[X86] Improve unsigned saturation downconvert detection.

Summary:
New unsigned saturation downconvert patterns detection was implemented in
X86 Codegen:

(truncate (smin (smax (x, C1), C2)) to dest_type),
where C1 >= 0 and C2 is unsigned max of destination type.

(truncate (smax (smin (x, C2), C1)) to dest_type)
where C1 >= 0, C2 is unsigned max of destination type and C1 <= C2.
These two patterns are equivalent to:

(truncate (umin (smax(x, C1), unsigned_max_of_dest_type)) to dest_type)

Reviewers: RKSimon

Subscribers: llvm-commits, a.elovikov

Differential Revision: https://reviews.llvm.org/D45315

llvm-svn: 332336

2 files changed, 29 insertions, 58 deletions

diff --git a/llvm/test/CodeGen/X86/avx512-trunc.ll b/llvm/test/CodeGen/X86/avx512-trunc.ll
index 8bd29e14809..ca7e22316fb 100644
--- a/llvm/test/CodeGen/X86/avx512-trunc.ll
+++ b/llvm/test/CodeGen/X86/avx512-trunc.ll
@@ -790,8 +790,7 @@ define void @smax_usat_trunc_wb_256_mem1(<16 x i16> %i, <16 x i8>* %res) {
 ; SKX:       ## %bb.0:
 ; SKX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; SKX-NEXT:    vpmaxsw %ymm1, %ymm0, %ymm0
-; SKX-NEXT:    vpminsw {{.*}}(%rip), %ymm0, %ymm0
-; SKX-NEXT:    vpmovwb %ymm0, (%rdi)
+; SKX-NEXT:    vpmovuswb %ymm0, (%rdi)
 ; SKX-NEXT:    vzeroupper
 ; SKX-NEXT:    retq
   %x1 = icmp sgt <16 x i16> %i, <i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0>
@@ -817,10 +816,9 @@ define void @smax_usat_trunc_wb_256_mem2(<16 x i16> %i, <16 x i8>* %res) {
 ;
 ; SKX-LABEL: smax_usat_trunc_wb_256_mem2:
 ; SKX:       ## %bb.0:
-; SKX-NEXT:    vpminsw {{.*}}(%rip), %ymm0, %ymm0
 ; SKX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; SKX-NEXT:    vpmaxsw %ymm1, %ymm0, %ymm0
-; SKX-NEXT:    vpmovwb %ymm0, (%rdi)
+; SKX-NEXT:    vpmovuswb %ymm0, (%rdi)
 ; SKX-NEXT:    vzeroupper
 ; SKX-NEXT:    retq
   %x1 = icmp slt <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>
@@ -847,8 +845,7 @@ define <16 x i8> @smax_usat_trunc_wb_256(<16 x i16> %i) {
 ; SKX:       ## %bb.0:
 ; SKX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; SKX-NEXT:    vpmaxsw %ymm1, %ymm0, %ymm0
-; SKX-NEXT:    vpminsw {{.*}}(%rip), %ymm0, %ymm0
-; SKX-NEXT:    vpmovwb %ymm0, %xmm0
+; SKX-NEXT:    vpmovuswb %ymm0, %xmm0
 ; SKX-NEXT:    vzeroupper
 ; SKX-NEXT:    retq
   %x1 = icmp sgt <16 x i16> %i, <i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0>
@@ -873,8 +870,7 @@ define void @smax_usat_trunc_wb_128_mem(<8 x i16> %i, <8 x i8>* %res) {
 ; SKX:       ## %bb.0:
 ; SKX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; SKX-NEXT:    vpmaxsw %xmm1, %xmm0, %xmm0
-; SKX-NEXT:    vpminsw {{.*}}(%rip), %xmm0, %xmm0
-; SKX-NEXT:    vpmovwb %xmm0, (%rdi)
+; SKX-NEXT:    vpmovuswb %xmm0, (%rdi)
 ; SKX-NEXT:    retq
   %x1 = icmp sgt <8 x i16> %i, <i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0>
   %x2 = select <8 x i1> %x1, <8 x i16> %i, <8 x i16> <i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0>
@@ -890,8 +886,7 @@ define void @smax_usat_trunc_db_512_mem(<16 x i32> %i, <16 x i8>* %res) {
 ; ALL:       ## %bb.0:
 ; ALL-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; ALL-NEXT:    vpmaxsd %zmm1, %zmm0, %zmm0
-; ALL-NEXT:    vpminsd {{.*}}(%rip){1to16}, %zmm0, %zmm0
-; ALL-NEXT:    vpmovdb %zmm0, (%rdi)
+; ALL-NEXT:    vpmovusdb %zmm0, (%rdi)
 ; ALL-NEXT:    vzeroupper
 ; ALL-NEXT:    retq
   %x1 = icmp sgt <16 x i32> %i, <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -908,8 +903,7 @@ define void @smax_usat_trunc_qb_512_mem(<8 x i64> %i, <8 x i8>* %res) {
 ; ALL:       ## %bb.0:
 ; ALL-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; ALL-NEXT:    vpmaxsq %zmm1, %zmm0, %zmm0
-; ALL-NEXT:    vpminsq {{.*}}(%rip){1to8}, %zmm0, %zmm0
-; ALL-NEXT:    vpmovqb %zmm0, (%rdi)
+; ALL-NEXT:    vpmovusqb %zmm0, (%rdi)
 ; ALL-NEXT:    vzeroupper
 ; ALL-NEXT:    retq
   %x1 = icmp sgt <8 x i64> %i, <i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0>
@@ -926,8 +920,7 @@ define void @smax_usat_trunc_qd_512_mem(<8 x i64> %i, <8 x i32>* %res) {
 ; ALL:       ## %bb.0:
 ; ALL-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; ALL-NEXT:    vpmaxsq %zmm1, %zmm0, %zmm0
-; ALL-NEXT:    vpminsq {{.*}}(%rip){1to8}, %zmm0, %zmm0
-; ALL-NEXT:    vpmovqd %zmm0, (%rdi)
+; ALL-NEXT:    vpmovusqd %zmm0, (%rdi)
 ; ALL-NEXT:    vzeroupper
 ; ALL-NEXT:    retq
   %x1 = icmp sgt <8 x i64> %i, <i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0>
@@ -944,8 +937,7 @@ define void @smax_usat_trunc_qw_512_mem(<8 x i64> %i, <8 x i16>* %res) {
 ; ALL:       ## %bb.0:
 ; ALL-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; ALL-NEXT:    vpmaxsq %zmm1, %zmm0, %zmm0
-; ALL-NEXT:    vpminsq {{.*}}(%rip){1to8}, %zmm0, %zmm0
-; ALL-NEXT:    vpmovqw %zmm0, (%rdi)
+; ALL-NEXT:    vpmovusqw %zmm0, (%rdi)
 ; ALL-NEXT:    vzeroupper
 ; ALL-NEXT:    retq
   %x1 = icmp sgt <8 x i64> %i, <i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0>
@@ -961,13 +953,10 @@ define <32 x i8> @smax_usat_trunc_db_1024(<32 x i32> %i) {
 ; KNL-LABEL: smax_usat_trunc_db_1024:
 ; KNL:       ## %bb.0:
 ; KNL-NEXT:    vpxor %xmm2, %xmm2, %xmm2
-; KNL-NEXT:    vpmaxsd %zmm2, %zmm0, %zmm0
 ; KNL-NEXT:    vpmaxsd %zmm2, %zmm1, %zmm1
-; KNL-NEXT:    vpbroadcastd {{.*#+}} zmm2 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
-; KNL-NEXT:    vpminsd %zmm2, %zmm1, %zmm1
-; KNL-NEXT:    vpminsd %zmm2, %zmm0, %zmm0
-; KNL-NEXT:    vpmovdb %zmm0, %xmm0
-; KNL-NEXT:    vpmovdb %zmm1, %xmm1
+; KNL-NEXT:    vpmaxsd %zmm2, %zmm0, %zmm0
+; KNL-NEXT:    vpmovusdb %zmm0, %xmm0
+; KNL-NEXT:    vpmovusdb %zmm1, %xmm1
 ; KNL-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
 ; KNL-NEXT:    retq
 ;
@@ -996,13 +985,10 @@ define void @smax_usat_trunc_db_1024_mem(<32 x i32> %i, <32 x i8>* %p) {
 ; KNL-LABEL: smax_usat_trunc_db_1024_mem:
 ; KNL:       ## %bb.0:
 ; KNL-NEXT:    vpxor %xmm2, %xmm2, %xmm2
-; KNL-NEXT:    vpmaxsd %zmm2, %zmm0, %zmm0
 ; KNL-NEXT:    vpmaxsd %zmm2, %zmm1, %zmm1
-; KNL-NEXT:    vpbroadcastd {{.*#+}} zmm2 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
-; KNL-NEXT:    vpminsd %zmm2, %zmm1, %zmm1
-; KNL-NEXT:    vpminsd %zmm2, %zmm0, %zmm0
-; KNL-NEXT:    vpmovdb %zmm0, %xmm0
-; KNL-NEXT:    vpmovdb %zmm1, %xmm1
+; KNL-NEXT:    vpmaxsd %zmm2, %zmm0, %zmm0
+; KNL-NEXT:    vpmovusdb %zmm0, %xmm0
+; KNL-NEXT:    vpmovusdb %zmm1, %xmm1
 ; KNL-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
 ; KNL-NEXT:    vmovdqu %ymm0, (%rdi)
 ; KNL-NEXT:    vzeroupper
@@ -1036,8 +1022,7 @@ define <16 x i16> @smax_usat_trunc_dw_512(<16 x i32> %i) {
 ; ALL:       ## %bb.0:
 ; ALL-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; ALL-NEXT:    vpmaxsd %zmm1, %zmm0, %zmm0
-; ALL-NEXT:    vpminsd {{.*}}(%rip){1to16}, %zmm0, %zmm0
-; ALL-NEXT:    vpmovdw %zmm0, %ymm0
+; ALL-NEXT:    vpmovusdw %zmm0, %ymm0
 ; ALL-NEXT:    retq
   %x1 = icmp sgt <16 x i32> %i, <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
   %x2 = select <16 x i1> %x1, <16 x i32> %i, <16 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
diff --git a/llvm/test/CodeGen/X86/vector-trunc-packus.ll b/llvm/test/CodeGen/X86/vector-trunc-packus.ll
index f47425b92c4..afd692866db 100644
--- a/llvm/test/CodeGen/X86/vector-trunc-packus.ll
+++ b/llvm/test/CodeGen/X86/vector-trunc-packus.ll
@@ -244,10 +244,9 @@ define <4 x i32> @trunc_packus_v4i64_v4i32(<4 x i64> %a0) {
 ;
 ; AVX512VL-LABEL: trunc_packus_v4i64_v4i32:
 ; AVX512VL:       # %bb.0:
-; AVX512VL-NEXT:    vpminsq {{.*}}(%rip){1to4}, %ymm0, %ymm0
 ; AVX512VL-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX512VL-NEXT:    vpmaxsq %ymm1, %ymm0, %ymm0
-; AVX512VL-NEXT:    vpmovqd %ymm0, %xmm0
+; AVX512VL-NEXT:    vpmovusqd %ymm0, %xmm0
 ; AVX512VL-NEXT:    vzeroupper
 ; AVX512VL-NEXT:    retq
 ;
@@ -265,10 +264,9 @@ define <4 x i32> @trunc_packus_v4i64_v4i32(<4 x i64> %a0) {
 ;
 ; AVX512BWVL-LABEL: trunc_packus_v4i64_v4i32:
 ; AVX512BWVL:       # %bb.0:
-; AVX512BWVL-NEXT:    vpminsq {{.*}}(%rip){1to4}, %ymm0, %ymm0
 ; AVX512BWVL-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX512BWVL-NEXT:    vpmaxsq %ymm1, %ymm0, %ymm0
-; AVX512BWVL-NEXT:    vpmovqd %ymm0, %xmm0
+; AVX512BWVL-NEXT:    vpmovusqd %ymm0, %xmm0
 ; AVX512BWVL-NEXT:    vzeroupper
 ; AVX512BWVL-NEXT:    retq
   %1 = icmp slt <4 x i64> %a0, <i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295>
@@ -665,10 +663,9 @@ define <8 x i32> @trunc_packus_v8i64_v8i32(<8 x i64> %a0) {
 ;
 ; AVX512-LABEL: trunc_packus_v8i64_v8i32:
 ; AVX512:       # %bb.0:
-; AVX512-NEXT:    vpminsq {{.*}}(%rip){1to8}, %zmm0, %zmm0
 ; AVX512-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX512-NEXT:    vpmaxsq %zmm1, %zmm0, %zmm0
-; AVX512-NEXT:    vpmovqd %zmm0, %ymm0
+; AVX512-NEXT:    vpmovusqd %zmm0, %ymm0
 ; AVX512-NEXT:    retq
   %1 = icmp slt <8 x i64> %a0, <i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295>
   %2 = select <8 x i1> %1, <8 x i64> %a0, <8 x i64> <i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295>
@@ -1070,10 +1067,9 @@ define <8 x i16> @trunc_packus_v8i64_v8i16(<8 x i64> %a0) {
 ;
 ; AVX512-LABEL: trunc_packus_v8i64_v8i16:
 ; AVX512:       # %bb.0:
-; AVX512-NEXT:    vpminsq {{.*}}(%rip){1to8}, %zmm0, %zmm0
 ; AVX512-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX512-NEXT:    vpmaxsq %zmm1, %zmm0, %zmm0
-; AVX512-NEXT:    vpmovqw %zmm0, %xmm0
+; AVX512-NEXT:    vpmovusqw %zmm0, %xmm0
 ; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
   %1 = icmp slt <8 x i64> %a0, <i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535>
@@ -1170,10 +1166,9 @@ define <8 x i16> @trunc_packus_v8i32_v8i16(<8 x i32> %a0) {
 ;
 ; AVX512VL-LABEL: trunc_packus_v8i32_v8i16:
 ; AVX512VL:       # %bb.0:
-; AVX512VL-NEXT:    vpminsd {{.*}}(%rip){1to8}, %ymm0, %ymm0
 ; AVX512VL-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX512VL-NEXT:    vpmaxsd %ymm1, %ymm0, %ymm0
-; AVX512VL-NEXT:    vpmovdw %ymm0, %xmm0
+; AVX512VL-NEXT:    vpmovusdw %ymm0, %xmm0
 ; AVX512VL-NEXT:    vzeroupper
 ; AVX512VL-NEXT:    retq
 ;
@@ -1190,10 +1185,9 @@ define <8 x i16> @trunc_packus_v8i32_v8i16(<8 x i32> %a0) {
 ;
 ; AVX512BWVL-LABEL: trunc_packus_v8i32_v8i16:
 ; AVX512BWVL:       # %bb.0:
-; AVX512BWVL-NEXT:    vpminsd {{.*}}(%rip){1to8}, %ymm0, %ymm0
 ; AVX512BWVL-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX512BWVL-NEXT:    vpmaxsd %ymm1, %ymm0, %ymm0
-; AVX512BWVL-NEXT:    vpmovdw %ymm0, %xmm0
+; AVX512BWVL-NEXT:    vpmovusdw %ymm0, %xmm0
 ; AVX512BWVL-NEXT:    vzeroupper
 ; AVX512BWVL-NEXT:    retq
   %1 = icmp slt <8 x i32> %a0, <i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535>
@@ -1325,10 +1319,9 @@ define <16 x i16> @trunc_packus_v16i32_v16i16(<16 x i32> %a0) {
 ;
 ; AVX512-LABEL: trunc_packus_v16i32_v16i16:
 ; AVX512:       # %bb.0:
-; AVX512-NEXT:    vpminsd {{.*}}(%rip){1to16}, %zmm0, %zmm0
 ; AVX512-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX512-NEXT:    vpmaxsd %zmm1, %zmm0, %zmm0
-; AVX512-NEXT:    vpmovdw %zmm0, %ymm0
+; AVX512-NEXT:    vpmovusdw %zmm0, %ymm0
 ; AVX512-NEXT:    retq
   %1 = icmp slt <16 x i32> %a0, <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>
   %2 = select <16 x i1> %1, <16 x i32> %a0, <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>
@@ -2130,10 +2123,9 @@ define void @trunc_packus_v8i64_v8i8_store(<8 x i64> %a0, <8 x i8> *%p1) {
 ;
 ; AVX512-LABEL: trunc_packus_v8i64_v8i8_store:
 ; AVX512:       # %bb.0:
-; AVX512-NEXT:    vpminsq {{.*}}(%rip){1to8}, %zmm0, %zmm0
 ; AVX512-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX512-NEXT:    vpmaxsq %zmm1, %zmm0, %zmm0
-; AVX512-NEXT:    vpmovqb %zmm0, (%rdi)
+; AVX512-NEXT:    vpmovusqb %zmm0, (%rdi)
 ; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
   %1 = icmp slt <8 x i64> %a0, <i64 255, i64 255, i64 255, i64 255, i64 255, i64 255, i64 255, i64 255>
@@ -3042,10 +3034,9 @@ define void @trunc_packus_v8i32_v8i8_store(<8 x i32> %a0, <8 x i8> *%p1) {
 ;
 ; AVX512VL-LABEL: trunc_packus_v8i32_v8i8_store:
 ; AVX512VL:       # %bb.0:
-; AVX512VL-NEXT:    vpminsd {{.*}}(%rip){1to8}, %ymm0, %ymm0
 ; AVX512VL-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX512VL-NEXT:    vpmaxsd %ymm1, %ymm0, %ymm0
-; AVX512VL-NEXT:    vpmovdb %ymm0, (%rdi)
+; AVX512VL-NEXT:    vpmovusdb %ymm0, (%rdi)
 ; AVX512VL-NEXT:    vzeroupper
 ; AVX512VL-NEXT:    retq
 ;
@@ -3063,10 +3054,9 @@ define void @trunc_packus_v8i32_v8i8_store(<8 x i32> %a0, <8 x i8> *%p1) {
 ;
 ; AVX512BWVL-LABEL: trunc_packus_v8i32_v8i8_store:
 ; AVX512BWVL:       # %bb.0:
-; AVX512BWVL-NEXT:    vpminsd {{.*}}(%rip){1to8}, %ymm0, %ymm0
 ; AVX512BWVL-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX512BWVL-NEXT:    vpmaxsd %ymm1, %ymm0, %ymm0
-; AVX512BWVL-NEXT:    vpmovdb %ymm0, (%rdi)
+; AVX512BWVL-NEXT:    vpmovusdb %ymm0, (%rdi)
 ; AVX512BWVL-NEXT:    vzeroupper
 ; AVX512BWVL-NEXT:    retq
   %1 = icmp slt <8 x i32> %a0, <i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255>
@@ -3107,10 +3097,9 @@ define <16 x i8> @trunc_packus_v16i32_v16i8(<16 x i32> %a0) {
 ;
 ; AVX512-LABEL: trunc_packus_v16i32_v16i8:
 ; AVX512:       # %bb.0:
-; AVX512-NEXT:    vpminsd {{.*}}(%rip){1to16}, %zmm0, %zmm0
 ; AVX512-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX512-NEXT:    vpmaxsd %zmm1, %zmm0, %zmm0
-; AVX512-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512-NEXT:    vpmovusdb %zmm0, %xmm0
 ; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
   %1 = icmp slt <16 x i32> %a0, <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>
@@ -3173,10 +3162,9 @@ define <16 x i8> @trunc_packus_v16i16_v16i8(<16 x i16> %a0) {
 ;
 ; AVX512BWVL-LABEL: trunc_packus_v16i16_v16i8:
 ; AVX512BWVL:       # %bb.0:
-; AVX512BWVL-NEXT:    vpminsw {{.*}}(%rip), %ymm0, %ymm0
 ; AVX512BWVL-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX512BWVL-NEXT:    vpmaxsw %ymm1, %ymm0, %ymm0
-; AVX512BWVL-NEXT:    vpmovwb %ymm0, %xmm0
+; AVX512BWVL-NEXT:    vpmovuswb %ymm0, %xmm0
 ; AVX512BWVL-NEXT:    vzeroupper
 ; AVX512BWVL-NEXT:    retq
   %1 = icmp slt <16 x i16> %a0, <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>
@@ -3242,18 +3230,16 @@ define <32 x i8> @trunc_packus_v32i16_v32i8(<32 x i16> %a0) {
 ;
 ; AVX512BW-LABEL: trunc_packus_v32i16_v32i8:
 ; AVX512BW:       # %bb.0:
-; AVX512BW-NEXT:    vpminsw {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512BW-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX512BW-NEXT:    vpmaxsw %zmm1, %zmm0, %zmm0
-; AVX512BW-NEXT:    vpmovwb %zmm0, %ymm0
+; AVX512BW-NEXT:    vpmovuswb %zmm0, %ymm0
 ; AVX512BW-NEXT:    retq
 ;
 ; AVX512BWVL-LABEL: trunc_packus_v32i16_v32i8:
 ; AVX512BWVL:       # %bb.0:
-; AVX512BWVL-NEXT:    vpminsw {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512BWVL-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX512BWVL-NEXT:    vpmaxsw %zmm1, %zmm0, %zmm0
-; AVX512BWVL-NEXT:    vpmovwb %zmm0, %ymm0
+; AVX512BWVL-NEXT:    vpmovuswb %zmm0, %ymm0
 ; AVX512BWVL-NEXT:    retq
   %1 = icmp slt <32 x i16> %a0, <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, 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>
   %2 = select <32 x i1> %1, <32 x i16> %a0, <32 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, 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>