[19/23] i386: Destructive FP helpers for AVX

Commit Message

Paolo Bonzini Aug. 26, 2022, 11:12 p.m. UTC

From: Paul Brook <[e-mail]>

Perpare the horizontal atithmetic vector helpers for AVX
These currently use a dummy Reg typed variable to store the result then
assign the whole register.  This will cause 128 bit operations to corrupt
the upper half of the register, so replace it with explicit temporaries
and element assignments.

Signed-off-by: Paul Brook <[e-mail]>
Message-Id: <[e-mail]>
Reviewed-by: Richard Henderson <[e-mail]>
Signed-off-by: Paolo Bonzini <[e-mail]>
---
 target/i386/ops_sse.h | 70 +++++++++++++++++++++----------------------
 1 file changed, 35 insertions(+), 35 deletions(-)

Patch

diff --git a/target/i386/ops_sse.h b/target/i386/ops_sse.h
index 17d04888c5..ed2f04ded5 100644
--- a/target/i386/ops_sse.h
+++ b/target/i386/ops_sse.h
@@ -940,45 +940,45 @@  void helper_insertq_i(CPUX86State *env, ZMMReg *d, int index, int length)
     d->ZMM_Q(0) = helper_insertq(d->ZMM_Q(0), index, length);
 }
 
-void glue(helper_haddps, SUFFIX)(CPUX86State *env, ZMMReg *d, ZMMReg *s)
-{
-    ZMMReg r;
-
-    r.ZMM_S(0) = float32_add(d->ZMM_S(0), d->ZMM_S(1), &env->sse_status);
-    r.ZMM_S(1) = float32_add(d->ZMM_S(2), d->ZMM_S(3), &env->sse_status);
-    r.ZMM_S(2) = float32_add(s->ZMM_S(0), s->ZMM_S(1), &env->sse_status);
-    r.ZMM_S(3) = float32_add(s->ZMM_S(2), s->ZMM_S(3), &env->sse_status);
-    MOVE(*d, r);
+#define SSE_HELPER_HPS(name, F)  \
+void glue(helper_ ## name, SUFFIX)(CPUX86State *env, Reg *d, Reg *s) \
+{                                                                 \
+    Reg *v = d;                                                   \
+    float32 r[2 << SHIFT];                                        \
+    int i, j;                                                     \
+    for (i = j = 0; j < 4; i++, j += 2) {                         \
+        r[i] = F(v->ZMM_S(j), v->ZMM_S(j + 1), &env->sse_status); \
+    }                                                             \
+    for (j = 0; j < 4; i++, j += 2) {                             \
+        r[i] = F(s->ZMM_S(j), s->ZMM_S(j + 1), &env->sse_status); \
+    }                                                             \
+    for (i = 0; i < 2 << SHIFT; i++) {                            \
+        d->ZMM_S(i) = r[i];                                       \
+    }                                                             \
 }
 
-void glue(helper_haddpd, SUFFIX)(CPUX86State *env, ZMMReg *d, ZMMReg *s)
-{
-    ZMMReg r;
+SSE_HELPER_HPS(haddps, float32_add)
+SSE_HELPER_HPS(hsubps, float32_sub)
 
-    r.ZMM_D(0) = float64_add(d->ZMM_D(0), d->ZMM_D(1), &env->sse_status);
-    r.ZMM_D(1) = float64_add(s->ZMM_D(0), s->ZMM_D(1), &env->sse_status);
-    MOVE(*d, r);
+#define SSE_HELPER_HPD(name, F)  \
+void glue(helper_ ## name, SUFFIX)(CPUX86State *env, Reg *d, Reg *s) \
+{                                                                 \
+    Reg *v = d;                                                   \
+    float64 r[2 << SHIFT];                                        \
+    int i, j;                                                     \
+    for (i = j = 0; j < 2; i++, j += 2) {                         \
+        r[i] = F(v->ZMM_D(j), v->ZMM_D(j + 1), &env->sse_status); \
+    }                                                             \
+    for (j = 0; j < 2; i++, j += 2) {                             \
+        r[i] = F(s->ZMM_D(j), s->ZMM_D(j + 1), &env->sse_status); \
+    }                                                             \
+    for (i = 0; i < 1 << SHIFT; i++) {                            \
+        d->ZMM_D(i) = r[i];                                       \
+    }                                                             \
 }
 
-void glue(helper_hsubps, SUFFIX)(CPUX86State *env, ZMMReg *d, ZMMReg *s)
-{
-    ZMMReg r;
-
-    r.ZMM_S(0) = float32_sub(d->ZMM_S(0), d->ZMM_S(1), &env->sse_status);
-    r.ZMM_S(1) = float32_sub(d->ZMM_S(2), d->ZMM_S(3), &env->sse_status);
-    r.ZMM_S(2) = float32_sub(s->ZMM_S(0), s->ZMM_S(1), &env->sse_status);
-    r.ZMM_S(3) = float32_sub(s->ZMM_S(2), s->ZMM_S(3), &env->sse_status);
-    MOVE(*d, r);
-}
-
-void glue(helper_hsubpd, SUFFIX)(CPUX86State *env, ZMMReg *d, ZMMReg *s)
-{
-    ZMMReg r;
-
-    r.ZMM_D(0) = float64_sub(d->ZMM_D(0), d->ZMM_D(1), &env->sse_status);
-    r.ZMM_D(1) = float64_sub(s->ZMM_D(0), s->ZMM_D(1), &env->sse_status);
-    MOVE(*d, r);
-}
+SSE_HELPER_HPD(haddpd, float64_add)
+SSE_HELPER_HPD(hsubpd, float64_sub)
 
 void glue(helper_addsubps, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
 {
@@ -1999,7 +1999,7 @@  void glue(helper_mpsadbw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
     int i, j;
     uint16_t r[8];
 
-    for (j = 0; j < 4 << SHIFT; j++) {
+    for (j = 0; j < 4 << SHIFT; ) {
         int s0 = (j * 2) + ((offset & 3) << 2);
         int d0 = (j * 2) + ((offset & 4) << 0);
         for (i = 0; i < 8; i++, d0++) {