X86 CodeGen: Optimized pattern for truncate with unsigned saturation.

DAG patterns optimization: truncate + unsigned saturation supported by VPMOVUS* instructions in AVX-512.
And VPACKUS* instructions on SEE* targets.

Differential Revision: https://reviews.llvm.org/D28216

llvm-svn: 291670

2 files changed, 231 insertions, 0 deletions

diff --git a/llvm/test/CodeGen/X86/avx-trunc.ll b/llvm/test/CodeGen/X86/avx-trunc.ll
index 789ca241394..c729b988cfb 100644
--- a/llvm/test/CodeGen/X86/avx-trunc.ll
+++ b/llvm/test/CodeGen/X86/avx-trunc.ll
@@ -39,3 +39,29 @@ define <16 x i8> @trunc_16_8(<16 x i16> %A) nounwind uwtable readnone ssp{
   %B = trunc <16 x i16> %A to <16 x i8>
   ret <16 x i8> %B
 }
+
+define <16 x i8> @usat_trunc_wb_256(<16 x i16> %i) {
+; CHECK-LABEL: usat_trunc_wb_256:
+; CHECK:       # BB#0:
+; CHECK-NEXT:    vextractf128 $1, %ymm0, %xmm1
+; CHECK-NEXT:    vpackuswb %xmm1, %xmm0, %xmm0
+; CHECK-NEXT:    vzeroupper
+; CHECK-NEXT:    retq
+  %x3 = icmp ult <16 x i16> %i, <i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255>
+  %x5 = select <16 x i1> %x3, <16 x i16> %i, <16 x i16> <i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255>
+  %x6 = trunc <16 x i16> %x5 to <16 x i8>
+  ret <16 x i8> %x6
+}
+
+define <8 x i16> @usat_trunc_dw_256(<8 x i32> %i) {
+; CHECK-LABEL: usat_trunc_dw_256:
+; CHECK:       # BB#0:
+; CHECK-NEXT:    vextractf128 $1, %ymm0, %xmm1
+; CHECK-NEXT:    vpackusdw %xmm1, %xmm0, %xmm0
+; CHECK-NEXT:    vzeroupper
+; CHECK-NEXT:    retq
+  %x3 = icmp ult <8 x i32> %i, <i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535>
+  %x5 = select <8 x i1> %x3, <8 x i32> %i, <8 x i32> <i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535>
+  %x6 = trunc <8 x i32> %x5 to <8 x i16>
+  ret <8 x i16> %x6
+}
diff --git a/llvm/test/CodeGen/X86/avx512-trunc.ll b/llvm/test/CodeGen/X86/avx512-trunc.ll
index 646697b82c2..fb6c55b26e7 100644
--- a/llvm/test/CodeGen/X86/avx512-trunc.ll
+++ b/llvm/test/CodeGen/X86/avx512-trunc.ll
@@ -500,3 +500,208 @@ define void @trunc_wb_128_mem(<8 x i16> %i, <8 x i8>* %res) #0 {
     store <8 x i8> %x, <8 x i8>* %res
     ret void
 }
+
+
+define void @usat_trunc_wb_256_mem(<16 x i16> %i, <16 x i8>* %res) {
+; KNL-LABEL: usat_trunc_wb_256_mem:
+; KNL:       ## BB#0:
+; KNL-NEXT:    vextracti128 $1, %ymm0, %xmm1
+; KNL-NEXT:    vpackuswb %xmm1, %xmm0, %xmm0
+; KNL-NEXT:    vmovdqu %xmm0, (%rdi)
+; KNL-NEXT:    retq
+;
+; SKX-LABEL: usat_trunc_wb_256_mem:
+; SKX:       ## BB#0:
+; SKX-NEXT:    vpmovuswb %ymm0, (%rdi)
+; SKX-NEXT:    retq
+  %x3 = icmp ult <16 x i16> %i, <i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255>
+  %x5 = select <16 x i1> %x3, <16 x i16> %i, <16 x i16> <i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255>
+  %x6 = trunc <16 x i16> %x5 to <16 x i8>
+  store <16 x i8> %x6, <16 x i8>* %res, align 1
+  ret void
+}
+
+define <16 x i8> @usat_trunc_wb_256(<16 x i16> %i) {
+; KNL-LABEL: usat_trunc_wb_256:
+; KNL:       ## BB#0:
+; KNL-NEXT:    vextracti128 $1, %ymm0, %xmm1
+; KNL-NEXT:    vpackuswb %xmm1, %xmm0, %xmm0
+; KNL-NEXT:    retq
+;
+; SKX-LABEL: usat_trunc_wb_256:
+; SKX:       ## BB#0:
+; SKX-NEXT:    vpmovuswb %ymm0, %xmm0
+; SKX-NEXT:    retq
+  %x3 = icmp ult <16 x i16> %i, <i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255>
+  %x5 = select <16 x i1> %x3, <16 x i16> %i, <16 x i16> <i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255>
+  %x6 = trunc <16 x i16> %x5 to <16 x i8>
+  ret <16 x i8> %x6
+}
+
+define void @usat_trunc_wb_128_mem(<8 x i16> %i, <8 x i8>* %res) {
+; KNL-LABEL: usat_trunc_wb_128_mem:
+; KNL:       ## BB#0:
+; KNL-NEXT:    vpminuw {{.*}}(%rip), %xmm0, %xmm0
+; KNL-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
+; KNL-NEXT:    vmovq %xmm0, (%rdi)
+; KNL-NEXT:    retq
+;
+; SKX-LABEL: usat_trunc_wb_128_mem:
+; SKX:       ## BB#0:
+; SKX-NEXT:    vpmovuswb %xmm0, (%rdi)
+; SKX-NEXT:    retq
+  %x3 = icmp ult <8 x i16> %i, <i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255>
+  %x5 = select <8 x i1> %x3, <8 x i16> %i, <8 x i16> <i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255>
+  %x6 = trunc <8 x i16> %x5 to <8 x i8>
+  store <8 x i8> %x6, <8 x i8>* %res, align 1
+  ret void
+}
+
+define void @usat_trunc_db_512_mem(<16 x i32> %i, <16 x i8>* %res) {
+; ALL-LABEL: usat_trunc_db_512_mem:
+; ALL:       ## BB#0:
+; ALL-NEXT:    vpmovusdb %zmm0, (%rdi)
+; ALL-NEXT:    retq
+  %x3 = icmp ult <16 x i32> %i, <i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255>
+  %x5 = select <16 x i1> %x3, <16 x i32> %i, <16 x i32> <i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255>
+  %x6 = trunc <16 x i32> %x5 to <16 x i8>
+  store <16 x i8> %x6, <16 x i8>* %res, align 1
+  ret void
+}
+
+define void @usat_trunc_qb_512_mem(<8 x i64> %i, <8 x i8>* %res) {
+; ALL-LABEL: usat_trunc_qb_512_mem:
+; ALL:       ## BB#0:
+; ALL-NEXT:    vpmovusqb %zmm0, (%rdi)
+; ALL-NEXT:    retq
+  %x3 = icmp ult <8 x i64> %i, <i64 255, i64 255, i64 255, i64 255, i64 255, i64 255, i64 255, i64 255>
+  %x5 = select <8 x i1> %x3, <8 x i64> %i, <8 x i64> <i64 255, i64 255, i64 255, i64 255, i64 255, i64 255, i64 255, i64 255>
+  %x6 = trunc <8 x i64> %x5 to <8 x i8>
+  store <8 x i8> %x6, <8 x i8>* %res, align 1
+  ret void
+}
+
+define void @usat_trunc_qd_512_mem(<8 x i64> %i, <8 x i32>* %res) {
+; ALL-LABEL: usat_trunc_qd_512_mem:
+; ALL:       ## BB#0:
+; ALL-NEXT:    vpmovusqd %zmm0, (%rdi)
+; ALL-NEXT:    retq
+  %x3 = icmp ult <8 x i64> %i, <i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295>
+  %x5 = select <8 x i1> %x3, <8 x i64> %i, <8 x i64> <i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295>
+  %x6 = trunc <8 x i64> %x5 to <8 x i32>
+  store <8 x i32> %x6, <8 x i32>* %res, align 1
+  ret void
+}
+
+define void @usat_trunc_qw_512_mem(<8 x i64> %i, <8 x i16>* %res) {
+; ALL-LABEL: usat_trunc_qw_512_mem:
+; ALL:       ## BB#0:
+; ALL-NEXT:    vpmovusqw %zmm0, (%rdi)
+; ALL-NEXT:    retq
+  %x3 = icmp ult <8 x i64> %i, <i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535>
+  %x5 = select <8 x i1> %x3, <8 x i64> %i, <8 x i64> <i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535>
+  %x6 = trunc <8 x i64> %x5 to <8 x i16>
+  store <8 x i16> %x6, <8 x i16>* %res, align 1
+  ret void
+}
+
+define <32 x i8> @usat_trunc_db_1024(<32 x i32> %i) {
+; KNL-LABEL: usat_trunc_db_1024:
+; KNL:       ## BB#0:
+; KNL-NEXT:    vpmovusdb %zmm0, %xmm0
+; KNL-NEXT:    vpmovusdb %zmm1, %xmm1
+; KNL-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
+; KNL-NEXT:    retq
+;
+; SKX-LABEL: usat_trunc_db_1024:
+; SKX:       ## BB#0:
+; SKX-NEXT:    vpbroadcastd {{.*}}(%rip), %zmm2
+; SKX-NEXT:    vpminud %zmm2, %zmm1, %zmm1
+; SKX-NEXT:    vpminud %zmm2, %zmm0, %zmm0
+; SKX-NEXT:    vpmovdw %zmm0, %ymm0
+; SKX-NEXT:    vpmovdw %zmm1, %ymm1
+; SKX-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
+; SKX-NEXT:    vpmovwb %zmm0, %ymm0
+; SKX-NEXT:    retq
+  %x3 = icmp ult <32 x i32> %i, <i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255>
+  %x5 = select <32 x i1> %x3, <32 x i32> %i, <32 x i32> <i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255>
+  %x6 = trunc <32 x i32> %x5 to <32 x i8>
+  ret <32 x i8> %x6
+}
+
+define void @usat_trunc_db_1024_mem(<32 x i32> %i, <32 x i8>* %p) {
+; KNL-LABEL: usat_trunc_db_1024_mem:
+; KNL:       ## BB#0:
+; KNL-NEXT:    vpmovusdb %zmm0, %xmm0
+; KNL-NEXT:    vpmovusdb %zmm1, %xmm1
+; KNL-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
+; KNL-NEXT:    vmovdqu %ymm0, (%rdi)
+; KNL-NEXT:    retq
+;
+; SKX-LABEL: usat_trunc_db_1024_mem:
+; SKX:       ## BB#0:
+; SKX-NEXT:    vpbroadcastd {{.*}}(%rip), %zmm2
+; SKX-NEXT:    vpminud %zmm2, %zmm1, %zmm1
+; SKX-NEXT:    vpminud %zmm2, %zmm0, %zmm0
+; SKX-NEXT:    vpmovdw %zmm0, %ymm0
+; SKX-NEXT:    vpmovdw %zmm1, %ymm1
+; SKX-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
+; SKX-NEXT:    vpmovwb %zmm0, (%rdi)
+; SKX-NEXT:    retq
+  %x3 = icmp ult <32 x i32> %i, <i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255>
+  %x5 = select <32 x i1> %x3, <32 x i32> %i, <32 x i32> <i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255>
+  %x6 = trunc <32 x i32> %x5 to <32 x i8>
+  store <32 x i8>%x6, <32 x i8>* %p, align 1
+  ret void
+}
+
+define <16 x i16> @usat_trunc_dw_512(<16 x i32> %i) {
+; ALL-LABEL: usat_trunc_dw_512:
+; ALL:       ## BB#0:
+; ALL-NEXT:    vpmovusdw %zmm0, %ymm0
+; ALL-NEXT:    retq
+  %x3 = icmp ult <16 x i32> %i, <i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535>
+  %x5 = select <16 x i1> %x3, <16 x i32> %i, <16 x i32> <i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535>
+  %x6 = trunc <16 x i32> %x5 to <16 x i16>
+  ret <16 x i16> %x6
+}
+
+define <8 x i8> @usat_trunc_wb_128(<8 x i16> %i) {
+; ALL-LABEL: usat_trunc_wb_128:
+; ALL:       ## BB#0:
+; ALL-NEXT:    vpminuw {{.*}}(%rip), %xmm0, %xmm0
+; ALL-NEXT:    retq
+  %x3 = icmp ult <8 x i16> %i, <i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255>
+  %x5 = select <8 x i1> %x3, <8 x i16> %i, <8 x i16> <i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255>
+  %x6 = trunc <8 x i16> %x5 to <8 x i8>
+  ret <8 x i8>%x6
+}
+
+define <16 x i16> @usat_trunc_qw_1024(<16 x i64> %i) {
+; KNL-LABEL: usat_trunc_qw_1024:
+; KNL:       ## BB#0:
+; KNL-NEXT:    vpbroadcastq {{.*}}(%rip), %zmm2
+; KNL-NEXT:    vpminuq %zmm2, %zmm1, %zmm1
+; KNL-NEXT:    vpminuq %zmm2, %zmm0, %zmm0
+; KNL-NEXT:    vpmovqd %zmm0, %ymm0
+; KNL-NEXT:    vpmovqd %zmm1, %ymm1
+; KNL-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
+; KNL-NEXT:    vpmovdw %zmm0, %ymm0
+; KNL-NEXT:    retq
+;
+; SKX-LABEL: usat_trunc_qw_1024:
+; SKX:       ## BB#0:
+; SKX-NEXT:    vpbroadcastq {{.*}}(%rip), %zmm2
+; SKX-NEXT:    vpminuq %zmm2, %zmm1, %zmm1
+; SKX-NEXT:    vpminuq %zmm2, %zmm0, %zmm0
+; SKX-NEXT:    vpmovqd %zmm0, %ymm0
+; SKX-NEXT:    vpmovqd %zmm1, %ymm1
+; SKX-NEXT:    vinserti32x8 $1, %ymm1, %zmm0, %zmm0
+; SKX-NEXT:    vpmovdw %zmm0, %ymm0
+; SKX-NEXT:    retq
+  %x3 = icmp ult <16 x i64> %i, <i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535>
+  %x5 = select <16 x i1> %x3, <16 x i64> %i, <16 x i64> <i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535>
+  %x6 = trunc <16 x i64> %x5 to <16 x i16>
+  ret <16 x i16> %x6
+}
+