[PATCH v3 19/23] i386: Destructive FP helpers for AVX

[Paolo Bonzini <pbonzini@redhat.com>]

From: Paul Brook <paul@nowt.org>

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 <paul@nowt.org>
Message-Id: <20220424220204.2493824-18-paul@nowt.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 target/i386/ops_sse.h | 93 ++++++++++++++++++-------------------------
 1 file changed, 39 insertions(+), 54 deletions(-)

diff --git a/target/i386/ops_sse.h b/target/i386/ops_sse.h
index 59ed30071e..61722fe4a2 100644
--- a/target/i386/ops_sse.h
+++ b/target/i386/ops_sse.h
@@ -945,45 +927,49 @@ 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, k;                                                  \
+    for (k = 0; k < 2 << SHIFT; k += LANE_WIDTH / 4) {            \
+        for (i = j = 0; j < 4; i++, j += 2) {                     \
+            r[i + k] = F(v->ZMM_S(j + k), v->ZMM_S(j + k + 1), &env->sse_status); \
+        }                                                         \
+        for (j = 0; j < 4; i++, j += 2) {                         \
+            r[i + k] = F(s->ZMM_S(j + k), s->ZMM_S(j + k + 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[1 << SHIFT];                                        \
+    int i, j, k;                                                  \
+    for (k = 0; k < 1 << SHIFT; k += LANE_WIDTH / 8) {            \
+        for (i = j = 0; j < 2; i++, j += 2) {                     \
+            r[i + k] = F(v->ZMM_D(j + k), v->ZMM_D(j + k + 1), &env->sse_status); \
+        }                                                         \
+        for (j = 0; j < 2; i++, j += 2) {                         \
+            r[i + k] = F(s->ZMM_D(j + k), s->ZMM_D(j + k + 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)
 {
-- 
2.37.1