target/i386: Rewrite vector shift helper

Rewrite the vector shift helpers in preperation for AVX support (3 operand
form and 256 bit vectors).

For now keep the existing two operand interface.

No functional changes to existing helpers.

Signed-off-by: Paul Brook <paul@nowt.org>
Message-Id: <20220424220204.2493824-11-paul@nowt.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 108 insertions, 131 deletions

diff --git a/target/i386/ops_sse.h b/target/i386/ops_sse.h
index 2c0090a..a4a0922 100644
--- a/target/i386/ops_sse.h
+++ b/target/i386/ops_sse.h
@@ -40,6 +40,8 @@
 #define SUFFIX _xmm
 #endif
 
+#define LANE_WIDTH (SHIFT ? 16 : 8)
+
 /*
  * Copy the relevant parts of a Reg value around. In the case where
  * sizeof(Reg) > SIZE, these helpers operate only on the lower bytes of
@@ -56,198 +58,173 @@
 #define MOVE(d, r) memcpy(&(d).B(0), &(r).B(0), SIZE)
 #endif
 
-void glue(helper_psrlw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+#if SHIFT == 0
+#define FPSRL(x, c) ((x) >> shift)
+#define FPSRAW(x, c) ((int16_t)(x) >> shift)
+#define FPSRAL(x, c) ((int32_t)(x) >> shift)
+#define FPSLL(x, c) ((x) << shift)
+#endif
+
+void glue(helper_psrlw, SUFFIX)(CPUX86State *env, Reg *d, Reg *c)
 {
+    Reg *s = d;
     int shift;
-
-    if (s->Q(0) > 15) {
-        d->Q(0) = 0;
-#if SHIFT == 1
-        d->Q(1) = 0;
-#endif
+    if (c->Q(0) > 15) {
+        for (int i = 0; i < 1 << SHIFT; i++) {
+            d->Q(i) = 0;
+        }
     } else {
-        shift = s->B(0);
-        d->W(0) >>= shift;
-        d->W(1) >>= shift;
-        d->W(2) >>= shift;
-        d->W(3) >>= shift;
-#if SHIFT == 1
-        d->W(4) >>= shift;
-        d->W(5) >>= shift;
-        d->W(6) >>= shift;
-        d->W(7) >>= shift;
-#endif
+        shift = c->B(0);
+        for (int i = 0; i < 4 << SHIFT; i++) {
+            d->W(i) = FPSRL(s->W(i), shift);
+        }
     }
 }
 
-void glue(helper_psraw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+void glue(helper_psllw, SUFFIX)(CPUX86State *env, Reg *d, Reg *c)
 {
+    Reg *s = d;
     int shift;
-
-    if (s->Q(0) > 15) {
-        shift = 15;
+    if (c->Q(0) > 15) {
+        for (int i = 0; i < 1 << SHIFT; i++) {
+            d->Q(i) = 0;
+        }
     } else {
-        shift = s->B(0);
+        shift = c->B(0);
+        for (int i = 0; i < 4 << SHIFT; i++) {
+            d->W(i) = FPSLL(s->W(i), shift);
+        }
     }
-    d->W(0) = (int16_t)d->W(0) >> shift;
-    d->W(1) = (int16_t)d->W(1) >> shift;
-    d->W(2) = (int16_t)d->W(2) >> shift;
-    d->W(3) = (int16_t)d->W(3) >> shift;
-#if SHIFT == 1
-    d->W(4) = (int16_t)d->W(4) >> shift;
-    d->W(5) = (int16_t)d->W(5) >> shift;
-    d->W(6) = (int16_t)d->W(6) >> shift;
-    d->W(7) = (int16_t)d->W(7) >> shift;
-#endif
 }
 
-void glue(helper_psllw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+void glue(helper_psraw, SUFFIX)(CPUX86State *env, Reg *d, Reg *c)
 {
+    Reg *s = d;
     int shift;
-
-    if (s->Q(0) > 15) {
-        d->Q(0) = 0;
-#if SHIFT == 1
-        d->Q(1) = 0;
-#endif
+    if (c->Q(0) > 15) {
+        shift = 15;
     } else {
-        shift = s->B(0);
-        d->W(0) <<= shift;
-        d->W(1) <<= shift;
-        d->W(2) <<= shift;
-        d->W(3) <<= shift;
-#if SHIFT == 1
-        d->W(4) <<= shift;
-        d->W(5) <<= shift;
-        d->W(6) <<= shift;
-        d->W(7) <<= shift;
-#endif
+        shift = c->B(0);
+    }
+    for (int i = 0; i < 4 << SHIFT; i++) {
+        d->W(i) = FPSRAW(s->W(i), shift);
     }
 }
 
-void glue(helper_psrld, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+void glue(helper_psrld, SUFFIX)(CPUX86State *env, Reg *d, Reg *c)
 {
+    Reg *s = d;
     int shift;
-
-    if (s->Q(0) > 31) {
-        d->Q(0) = 0;
-#if SHIFT == 1
-        d->Q(1) = 0;
-#endif
+    if (c->Q(0) > 31) {
+        for (int i = 0; i < 1 << SHIFT; i++) {
+            d->Q(i) = 0;
+        }
     } else {
-        shift = s->B(0);
-        d->L(0) >>= shift;
-        d->L(1) >>= shift;
-#if SHIFT == 1
-        d->L(2) >>= shift;
-        d->L(3) >>= shift;
-#endif
+        shift = c->B(0);
+        for (int i = 0; i < 2 << SHIFT; i++) {
+            d->L(i) = FPSRL(s->L(i), shift);
+        }
     }
 }
 
-void glue(helper_psrad, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+void glue(helper_pslld, SUFFIX)(CPUX86State *env, Reg *d, Reg *c)
 {
+    Reg *s = d;
     int shift;
-
-    if (s->Q(0) > 31) {
-        shift = 31;
+    if (c->Q(0) > 31) {
+        for (int i = 0; i < 1 << SHIFT; i++) {
+            d->Q(i) = 0;
+        }
     } else {
-        shift = s->B(0);
+        shift = c->B(0);
+        for (int i = 0; i < 2 << SHIFT; i++) {
+            d->L(i) = FPSLL(s->L(i), shift);
+        }
     }
-    d->L(0) = (int32_t)d->L(0) >> shift;
-    d->L(1) = (int32_t)d->L(1) >> shift;
-#if SHIFT == 1
-    d->L(2) = (int32_t)d->L(2) >> shift;
-    d->L(3) = (int32_t)d->L(3) >> shift;
-#endif
 }
 
-void glue(helper_pslld, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+void glue(helper_psrad, SUFFIX)(CPUX86State *env, Reg *d, Reg *c)
 {
+    Reg *s = d;
     int shift;
-
-    if (s->Q(0) > 31) {
-        d->Q(0) = 0;
-#if SHIFT == 1
-        d->Q(1) = 0;
-#endif
+    if (c->Q(0) > 31) {
+        shift = 31;
     } else {
-        shift = s->B(0);
-        d->L(0) <<= shift;
-        d->L(1) <<= shift;
-#if SHIFT == 1
-        d->L(2) <<= shift;
-        d->L(3) <<= shift;
-#endif
+        shift = c->B(0);
+    }
+    for (int i = 0; i < 2 << SHIFT; i++) {
+        d->L(i) = FPSRAL(s->L(i), shift);
     }
 }
 
-void glue(helper_psrlq, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+void glue(helper_psrlq, SUFFIX)(CPUX86State *env, Reg *d, Reg *c)
 {
+    Reg *s = d;
     int shift;
-
-    if (s->Q(0) > 63) {
-        d->Q(0) = 0;
-#if SHIFT == 1
-        d->Q(1) = 0;
-#endif
+    if (c->Q(0) > 63) {
+        for (int i = 0; i < 1 << SHIFT; i++) {
+            d->Q(i) = 0;
+        }
     } else {
-        shift = s->B(0);
-        d->Q(0) >>= shift;
-#if SHIFT == 1
-        d->Q(1) >>= shift;
-#endif
+        shift = c->B(0);
+        for (int i = 0; i < 1 << SHIFT; i++) {
+            d->Q(i) = FPSRL(s->Q(i), shift);
+        }
     }
 }
 
-void glue(helper_psllq, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+void glue(helper_psllq, SUFFIX)(CPUX86State *env, Reg *d, Reg *c)
 {
+    Reg *s = d;
     int shift;
-
-    if (s->Q(0) > 63) {
-        d->Q(0) = 0;
-#if SHIFT == 1
-        d->Q(1) = 0;
-#endif
+    if (c->Q(0) > 63) {
+        for (int i = 0; i < 1 << SHIFT; i++) {
+            d->Q(i) = 0;
+        }
     } else {
-        shift = s->B(0);
-        d->Q(0) <<= shift;
-#if SHIFT == 1
-        d->Q(1) <<= shift;
-#endif
+        shift = c->B(0);
+        for (int i = 0; i < 1 << SHIFT; i++) {
+            d->Q(i) = FPSLL(s->Q(i), shift);
+        }
     }
 }
 
-#if SHIFT == 1
-void glue(helper_psrldq, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+#if SHIFT >= 1
+void glue(helper_psrldq, SUFFIX)(CPUX86State *env, Reg *d, Reg *c)
 {
-    int shift, i;
+    Reg *s = d;
+    int shift, i, j;
 
-    shift = s->L(0);
+    shift = c->L(0);
     if (shift > 16) {
         shift = 16;
     }
-    for (i = 0; i < 16 - shift; i++) {
-        d->B(i) = d->B(i + shift);
-    }
-    for (i = 16 - shift; i < 16; i++) {
-        d->B(i) = 0;
+    for (j = 0; j < 8 << SHIFT; j += LANE_WIDTH) {
+        for (i = 0; i < 16 - shift; i++) {
+            d->B(j + i) = s->B(j + i + shift);
+        }
+        for (i = 16 - shift; i < 16; i++) {
+            d->B(j + i) = 0;
+        }
     }
 }
 
-void glue(helper_pslldq, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+void glue(helper_pslldq, SUFFIX)(CPUX86State *env, Reg *d, Reg *c)
 {
-    int shift, i;
+    Reg *s = d;
+    int shift, i, j;
 
-    shift = s->L(0);
+    shift = c->L(0);
     if (shift > 16) {
         shift = 16;
     }
-    for (i = 15; i >= shift; i--) {
-        d->B(i) = d->B(i - shift);
-    }
-    for (i = 0; i < shift; i++) {
-        d->B(i) = 0;
+    for (j = 0; j < 8 << SHIFT; j += LANE_WIDTH) {
+        for (i = 15; i >= shift; i--) {
+            d->B(j + i) = s->B(j + i - shift);
+        }
+        for (i = 0; i < shift; i++) {
+            d->B(j + i) = 0;
+        }
     }
 }
 #endif