Optimize vlddqu + inserti128 to vbroadcasti128

vlddqu + vinserti128 will use shuffle port in addition to load port
comparing to vbroadcasti128, For latency perspective,vbroadcasti is no
worse than vlddqu + vinserti128.

gcc/ChangeLog:

	* config/i386/sse.md (*avx2_lddqu_inserti_to_bcasti): New
	pre_reload define_insn_and_split.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/vlddqu_vinserti128.c: New test.

diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index 51961bbfc0b535b80e772bcd2ded9578862e39fd..8dea05703569f893d955ac9c2799e7eb3d405cc2 100644 (file)
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -26609,6 +26609,24 @@
    (set_attr "prefix" "vex,evex,evex")
    (set_attr "mode" "OI")])
 
+;; optimize vlddqu + vinserti128 to vbroadcasti128, the former will use
+;; extra shuffle port in addition to load port than the latter.
+;; For latency perspective,vbroadcasti is no worse.
+(define_insn_and_split "avx2_lddqu_inserti_to_bcasti"
+  [(set (match_operand:V4DI 0 "register_operand" "=x,v,v")
+       (vec_concat:V4DI
+         (subreg:V2DI
+           (unspec:V16QI [(match_operand:V16QI 1 "memory_operand")]
+                         UNSPEC_LDDQU) 0)
+         (subreg:V2DI (unspec:V16QI [(match_dup 1)]
+                         UNSPEC_LDDQU) 0)))]
+  "TARGET_AVX2 && ix86_pre_reload_split ()"
+  "#"
+  "&& 1"
+  [(set (match_dup 0)
+       (vec_concat:V4DI (match_dup 1) (match_dup 1)))]
+  "operands[1] = adjust_address_nv (operands[1], V2DImode, 0);")
+
 ;; Modes handled by AVX vec_dup patterns.
 (define_mode_iterator AVX_VEC_DUP_MODE
   [V8SI V8SF V4DI V4DF])

diff --git a/gcc/testsuite/gcc.target/i386/vlddqu_vinserti128.c b/gcc/testsuite/gcc.target/i386/vlddqu_vinserti128.c
new file mode 100644 (file)
index 0000000..29699a5
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/vlddqu_vinserti128.c
@@ -0,0 +1,11 @@
+/* { dg-do compile } */
+/* { dg-options "-mavx2 -O2" } */
+/* { dg-final { scan-assembler-times "vbroadcasti128" 1 } } */
+/* { dg-final { scan-assembler-not {(?n)vlddqu.*xmm} } } */
+
+#include <immintrin.h>
+__m256i foo(void *data) {
+    __m128i X1 = _mm_lddqu_si128((__m128i*)data);
+    __m256i V1 = _mm256_broadcastsi128_si256 (X1);
+    return V1;
+}