diff mbox series

[PULL,10/28] target/arm: squash FZ16 behaviour for conversions

Message ID 20180516155243.16937-11-richard.henderson@linaro.org
State Accepted
Commit 0acb9e7cb341cd767e39ec0875c8706eb2f1c359
Headers show
Series softfloat patch roundup | expand

Commit Message

Richard Henderson May 16, 2018, 3:52 p.m. UTC
From: Alex Bennée <alex.bennee@linaro.org>


The ARM ARM specifies FZ16 is suppressed for conversions. Rather than
pushing this logic into the softfloat code we can simply save the FZ
state and temporarily disable it for the softfloat call.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>

Signed-off-by: Alex Bennée <alex.bennee@linaro.org>

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

---
 target/arm/helper.c | 40 ++++++++++++++++++++++++++++++++++++----
 1 file changed, 36 insertions(+), 4 deletions(-)

-- 
2.17.0
diff mbox series

Patch

diff --git a/target/arm/helper.c b/target/arm/helper.c
index 1762042fc7..238a3ceba8 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -11542,22 +11542,54 @@  uint32_t HELPER(set_neon_rmode)(uint32_t rmode, CPUARMState *env)
 /* Half precision conversions.  */
 float32 HELPER(vfp_fcvt_f16_to_f32)(float16 a, void *fpstp, uint32_t ahp_mode)
 {
-    return float16_to_float32(a, !ahp_mode, fpstp);
+    /* Squash FZ16 to 0 for the duration of conversion.  In this case,
+     * it would affect flushing input denormals.
+     */
+    float_status *fpst = fpstp;
+    flag save = get_flush_inputs_to_zero(fpst);
+    set_flush_inputs_to_zero(false, fpst);
+    float32 r = float16_to_float32(a, !ahp_mode, fpst);
+    set_flush_inputs_to_zero(save, fpst);
+    return r;
 }
 
 float16 HELPER(vfp_fcvt_f32_to_f16)(float32 a, void *fpstp, uint32_t ahp_mode)
 {
-    return float32_to_float16(a, !ahp_mode, fpstp);
+    /* Squash FZ16 to 0 for the duration of conversion.  In this case,
+     * it would affect flushing output denormals.
+     */
+    float_status *fpst = fpstp;
+    flag save = get_flush_to_zero(fpst);
+    set_flush_to_zero(false, fpst);
+    float16 r = float32_to_float16(a, !ahp_mode, fpst);
+    set_flush_to_zero(save, fpst);
+    return r;
 }
 
 float64 HELPER(vfp_fcvt_f16_to_f64)(float16 a, void *fpstp, uint32_t ahp_mode)
 {
-    return float16_to_float64(a, !ahp_mode, fpstp);
+    /* Squash FZ16 to 0 for the duration of conversion.  In this case,
+     * it would affect flushing input denormals.
+     */
+    float_status *fpst = fpstp;
+    flag save = get_flush_inputs_to_zero(fpst);
+    set_flush_inputs_to_zero(false, fpst);
+    float64 r = float16_to_float64(a, !ahp_mode, fpst);
+    set_flush_inputs_to_zero(save, fpst);
+    return r;
 }
 
 float16 HELPER(vfp_fcvt_f64_to_f16)(float64 a, void *fpstp, uint32_t ahp_mode)
 {
-    return float64_to_float16(a, !ahp_mode, fpstp);
+    /* Squash FZ16 to 0 for the duration of conversion.  In this case,
+     * it would affect flushing output denormals.
+     */
+    float_status *fpst = fpstp;
+    flag save = get_flush_to_zero(fpst);
+    set_flush_to_zero(false, fpst);
+    float16 r = float64_to_float16(a, !ahp_mode, fpst);
+    set_flush_to_zero(save, fpst);
+    return r;
 }
 
 #define float32_two make_float32(0x40000000)