Support reduc_{and,ior,xor}_scal_m for V4HI/V8QI/V4QImode

gcc/ChangeLog:

	PR target/112325
	* config/i386/i386-expand.cc (emit_reduc_half): Hanlde
	V8QImode.
	* config/i386/mmx.md (reduc_<code>_scal_<mode>): New expander.
	(reduc_<code>_scal_v4qi): Ditto.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/pr112325-mmx-1.c: New test.

3 files changed, 70 insertions, 2 deletions

diff --git a/gcc/config/i386/i386-expand.cc b/gcc/config/i386/i386-expand.cc
index a8d871d..fe56d2f 100644
--- a/gcc/config/i386/i386-expand.cc
+++ b/gcc/config/i386/i386-expand.cc
@@ -17748,6 +17748,7 @@ emit_reduc_half (rtx dest, rtx src, int i)
       tem = gen_mmx_lshrv1si3 (d, gen_lowpart (V1SImode, src),
 			       GEN_INT (i / 2));
       break;
+    case E_V8QImode:
     case E_V4HImode:
       d = gen_reg_rtx (V1DImode);
       tem = gen_mmx_lshrv1di3 (d, gen_lowpart (V1DImode, src),
diff --git a/gcc/config/i386/mmx.md b/gcc/config/i386/mmx.md
index 0f16d2a..a07a921 100644
--- a/gcc/config/i386/mmx.md
+++ b/gcc/config/i386/mmx.md
@@ -120,13 +120,15 @@
   [(V2SI "SI") (V2SF "SF")
    (V4HF "HF") (V4BF "BF")
    (V2HF "HF") (V2BF "BF")
-   (V4HI "HI") (V2HI "HI")])
+   (V4HI "HI") (V2HI "HI")
+   (V8QI "QI")])
 
 (define_mode_attr mmxscalarmodelower
   [(V2SI "si") (V2SF "sf")
    (V4HF "hf") (V4BF "bf")
    (V2HF "hf") (V2BF "bf")
-   (V4HI "hi") (V2HI "hi")])
+   (V4HI "hi") (V2HI "hi")
+   (V8QI "qi")])
 
 (define_mode_attr Yv_Yw
   [(V8QI "Yw") (V4HI "Yw") (V2SI "Yv") (V1DI "Yv") (V2SF "Yv")])
@@ -6094,6 +6096,31 @@
    (set_attr "type" "mmxshft,sseiadd,sseiadd")
    (set_attr "mode" "DI,TI,TI")])
 
+(define_expand "reduc_<code>_scal_<mode>"
+ [(any_logic:MMXMODE12
+    (match_operand:<mmxscalarmode> 0 "register_operand")
+    (match_operand:MMXMODE12 1 "register_operand"))]
+ "TARGET_MMX_WITH_SSE"
+{
+  rtx tmp = gen_reg_rtx (<MODE>mode);
+  ix86_expand_reduc (gen_<code><mode>3, tmp, operands[1]);
+  emit_insn (gen_vec_extract<mode><mmxscalarmodelower> (operands[0],
+						       tmp, const0_rtx));
+  DONE;
+})
+
+(define_expand "reduc_<code>_scal_v4qi"
+ [(any_logic:V4QI
+    (match_operand:QI 0 "register_operand")
+    (match_operand:V4QI 1 "register_operand"))]
+ "TARGET_SSE2"
+{
+  rtx tmp = gen_reg_rtx (V4QImode);
+  ix86_expand_reduc (gen_<code>v4qi3, tmp, operands[1]);
+  emit_insn (gen_vec_extractv4qiqi (operands[0], tmp, const0_rtx));
+  DONE;
+})
+
 (define_expand "reduc_plus_scal_v8qi"
  [(plus:V8QI
     (match_operand:QI 0 "register_operand")
diff --git a/gcc/testsuite/gcc.target/i386/pr112325-mmx-1.c b/gcc/testsuite/gcc.target/i386/pr112325-mmx-1.c
new file mode 100644
index 0000000..887249f
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr112325-mmx-1.c
@@ -0,0 +1,40 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-msse2 -O2 -fdump-tree-slp2" } */
+/* { dg-final { scan-tree-dump-times ".REDUC_IOR" 3 "slp2" } } */
+
+short
+foo1 (short* a)
+{
+  short sum = 0;
+  sum |= a[0];
+  sum |= a[1];
+  sum |= a[2];
+  sum |= a[3];
+  return sum;
+}
+
+char
+foo2 (char* a)
+{
+  char sum = 0;
+  sum |= a[0];
+  sum |= a[1];
+  sum |= a[2];
+  sum |= a[3];
+  sum |= a[4];
+  sum |= a[5];
+  sum |= a[6];
+  sum |= a[7];
+  return sum;
+}
+
+char
+foo3 (char* a)
+{
+  char sum = 0;
+  sum |= a[0];
+  sum |= a[1];
+  sum |= a[2];
+  sum |= a[3];
+  return sum;
+}