i386: Add uavg_ceil patterns for 4-byte vectors [PR100637]

2021-05-27  Uroš Bizjak  <ubizjak@gmail.com>

gcc/
	PR target/100637
	* config/i386/mmx.md (uavgv4qi3_ceil): New insn pattern.
	(uavgv2hi3_ceil): Ditto.

gcc/testsuite/

	PR target/100637
	* gcc.target/i386/pr100637-3b.c (avgu): New test.
	* gcc.target/i386/pr100637-3w.c (avgu): Ditto.

diff --git a/gcc/config/i386/mmx.md b/gcc/config/i386/mmx.md
index 453e8ea406dccc767c0d4a358fe5057c5d46ab79..23d88a4c2656dfb25bd1aa80b091a19e64cac6f9 100644 (file)
--- a/gcc/config/i386/mmx.md
+++ b/gcc/config/i386/mmx.md
@@ -3270,6 +3270,47 @@
   ix86_fixup_binary_operands_no_copy (PLUS, <MODE>mode, operands);
 })
 
+(define_insn "uavgv4qi3_ceil"
+  [(set (match_operand:V4QI 0 "register_operand" "=x,Yw")
+       (truncate:V4QI
+         (lshiftrt:V4HI
+           (plus:V4HI
+             (plus:V4HI
+               (zero_extend:V4HI
+                 (match_operand:V4QI 1 "register_operand" "%0,Yw"))
+               (zero_extend:V4HI
+                 (match_operand:V4QI 2 "register_operand" "x,Yw")))
+             (const_vector:V4HI [(const_int 1) (const_int 1)
+                                 (const_int 1) (const_int 1)]))
+           (const_int 1))))]
+  "TARGET_SSE2"
+  "@
+   pavgb\t{%2, %0|%0, %2}
+   vpavgb\t{%2, %1, %0|%0, %1, %2}"
+  [(set_attr "isa" "noavx,avx")
+   (set_attr "type" "sseiadd")
+   (set_attr "mode" "TI")])
+
+(define_insn "uavgv2hi3_ceil"
+  [(set (match_operand:V2HI 0 "register_operand" "=x,Yw")
+       (truncate:V2HI
+         (lshiftrt:V2SI
+           (plus:V2SI
+             (plus:V2SI
+               (zero_extend:V2SI
+                 (match_operand:V2HI 1 "register_operand" "%0,Yw"))
+               (zero_extend:V2SI
+                 (match_operand:V2HI 2 "register_operand" "x,Yw")))
+             (const_vector:V2SI [(const_int 1) (const_int 1)]))
+           (const_int 1))))]
+  "TARGET_SSE2"
+  "@
+   pavgw\t{%2, %0|%0, %2}
+   vpavgw\t{%2, %1, %0|%0, %1, %2}"
+  [(set_attr "isa" "noavx,avx")
+   (set_attr "type" "sseiadd")
+   (set_attr "mode" "TI")])
+
 (define_insn "mmx_psadbw"
   [(set (match_operand:V1DI 0 "register_operand" "=y,x,Yw")
         (unspec:V1DI [(match_operand:V8QI 1 "register_operand" "0,0,Yw")

diff --git a/gcc/testsuite/gcc.target/i386/pr100637-3b.c b/gcc/testsuite/gcc.target/i386/pr100637-3b.c
index 16df70059a94432baa5266a589440526de8b10fa..b17f8b8c19bc4eac08791ee3640d909b86efbee4 100644 (file)
--- a/gcc/testsuite/gcc.target/i386/pr100637-3b.c
+++ b/gcc/testsuite/gcc.target/i386/pr100637-3b.c
@@ -54,3 +54,13 @@ void _abs (void)
 }
 
 /* { dg-final { scan-assembler "pabsb" } } */
+
+void avgu (void)
+{
+  int i;
+
+  for (i = 0; i < 4; i++)
+    ur[i] = (ua[i] + ub[i] + 1) >> 1;
+}
+
+/* { dg-final { scan-assembler "pavgb" } } */

diff --git a/gcc/testsuite/gcc.target/i386/pr100637-3w.c b/gcc/testsuite/gcc.target/i386/pr100637-3w.c
index 7f1882e7a562b2132f54112beef942421504457a..b951f30f5713908fdc95f0857646bfae0a429509 100644 (file)
--- a/gcc/testsuite/gcc.target/i386/pr100637-3w.c
+++ b/gcc/testsuite/gcc.target/i386/pr100637-3w.c
@@ -84,3 +84,13 @@ void _abs (void)
 }
 
 /* { dg-final { scan-assembler "pabsw" } } */
+
+void avgu (void)
+{
+  int i;
+
+  for (i = 0; i < 2; i++)
+    ur[i] = (ua[i] + ub[i] + 1) >> 1;
+}
+
+/* { dg-final { scan-assembler "pavgw" } } */