPST_ZA_F16 Rather than repeatedly copying FPST_FPCR to locals and setting default nan mode, create dedicated float_status. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20250704142112.1018902-12-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/cpu.c | 4 ++++ target/arm/cpu.h | 12 +++++++++++- target/arm/tcg/vfp_helper.c | 12 +++++++++++- 3 files changed, 26 insertions(+), 2 deletions(-) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index ebac86f70d3..7b207f2620c 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -554,11 +554,15 @@ static void arm_cpu_reset_hold(Object *obj, ResetType type) set_flush_inputs_to_zero(1, &env->vfp.fp_status[FPST_STD]); set_default_nan_mode(1, &env->vfp.fp_status[FPST_STD]); set_default_nan_mode(1, &env->vfp.fp_status[FPST_STD_F16]); + set_default_nan_mode(1, &env->vfp.fp_status[FPST_ZA]); + set_default_nan_mode(1, &env->vfp.fp_status[FPST_ZA_F16]); arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A32]); arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A64]); + arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_ZA]); arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_STD]); arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A32_F16]); arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A64_F16]); + arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_ZA_F16]); arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_STD_F16]); arm_set_ah_fp_behaviours(&env->vfp.fp_status[FPST_AH]); set_flush_to_zero(1, &env->vfp.fp_status[FPST_AH]); diff --git a/target/arm/cpu.h b/target/arm/cpu.h index 96a49072665..2530aaca22c 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -207,6 +207,8 @@ typedef struct NVICState NVICState; * when FPCR.AH == 1 (bfloat16 conversions and multiplies, * and the reciprocal and square root estimate/step insns); * for half-precision + * ZA: the "streaming sve" fp status. + * ZA_F16: likewise for half-precision. * * Half-precision operations are governed by a separate * flush-to-zero control bit in FPSCR:FZ16. We pass a separate @@ -227,6 +229,12 @@ typedef struct NVICState NVICState; * they ignore FPCR.RMode. But they don't ignore FPCR.FZ16, * which means we need an FPST_AH_F16 as well. * + * The "ZA" float_status are for Streaming SVE operations which use + * default-NaN and do not generate fp exceptions, which means that they + * do not accumulate exception bits back into FPCR. + * See e.g. FPAdd vs FPAdd_ZA pseudocode functions, and the setting + * of fpcr.DN and fpexec parameters. + * * To avoid having to transfer exception bits around, we simply * say that the FPSCR cumulative exception flags are the logical * OR of the flags in the four fp statuses. This relies on the @@ -240,10 +248,12 @@ typedef enum ARMFPStatusFlavour { FPST_A64_F16, FPST_AH, FPST_AH_F16, + FPST_ZA, + FPST_ZA_F16, FPST_STD, FPST_STD_F16, } ARMFPStatusFlavour; -#define FPST_COUNT 8 +#define FPST_COUNT 10 typedef struct CPUArchState { /* Regs for current mode. */ diff --git a/target/arm/tcg/vfp_helper.c b/target/arm/tcg/vfp_helper.c index b1324c5c0a6..e156e3774ad 100644 --- a/target/arm/tcg/vfp_helper.c +++ b/target/arm/tcg/vfp_helper.c @@ -123,7 +123,7 @@ uint32_t vfp_get_fpsr_from_host(CPUARMState *env) a64_flags |= (get_float_exception_flags(&env->vfp.fp_status[FPST_A64_F16]) & ~(float_flag_input_denormal_flushed | float_flag_input_denormal_used)); /* - * We do not merge in flags from FPST_AH or FPST_AH_F16, because + * We do not merge in flags from FPST_{AH,ZA} or FPST_{AH,ZA}_F16, because * they are used for insns that must not set the cumulative exception bits. */ @@ -196,6 +196,8 @@ void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val, uint32_t mask) set_float_rounding_mode(i, &env->vfp.fp_status[FPST_A64]); set_float_rounding_mode(i, &env->vfp.fp_status[FPST_A32_F16]); set_float_rounding_mode(i, &env->vfp.fp_status[FPST_A64_F16]); + set_float_rounding_mode(i, &env->vfp.fp_status[FPST_ZA]); + set_float_rounding_mode(i, &env->vfp.fp_status[FPST_ZA_F16]); } if (changed & FPCR_FZ16) { bool ftz_enabled = val & FPCR_FZ16; @@ -203,15 +205,18 @@ void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val, uint32_t mask) set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A64_F16]); set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_STD_F16]); set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_AH_F16]); + set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_ZA_F16]); set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A32_F16]); set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A64_F16]); set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_STD_F16]); set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_AH_F16]); + set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_ZA_F16]); } if (changed & FPCR_FZ) { bool ftz_enabled = val & FPCR_FZ; set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A32]); set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A64]); + set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_ZA]); /* FIZ is A64 only so FZ always makes A32 code flush inputs to zero */ set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A32]); } @@ -223,6 +228,7 @@ void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val, uint32_t mask) bool fitz_enabled = (val & FPCR_FIZ) || (val & (FPCR_FZ | FPCR_AH)) == FPCR_FZ; set_flush_inputs_to_zero(fitz_enabled, &env->vfp.fp_status[FPST_A64]); + set_flush_inputs_to_zero(fitz_enabled, &env->vfp.fp_status[FPST_ZA]); } if (changed & FPCR_DN) { bool dnan_enabled = val & FPCR_DN; @@ -240,9 +246,13 @@ void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val, uint32_t mask) /* Change behaviours for A64 FP operations */ arm_set_ah_fp_behaviours(&env->vfp.fp_status[FPST_A64]); arm_set_ah_fp_behaviours(&env->vfp.fp_status[FPST_A64_F16]); + arm_set_ah_fp_behaviours(&env->vfp.fp_status[FPST_ZA]); + arm_set_ah_fp_behaviours(&env->vfp.fp_status[FPST_ZA_F16]); } else { arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A64]); arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A64_F16]); + arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_ZA]); + arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_ZA_F16]); } } /* -- 2.47.2