target/i386: fix pmovsx/pmovzx in-place operations

The SSE4.1 pmovsx* and pmovzx* instructions take packed 1-byte, 2-byte
or 4-byte inputs and sign-extend or zero-extend them to a wider vector
output.  The associated helpers for these instructions do the
extension on each element in turn, starting with the lowest.  If the
input and output are the same register, this means that all the input
elements after the first have been overwritten before they are read.
This patch makes the helpers extend starting with the highest element,
not the lowest, to avoid such overwriting.  This fixes many GCC test
failures (161 in the gcc testsuite in my GCC 6-based testing) when
testing with a default CPU setting enabling those instructions.

Signed-off-by: Joseph Myers <joseph@codesourcery.com>
Message-Id: <alpine.DEB.2.20.1708082018390.23380@digraph.polyomino.org.uk>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/target/i386/ops_sse.h b/target/i386/ops_sse.h
index 16509d0a746ceef9b5d84fdfc6eb25b2def07117..d5782167d1ed183a24ba45ee9b32510973dcce07 100644 (file)
--- a/target/i386/ops_sse.h
+++ b/target/i386/ops_sse.h
@@ -1617,18 +1617,18 @@ void glue(helper_ptest, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
 #define SSE_HELPER_F(name, elem, num, F)        \
     void glue(name, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)     \
     {                                           \
-        d->elem(0) = F(0);                      \
-        d->elem(1) = F(1);                      \
         if (num > 2) {                          \
-            d->elem(2) = F(2);                  \
-            d->elem(3) = F(3);                  \
             if (num > 4) {                      \
-                d->elem(4) = F(4);              \
-                d->elem(5) = F(5);              \
-                d->elem(6) = F(6);              \
                 d->elem(7) = F(7);              \
+                d->elem(6) = F(6);              \
+                d->elem(5) = F(5);              \
+                d->elem(4) = F(4);              \
             }                                   \
+            d->elem(3) = F(3);                  \
+            d->elem(2) = F(2);                  \
         }                                       \
+        d->elem(1) = F(1);                      \
+        d->elem(0) = F(0);                      \
     }
 
 SSE_HELPER_F(helper_pmovsxbw, W, 8, (int8_t) s->B)