diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -39841,6 +39841,21 @@
     if (auto USatVal = detectUSatPattern(In, VT, DAG, DL))
       return DAG.getNode(X86ISD::VTRUNCUS, DL, VT, USatVal);
   }
+
+  // If we're clamping a signed 32-bit vector to 0-255 and the 32-bit vector is
+  // split across two registers. We can use a packusdw+perm to clamp to 0-65535
+  // and concatenate at the same time. Then we can use a final vpmovuswb to
+  // clip to 0-255.
+  if (Subtarget.hasBWI() && !Subtarget.useAVX512Regs() &&
+      InVT == MVT::v16i32 && VT == MVT::v16i8) {
+    if (auto USatVal = detectSSatPattern(In, VT, true)) {
+      // Emit a VPACKUSDW+VPERMQ followed by a VPMOVUSWB.
+      SDValue Mid = truncateVectorWithPACK(X86ISD::PACKUS, MVT::v16i16, USatVal,
+                                           DL, DAG, Subtarget);
+      return DAG.getNode(X86ISD::VTRUNCUS, DL, VT, Mid);
+    }
+  }
+
   if (VT.isVector() && isPowerOf2_32(VT.getVectorNumElements()) &&
       !(Subtarget.hasAVX512() && InSVT == MVT::i32) &&
       !(Subtarget.hasBWI() && InSVT == MVT::i16) &&
diff --git a/llvm/test/CodeGen/X86/min-legal-vector-width.ll b/llvm/test/CodeGen/X86/min-legal-vector-width.ll
--- a/llvm/test/CodeGen/X86/min-legal-vector-width.ll
+++ b/llvm/test/CodeGen/X86/min-legal-vector-width.ll
@@ -1083,12 +1083,10 @@
 define <16 x i8> @trunc_packus_v16i32_v16i8(<16 x i32>* %p, <16 x i8>* %q) "min-legal-vector-width"="256" {
 ; CHECK-LABEL: trunc_packus_v16i32_v16i8:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vpxor %xmm0, %xmm0, %xmm0
-; CHECK-NEXT:    vpmaxsd 32(%rdi), %ymm0, %ymm1
-; CHECK-NEXT:    vpmovusdb %ymm1, %xmm1
-; CHECK-NEXT:    vpmaxsd (%rdi), %ymm0, %ymm0
-; CHECK-NEXT:    vpmovusdb %ymm0, %xmm0
-; CHECK-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; CHECK-NEXT:    vmovdqa (%rdi), %ymm0
+; CHECK-NEXT:    vpackusdw 32(%rdi), %ymm0, %ymm0
+; CHECK-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
+; CHECK-NEXT:    vpmovuswb %ymm0, %xmm0
 ; CHECK-NEXT:    vzeroupper
 ; CHECK-NEXT:    retq
   %a = load <16 x i32>, <16 x i32>* %p