diff mbox series

[09/61] target/arm: Introduce FPST_ZA, FPST_ZA_F16

Message ID 20250206195715.2150758-10-richard.henderson@linaro.org
State New
Headers show
Series target/arm: Implement FEAT_SME2 | expand

Commit Message

Richard Henderson Feb. 6, 2025, 7:56 p.m. UTC 
Rather than repeatedly copying FPST_FPCR to locals
and setting default nan mode, create dedicated float_status.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/cpu.h        | 12 +++++++++++-
 target/arm/cpu.c        |  4 ++++
 target/arm/vfp_helper.c | 10 ++++++++++
 3 files changed, 25 insertions(+), 1 deletion(-)
diff mbox series

Patch

diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index e6513ef1e5..42c39ac6bd 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -219,6 +219,8 @@  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
@@ -239,6 +241,12 @@  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
@@ -252,10 +260,12 @@  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/cpu.c b/target/arm/cpu.c
index 180e11c5d7..ba08c05ec6 100644
--- a/target/arm/cpu.c
+++ b/target/arm/cpu.c
@@ -550,11 +550,15 @@  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/vfp_helper.c b/target/arm/vfp_helper.c
index ff4b25bf28..f26c0d211e 100644
--- a/target/arm/vfp_helper.c
+++ b/target/arm/vfp_helper.c
@@ -202,6 +202,8 @@  static 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;
@@ -209,15 +211,18 @@  static 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]);
     }
@@ -229,6 +234,7 @@  static 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;
@@ -246,9 +252,13 @@  static 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]);
         }
     }
     /*