[X86] Don't generate vbroadcasti128 for v4i64 splats from memory.

We used to erroneously match:
    (v4i64 shuffle (v2i64 load), <0,0,0,0>)

Whereas vbroadcasti128 is more like:
    (v4i64 shuffle (v2i64 load), <0,1,0,1>)

This problem doesn't exist for vbroadcastf128, which kept matching
the intrinsic after r231182.  We should perhaps re-introduce the
intrinsic here as well, but that's a separate issue still being
discussed.

While there, add some proper vbroadcastf128 tests.  We don't currently
match those, like for loading vbroadcastsd/ss on AVX (the reg-reg
broadcasts where added in AVX2).

Fixes PR23886.

llvm-svn: 240488

2 files changed, 59 insertions, 4 deletions

diff --git a/llvm/lib/Target/X86/X86InstrSSE.td b/llvm/lib/Target/X86/X86InstrSSE.td
index 95629184f2c..2a896dfe8aa 100644
--- a/llvm/lib/Target/X86/X86InstrSSE.td
+++ b/llvm/lib/Target/X86/X86InstrSSE.td
@@ -7860,10 +7860,11 @@ def VBROADCASTSDYrr  : avx2_broadcast_reg<0x19, "vbroadcastsd", VR256,
                                       int_x86_avx2_vbroadcast_sd_pd_256,
                                       WriteFShuffle256>, VEX_L;
 
-let Predicates = [HasAVX2] in
-def VBROADCASTI128 : avx_broadcast_no_int<0x5A, "vbroadcasti128", VR256,
-                                          i128mem, v4i64, loadv2i64,
-                                          WriteLoad>, VEX_L;
+let mayLoad = 1, Predicates = [HasAVX2] in
+def VBROADCASTI128 : AVX8I<0x5A, MRMSrcMem, (outs VR256:$dst),
+                           (ins i128mem:$src),
+                           "vbroadcasti128\t{$src, $dst|$dst, $src}", []>,
+                           Sched<[WriteLoad]>, VEX, VEX_L;
 
 let Predicates = [HasAVX] in
 def : Pat<(int_x86_avx_vbroadcastf128_ps_256 addr:$src),
diff --git a/llvm/test/CodeGen/X86/vector-shuffle-256-v4.ll b/llvm/test/CodeGen/X86/vector-shuffle-256-v4.ll
index f5cc989de34..62bf288a870 100644
--- a/llvm/test/CodeGen/X86/vector-shuffle-256-v4.ll
+++ b/llvm/test/CodeGen/X86/vector-shuffle-256-v4.ll
@@ -900,6 +900,60 @@ define <4 x double> @splat_v4f64(<2 x double> %r) {
   ret <4 x double> %1
 }
 
+define <4 x i64> @splat_mem_v4i64_from_v2i64(<2 x i64>* %ptr) {
+; AVX1-LABEL: splat_mem_v4i64_from_v2i64:
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vmovddup {{.*#+}} xmm0 = mem[0,0]
+; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: splat_mem_v4i64_from_v2i64:
+; AVX2:       # BB#0:
+; AVX2-NEXT:    vbroadcastsd (%rdi), %ymm0
+; AVX2-NEXT:    retq
+  %v = load <2 x i64>, <2 x i64>* %ptr
+  %shuffle = shufflevector <2 x i64> %v, <2 x i64> undef, <4 x i32> <i32 0, i32 0, i32 0, i32 0>
+  ret <4 x i64> %shuffle
+}
+
+define <4 x double> @splat_mem_v4f64_from_v2f64(<2 x double>* %ptr) {
+; AVX1-LABEL: splat_mem_v4f64_from_v2f64:
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vmovddup {{.*#+}} xmm0 = mem[0,0]
+; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: splat_mem_v4f64_from_v2f64:
+; AVX2:       # BB#0:
+; AVX2-NEXT:    vbroadcastsd (%rdi), %ymm0
+; AVX2-NEXT:    retq
+  %v = load <2 x double>, <2 x double>* %ptr
+  %shuffle = shufflevector <2 x double> %v, <2 x double> undef, <4 x i32> <i32 0, i32 0, i32 0, i32 0>
+  ret <4 x double> %shuffle
+}
+
+define <4 x i64> @splat128_mem_v4i64_from_v2i64(<2 x i64>* %ptr) {
+; ALL-LABEL: splat128_mem_v4i64_from_v2i64:
+; ALL:       # BB#0:
+; ALL-NEXT:    vmovaps (%rdi), %xmm0
+; ALL-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; ALL-NEXT:    retq
+  %v = load <2 x i64>, <2 x i64>* %ptr
+  %shuffle = shufflevector <2 x i64> %v, <2 x i64> undef, <4 x i32> <i32 0, i32 1, i32 0, i32 1>
+  ret <4 x i64> %shuffle
+}
+
+define <4 x double> @splat128_mem_v4f64_from_v2f64(<2 x double>* %ptr) {
+; ALL-LABEL: splat128_mem_v4f64_from_v2f64:
+; ALL:       # BB#0:
+; ALL-NEXT:    vmovaps (%rdi), %xmm0
+; ALL-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; ALL-NEXT:    retq
+  %v = load <2 x double>, <2 x double>* %ptr
+  %shuffle = shufflevector <2 x double> %v, <2 x double> undef, <4 x i32> <i32 0, i32 1, i32 0, i32 1>
+  ret <4 x double> %shuffle
+}
+
 define <4 x double> @bitcast_v4f64_0426(<4 x double> %a, <4 x double> %b) {
 ; AVX1-LABEL: bitcast_v4f64_0426:
 ; AVX1:       # BB#0: