Bootstrapped and check-gcc on x86_64-none-linux-gnu.

gcc/ChangeLog:

        * config/i386/i386.c (ix86_expand_reduc): Extract result into scalar.
        * config/i386/sse.md (reduc_splus_v8df, reduc_<code>_<mode> * 3,
        reduc_umin_v8hi): Rename to...
        (reduc_plus_scal_v8df, reduc_<code>_scal_<mode> * 3,
        reduc_umin_scal_v8hi): ...these, changing result mode to scalar.

        (reduc_splus_v4df, reduc_splus_v2df, reduc_splus_v16sf,
        reduc_splus_v8sf, reduc_splus_v4sf): Rename to...
        (reduc_plus_scal_v4df, reduc_plus_scal_v2df, reduc_plus_scal_v16sf,
        reduc_plus_scal_v8sf, reduc_plus_scal_v4sf): ...these, adding
        gen_vec_extract for scalar result.
commit 80b0d10a78b2f3e86325f373e99e9cf71e42e622
Author: Alan Lawrence <alan.lawre...@arm.com>
Date:   Tue Oct 7 13:25:08 2014 +0100

    i386

diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index 4c4a6eb..670a5f5 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -41211,12 +41211,12 @@ emit_reduc_half (rtx dest, rtx src, int i)
 }
 
 /* Expand a vector reduction.  FN is the binary pattern to reduce;
-   DEST is the destination; IN is the input vector.  */
+   DEST is the (scalar) destination; IN is the input vector.  */
 
 void
 ix86_expand_reduc (rtx (*fn) (rtx, rtx, rtx), rtx dest, rtx in)
 {
-  rtx half, dst, vec = in;
+  rtx half, dst = NULL_RTX, vec = in;
   enum machine_mode mode = GET_MODE (in);
   int i;
 
@@ -41225,23 +41225,21 @@ ix86_expand_reduc (rtx (*fn) (rtx, rtx, rtx), rtx dest, rtx in)
       && mode == V8HImode
       && fn == gen_uminv8hi3)
     {
-      emit_insn (gen_sse4_1_phminposuw (dest, in));
-      return;
+      dst = gen_reg_rtx (mode);
+      emit_insn (gen_sse4_1_phminposuw (dst, in));
     }
-
-  for (i = GET_MODE_BITSIZE (mode);
-       i > GET_MODE_BITSIZE (GET_MODE_INNER (mode));
-       i >>= 1)
-    {
+  else
+    for (i = GET_MODE_BITSIZE (mode);
+	  i > GET_MODE_BITSIZE (GET_MODE_INNER (mode));
+	  i >>= 1)
+      {
       half = gen_reg_rtx (mode);
       emit_reduc_half (half, vec, i);
-      if (i == GET_MODE_BITSIZE (GET_MODE_INNER (mode)) * 2)
-	dst = dest;
-      else
-	dst = gen_reg_rtx (mode);
+      dst = gen_reg_rtx (mode);
       emit_insn (fn (dst, half, vec));
       vec = dst;
     }
+  ix86_expand_vector_extract (false, dest, dst, 0);
 }
 
 /* Target hook for scalar_mode_supported_p.  */
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index e7646d7..e4e0b95 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -2238,8 +2238,8 @@
    (set_attr "prefix_rep" "1,*")
    (set_attr "mode" "V4SF")])
 
-(define_expand "reduc_splus_v8df"
-  [(match_operand:V8DF 0 "register_operand")
+(define_expand "reduc_plus_scal_v8df"
+  [(match_operand:DF 0 "register_operand")
    (match_operand:V8DF 1 "register_operand")]
   "TARGET_AVX512F"
 {
@@ -2247,30 +2247,35 @@
   DONE;
 })
 
-(define_expand "reduc_splus_v4df"
-  [(match_operand:V4DF 0 "register_operand")
+(define_expand "reduc_plus_scal_v4df"
+  [(match_operand:DF 0 "register_operand")
    (match_operand:V4DF 1 "register_operand")]
   "TARGET_AVX"
 {
   rtx tmp = gen_reg_rtx (V4DFmode);
   rtx tmp2 = gen_reg_rtx (V4DFmode);
+  rtx tmp3 = gen_reg_rtx (V4DFmode);
+  
   emit_insn (gen_avx_haddv4df3 (tmp, operands[1], operands[1]));
   emit_insn (gen_avx_vperm2f128v4df3 (tmp2, tmp, tmp, GEN_INT (1)));
-  emit_insn (gen_addv4df3 (operands[0], tmp, tmp2));
+  emit_insn (gen_addv4df3 (tmp3, tmp, tmp2));
+  emit_insn (gen_vec_extractv4df (operands[0], tmp3, GEN_INT (1)));
   DONE;
 })
 
-(define_expand "reduc_splus_v2df"
-  [(match_operand:V2DF 0 "register_operand")
+(define_expand "reduc_plus_scal_v2df"
+  [(match_operand:DF 0 "register_operand")
    (match_operand:V2DF 1 "register_operand")]
   "TARGET_SSE3"
 {
-  emit_insn (gen_sse3_haddv2df3 (operands[0], operands[1], operands[1]));
+  rtx tmp = gen_reg_rtx (V2DFmode);
+  emit_insn (gen_sse3_haddv2df3 (tmp, operands[1], operands[1]));
+  emit_insn (gen_vec_extractv2df (operands[0], tmp, GEN_INT (0)));
   DONE;
 })
 
-(define_expand "reduc_splus_v16sf"
-  [(match_operand:V16SF 0 "register_operand")
+(define_expand "reduc_plus_scal_v16sf"
+  [(match_operand:SF 0 "register_operand")
    (match_operand:V16SF 1 "register_operand")]
   "TARGET_AVX512F"
 {
@@ -2278,30 +2283,35 @@
   DONE;
 })
 
-(define_expand "reduc_splus_v8sf"
-  [(match_operand:V8SF 0 "register_operand")
+(define_expand "reduc_plus_scal_v8sf"
+  [(match_operand:SF 0 "register_operand")
    (match_operand:V8SF 1 "register_operand")]
   "TARGET_AVX"
 {
   rtx tmp = gen_reg_rtx (V8SFmode);
   rtx tmp2 = gen_reg_rtx (V8SFmode);
+  rtx tmp3 = gen_reg_rtx (V8SFmode);
+  
   emit_insn (gen_avx_haddv8sf3 (tmp, operands[1], operands[1]));
   emit_insn (gen_avx_haddv8sf3 (tmp2, tmp, tmp));
   emit_insn (gen_avx_vperm2f128v8sf3 (tmp, tmp2, tmp2, GEN_INT (1)));
-  emit_insn (gen_addv8sf3 (operands[0], tmp, tmp2));
+  emit_insn (gen_addv8sf3 (tmp3, tmp, tmp2));
+  emit_insn (gen_vec_extractv8sf (operands[0], tmp3, GEN_INT (0)));
   DONE;
 })
 
-(define_expand "reduc_splus_v4sf"
-  [(match_operand:V4SF 0 "register_operand")
+(define_expand "reduc_plus_scal_v4sf"
+  [(match_operand:SF 0 "register_operand")
    (match_operand:V4SF 1 "register_operand")]
   "TARGET_SSE"
 {
   if (TARGET_SSE3)
     {
       rtx tmp = gen_reg_rtx (V4SFmode);
+      rtx tmp2 = gen_reg_rtx (V4SFmode);
       emit_insn (gen_sse3_haddv4sf3 (tmp, operands[1], operands[1]));
-      emit_insn (gen_sse3_haddv4sf3 (operands[0], tmp, tmp));
+      emit_insn (gen_sse3_haddv4sf3 (tmp2, tmp, tmp));
+      emit_insn (gen_vec_extractv4sf (operands[0], tmp2, GEN_INT (0)));
     }
   else
     ix86_expand_reduc (gen_addv4sf3, operands[0], operands[1]);
@@ -2317,9 +2327,9 @@
    (V8DI "TARGET_AVX512F") (V16SF "TARGET_AVX512F")
    (V8DF "TARGET_AVX512F")])
 
-(define_expand "reduc_<code>_<mode>"
+(define_expand "reduc_<code>_scal_<mode>"
   [(smaxmin:REDUC_SMINMAX_MODE
-     (match_operand:REDUC_SMINMAX_MODE 0 "register_operand")
+     (match_operand:<ssescalarmode> 0 "register_operand")
      (match_operand:REDUC_SMINMAX_MODE 1 "register_operand"))]
   ""
 {
@@ -2327,9 +2337,9 @@
   DONE;
 })
 
-(define_expand "reduc_<code>_<mode>"
+(define_expand "reduc_<code>_scal_<mode>"
   [(umaxmin:VI48_512
-     (match_operand:VI48_512 0 "register_operand")
+     (match_operand:<ssescalarmode> 0 "register_operand")
      (match_operand:VI48_512 1 "register_operand"))]
   "TARGET_AVX512F"
 {
@@ -2337,9 +2347,9 @@
   DONE;
 })
 
-(define_expand "reduc_<code>_<mode>"
+(define_expand "reduc_<code>_scal_<mode>"
   [(umaxmin:VI_256
-     (match_operand:VI_256 0 "register_operand")
+     (match_operand:<ssescalarmode> 0 "register_operand")
      (match_operand:VI_256 1 "register_operand"))]
   "TARGET_AVX2"
 {
@@ -2347,9 +2357,9 @@
   DONE;
 })
 
-(define_expand "reduc_umin_v8hi"
+(define_expand "reduc_umin_scal_v8hi"
   [(umin:V8HI
-     (match_operand:V8HI 0 "register_operand")
+     (match_operand:HI 0 "register_operand")
      (match_operand:V8HI 1 "register_operand"))]
   "TARGET_SSE4_1"
 {

Reply via email to