[X86] Turn v16i16->v16i8 truncate+store into a any_extend+truncstore if we avx512f, but not avx512bw.

Ideally we'd be able to represent this truncate as a any_extend to
v16i32 and a truncate, but SelectionDAG doens't know how to not
fold those together.

We have isel patterns to use a vpmovzxwd+vpdmovdb for the truncate,
but we aren't able to simultaneously fold the load and the store
from the isel pattern. By pulling the truncate into the store we
can successfully hide it from the DAG combiner. Then we can isel
pattern match the truncstore and load+any_extend separately.

llvm-svn: 364163

4 files changed, 8 insertions, 12 deletions

diff --git a/llvm/test/CodeGen/X86/shuffle-vs-trunc-512-widen.ll b/llvm/test/CodeGen/X86/shuffle-vs-trunc-512-widen.ll
index 737925eca04..656dcf9b64f 100644
--- a/llvm/test/CodeGen/X86/shuffle-vs-trunc-512-widen.ll
+++ b/llvm/test/CodeGen/X86/shuffle-vs-trunc-512-widen.ll
@@ -88,20 +88,18 @@ define void @shuffle_v64i8_to_v32i8(<64 x i8>* %L, <32 x i8>* %S) nounwind {
 define void @trunc_v32i16_to_v32i8(<64 x i8>* %L, <32 x i8>* %S) nounwind {
 ; AVX512F-LABEL: trunc_v32i16_to_v32i8:
 ; AVX512F:       # %bb.0:
-; AVX512F-NEXT:    vmovdqa (%rdi), %ymm0
+; AVX512F-NEXT:    vpmovzxwd {{.*#+}} zmm0 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero,mem[8],zero,mem[9],zero,mem[10],zero,mem[11],zero,mem[12],zero,mem[13],zero,mem[14],zero,mem[15],zero
 ; AVX512F-NEXT:    vpmovzxwd {{.*#+}} zmm1 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero,mem[8],zero,mem[9],zero,mem[10],zero,mem[11],zero,mem[12],zero,mem[13],zero,mem[14],zero,mem[15],zero
 ; AVX512F-NEXT:    vpmovdb %zmm1, 16(%rsi)
-; AVX512F-NEXT:    vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
 ; AVX512F-NEXT:    vpmovdb %zmm0, (%rsi)
 ; AVX512F-NEXT:    vzeroupper
 ; AVX512F-NEXT:    retq
 ;
 ; AVX512VL-LABEL: trunc_v32i16_to_v32i8:
 ; AVX512VL:       # %bb.0:
-; AVX512VL-NEXT:    vmovdqa (%rdi), %ymm0
+; AVX512VL-NEXT:    vpmovzxwd {{.*#+}} zmm0 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero,mem[8],zero,mem[9],zero,mem[10],zero,mem[11],zero,mem[12],zero,mem[13],zero,mem[14],zero,mem[15],zero
 ; AVX512VL-NEXT:    vpmovzxwd {{.*#+}} zmm1 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero,mem[8],zero,mem[9],zero,mem[10],zero,mem[11],zero,mem[12],zero,mem[13],zero,mem[14],zero,mem[15],zero
 ; AVX512VL-NEXT:    vpmovdb %zmm1, 16(%rsi)
-; AVX512VL-NEXT:    vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
 ; AVX512VL-NEXT:    vpmovdb %zmm0, (%rsi)
 ; AVX512VL-NEXT:    vzeroupper
 ; AVX512VL-NEXT:    retq
diff --git a/llvm/test/CodeGen/X86/shuffle-vs-trunc-512.ll b/llvm/test/CodeGen/X86/shuffle-vs-trunc-512.ll
index 6f94e0c6086..c42f91f50c0 100644
--- a/llvm/test/CodeGen/X86/shuffle-vs-trunc-512.ll
+++ b/llvm/test/CodeGen/X86/shuffle-vs-trunc-512.ll
@@ -88,20 +88,18 @@ define void @shuffle_v64i8_to_v32i8(<64 x i8>* %L, <32 x i8>* %S) nounwind {
 define void @trunc_v32i16_to_v32i8(<64 x i8>* %L, <32 x i8>* %S) nounwind {
 ; AVX512F-LABEL: trunc_v32i16_to_v32i8:
 ; AVX512F:       # %bb.0:
-; AVX512F-NEXT:    vmovdqa (%rdi), %ymm0
+; AVX512F-NEXT:    vpmovzxwd {{.*#+}} zmm0 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero,mem[8],zero,mem[9],zero,mem[10],zero,mem[11],zero,mem[12],zero,mem[13],zero,mem[14],zero,mem[15],zero
 ; AVX512F-NEXT:    vpmovzxwd {{.*#+}} zmm1 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero,mem[8],zero,mem[9],zero,mem[10],zero,mem[11],zero,mem[12],zero,mem[13],zero,mem[14],zero,mem[15],zero
 ; AVX512F-NEXT:    vpmovdb %zmm1, 16(%rsi)
-; AVX512F-NEXT:    vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
 ; AVX512F-NEXT:    vpmovdb %zmm0, (%rsi)
 ; AVX512F-NEXT:    vzeroupper
 ; AVX512F-NEXT:    retq
 ;
 ; AVX512VL-LABEL: trunc_v32i16_to_v32i8:
 ; AVX512VL:       # %bb.0:
-; AVX512VL-NEXT:    vmovdqa (%rdi), %ymm0
+; AVX512VL-NEXT:    vpmovzxwd {{.*#+}} zmm0 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero,mem[8],zero,mem[9],zero,mem[10],zero,mem[11],zero,mem[12],zero,mem[13],zero,mem[14],zero,mem[15],zero
 ; AVX512VL-NEXT:    vpmovzxwd {{.*#+}} zmm1 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero,mem[8],zero,mem[9],zero,mem[10],zero,mem[11],zero,mem[12],zero,mem[13],zero,mem[14],zero,mem[15],zero
 ; AVX512VL-NEXT:    vpmovdb %zmm1, 16(%rsi)
-; AVX512VL-NEXT:    vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
 ; AVX512VL-NEXT:    vpmovdb %zmm0, (%rsi)
 ; AVX512VL-NEXT:    vzeroupper
 ; AVX512VL-NEXT:    retq
diff --git a/llvm/test/CodeGen/X86/vector-trunc-widen.ll b/llvm/test/CodeGen/X86/vector-trunc-widen.ll
index 6a504269b93..23a4a978a2d 100644
--- a/llvm/test/CodeGen/X86/vector-trunc-widen.ll
+++ b/llvm/test/CodeGen/X86/vector-trunc-widen.ll
@@ -1148,7 +1148,7 @@ define void @trunc16i16_16i8_ashr(<16 x i16> %a) {
 ;
 ; AVX512F-LABEL: trunc16i16_16i8_ashr:
 ; AVX512F:       # %bb.0: # %entry
-; AVX512F-NEXT:    vpsraw $8, %ymm0, %ymm0
+; AVX512F-NEXT:    vpsrlw $8, %ymm0, %ymm0
 ; AVX512F-NEXT:    vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
 ; AVX512F-NEXT:    vpmovdb %zmm0, (%rax)
 ; AVX512F-NEXT:    vzeroupper
@@ -1156,7 +1156,7 @@ define void @trunc16i16_16i8_ashr(<16 x i16> %a) {
 ;
 ; AVX512VL-LABEL: trunc16i16_16i8_ashr:
 ; AVX512VL:       # %bb.0: # %entry
-; AVX512VL-NEXT:    vpsraw $8, %ymm0, %ymm0
+; AVX512VL-NEXT:    vpsrlw $8, %ymm0, %ymm0
 ; AVX512VL-NEXT:    vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
 ; AVX512VL-NEXT:    vpmovdb %zmm0, (%rax)
 ; AVX512VL-NEXT:    vzeroupper
diff --git a/llvm/test/CodeGen/X86/vector-trunc.ll b/llvm/test/CodeGen/X86/vector-trunc.ll
index 0027fbe2657..35b190b1132 100644
--- a/llvm/test/CodeGen/X86/vector-trunc.ll
+++ b/llvm/test/CodeGen/X86/vector-trunc.ll
@@ -1158,7 +1158,7 @@ define void @trunc16i16_16i8_ashr(<16 x i16> %a) {
 ;
 ; AVX512F-LABEL: trunc16i16_16i8_ashr:
 ; AVX512F:       # %bb.0: # %entry
-; AVX512F-NEXT:    vpsraw $8, %ymm0, %ymm0
+; AVX512F-NEXT:    vpsrlw $8, %ymm0, %ymm0
 ; AVX512F-NEXT:    vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
 ; AVX512F-NEXT:    vpmovdb %zmm0, (%rax)
 ; AVX512F-NEXT:    vzeroupper
@@ -1166,7 +1166,7 @@ define void @trunc16i16_16i8_ashr(<16 x i16> %a) {
 ;
 ; AVX512VL-LABEL: trunc16i16_16i8_ashr:
 ; AVX512VL:       # %bb.0: # %entry
-; AVX512VL-NEXT:    vpsraw $8, %ymm0, %ymm0
+; AVX512VL-NEXT:    vpsrlw $8, %ymm0, %ymm0
 ; AVX512VL-NEXT:    vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
 ; AVX512VL-NEXT:    vpmovdb %zmm0, (%rax)
 ; AVX512VL-NEXT:    vzeroupper