Index: lib/Target/X86/X86ISelLowering.cpp
===================================================================
--- lib/Target/X86/X86ISelLowering.cpp
+++ lib/Target/X86/X86ISelLowering.cpp
@@ -16227,12 +16227,13 @@
   assert((Opcode == X86ISD::PACKSS || Opcode == X86ISD::PACKUS) &&
          "Unexpected PACK opcode");
 
+  EVT SrcVT = In.getValueType();
+
   // Requires SSE2 but AVX512 has fast truncate.
-  if (!Subtarget.hasSSE2() || Subtarget.hasAVX512())
+  if (!Subtarget.hasSSE2() || Subtarget.hasBWI() ||
+      (Subtarget.hasAVX512() && SrcVT.getScalarType() != MVT::i16))
     return SDValue();
 
-  EVT SrcVT = In.getValueType();
-
   // No truncation required, we might get here due to recursive calls.
   if (SrcVT == DstVT)
     return In;
@@ -34649,10 +34650,6 @@
 static SDValue combineVectorSignBitsTruncation(SDNode *N, SDLoc &DL,
                                                SelectionDAG &DAG,
                                                const X86Subtarget &Subtarget) {
-  // Requires SSE2 but AVX512 has fast truncate.
-  if (!Subtarget.hasSSE2() || Subtarget.hasAVX512())
-    return SDValue();
-
   if (!N->getValueType(0).isVector() || !N->getValueType(0).isSimple())
     return SDValue();
 
@@ -34666,6 +34663,11 @@
   MVT InVT = In.getValueType().getSimpleVT();
   MVT InSVT = InVT.getScalarType();
 
+  // Requires SSE2 but AVX512 has fast truncate.
+  if (!Subtarget.hasSSE2() || Subtarget.hasBWI() ||
+      (Subtarget.hasAVX512() && InSVT != MVT::i16))
+    return SDValue();
+
   // Check we have a truncation suited for PACKSS.
   if (!VT.is128BitVector() && !VT.is256BitVector())
     return SDValue();
Index: test/CodeGen/X86/avx512-ext.ll
===================================================================
--- test/CodeGen/X86/avx512-ext.ll
+++ test/CodeGen/X86/avx512-ext.ll
@@ -1720,13 +1720,10 @@
 define <32 x i8> @zext_32xi1_to_32xi8(<32 x i16> %x, <32 x i16> %y) #0 {
 ; KNL-LABEL: zext_32xi1_to_32xi8:
 ; KNL:       # BB#0:
-; KNL-NEXT:    vpcmpeqw %ymm2, %ymm0, %ymm0
-; KNL-NEXT:    vpmovsxwd %ymm0, %zmm0
-; KNL-NEXT:    vpmovdb %zmm0, %xmm0
 ; KNL-NEXT:    vpcmpeqw %ymm3, %ymm1, %ymm1
-; KNL-NEXT:    vpmovsxwd %ymm1, %zmm1
-; KNL-NEXT:    vpmovdb %zmm1, %xmm1
-; KNL-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
+; KNL-NEXT:    vpcmpeqw %ymm2, %ymm0, %ymm0
+; KNL-NEXT:    vpacksswb %ymm1, %ymm0, %ymm0
+; KNL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
 ; KNL-NEXT:    vpand {{.*}}(%rip), %ymm0, %ymm0
 ; KNL-NEXT:    retq
 ;
Index: test/CodeGen/X86/avx512-trunc.ll
===================================================================
--- test/CodeGen/X86/avx512-trunc.ll
+++ test/CodeGen/X86/avx512-trunc.ll
@@ -542,8 +542,8 @@
 ; KNL-LABEL: usat_trunc_wb_256_mem:
 ; KNL:       ## BB#0:
 ; KNL-NEXT:    vpminuw {{.*}}(%rip), %ymm0, %ymm0
-; KNL-NEXT:    vpmovsxwd %ymm0, %zmm0
-; KNL-NEXT:    vpmovdb %zmm0, %xmm0
+; KNL-NEXT:    vextracti128 $1, %ymm0, %xmm1
+; KNL-NEXT:    vpackuswb %xmm1, %xmm0, %xmm0
 ; KNL-NEXT:    vmovdqu %xmm0, (%rdi)
 ; KNL-NEXT:    vzeroupper
 ; KNL-NEXT:    retq
@@ -564,8 +564,8 @@
 ; KNL-LABEL: usat_trunc_wb_256:
 ; KNL:       ## BB#0:
 ; KNL-NEXT:    vpminuw {{.*}}(%rip), %ymm0, %ymm0
-; KNL-NEXT:    vpmovsxwd %ymm0, %zmm0
-; KNL-NEXT:    vpmovdb %zmm0, %xmm0
+; KNL-NEXT:    vextracti128 $1, %ymm0, %xmm1
+; KNL-NEXT:    vpackuswb %xmm1, %xmm0, %xmm0
 ; KNL-NEXT:    vzeroupper
 ; KNL-NEXT:    retq
 ;
Index: test/CodeGen/X86/vector-compare-results.ll
===================================================================
--- test/CodeGen/X86/vector-compare-results.ll
+++ test/CodeGen/X86/vector-compare-results.ll
@@ -317,16 +317,16 @@
 ; AVX512F-LABEL: test_cmp_v16i16:
 ; AVX512F:       # BB#0:
 ; AVX512F-NEXT:    vpcmpgtw %ymm1, %ymm0, %ymm0
-; AVX512F-NEXT:    vpmovsxwd %ymm0, %zmm0
-; AVX512F-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512F-NEXT:    vextracti128 $1, %ymm0, %xmm1
+; AVX512F-NEXT:    vpacksswb %xmm1, %xmm0, %xmm0
 ; AVX512F-NEXT:    vzeroupper
 ; AVX512F-NEXT:    retq
 ;
 ; AVX512DQ-LABEL: test_cmp_v16i16:
 ; AVX512DQ:       # BB#0:
 ; AVX512DQ-NEXT:    vpcmpgtw %ymm1, %ymm0, %ymm0
-; AVX512DQ-NEXT:    vpmovsxwd %ymm0, %zmm0
-; AVX512DQ-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512DQ-NEXT:    vextracti128 $1, %ymm0, %xmm1
+; AVX512DQ-NEXT:    vpacksswb %xmm1, %xmm0, %xmm0
 ; AVX512DQ-NEXT:    vzeroupper
 ; AVX512DQ-NEXT:    retq
 ;
@@ -1122,24 +1122,18 @@
 ;
 ; AVX512F-LABEL: test_cmp_v32i16:
 ; AVX512F:       # BB#0:
-; AVX512F-NEXT:    vpcmpgtw %ymm2, %ymm0, %ymm0
-; AVX512F-NEXT:    vpmovsxwd %ymm0, %zmm0
-; AVX512F-NEXT:    vpmovdb %zmm0, %xmm0
 ; AVX512F-NEXT:    vpcmpgtw %ymm3, %ymm1, %ymm1
-; AVX512F-NEXT:    vpmovsxwd %ymm1, %zmm1
-; AVX512F-NEXT:    vpmovdb %zmm1, %xmm1
-; AVX512F-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
+; AVX512F-NEXT:    vpcmpgtw %ymm2, %ymm0, %ymm0
+; AVX512F-NEXT:    vpacksswb %ymm1, %ymm0, %ymm0
+; AVX512F-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
 ; AVX512F-NEXT:    retq
 ;
 ; AVX512DQ-LABEL: test_cmp_v32i16:
 ; AVX512DQ:       # BB#0:
-; AVX512DQ-NEXT:    vpcmpgtw %ymm2, %ymm0, %ymm0
-; AVX512DQ-NEXT:    vpmovsxwd %ymm0, %zmm0
-; AVX512DQ-NEXT:    vpmovdb %zmm0, %xmm0
 ; AVX512DQ-NEXT:    vpcmpgtw %ymm3, %ymm1, %ymm1
-; AVX512DQ-NEXT:    vpmovsxwd %ymm1, %zmm1
-; AVX512DQ-NEXT:    vpmovdb %zmm1, %xmm1
-; AVX512DQ-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
+; AVX512DQ-NEXT:    vpcmpgtw %ymm2, %ymm0, %ymm0
+; AVX512DQ-NEXT:    vpacksswb %ymm1, %ymm0, %ymm0
+; AVX512DQ-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
 ; AVX512DQ-NEXT:    retq
 ;
 ; AVX512BW-LABEL: test_cmp_v32i16:
Index: test/CodeGen/X86/vector-sext.ll
===================================================================
--- test/CodeGen/X86/vector-sext.ll
+++ test/CodeGen/X86/vector-sext.ll
@@ -5017,13 +5017,10 @@
 ;
 ; AVX512F-LABEL: sext_32xi1_to_32xi8:
 ; AVX512F:       # BB#0:
-; AVX512F-NEXT:    vpcmpeqw %ymm2, %ymm0, %ymm0
-; AVX512F-NEXT:    vpmovsxwd %ymm0, %zmm0
-; AVX512F-NEXT:    vpmovdb %zmm0, %xmm0
 ; AVX512F-NEXT:    vpcmpeqw %ymm3, %ymm1, %ymm1
-; AVX512F-NEXT:    vpmovsxwd %ymm1, %zmm1
-; AVX512F-NEXT:    vpmovdb %zmm1, %xmm1
-; AVX512F-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
+; AVX512F-NEXT:    vpcmpeqw %ymm2, %ymm0, %ymm0
+; AVX512F-NEXT:    vpacksswb %ymm1, %ymm0, %ymm0
+; AVX512F-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
 ; AVX512F-NEXT:    retq
 ;
 ; AVX512BW-LABEL: sext_32xi1_to_32xi8:
Index: test/CodeGen/X86/vector-trunc.ll
===================================================================
--- test/CodeGen/X86/vector-trunc.ll
+++ test/CodeGen/X86/vector-trunc.ll
@@ -1137,8 +1137,8 @@
 ; AVX512F-LABEL: trunc16i16_16i8_ashr:
 ; AVX512F:       # BB#0: # %entry
 ; AVX512F-NEXT:    vpsraw $8, %ymm0, %ymm0
-; AVX512F-NEXT:    vpmovsxwd %ymm0, %zmm0
-; AVX512F-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512F-NEXT:    vextracti128 $1, %ymm0, %xmm1
+; AVX512F-NEXT:    vpacksswb %xmm1, %xmm0, %xmm0
 ; AVX512F-NEXT:    vmovdqu %xmm0, (%rax)
 ; AVX512F-NEXT:    vzeroupper
 ; AVX512F-NEXT:    retq
@@ -1146,8 +1146,8 @@
 ; AVX512VL-LABEL: trunc16i16_16i8_ashr:
 ; AVX512VL:       # BB#0: # %entry
 ; AVX512VL-NEXT:    vpsraw $8, %ymm0, %ymm0
-; AVX512VL-NEXT:    vpmovsxwd %ymm0, %zmm0
-; AVX512VL-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512VL-NEXT:    vextracti128 $1, %ymm0, %xmm1
+; AVX512VL-NEXT:    vpacksswb %xmm1, %xmm0, %xmm0
 ; AVX512VL-NEXT:    vmovdqu %xmm0, (%rax)
 ; AVX512VL-NEXT:    vzeroupper
 ; AVX512VL-NEXT:    retq
@@ -1204,8 +1204,8 @@
 ; AVX512F-LABEL: trunc16i16_16i8_lshr:
 ; AVX512F:       # BB#0: # %entry
 ; AVX512F-NEXT:    vpsrlw $8, %ymm0, %ymm0
-; AVX512F-NEXT:    vpmovsxwd %ymm0, %zmm0
-; AVX512F-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512F-NEXT:    vextracti128 $1, %ymm0, %xmm1
+; AVX512F-NEXT:    vpackuswb %xmm1, %xmm0, %xmm0
 ; AVX512F-NEXT:    vmovdqu %xmm0, (%rax)
 ; AVX512F-NEXT:    vzeroupper
 ; AVX512F-NEXT:    retq
@@ -1213,8 +1213,8 @@
 ; AVX512VL-LABEL: trunc16i16_16i8_lshr:
 ; AVX512VL:       # BB#0: # %entry
 ; AVX512VL-NEXT:    vpsrlw $8, %ymm0, %ymm0
-; AVX512VL-NEXT:    vpmovsxwd %ymm0, %zmm0
-; AVX512VL-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512VL-NEXT:    vextracti128 $1, %ymm0, %xmm1
+; AVX512VL-NEXT:    vpackuswb %xmm1, %xmm0, %xmm0
 ; AVX512VL-NEXT:    vmovdqu %xmm0, (%rax)
 ; AVX512VL-NEXT:    vzeroupper
 ; AVX512VL-NEXT:    retq
@@ -1943,10 +1943,10 @@
 ; AVX512F-NEXT:    vmovdqu 32(%rdi), %ymm1
 ; AVX512F-NEXT:    vpsrlw $8, %ymm0, %ymm0
 ; AVX512F-NEXT:    vpsrlw $8, %ymm1, %ymm1
-; AVX512F-NEXT:    vpmovsxwd %ymm0, %zmm0
-; AVX512F-NEXT:    vpmovdb %zmm0, %xmm0
-; AVX512F-NEXT:    vpmovsxwd %ymm1, %zmm1
-; AVX512F-NEXT:    vpmovdb %zmm1, %xmm1
+; AVX512F-NEXT:    vextracti128 $1, %ymm0, %xmm2
+; AVX512F-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
+; AVX512F-NEXT:    vextracti128 $1, %ymm1, %xmm2
+; AVX512F-NEXT:    vpackuswb %xmm2, %xmm1, %xmm1
 ; AVX512F-NEXT:    vmovdqu %xmm0, (%rsi)
 ; AVX512F-NEXT:    vmovdqu %xmm1, 16(%rsi)
 ; AVX512F-NEXT:    vzeroupper
@@ -1958,10 +1958,10 @@
 ; AVX512VL-NEXT:    vmovdqu 32(%rdi), %ymm1
 ; AVX512VL-NEXT:    vpsrlw $8, %ymm0, %ymm0
 ; AVX512VL-NEXT:    vpsrlw $8, %ymm1, %ymm1
-; AVX512VL-NEXT:    vpmovsxwd %ymm0, %zmm0
-; AVX512VL-NEXT:    vpmovdb %zmm0, %xmm0
-; AVX512VL-NEXT:    vpmovsxwd %ymm1, %zmm1
-; AVX512VL-NEXT:    vpmovdb %zmm1, %xmm1
+; AVX512VL-NEXT:    vextracti128 $1, %ymm0, %xmm2
+; AVX512VL-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
+; AVX512VL-NEXT:    vextracti128 $1, %ymm1, %xmm2
+; AVX512VL-NEXT:    vpackuswb %xmm2, %xmm1, %xmm1
 ; AVX512VL-NEXT:    vmovdqu %xmm0, (%rsi)
 ; AVX512VL-NEXT:    vmovdqu %xmm1, 16(%rsi)
 ; AVX512VL-NEXT:    vzeroupper
Index: test/CodeGen/X86/vselect-packss.ll
===================================================================
--- test/CodeGen/X86/vselect-packss.ll
+++ test/CodeGen/X86/vselect-packss.ll
@@ -53,8 +53,8 @@
 ; AVX512-LABEL: vselect_packss_v16i16:
 ; AVX512:       # BB#0:
 ; AVX512-NEXT:    vpcmpeqw %ymm1, %ymm0, %ymm0
-; AVX512-NEXT:    vpmovsxwd %ymm0, %zmm0
-; AVX512-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512-NEXT:    vextracti128 $1, %ymm0, %xmm1
+; AVX512-NEXT:    vpacksswb %xmm1, %xmm0, %xmm0
 ; AVX512-NEXT:    vpblendvb %xmm0, %xmm2, %xmm3, %xmm0
 ; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq