target/i386: Floating point arithmetic helper AVX prep

Prepare the "easy" floating point vector helpers for AVX

No functional changes to existing helpers.

Signed-off-by: Paul Brook <paul@nowt.org>
Message-Id: <20220424220204.2493824-16-paul@nowt.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 87 insertions, 41 deletions

diff --git a/target/i386/ops_sse.h b/target/i386/ops_sse.h
index bb50ca6f8d..86ca74492e 100644
--- a/target/i386/ops_sse.h
+++ b/target/i386/ops_sse.h
@@ -553,40 +553,58 @@ void glue(helper_pshufhw, SUFFIX)(Reg *d, Reg *s, int order)
 }
 #endif
 
-#if SHIFT == 1
+#if SHIFT >= 1
 /* FPU ops */
 /* XXX: not accurate */
 
-#define SSE_HELPER_S(name, F)                                           \
-    void glue(helper_ ## name ## ps, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)\
+#define SSE_HELPER_P(name, F)                                           \
+    void glue(helper_ ## name ## ps, SUFFIX)(CPUX86State *env,          \
+            Reg *d, Reg *s)                                             \
     {                                                                   \
-        d->ZMM_S(0) = F(32, d->ZMM_S(0), s->ZMM_S(0));                  \
-        d->ZMM_S(1) = F(32, d->ZMM_S(1), s->ZMM_S(1));                  \
-        d->ZMM_S(2) = F(32, d->ZMM_S(2), s->ZMM_S(2));                  \
-        d->ZMM_S(3) = F(32, d->ZMM_S(3), s->ZMM_S(3));                  \
+        Reg *v = d;                                                     \
+        int i;                                                          \
+        for (i = 0; i < 2 << SHIFT; i++) {                              \
+            d->ZMM_S(i) = F(32, v->ZMM_S(i), s->ZMM_S(i));              \
+        }                                                               \
     }                                                                   \
                                                                         \
-    void helper_ ## name ## ss(CPUX86State *env, Reg *d, Reg *s)        \
+    void glue(helper_ ## name ## pd, SUFFIX)(CPUX86State *env,          \
+            Reg *d, Reg *s)                                     \
     {                                                                   \
-        d->ZMM_S(0) = F(32, d->ZMM_S(0), s->ZMM_S(0));                  \
-    }                                                                   \
+        Reg *v = d;                                                     \
+        int i;                                                          \
+        for (i = 0; i < 1 << SHIFT; i++) {                              \
+            d->ZMM_D(i) = F(64, v->ZMM_D(i), s->ZMM_D(i));              \
+        }                                                               \
+    }
+
+#if SHIFT == 1
+
+#define SSE_HELPER_S(name, F)                                           \
+    SSE_HELPER_P(name, F)                                               \
                                                                         \
-    void glue(helper_ ## name ## pd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)\
+    void helper_ ## name ## ss(CPUX86State *env, Reg *d, Reg *s)\
     {                                                                   \
-        d->ZMM_D(0) = F(64, d->ZMM_D(0), s->ZMM_D(0));                  \
-        d->ZMM_D(1) = F(64, d->ZMM_D(1), s->ZMM_D(1));                  \
+        Reg *v = d;                                                     \
+        d->ZMM_S(0) = F(32, v->ZMM_S(0), s->ZMM_S(0));                  \
     }                                                                   \
                                                                         \
-    void helper_ ## name ## sd(CPUX86State *env, Reg *d, Reg *s)        \
+    void helper_ ## name ## sd(CPUX86State *env, Reg *d, Reg *s)\
     {                                                                   \
-        d->ZMM_D(0) = F(64, d->ZMM_D(0), s->ZMM_D(0));                  \
+        Reg *v = d;                                                     \
+        d->ZMM_D(0) = F(64, v->ZMM_D(0), s->ZMM_D(0));                  \
     }
 
+#else
+
+#define SSE_HELPER_S(name, F) SSE_HELPER_P(name, F)
+
+#endif
+
 #define FPU_ADD(size, a, b) float ## size ## _add(a, b, &env->sse_status)
 #define FPU_SUB(size, a, b) float ## size ## _sub(a, b, &env->sse_status)
 #define FPU_MUL(size, a, b) float ## size ## _mul(a, b, &env->sse_status)
 #define FPU_DIV(size, a, b) float ## size ## _div(a, b, &env->sse_status)
-#define FPU_SQRT(size, a, b) float ## size ## _sqrt(b, &env->sse_status)
 
 /* Note that the choice of comparison op here is important to get the
  * special cases right: for min and max Intel specifies that (-0,0),
@@ -603,8 +621,34 @@ SSE_HELPER_S(mul, FPU_MUL)
 SSE_HELPER_S(div, FPU_DIV)
 SSE_HELPER_S(min, FPU_MIN)
 SSE_HELPER_S(max, FPU_MAX)
-SSE_HELPER_S(sqrt, FPU_SQRT)
 
+void glue(helper_sqrtps, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+{
+    int i;
+    for (i = 0; i < 2 << SHIFT; i++) {
+        d->ZMM_S(i) = float32_sqrt(s->ZMM_S(i), &env->sse_status);
+    }
+}
+
+void glue(helper_sqrtpd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+{
+    int i;
+    for (i = 0; i < 1 << SHIFT; i++) {
+        d->ZMM_D(i) = float64_sqrt(s->ZMM_D(i), &env->sse_status);
+    }
+}
+
+#if SHIFT == 1
+void helper_sqrtss(CPUX86State *env, Reg *d, Reg *s)
+{
+    d->ZMM_S(0) = float32_sqrt(s->ZMM_S(0), &env->sse_status);
+}
+
+void helper_sqrtsd(CPUX86State *env, Reg *d, Reg *s)
+{
+    d->ZMM_D(0) = float64_sqrt(s->ZMM_D(0), &env->sse_status);
+}
+#endif
 
 /* float to float conversions */
 void glue(helper_cvtps2pd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
@@ -822,18 +866,12 @@ int64_t helper_cvttsd2sq(CPUX86State *env, ZMMReg *s)
 void glue(helper_rsqrtps, SUFFIX)(CPUX86State *env, ZMMReg *d, ZMMReg *s)
 {
     uint8_t old_flags = get_float_exception_flags(&env->sse_status);
-    d->ZMM_S(0) = float32_div(float32_one,
-                              float32_sqrt(s->ZMM_S(0), &env->sse_status),
-                              &env->sse_status);
-    d->ZMM_S(1) = float32_div(float32_one,
-                              float32_sqrt(s->ZMM_S(1), &env->sse_status),
-                              &env->sse_status);
-    d->ZMM_S(2) = float32_div(float32_one,
-                              float32_sqrt(s->ZMM_S(2), &env->sse_status),
-                              &env->sse_status);
-    d->ZMM_S(3) = float32_div(float32_one,
-                              float32_sqrt(s->ZMM_S(3), &env->sse_status),
-                              &env->sse_status);
+    int i;
+    for (i = 0; i < 2 << SHIFT; i++) {
+        d->ZMM_S(i) = float32_div(float32_one,
+                                  float32_sqrt(s->ZMM_S(i), &env->sse_status),
+                                  &env->sse_status);
+    }
     set_float_exception_flags(old_flags, &env->sse_status);
 }
 
@@ -849,10 +887,10 @@ void helper_rsqrtss(CPUX86State *env, ZMMReg *d, ZMMReg *s)
 void glue(helper_rcpps, SUFFIX)(CPUX86State *env, ZMMReg *d, ZMMReg *s)
 {
     uint8_t old_flags = get_float_exception_flags(&env->sse_status);
-    d->ZMM_S(0) = float32_div(float32_one, s->ZMM_S(0), &env->sse_status);
-    d->ZMM_S(1) = float32_div(float32_one, s->ZMM_S(1), &env->sse_status);
-    d->ZMM_S(2) = float32_div(float32_one, s->ZMM_S(2), &env->sse_status);
-    d->ZMM_S(3) = float32_div(float32_one, s->ZMM_S(3), &env->sse_status);
+    int i;
+    for (i = 0; i < 2 << SHIFT; i++) {
+        d->ZMM_S(i) = float32_div(float32_one, s->ZMM_S(i), &env->sse_status);
+    }
     set_float_exception_flags(old_flags, &env->sse_status);
 }
 
@@ -947,18 +985,24 @@ void glue(helper_hsubpd, SUFFIX)(CPUX86State *env, ZMMReg *d, ZMMReg *s)
     MOVE(*d, r);
 }
 
-void glue(helper_addsubps, SUFFIX)(CPUX86State *env, ZMMReg *d, ZMMReg *s)
+void glue(helper_addsubps, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
 {
-    d->ZMM_S(0) = float32_sub(d->ZMM_S(0), s->ZMM_S(0), &env->sse_status);
-    d->ZMM_S(1) = float32_add(d->ZMM_S(1), s->ZMM_S(1), &env->sse_status);
-    d->ZMM_S(2) = float32_sub(d->ZMM_S(2), s->ZMM_S(2), &env->sse_status);
-    d->ZMM_S(3) = float32_add(d->ZMM_S(3), s->ZMM_S(3), &env->sse_status);
+    Reg *v = d;
+    int i;
+    for (i = 0; i < 2 << SHIFT; i += 2) {
+        d->ZMM_S(i) = float32_sub(v->ZMM_S(i), s->ZMM_S(i), &env->sse_status);
+        d->ZMM_S(i+1) = float32_add(v->ZMM_S(i+1), s->ZMM_S(i+1), &env->sse_status);
+    }
 }
 
-void glue(helper_addsubpd, SUFFIX)(CPUX86State *env, ZMMReg *d, ZMMReg *s)
+void glue(helper_addsubpd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
 {
-    d->ZMM_D(0) = float64_sub(d->ZMM_D(0), s->ZMM_D(0), &env->sse_status);
-    d->ZMM_D(1) = float64_add(d->ZMM_D(1), s->ZMM_D(1), &env->sse_status);
+    Reg *v = d;
+    int i;
+    for (i = 0; i < 1 << SHIFT; i += 2) {
+        d->ZMM_D(i) = float64_sub(v->ZMM_D(i), s->ZMM_D(i), &env->sse_status);
+        d->ZMM_D(i+1) = float64_add(v->ZMM_D(i+1), s->ZMM_D(i+1), &env->sse_status);
+    }
 }
 
 /* XXX: unordered */
@@ -2258,6 +2302,8 @@ void glue(helper_aeskeygenassist, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
 }
 #endif
 
+#undef SSE_HELPER_S
+
 #undef SHIFT
 #undef XMM_ONLY
 #undef Reg