[PATCH 07/18] i386: Rewrite simple integer vector helpers

[Paolo Bonzini <pbonzini@redhat.com>]

From: Paul Brook <paul@nowt.org>

Rewrite the "simple" vector integer helpers in preperation for AVX support.

While the current code is able to use the same prototype for unary
(a = F(b)) and binary (a = F(b, c)) operations, future changes will cause
them to diverge.

No functional changes to existing helpers

Signed-off-by: Paul Brook <paul@nowt.org>
Message-Id: <20220424220204.2493824-12-paul@nowt.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 target/i386/ops_sse.h | 96 +++++++++++++++++--------------------------
 1 file changed, 38 insertions(+), 58 deletions(-)

diff --git a/target/i386/ops_sse.h b/target/i386/ops_sse.h
index a1d3fbc482..0b5a8a9b34 100644
--- a/target/i386/ops_sse.h
+++ b/target/i386/ops_sse.h
@@ -223,63 +223,36 @@ void glue(helper_pslldq, SUFFIX)(CPUX86State *env, Reg *d, Reg *c)
 }
 #endif
 
-#define SSE_HELPER_B(name, F)                                   \
+#define SSE_HELPER_1(name, elem, num, F)                        \
     void glue(name, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)   \
     {                                                           \
-        d->B(0) = F(d->B(0), s->B(0));                          \
-        d->B(1) = F(d->B(1), s->B(1));                          \
-        d->B(2) = F(d->B(2), s->B(2));                          \
-        d->B(3) = F(d->B(3), s->B(3));                          \
-        d->B(4) = F(d->B(4), s->B(4));                          \
-        d->B(5) = F(d->B(5), s->B(5));                          \
-        d->B(6) = F(d->B(6), s->B(6));                          \
-        d->B(7) = F(d->B(7), s->B(7));                          \
-        XMM_ONLY(                                               \
-                 d->B(8) = F(d->B(8), s->B(8));                 \
-                 d->B(9) = F(d->B(9), s->B(9));                 \
-                 d->B(10) = F(d->B(10), s->B(10));              \
-                 d->B(11) = F(d->B(11), s->B(11));              \
-                 d->B(12) = F(d->B(12), s->B(12));              \
-                 d->B(13) = F(d->B(13), s->B(13));              \
-                 d->B(14) = F(d->B(14), s->B(14));              \
-                 d->B(15) = F(d->B(15), s->B(15));              \
-                                                        )       \
-            }
+        int n = num;                                            \
+        for (int i = 0; i < n; i++) {                           \
+            d->elem(i) = F(s->elem(i));                         \
+        }                                                       \
+    }
+
+#define SSE_HELPER_2(name, elem, num, F)                        \
+    void glue(name, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)   \
+    {                                                           \
+	Reg *v = d;                                             \
+        int n = num;                                            \
+        for (int i = 0; i < n; i++) {                           \
+            d->elem(i) = F(v->elem(i), s->elem(i));             \
+        }                                                       \
+    }
+
+#define SSE_HELPER_B(name, F)                                   \
+    SSE_HELPER_2(name, B, 8 << SHIFT, F)
 
 #define SSE_HELPER_W(name, F)                                   \
-    void glue(name, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)   \
-    {                                                           \
-        d->W(0) = F(d->W(0), s->W(0));                          \
-        d->W(1) = F(d->W(1), s->W(1));                          \
-        d->W(2) = F(d->W(2), s->W(2));                          \
-        d->W(3) = F(d->W(3), s->W(3));                          \
-        XMM_ONLY(                                               \
-                 d->W(4) = F(d->W(4), s->W(4));                 \
-                 d->W(5) = F(d->W(5), s->W(5));                 \
-                 d->W(6) = F(d->W(6), s->W(6));                 \
-                 d->W(7) = F(d->W(7), s->W(7));                 \
-                                                        )       \
-            }
+    SSE_HELPER_2(name, W, 4 << SHIFT, F)
 
 #define SSE_HELPER_L(name, F)                                   \
-    void glue(name, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)   \
-    {                                                           \
-        d->L(0) = F(d->L(0), s->L(0));                          \
-        d->L(1) = F(d->L(1), s->L(1));                          \
-        XMM_ONLY(                                               \
-                 d->L(2) = F(d->L(2), s->L(2));                 \
-                 d->L(3) = F(d->L(3), s->L(3));                 \
-                                                        )       \
-            }
+    SSE_HELPER_2(name, L, 2 << SHIFT, F)
 
 #define SSE_HELPER_Q(name, F)                                   \
-    void glue(name, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)   \
-    {                                                           \
-        d->Q(0) = F(d->Q(0), s->Q(0));                          \
-        XMM_ONLY(                                               \
-                 d->Q(1) = F(d->Q(1), s->Q(1));                 \
-                                                        )       \
-            }
+    SSE_HELPER_2(name, Q, 1 << SHIFT, F)
 
 #if SHIFT == 0
 static inline int satub(int x)
@@ -400,12 +373,19 @@ SSE_HELPER_W(helper_pcmpeqw, FCMPEQ)
 SSE_HELPER_L(helper_pcmpeql, FCMPEQ)
 
 SSE_HELPER_W(helper_pmullw, FMULLW)
-#if SHIFT == 0
-SSE_HELPER_W(helper_pmulhrw, FMULHRW)
-#endif
 SSE_HELPER_W(helper_pmulhuw, FMULHUW)
 SSE_HELPER_W(helper_pmulhw, FMULHW)
 
+#if SHIFT == 0
+void glue(helper_pmulhrw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+{
+    d->W(0) = FMULHRW(d->W(0), s->W(0));
+    d->W(1) = FMULHRW(d->W(1), s->W(1));
+    d->W(2) = FMULHRW(d->W(2), s->W(2));
+    d->W(3) = FMULHRW(d->W(3), s->W(3));
+}
+#endif
+
 SSE_HELPER_B(helper_pavgb, FAVG)
 SSE_HELPER_W(helper_pavgw, FAVG)
 
@@ -1538,12 +1518,12 @@ void glue(helper_phsubsw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
     MOVE(*d, r);
 }
 
-#define FABSB(_, x) (x > INT8_MAX  ? -(int8_t)x : x)
-#define FABSW(_, x) (x > INT16_MAX ? -(int16_t)x : x)
-#define FABSL(_, x) (x > INT32_MAX ? -(int32_t)x : x)
-SSE_HELPER_B(helper_pabsb, FABSB)
-SSE_HELPER_W(helper_pabsw, FABSW)
-SSE_HELPER_L(helper_pabsd, FABSL)
+#define FABSB(x) (x > INT8_MAX  ? -(int8_t)x : x)
+#define FABSW(x) (x > INT16_MAX ? -(int16_t)x : x)
+#define FABSL(x) (x > INT32_MAX ? -(int32_t)x : x)
+SSE_HELPER_1(helper_pabsb, B, 8 << SHIFT, FABSB)
+SSE_HELPER_1(helper_pabsw, W, 4 << SHIFT, FABSW)
+SSE_HELPER_1(helper_pabsd, L, 2 << SHIFT, FABSL)
 
 #define FMULHRSW(d, s) (((int16_t) d * (int16_t)s + 0x4000) >> 15)
 SSE_HELPER_W(helper_pmulhrsw, FMULHRSW)
-- 
2.37.1