[DAGCombiner] narrow truncated vector binops when legal

[spatel]

Summary

This is the smallest vector enhancement I could find to D54640. Here, we're allowing narrowing to only legal vector ops because we'll see regressions without that. All of the test diffs are wins from what I can tell. With AVX/AVX512, we can shrink ymm/zmm ops to xmm.

x86 vector multiplies are the problem case due to the patchwork ISA, and it's not clear to me if we can dance around those regressions using TLI hooks or if we need preliminary patches to plug those holes.

This patch probably makes some of the custom x86 code in "combineTruncatedArithmetic" unnecessary, but I'd rather wait to try removing anything from there until we're sure this code doesn't cause regressions for other targets and evolves to handle more cases.

[RKSimon]

LGTM - if you're not going to work on simplifying/removing X86's combineTruncatedArithmetic immediately please add a TODO comment.

llvm/trunk/lib/CodeGen/SelectionDAG/DAGCombiner.cpp

SDValue DAGCombiner::visitTRUNCATE(SDNode *N) {
   switch (N0.getOpcode()) {
   // TODO: Add case for ADD - that will likely require a change in logic here
   // or target-specific changes to avoid regressions.
   case ISD::SUB:
   case ISD::MUL:
   case ISD::AND:
   case ISD::OR:
   case ISD::XOR:
-    // TODO: This should allow vector constants/types too.
     if (!LegalOperations && N0.hasOneUse() &&
-        (isa<ConstantSDNode>(N0.getOperand(0)) ||
-         isa<ConstantSDNode>(N0.getOperand(1)))) {
+        (isConstantOrConstantVector(N0.getOperand(0)) ||
+         isConstantOrConstantVector(N0.getOperand(1)))) {
+      // TODO: We already restricted this to pre-legalization, but for vectors
+      // we are extra cautious to not create an unsupported operation.
+      // Target-specific changes are likely needed to avoid regressions here.
+      if (VT.isScalarInteger() || TLI.isOperationLegal(N0.getOpcode(), VT)) {
         SDLoc DL(N);
         SDValue NarrowL = DAG.getNode(ISD::TRUNCATE, DL, VT, N0.getOperand(0));
         SDValue NarrowR = DAG.getNode(ISD::TRUNCATE, DL, VT, N0.getOperand(1));
         return DAG.getNode(N0.getOpcode(), DL, VT, NarrowL, NarrowR);
       }
     }
+  }
 
   return SDValue();
 }
 
 static SDNode *getBuildPairElt(SDNode *N, unsigned i) {
   SDValue Elt = N->getOperand(i);
   if (Elt.getOpcode() != ISD::MERGE_VALUES)
     return Elt.getNode();

llvm/trunk/lib/Target/X86/X86ISelLowering.cpp

if (((Subtarget.hasSSE3() && (VT == MVT::v4f32 || VT == MVT::v2f64)) ||
     return DAG.getNode(NewOpcode, SDLoc(N), VT, LHS, RHS);
   }
   return SDValue();
 }
 
 /// Attempt to pre-truncate inputs to arithmetic ops if it will simplify
 /// the codegen.
 /// e.g. TRUNC( BINOP( X, Y ) ) --> BINOP( TRUNC( X ), TRUNC( Y ) )
+/// TODO: This overlaps with the generic combiner's visitTRUNCATE. Remove
+///       anything that is guaranteed to be transformed by DAGCombiner.
 static SDValue combineTruncatedArithmetic(SDNode *N, SelectionDAG &DAG,
                                           const X86Subtarget &Subtarget,
                                           const SDLoc &DL) {
   assert(N->getOpcode() == ISD::TRUNCATE && "Wrong opcode");
   SDValue Src = N->getOperand(0);
   unsigned Opcode = Src.getOpcode();
   const TargetLowering &TLI = DAG.getTargetLoweringInfo();
 

llvm/trunk/test/CodeGen/X86/vector-trunc-math-widen.ll

 
 ;
 ; sub to constant
 ;
 
 define <4 x i32> @trunc_sub_const_v4i64_v4i32(<4 x i64> %a0) nounwind {
 ; SSE-LABEL: trunc_sub_const_v4i64_v4i32:
 ; SSE:       # %bb.0:
-; SSE-NEXT:    movl $1, %eax
-; SSE-NEXT:    movq %rax, %xmm2
-; SSE-NEXT:    pslldq {{.*#+}} xmm2 = zero,zero,zero,zero,zero,zero,zero,zero,xmm2[0,1,2,3,4,5,6,7]
-; SSE-NEXT:    psubq %xmm2, %xmm0
-; SSE-NEXT:    psubq {{.*}}(%rip), %xmm1
 ; SSE-NEXT:    shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
+; SSE-NEXT:    psubd {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_sub_const_v4i64_v4i32:
 ; AVX1:       # %bb.0:
-; AVX1-NEXT:    movl $1, %eax
-; AVX1-NEXT:    vmovq %rax, %xmm1
-; AVX1-NEXT:    vpslldq {{.*#+}} xmm1 = zero,zero,zero,zero,zero,zero,zero,zero,xmm1[0,1,2,3,4,5,6,7]
-; AVX1-NEXT:    vpsubq %xmm1, %xmm0, %xmm1
-; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpsubq {{.*}}(%rip), %xmm0, %xmm0
-; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm1[0,2],xmm0[0,2]
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
+; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
+; AVX1-NEXT:    vpsubd {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-SLOW-LABEL: trunc_sub_const_v4i64_v4i32:
 ; AVX2-SLOW:       # %bb.0:
-; AVX2-SLOW-NEXT:    vpsubq {{.*}}(%rip), %ymm0, %ymm0
 ; AVX2-SLOW-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
 ; AVX2-SLOW-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX2-SLOW-NEXT:    # kill: def $xmm0 killed $xmm0 killed $ymm0
+; AVX2-SLOW-NEXT:    vpsubd {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-SLOW-NEXT:    vzeroupper
 ; AVX2-SLOW-NEXT:    retq
 ;
 ; AVX2-FAST-LABEL: trunc_sub_const_v4i64_v4i32:
 ; AVX2-FAST:       # %bb.0:
-; AVX2-FAST-NEXT:    vpsubq {{.*}}(%rip), %ymm0, %ymm0
 ; AVX2-FAST-NEXT:    vmovdqa {{.*#+}} ymm1 = [0,2,4,6,4,6,6,7]
 ; AVX2-FAST-NEXT:    vpermd %ymm0, %ymm1, %ymm0
-; AVX2-FAST-NEXT:    # kill: def $xmm0 killed $xmm0 killed $ymm0
+; AVX2-FAST-NEXT:    vpsubd {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-FAST-NEXT:    vzeroupper
 ; AVX2-FAST-NEXT:    retq
 ;
 ; AVX512-LABEL: trunc_sub_const_v4i64_v4i32:
 ; AVX512:       # %bb.0:
-; AVX512-NEXT:    vpsubq {{.*}}(%rip), %ymm0, %ymm0
+; AVX512-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
 ; AVX512-NEXT:    vpmovqd %zmm0, %ymm0
-; AVX512-NEXT:    # kill: def $xmm0 killed $xmm0 killed $ymm0
+; AVX512-NEXT:    vpsubd {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
   %1 = sub <4 x i64> %a0, <i64 0, i64 1, i64 2, i64 3>
   %2 = trunc <4 x i64> %1 to <4 x i32>
   ret <4 x i32> %2
 }
 
 define <8 x i16> @trunc_sub_const_v8i64_v8i16(<8 x i64> %a0) nounwind {
 ; SSE-LABEL: trunc_sub_const_v8i64_v8i16:
 ; SSE:       # %bb.0:
-; SSE-NEXT:    movl $1, %eax
-; SSE-NEXT:    movq %rax, %xmm4
-; SSE-NEXT:    pslldq {{.*#+}} xmm4 = zero,zero,zero,zero,zero,zero,zero,zero,xmm4[0,1,2,3,4,5,6,7]
-; SSE-NEXT:    psubq %xmm4, %xmm0
-; SSE-NEXT:    psubq {{.*}}(%rip), %xmm1
-; SSE-NEXT:    psubq {{.*}}(%rip), %xmm2
-; SSE-NEXT:    psubq {{.*}}(%rip), %xmm3
-; SSE-NEXT:    pshufd {{.*#+}} xmm3 = xmm3[0,2,2,3]
-; SSE-NEXT:    pshuflw {{.*#+}} xmm3 = xmm3[0,1,0,2,4,5,6,7]
-; SSE-NEXT:    pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
-; SSE-NEXT:    pshuflw {{.*#+}} xmm2 = xmm2[0,1,0,2,4,5,6,7]
-; SSE-NEXT:    punpckldq {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1]
-; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
-; SSE-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
 ; SSE-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
 ; SSE-NEXT:    pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
+; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
+; SSE-NEXT:    pshuflw {{.*#+}} xmm4 = xmm0[0,2,2,3,4,5,6,7]
+; SSE-NEXT:    punpckldq {{.*#+}} xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1]
+; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm3[0,2,2,3]
+; SSE-NEXT:    pshuflw {{.*#+}} xmm1 = xmm0[0,1,0,2,4,5,6,7]
+; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm2[0,2,2,3]
+; SSE-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[0,1,0,2,4,5,6,7]
 ; SSE-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
-; SSE-NEXT:    movsd {{.*#+}} xmm2 = xmm0[0],xmm2[1]
-; SSE-NEXT:    movapd %xmm2, %xmm0
+; SSE-NEXT:    movsd {{.*#+}} xmm0 = xmm4[0],xmm0[1]
+; SSE-NEXT:    psubw {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_sub_const_v8i64_v8i16:
 ; AVX1:       # %bb.0:
-; AVX1-NEXT:    movl $1, %eax
-; AVX1-NEXT:    vmovq %rax, %xmm2
-; AVX1-NEXT:    vpslldq {{.*#+}} xmm2 = zero,zero,zero,zero,zero,zero,zero,zero,xmm2[0,1,2,3,4,5,6,7]
-; AVX1-NEXT:    vpsubq %xmm2, %xmm0, %xmm2
-; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpsubq {{.*}}(%rip), %xmm0, %xmm0
-; AVX1-NEXT:    vpsubq {{.*}}(%rip), %xmm1, %xmm3
-; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm1
-; AVX1-NEXT:    vpsubq {{.*}}(%rip), %xmm1, %xmm1
-; AVX1-NEXT:    vpxor %xmm4, %xmm4, %xmm4
-; AVX1-NEXT:    vpblendw {{.*#+}} xmm1 = xmm1[0],xmm4[1,2,3],xmm1[4],xmm4[5,6,7]
-; AVX1-NEXT:    vpblendw {{.*#+}} xmm3 = xmm3[0],xmm4[1,2,3],xmm3[4],xmm4[5,6,7]
-; AVX1-NEXT:    vpackusdw %xmm1, %xmm3, %xmm1
-; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0],xmm4[1,2,3],xmm0[4],xmm4[5,6,7]
-; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm2[0],xmm4[1,2,3],xmm2[4],xmm4[5,6,7]
-; AVX1-NEXT:    vpackusdw %xmm0, %xmm2, %xmm0
+; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
+; AVX1-NEXT:    vpxor %xmm3, %xmm3, %xmm3
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm2[0],xmm3[1,2,3],xmm2[4],xmm3[5,6,7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm1 = xmm1[0],xmm3[1,2,3],xmm1[4],xmm3[5,6,7]
+; AVX1-NEXT:    vpackusdw %xmm2, %xmm1, %xmm1
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm2[0],xmm3[1,2,3],xmm2[4],xmm3[5,6,7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0],xmm3[1,2,3],xmm0[4],xmm3[5,6,7]
+; AVX1-NEXT:    vpackusdw %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vpackusdw %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpsubw {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-SLOW-LABEL: trunc_sub_const_v8i64_v8i16:
 ; AVX2-SLOW:       # %bb.0:
-; AVX2-SLOW-NEXT:    vpsubq {{.*}}(%rip), %ymm1, %ymm1
-; AVX2-SLOW-NEXT:    vpsubq {{.*}}(%rip), %ymm0, %ymm0
 ; AVX2-SLOW-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
 ; AVX2-SLOW-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
 ; AVX2-SLOW-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
 ; AVX2-SLOW-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
 ; AVX2-SLOW-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
 ; AVX2-SLOW-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
 ; AVX2-SLOW-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX2-SLOW-NEXT:    # kill: def $xmm0 killed $xmm0 killed $ymm0
+; AVX2-SLOW-NEXT:    vpsubw {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-SLOW-NEXT:    vzeroupper
 ; AVX2-SLOW-NEXT:    retq
 ;
 ; AVX2-FAST-LABEL: trunc_sub_const_v8i64_v8i16:
 ; AVX2-FAST:       # %bb.0:
-; AVX2-FAST-NEXT:    vpsubq {{.*}}(%rip), %ymm1, %ymm1
-; AVX2-FAST-NEXT:    vpsubq {{.*}}(%rip), %ymm0, %ymm0
 ; AVX2-FAST-NEXT:    vmovdqa {{.*#+}} ymm2 = [0,2,4,6,4,6,6,7]
 ; AVX2-FAST-NEXT:    vpermd %ymm0, %ymm2, %ymm0
 ; AVX2-FAST-NEXT:    vpermd %ymm1, %ymm2, %ymm1
 ; AVX2-FAST-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
 ; AVX2-FAST-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
 ; AVX2-FAST-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX2-FAST-NEXT:    # kill: def $xmm0 killed $xmm0 killed $ymm0
+; AVX2-FAST-NEXT:    vpsubw {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-FAST-NEXT:    vzeroupper
 ; AVX2-FAST-NEXT:    retq
 ;
 ; AVX512-LABEL: trunc_sub_const_v8i64_v8i16:
 ; AVX512:       # %bb.0:
-; AVX512-NEXT:    vpsubq {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512-NEXT:    vpmovqw %zmm0, %xmm0
+; AVX512-NEXT:    vpsubw {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
   %1 = sub <8 x i64> %a0, <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7>
   %2 = trunc <8 x i64> %1 to <8 x i16>
   ret <8 x i16> %2
 }
 
 define <8 x i16> @trunc_sub_const_v8i32_v8i16(<8 x i32> %a0) nounwind {
 ; SSE-LABEL: trunc_sub_const_v8i32_v8i16:
 ; SSE:       # %bb.0:
-; SSE-NEXT:    psubd {{.*}}(%rip), %xmm0
-; SSE-NEXT:    psubd {{.*}}(%rip), %xmm1
 ; SSE-NEXT:    pslld $16, %xmm1
 ; SSE-NEXT:    psrad $16, %xmm1
 ; SSE-NEXT:    pslld $16, %xmm0
 ; SSE-NEXT:    psrad $16, %xmm0
 ; SSE-NEXT:    packssdw %xmm1, %xmm0
+; SSE-NEXT:    psubw {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_sub_const_v8i32_v8i16:
 ; AVX1:       # %bb.0:
-; AVX1-NEXT:    vpsubd {{.*}}(%rip), %xmm0, %xmm1
-; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpsubd {{.*}}(%rip), %xmm0, %xmm0
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
 ; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
-; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
-; AVX1-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; AVX1-NEXT:    vpsubw {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_sub_const_v8i32_v8i16:
 ; AVX2:       # %bb.0:
-; AVX2-NEXT:    vpsubd {{.*}}(%rip), %ymm0, %ymm0
 ; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX2-NEXT:    # kill: def $xmm0 killed $xmm0 killed $ymm0
+; AVX2-NEXT:    vpsubw {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: trunc_sub_const_v8i32_v8i16:
 ; AVX512:       # %bb.0:
-; AVX512-NEXT:    vpsubd {{.*}}(%rip), %ymm0, %ymm0
+; AVX512-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
 ; AVX512-NEXT:    vpmovdw %zmm0, %ymm0
-; AVX512-NEXT:    # kill: def $xmm0 killed $xmm0 killed $ymm0
+; AVX512-NEXT:    vpsubw {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
   %1 = sub <8 x i32> %a0, <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
   %2 = trunc <8 x i32> %1 to <8 x i16>
   ret <8 x i16> %2
 }
 
 define <16 x i8> @trunc_sub_const_v16i64_v16i8(<16 x i64> %a0) nounwind {
 ; SSE-LABEL: trunc_sub_const_v16i64_v16i8:
 ; SSE:       # %bb.0:
-; SSE-NEXT:    movl $1, %eax
-; SSE-NEXT:    movq %rax, %xmm8
-; SSE-NEXT:    pslldq {{.*#+}} xmm8 = zero,zero,zero,zero,zero,zero,zero,zero,xmm8[0,1,2,3,4,5,6,7]
-; SSE-NEXT:    psubq %xmm8, %xmm0
-; SSE-NEXT:    psubq {{.*}}(%rip), %xmm1
-; SSE-NEXT:    psubq {{.*}}(%rip), %xmm2
-; SSE-NEXT:    psubq {{.*}}(%rip), %xmm3
-; SSE-NEXT:    psubq {{.*}}(%rip), %xmm4
-; SSE-NEXT:    psubq {{.*}}(%rip), %xmm5
-; SSE-NEXT:    psubq {{.*}}(%rip), %xmm6
-; SSE-NEXT:    psubq {{.*}}(%rip), %xmm7
 ; SSE-NEXT:    movdqa {{.*#+}} xmm8 = [255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0]
 ; SSE-NEXT:    pand %xmm8, %xmm7
 ; SSE-NEXT:    pand %xmm8, %xmm6
 ; SSE-NEXT:    packuswb %xmm7, %xmm6
 ; SSE-NEXT:    pand %xmm8, %xmm5
 ; SSE-NEXT:    pand %xmm8, %xmm4
 ; SSE-NEXT:    packuswb %xmm5, %xmm4
 ; SSE-NEXT:    packuswb %xmm6, %xmm4
 ; SSE-NEXT:    pand %xmm8, %xmm3
 ; SSE-NEXT:    pand %xmm8, %xmm2
 ; SSE-NEXT:    packuswb %xmm3, %xmm2
 ; SSE-NEXT:    pand %xmm8, %xmm1
 ; SSE-NEXT:    pand %xmm8, %xmm0
 ; SSE-NEXT:    packuswb %xmm1, %xmm0
 ; SSE-NEXT:    packuswb %xmm2, %xmm0
 ; SSE-NEXT:    packuswb %xmm4, %xmm0
+; SSE-NEXT:    psubb {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_sub_const_v16i64_v16i8:
 ; AVX1:       # %bb.0:
-; AVX1-NEXT:    movl $1, %eax
-; AVX1-NEXT:    vmovq %rax, %xmm4
-; AVX1-NEXT:    vpslldq {{.*#+}} xmm4 = zero,zero,zero,zero,zero,zero,zero,zero,xmm4[0,1,2,3,4,5,6,7]
-; AVX1-NEXT:    vpsubq %xmm4, %xmm0, %xmm8
-; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpsubq {{.*}}(%rip), %xmm0, %xmm0
-; AVX1-NEXT:    vpsubq {{.*}}(%rip), %xmm1, %xmm5
-; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm1
-; AVX1-NEXT:    vpsubq {{.*}}(%rip), %xmm1, %xmm1
-; AVX1-NEXT:    vpsubq {{.*}}(%rip), %xmm2, %xmm6
-; AVX1-NEXT:    vextractf128 $1, %ymm2, %xmm2
-; AVX1-NEXT:    vpsubq {{.*}}(%rip), %xmm2, %xmm2
-; AVX1-NEXT:    vpsubq {{.*}}(%rip), %xmm3, %xmm7
-; AVX1-NEXT:    vextractf128 $1, %ymm3, %xmm3
-; AVX1-NEXT:    vpsubq {{.*}}(%rip), %xmm3, %xmm3
-; AVX1-NEXT:    vmovddup {{.*#+}} xmm4 = [1.2598673968951787E-321,1.2598673968951787E-321]
-; AVX1-NEXT:    # xmm4 = mem[0,0]
-; AVX1-NEXT:    vpand %xmm4, %xmm3, %xmm3
-; AVX1-NEXT:    vpand %xmm4, %xmm7, %xmm7
-; AVX1-NEXT:    vpackusdw %xmm3, %xmm7, %xmm3
-; AVX1-NEXT:    vpand %xmm4, %xmm2, %xmm2
-; AVX1-NEXT:    vpand %xmm4, %xmm6, %xmm6
-; AVX1-NEXT:    vpackusdw %xmm2, %xmm6, %xmm2
+; AVX1-NEXT:    vextractf128 $1, %ymm3, %xmm4
+; AVX1-NEXT:    vmovddup {{.*#+}} xmm5 = [1.2598673968951787E-321,1.2598673968951787E-321]
+; AVX1-NEXT:    # xmm5 = mem[0,0]
+; AVX1-NEXT:    vandpd %xmm5, %xmm4, %xmm4
+; AVX1-NEXT:    vandpd %xmm5, %xmm3, %xmm3
+; AVX1-NEXT:    vpackusdw %xmm4, %xmm3, %xmm3
+; AVX1-NEXT:    vextractf128 $1, %ymm2, %xmm4
+; AVX1-NEXT:    vandpd %xmm5, %xmm4, %xmm4
+; AVX1-NEXT:    vandpd %xmm5, %xmm2, %xmm2
+; AVX1-NEXT:    vpackusdw %xmm4, %xmm2, %xmm2
 ; AVX1-NEXT:    vpackusdw %xmm3, %xmm2, %xmm2
-; AVX1-NEXT:    vpand %xmm4, %xmm1, %xmm1
-; AVX1-NEXT:    vpand %xmm4, %xmm5, %xmm3
-; AVX1-NEXT:    vpackusdw %xmm1, %xmm3, %xmm1
-; AVX1-NEXT:    vpand %xmm4, %xmm0, %xmm0
-; AVX1-NEXT:    vpand %xmm4, %xmm8, %xmm3
-; AVX1-NEXT:    vpackusdw %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm3
+; AVX1-NEXT:    vandpd %xmm5, %xmm3, %xmm3
+; AVX1-NEXT:    vandpd %xmm5, %xmm1, %xmm1
+; AVX1-NEXT:    vpackusdw %xmm3, %xmm1, %xmm1
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm3
+; AVX1-NEXT:    vandpd %xmm5, %xmm3, %xmm3
+; AVX1-NEXT:    vandpd %xmm5, %xmm0, %xmm0
+; AVX1-NEXT:    vpackusdw %xmm3, %xmm0, %xmm0
 ; AVX1-NEXT:    vpackusdw %xmm1, %xmm0, %xmm0
 ; AVX1-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpsubb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-SLOW-LABEL: trunc_sub_const_v16i64_v16i8:
 ; AVX2-SLOW:       # %bb.0:
-; AVX2-SLOW-NEXT:    vpsubq {{.*}}(%rip), %ymm1, %ymm1
-; AVX2-SLOW-NEXT:    vpsubq {{.*}}(%rip), %ymm0, %ymm0
-; AVX2-SLOW-NEXT:    vpsubq {{.*}}(%rip), %ymm3, %ymm3
-; AVX2-SLOW-NEXT:    vpsubq {{.*}}(%rip), %ymm2, %ymm2
 ; AVX2-SLOW-NEXT:    vpshufd {{.*#+}} ymm2 = ymm2[0,2,2,3,4,6,6,7]
 ; AVX2-SLOW-NEXT:    vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
 ; AVX2-SLOW-NEXT:    vpshufd {{.*#+}} ymm3 = ymm3[0,2,2,3,4,6,6,7]
 ; AVX2-SLOW-NEXT:    vpermq {{.*#+}} ymm3 = ymm3[0,2,2,3]
 ; AVX2-SLOW-NEXT:    vinserti128 $1, %xmm3, %ymm2, %ymm2
 ; AVX2-SLOW-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
 ; AVX2-SLOW-NEXT:    vpshufb %ymm3, %ymm2, %ymm2
 ; AVX2-SLOW-NEXT:    vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
 ; AVX2-SLOW-NEXT:    vmovdqa {{.*#+}} xmm4 = [255,255,255,255,255,255,255,255]
 ; AVX2-SLOW-NEXT:    vpand %xmm4, %xmm2, %xmm2
 ; AVX2-SLOW-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
 ; AVX2-SLOW-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
 ; AVX2-SLOW-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
 ; AVX2-SLOW-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
 ; AVX2-SLOW-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
 ; AVX2-SLOW-NEXT:    vpshufb %ymm3, %ymm0, %ymm0
 ; AVX2-SLOW-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
 ; AVX2-SLOW-NEXT:    vpand %xmm4, %xmm0, %xmm0
 ; AVX2-SLOW-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
+; AVX2-SLOW-NEXT:    vpsubb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-SLOW-NEXT:    vzeroupper
 ; AVX2-SLOW-NEXT:    retq
 ;
 ; AVX2-FAST-LABEL: trunc_sub_const_v16i64_v16i8:
 ; AVX2-FAST:       # %bb.0:
-; AVX2-FAST-NEXT:    vpsubq {{.*}}(%rip), %ymm1, %ymm1
-; AVX2-FAST-NEXT:    vpsubq {{.*}}(%rip), %ymm0, %ymm0
-; AVX2-FAST-NEXT:    vpsubq {{.*}}(%rip), %ymm3, %ymm3
-; AVX2-FAST-NEXT:    vpsubq {{.*}}(%rip), %ymm2, %ymm2
 ; AVX2-FAST-NEXT:    vmovdqa {{.*#+}} ymm4 = [0,2,4,6,4,6,6,7]
 ; AVX2-FAST-NEXT:    vpermd %ymm2, %ymm4, %ymm2
 ; AVX2-FAST-NEXT:    vpermd %ymm3, %ymm4, %ymm3
 ; AVX2-FAST-NEXT:    vinserti128 $1, %xmm3, %ymm2, %ymm2
 ; AVX2-FAST-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
 ; AVX2-FAST-NEXT:    vpshufb %ymm3, %ymm2, %ymm2
 ; AVX2-FAST-NEXT:    vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
 ; AVX2-FAST-NEXT:    vmovdqa {{.*#+}} xmm5 = [255,255,255,255,255,255,255,255]
 ; AVX2-FAST-NEXT:    vpand %xmm5, %xmm2, %xmm2
 ; AVX2-FAST-NEXT:    vpermd %ymm0, %ymm4, %ymm0
 ; AVX2-FAST-NEXT:    vpermd %ymm1, %ymm4, %ymm1
 ; AVX2-FAST-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
 ; AVX2-FAST-NEXT:    vpshufb %ymm3, %ymm0, %ymm0
 ; AVX2-FAST-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
 ; AVX2-FAST-NEXT:    vpand %xmm5, %xmm0, %xmm0
 ; AVX2-FAST-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
+; AVX2-FAST-NEXT:    vpsubb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-FAST-NEXT:    vzeroupper
 ; AVX2-FAST-NEXT:    retq
 ;
 ; AVX512-LABEL: trunc_sub_const_v16i64_v16i8:
 ; AVX512:       # %bb.0:
-; AVX512-NEXT:    vpsubq {{.*}}(%rip), %zmm1, %zmm1
-; AVX512-NEXT:    vpsubq {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512-NEXT:    vpmovqd %zmm0, %ymm0
 ; AVX512-NEXT:    vpmovqd %zmm1, %ymm1
 ; AVX512-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
 ; AVX512-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512-NEXT:    vpsubb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
   %1 = sub <16 x i64> %a0, <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11, i64 12, i64 13, i64 14, i64 15>
   %2 = trunc <16 x i64> %1 to <16 x i8>
   ret <16 x i8> %2
 }
 
 define <16 x i8> @trunc_sub_const_v16i32_v16i8(<16 x i32> %a0) nounwind {
 ; SSE-LABEL: trunc_sub_const_v16i32_v16i8:
 ; SSE:       # %bb.0:
-; SSE-NEXT:    psubd {{.*}}(%rip), %xmm0
-; SSE-NEXT:    psubd {{.*}}(%rip), %xmm1
-; SSE-NEXT:    psubd {{.*}}(%rip), %xmm2
-; SSE-NEXT:    psubd {{.*}}(%rip), %xmm3
 ; SSE-NEXT:    movdqa {{.*#+}} xmm4 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
 ; SSE-NEXT:    pand %xmm4, %xmm3
 ; SSE-NEXT:    pand %xmm4, %xmm2
 ; SSE-NEXT:    packuswb %xmm3, %xmm2
 ; SSE-NEXT:    pand %xmm4, %xmm1
 ; SSE-NEXT:    pand %xmm4, %xmm0
 ; SSE-NEXT:    packuswb %xmm1, %xmm0
 ; SSE-NEXT:    packuswb %xmm2, %xmm0
+; SSE-NEXT:    psubb {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_sub_const_v16i32_v16i8:
 ; AVX1:       # %bb.0:
-; AVX1-NEXT:    vpsubd {{.*}}(%rip), %xmm0, %xmm2
-; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpsubd {{.*}}(%rip), %xmm0, %xmm0
-; AVX1-NEXT:    vpsubd {{.*}}(%rip), %xmm1, %xmm3
-; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm1
-; AVX1-NEXT:    vpsubd {{.*}}(%rip), %xmm1, %xmm1
-; AVX1-NEXT:    vbroadcastss {{.*#+}} xmm4 = [3.57331108E-43,3.57331108E-43,3.57331108E-43,3.57331108E-43]
-; AVX1-NEXT:    vpand %xmm4, %xmm1, %xmm1
-; AVX1-NEXT:    vpand %xmm4, %xmm3, %xmm3
-; AVX1-NEXT:    vpackusdw %xmm1, %xmm3, %xmm1
-; AVX1-NEXT:    vpand %xmm4, %xmm0, %xmm0
-; AVX1-NEXT:    vpand %xmm4, %xmm2, %xmm2
-; AVX1-NEXT:    vpackusdw %xmm0, %xmm2, %xmm0
+; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
+; AVX1-NEXT:    vbroadcastss {{.*#+}} xmm3 = [3.57331108E-43,3.57331108E-43,3.57331108E-43,3.57331108E-43]
+; AVX1-NEXT:    vandps %xmm3, %xmm2, %xmm2
+; AVX1-NEXT:    vandps %xmm3, %xmm1, %xmm1
+; AVX1-NEXT:    vpackusdw %xmm2, %xmm1, %xmm1
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
+; AVX1-NEXT:    vandps %xmm3, %xmm2, %xmm2
+; AVX1-NEXT:    vandps %xmm3, %xmm0, %xmm0
+; AVX1-NEXT:    vpackusdw %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vpackuswb %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpsubb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_sub_const_v16i32_v16i8:
 ; AVX2:       # %bb.0:
-; AVX2-NEXT:    vpsubd {{.*}}(%rip), %ymm0, %ymm0
-; AVX2-NEXT:    vpsubd {{.*}}(%rip), %ymm1, %ymm1
 ; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
 ; AVX2-NEXT:    vpshufb %ymm2, %ymm1, %ymm1
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
 ; AVX2-NEXT:    vmovdqa {{.*#+}} xmm3 = [255,255,255,255,255,255,255,255]
 ; AVX2-NEXT:    vpand %xmm3, %xmm1, %xmm1
 ; AVX2-NEXT:    vpshufb %ymm2, %ymm0, %ymm0
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
 ; AVX2-NEXT:    vpand %xmm3, %xmm0, %xmm0
 ; AVX2-NEXT:    vpackuswb %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpsubb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: trunc_sub_const_v16i32_v16i8:
 ; AVX512:       # %bb.0:
-; AVX512-NEXT:    vpsubd {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512-NEXT:    vpsubb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
   %1 = sub <16 x i32> %a0, <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
   %2 = trunc <16 x i32> %1 to <16 x i8>
   ret <16 x i8> %2
 }
 
 define <16 x i8> @trunc_sub_const_v16i16_v16i8(<16 x i16> %a0) nounwind {
 ; SSE-LABEL: trunc_sub_const_v16i16_v16i8:
 ; SSE:       # %bb.0:
-; SSE-NEXT:    psubw {{.*}}(%rip), %xmm0
-; SSE-NEXT:    psubw {{.*}}(%rip), %xmm1
 ; SSE-NEXT:    movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255]
 ; SSE-NEXT:    pand %xmm2, %xmm1
 ; SSE-NEXT:    pand %xmm2, %xmm0
 ; SSE-NEXT:    packuswb %xmm1, %xmm0
+; SSE-NEXT:    psubb {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_sub_const_v16i16_v16i8:
 ; AVX1:       # %bb.0:
-; AVX1-NEXT:    vpsubw {{.*}}(%rip), %xmm0, %xmm1
-; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpsubw {{.*}}(%rip), %xmm0, %xmm0
-; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255]
-; AVX1-NEXT:    vpand %xmm2, %xmm0, %xmm0
-; AVX1-NEXT:    vpand %xmm2, %xmm1, %xmm1
-; AVX1-NEXT:    vpackuswb %xmm0, %xmm1, %xmm0
+; AVX1-NEXT:    vandps {{.*}}(%rip), %ymm0, %ymm0
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
+; AVX1-NEXT:    vpackuswb %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpsubb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_sub_const_v16i16_v16i8:
 ; AVX2:       # %bb.0:
-; AVX2-NEXT:    vpsubw {{.*}}(%rip), %ymm0, %ymm0
 ; AVX2-NEXT:    vpand {{.*}}(%rip), %ymm0, %ymm0
 ; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm1
 ; AVX2-NEXT:    vpackuswb %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpsubb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512F-LABEL: trunc_sub_const_v16i16_v16i8:
 ; AVX512F:       # %bb.0:
-; AVX512F-NEXT:    vpsubw {{.*}}(%rip), %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, %xmm0
+; AVX512F-NEXT:    vpsubb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512F-NEXT:    vzeroupper
 ; AVX512F-NEXT:    retq
 ;
 ; AVX512BW-LABEL: trunc_sub_const_v16i16_v16i8:
 ; AVX512BW:       # %bb.0:
-; AVX512BW-NEXT:    vpsubw {{.*}}(%rip), %ymm0, %ymm0
+; AVX512BW-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
 ; AVX512BW-NEXT:    vpmovwb %zmm0, %ymm0
-; AVX512BW-NEXT:    # kill: def $xmm0 killed $xmm0 killed $ymm0
+; AVX512BW-NEXT:    vpsubb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512BW-NEXT:    vzeroupper
 ; AVX512BW-NEXT:    retq
 ;
 ; AVX512DQ-LABEL: trunc_sub_const_v16i16_v16i8:
 ; AVX512DQ:       # %bb.0:
-; AVX512DQ-NEXT:    vpsubw {{.*}}(%rip), %ymm0, %ymm0
 ; AVX512DQ-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
 ; AVX512DQ-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512DQ-NEXT:    vpsubb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512DQ-NEXT:    vzeroupper
 ; AVX512DQ-NEXT:    retq
   %1 = sub <16 x i16> %a0, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15>
   %2 = trunc <16 x i16> %1 to <16 x i8>
   ret <16 x i8> %2
 }
 
 define <16 x i8> @trunc_ext_sub_const_rhs_v16i16_v16i8(<16 x i8> %x) {

llvm/trunk/test/CodeGen/X86/vector-trunc-math.ll

 
 ;
 ; sub to constant
 ;
 
 define <4 x i32> @trunc_sub_const_v4i64_v4i32(<4 x i64> %a0) nounwind {
 ; SSE-LABEL: trunc_sub_const_v4i64_v4i32:
 ; SSE:       # %bb.0:
-; SSE-NEXT:    movl $1, %eax
-; SSE-NEXT:    movq %rax, %xmm2
-; SSE-NEXT:    pslldq {{.*#+}} xmm2 = zero,zero,zero,zero,zero,zero,zero,zero,xmm2[0,1,2,3,4,5,6,7]
-; SSE-NEXT:    psubq %xmm2, %xmm0
-; SSE-NEXT:    psubq {{.*}}(%rip), %xmm1
 ; SSE-NEXT:    shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
+; SSE-NEXT:    psubd {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_sub_const_v4i64_v4i32:
 ; AVX1:       # %bb.0:
-; AVX1-NEXT:    movl $1, %eax
-; AVX1-NEXT:    vmovq %rax, %xmm1
-; AVX1-NEXT:    vpslldq {{.*#+}} xmm1 = zero,zero,zero,zero,zero,zero,zero,zero,xmm1[0,1,2,3,4,5,6,7]
-; AVX1-NEXT:    vpsubq %xmm1, %xmm0, %xmm1
-; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpsubq {{.*}}(%rip), %xmm0, %xmm0
-; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm1[0,2],xmm0[0,2]
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
+; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
+; AVX1-NEXT:    vpsubd {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-SLOW-LABEL: trunc_sub_const_v4i64_v4i32:
 ; AVX2-SLOW:       # %bb.0:
-; AVX2-SLOW-NEXT:    vpsubq {{.*}}(%rip), %ymm0, %ymm0
 ; AVX2-SLOW-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
 ; AVX2-SLOW-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX2-SLOW-NEXT:    # kill: def $xmm0 killed $xmm0 killed $ymm0
+; AVX2-SLOW-NEXT:    vpsubd {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-SLOW-NEXT:    vzeroupper
 ; AVX2-SLOW-NEXT:    retq
 ;
 ; AVX2-FAST-LABEL: trunc_sub_const_v4i64_v4i32:
 ; AVX2-FAST:       # %bb.0:
-; AVX2-FAST-NEXT:    vpsubq {{.*}}(%rip), %ymm0, %ymm0
 ; AVX2-FAST-NEXT:    vmovdqa {{.*#+}} ymm1 = [0,2,4,6,4,6,6,7]
 ; AVX2-FAST-NEXT:    vpermd %ymm0, %ymm1, %ymm0
-; AVX2-FAST-NEXT:    # kill: def $xmm0 killed $xmm0 killed $ymm0
+; AVX2-FAST-NEXT:    vpsubd {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-FAST-NEXT:    vzeroupper
 ; AVX2-FAST-NEXT:    retq
 ;
 ; AVX512-LABEL: trunc_sub_const_v4i64_v4i32:
 ; AVX512:       # %bb.0:
-; AVX512-NEXT:    vpsubq {{.*}}(%rip), %ymm0, %ymm0
+; AVX512-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
 ; AVX512-NEXT:    vpmovqd %zmm0, %ymm0
-; AVX512-NEXT:    # kill: def $xmm0 killed $xmm0 killed $ymm0
+; AVX512-NEXT:    vpsubd {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
   %1 = sub <4 x i64> %a0, <i64 0, i64 1, i64 2, i64 3>
   %2 = trunc <4 x i64> %1 to <4 x i32>
   ret <4 x i32> %2
 }
 
 define <8 x i16> @trunc_sub_const_v8i64_v8i16(<8 x i64> %a0) nounwind {
 ; SSE-LABEL: trunc_sub_const_v8i64_v8i16:
 ; SSE:       # %bb.0:
-; SSE-NEXT:    movl $1, %eax
-; SSE-NEXT:    movq %rax, %xmm4
-; SSE-NEXT:    pslldq {{.*#+}} xmm4 = zero,zero,zero,zero,zero,zero,zero,zero,xmm4[0,1,2,3,4,5,6,7]
-; SSE-NEXT:    psubq %xmm4, %xmm0
-; SSE-NEXT:    psubq {{.*}}(%rip), %xmm1
-; SSE-NEXT:    psubq {{.*}}(%rip), %xmm2
-; SSE-NEXT:    psubq {{.*}}(%rip), %xmm3
-; SSE-NEXT:    pshufd {{.*#+}} xmm3 = xmm3[0,2,2,3]
-; SSE-NEXT:    pshuflw {{.*#+}} xmm3 = xmm3[0,1,0,2,4,5,6,7]
-; SSE-NEXT:    pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
-; SSE-NEXT:    pshuflw {{.*#+}} xmm2 = xmm2[0,1,0,2,4,5,6,7]
-; SSE-NEXT:    punpckldq {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1]
-; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
-; SSE-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
 ; SSE-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
 ; SSE-NEXT:    pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
+; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
+; SSE-NEXT:    pshuflw {{.*#+}} xmm4 = xmm0[0,2,2,3,4,5,6,7]
+; SSE-NEXT:    punpckldq {{.*#+}} xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1]
+; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm3[0,2,2,3]
+; SSE-NEXT:    pshuflw {{.*#+}} xmm1 = xmm0[0,1,0,2,4,5,6,7]
+; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm2[0,2,2,3]
+; SSE-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[0,1,0,2,4,5,6,7]
 ; SSE-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
-; SSE-NEXT:    movsd {{.*#+}} xmm2 = xmm0[0],xmm2[1]
-; SSE-NEXT:    movapd %xmm2, %xmm0
+; SSE-NEXT:    movsd {{.*#+}} xmm0 = xmm4[0],xmm0[1]
+; SSE-NEXT:    psubw {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_sub_const_v8i64_v8i16:
 ; AVX1:       # %bb.0:
-; AVX1-NEXT:    movl $1, %eax
-; AVX1-NEXT:    vmovq %rax, %xmm2
-; AVX1-NEXT:    vpslldq {{.*#+}} xmm2 = zero,zero,zero,zero,zero,zero,zero,zero,xmm2[0,1,2,3,4,5,6,7]
-; AVX1-NEXT:    vpsubq %xmm2, %xmm0, %xmm2
-; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpsubq {{.*}}(%rip), %xmm0, %xmm0
-; AVX1-NEXT:    vpsubq {{.*}}(%rip), %xmm1, %xmm3
-; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm1
-; AVX1-NEXT:    vpsubq {{.*}}(%rip), %xmm1, %xmm1
-; AVX1-NEXT:    vpxor %xmm4, %xmm4, %xmm4
-; AVX1-NEXT:    vpblendw {{.*#+}} xmm1 = xmm1[0],xmm4[1,2,3],xmm1[4],xmm4[5,6,7]
-; AVX1-NEXT:    vpblendw {{.*#+}} xmm3 = xmm3[0],xmm4[1,2,3],xmm3[4],xmm4[5,6,7]
-; AVX1-NEXT:    vpackusdw %xmm1, %xmm3, %xmm1
-; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0],xmm4[1,2,3],xmm0[4],xmm4[5,6,7]
-; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm2[0],xmm4[1,2,3],xmm2[4],xmm4[5,6,7]
-; AVX1-NEXT:    vpackusdw %xmm0, %xmm2, %xmm0
+; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
+; AVX1-NEXT:    vpxor %xmm3, %xmm3, %xmm3
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm2[0],xmm3[1,2,3],xmm2[4],xmm3[5,6,7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm1 = xmm1[0],xmm3[1,2,3],xmm1[4],xmm3[5,6,7]
+; AVX1-NEXT:    vpackusdw %xmm2, %xmm1, %xmm1
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm2[0],xmm3[1,2,3],xmm2[4],xmm3[5,6,7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0],xmm3[1,2,3],xmm0[4],xmm3[5,6,7]
+; AVX1-NEXT:    vpackusdw %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vpackusdw %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpsubw {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-SLOW-LABEL: trunc_sub_const_v8i64_v8i16:
 ; AVX2-SLOW:       # %bb.0:
-; AVX2-SLOW-NEXT:    vpsubq {{.*}}(%rip), %ymm1, %ymm1
-; AVX2-SLOW-NEXT:    vpsubq {{.*}}(%rip), %ymm0, %ymm0
 ; AVX2-SLOW-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
 ; AVX2-SLOW-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
 ; AVX2-SLOW-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
 ; AVX2-SLOW-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
 ; AVX2-SLOW-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
 ; AVX2-SLOW-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
 ; AVX2-SLOW-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX2-SLOW-NEXT:    # kill: def $xmm0 killed $xmm0 killed $ymm0
+; AVX2-SLOW-NEXT:    vpsubw {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-SLOW-NEXT:    vzeroupper
 ; AVX2-SLOW-NEXT:    retq
 ;
 ; AVX2-FAST-LABEL: trunc_sub_const_v8i64_v8i16:
 ; AVX2-FAST:       # %bb.0:
-; AVX2-FAST-NEXT:    vpsubq {{.*}}(%rip), %ymm1, %ymm1
-; AVX2-FAST-NEXT:    vpsubq {{.*}}(%rip), %ymm0, %ymm0
 ; AVX2-FAST-NEXT:    vmovdqa {{.*#+}} ymm2 = [0,2,4,6,4,6,6,7]
 ; AVX2-FAST-NEXT:    vpermd %ymm0, %ymm2, %ymm0
 ; AVX2-FAST-NEXT:    vpermd %ymm1, %ymm2, %ymm1
 ; AVX2-FAST-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
 ; AVX2-FAST-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
 ; AVX2-FAST-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX2-FAST-NEXT:    # kill: def $xmm0 killed $xmm0 killed $ymm0
+; AVX2-FAST-NEXT:    vpsubw {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-FAST-NEXT:    vzeroupper
 ; AVX2-FAST-NEXT:    retq
 ;
 ; AVX512-LABEL: trunc_sub_const_v8i64_v8i16:
 ; AVX512:       # %bb.0:
-; AVX512-NEXT:    vpsubq {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512-NEXT:    vpmovqw %zmm0, %xmm0
+; AVX512-NEXT:    vpsubw {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
   %1 = sub <8 x i64> %a0, <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7>
   %2 = trunc <8 x i64> %1 to <8 x i16>
   ret <8 x i16> %2
 }
 
 define <8 x i16> @trunc_sub_const_v8i32_v8i16(<8 x i32> %a0) nounwind {
 ; SSE-LABEL: trunc_sub_const_v8i32_v8i16:
 ; SSE:       # %bb.0:
-; SSE-NEXT:    psubd {{.*}}(%rip), %xmm0
-; SSE-NEXT:    psubd {{.*}}(%rip), %xmm1
 ; SSE-NEXT:    pslld $16, %xmm1
 ; SSE-NEXT:    psrad $16, %xmm1
 ; SSE-NEXT:    pslld $16, %xmm0
 ; SSE-NEXT:    psrad $16, %xmm0
 ; SSE-NEXT:    packssdw %xmm1, %xmm0
+; SSE-NEXT:    psubw {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_sub_const_v8i32_v8i16:
 ; AVX1:       # %bb.0:
-; AVX1-NEXT:    vpsubd {{.*}}(%rip), %xmm0, %xmm1
-; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpsubd {{.*}}(%rip), %xmm0, %xmm0
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
 ; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
-; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
-; AVX1-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; AVX1-NEXT:    vpsubw {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_sub_const_v8i32_v8i16:
 ; AVX2:       # %bb.0:
-; AVX2-NEXT:    vpsubd {{.*}}(%rip), %ymm0, %ymm0
 ; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX2-NEXT:    # kill: def $xmm0 killed $xmm0 killed $ymm0
+; AVX2-NEXT:    vpsubw {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: trunc_sub_const_v8i32_v8i16:
 ; AVX512:       # %bb.0:
-; AVX512-NEXT:    vpsubd {{.*}}(%rip), %ymm0, %ymm0
+; AVX512-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
 ; AVX512-NEXT:    vpmovdw %zmm0, %ymm0
-; AVX512-NEXT:    # kill: def $xmm0 killed $xmm0 killed $ymm0
+; AVX512-NEXT:    vpsubw {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
   %1 = sub <8 x i32> %a0, <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
   %2 = trunc <8 x i32> %1 to <8 x i16>
   ret <8 x i16> %2
 }
 
 define <16 x i8> @trunc_sub_const_v16i64_v16i8(<16 x i64> %a0) nounwind {
 ; SSE-LABEL: trunc_sub_const_v16i64_v16i8:
 ; SSE:       # %bb.0:
-; SSE-NEXT:    movl $1, %eax
-; SSE-NEXT:    movq %rax, %xmm8
-; SSE-NEXT:    pslldq {{.*#+}} xmm8 = zero,zero,zero,zero,zero,zero,zero,zero,xmm8[0,1,2,3,4,5,6,7]
-; SSE-NEXT:    psubq %xmm8, %xmm0
-; SSE-NEXT:    psubq {{.*}}(%rip), %xmm1
-; SSE-NEXT:    psubq {{.*}}(%rip), %xmm2
-; SSE-NEXT:    psubq {{.*}}(%rip), %xmm3
-; SSE-NEXT:    psubq {{.*}}(%rip), %xmm4
-; SSE-NEXT:    psubq {{.*}}(%rip), %xmm5
-; SSE-NEXT:    psubq {{.*}}(%rip), %xmm6
-; SSE-NEXT:    psubq {{.*}}(%rip), %xmm7
 ; SSE-NEXT:    movdqa {{.*#+}} xmm8 = [255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0]
 ; SSE-NEXT:    pand %xmm8, %xmm7
 ; SSE-NEXT:    pand %xmm8, %xmm6
 ; SSE-NEXT:    packuswb %xmm7, %xmm6
 ; SSE-NEXT:    pand %xmm8, %xmm5
 ; SSE-NEXT:    pand %xmm8, %xmm4
 ; SSE-NEXT:    packuswb %xmm5, %xmm4
 ; SSE-NEXT:    packuswb %xmm6, %xmm4
 ; SSE-NEXT:    pand %xmm8, %xmm3
 ; SSE-NEXT:    pand %xmm8, %xmm2
 ; SSE-NEXT:    packuswb %xmm3, %xmm2
 ; SSE-NEXT:    pand %xmm8, %xmm1
 ; SSE-NEXT:    pand %xmm8, %xmm0
 ; SSE-NEXT:    packuswb %xmm1, %xmm0
 ; SSE-NEXT:    packuswb %xmm2, %xmm0
 ; SSE-NEXT:    packuswb %xmm4, %xmm0
+; SSE-NEXT:    psubb {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_sub_const_v16i64_v16i8:
 ; AVX1:       # %bb.0:
-; AVX1-NEXT:    movl $1, %eax
-; AVX1-NEXT:    vmovq %rax, %xmm4
-; AVX1-NEXT:    vpslldq {{.*#+}} xmm4 = zero,zero,zero,zero,zero,zero,zero,zero,xmm4[0,1,2,3,4,5,6,7]
-; AVX1-NEXT:    vpsubq %xmm4, %xmm0, %xmm8
-; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpsubq {{.*}}(%rip), %xmm0, %xmm0
-; AVX1-NEXT:    vpsubq {{.*}}(%rip), %xmm1, %xmm5
-; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm1
-; AVX1-NEXT:    vpsubq {{.*}}(%rip), %xmm1, %xmm1
-; AVX1-NEXT:    vpsubq {{.*}}(%rip), %xmm2, %xmm6
-; AVX1-NEXT:    vextractf128 $1, %ymm2, %xmm2
-; AVX1-NEXT:    vpsubq {{.*}}(%rip), %xmm2, %xmm2
-; AVX1-NEXT:    vpsubq {{.*}}(%rip), %xmm3, %xmm7
-; AVX1-NEXT:    vextractf128 $1, %ymm3, %xmm3
-; AVX1-NEXT:    vpsubq {{.*}}(%rip), %xmm3, %xmm3
-; AVX1-NEXT:    vmovddup {{.*#+}} xmm4 = [1.2598673968951787E-321,1.2598673968951787E-321]
-; AVX1-NEXT:    # xmm4 = mem[0,0]
-; AVX1-NEXT:    vpand %xmm4, %xmm3, %xmm3
-; AVX1-NEXT:    vpand %xmm4, %xmm7, %xmm7
-; AVX1-NEXT:    vpackusdw %xmm3, %xmm7, %xmm3
-; AVX1-NEXT:    vpand %xmm4, %xmm2, %xmm2
-; AVX1-NEXT:    vpand %xmm4, %xmm6, %xmm6
-; AVX1-NEXT:    vpackusdw %xmm2, %xmm6, %xmm2
+; AVX1-NEXT:    vextractf128 $1, %ymm3, %xmm4
+; AVX1-NEXT:    vmovddup {{.*#+}} xmm5 = [1.2598673968951787E-321,1.2598673968951787E-321]
+; AVX1-NEXT:    # xmm5 = mem[0,0]
+; AVX1-NEXT:    vandpd %xmm5, %xmm4, %xmm4
+; AVX1-NEXT:    vandpd %xmm5, %xmm3, %xmm3
+; AVX1-NEXT:    vpackusdw %xmm4, %xmm3, %xmm3
+; AVX1-NEXT:    vextractf128 $1, %ymm2, %xmm4
+; AVX1-NEXT:    vandpd %xmm5, %xmm4, %xmm4
+; AVX1-NEXT:    vandpd %xmm5, %xmm2, %xmm2
+; AVX1-NEXT:    vpackusdw %xmm4, %xmm2, %xmm2
 ; AVX1-NEXT:    vpackusdw %xmm3, %xmm2, %xmm2
-; AVX1-NEXT:    vpand %xmm4, %xmm1, %xmm1
-; AVX1-NEXT:    vpand %xmm4, %xmm5, %xmm3
-; AVX1-NEXT:    vpackusdw %xmm1, %xmm3, %xmm1
-; AVX1-NEXT:    vpand %xmm4, %xmm0, %xmm0
-; AVX1-NEXT:    vpand %xmm4, %xmm8, %xmm3
-; AVX1-NEXT:    vpackusdw %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm3
+; AVX1-NEXT:    vandpd %xmm5, %xmm3, %xmm3
+; AVX1-NEXT:    vandpd %xmm5, %xmm1, %xmm1
+; AVX1-NEXT:    vpackusdw %xmm3, %xmm1, %xmm1
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm3
+; AVX1-NEXT:    vandpd %xmm5, %xmm3, %xmm3
+; AVX1-NEXT:    vandpd %xmm5, %xmm0, %xmm0
+; AVX1-NEXT:    vpackusdw %xmm3, %xmm0, %xmm0
 ; AVX1-NEXT:    vpackusdw %xmm1, %xmm0, %xmm0
 ; AVX1-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpsubb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-SLOW-LABEL: trunc_sub_const_v16i64_v16i8:
 ; AVX2-SLOW:       # %bb.0:
-; AVX2-SLOW-NEXT:    vpsubq {{.*}}(%rip), %ymm1, %ymm1
-; AVX2-SLOW-NEXT:    vpsubq {{.*}}(%rip), %ymm0, %ymm0
-; AVX2-SLOW-NEXT:    vpsubq {{.*}}(%rip), %ymm3, %ymm3
-; AVX2-SLOW-NEXT:    vpsubq {{.*}}(%rip), %ymm2, %ymm2
 ; AVX2-SLOW-NEXT:    vpshufd {{.*#+}} ymm2 = ymm2[0,2,2,3,4,6,6,7]
 ; AVX2-SLOW-NEXT:    vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
 ; AVX2-SLOW-NEXT:    vpshufd {{.*#+}} ymm3 = ymm3[0,2,2,3,4,6,6,7]
 ; AVX2-SLOW-NEXT:    vpermq {{.*#+}} ymm3 = ymm3[0,2,2,3]
 ; AVX2-SLOW-NEXT:    vinserti128 $1, %xmm3, %ymm2, %ymm2
 ; AVX2-SLOW-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
 ; AVX2-SLOW-NEXT:    vpshufb %ymm3, %ymm2, %ymm2
 ; AVX2-SLOW-NEXT:    vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
 ; AVX2-SLOW-NEXT:    vmovdqa {{.*#+}} xmm4 = [255,255,255,255,255,255,255,255]
 ; AVX2-SLOW-NEXT:    vpand %xmm4, %xmm2, %xmm2
 ; AVX2-SLOW-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
 ; AVX2-SLOW-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
 ; AVX2-SLOW-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
 ; AVX2-SLOW-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
 ; AVX2-SLOW-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
 ; AVX2-SLOW-NEXT:    vpshufb %ymm3, %ymm0, %ymm0
 ; AVX2-SLOW-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
 ; AVX2-SLOW-NEXT:    vpand %xmm4, %xmm0, %xmm0
 ; AVX2-SLOW-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
+; AVX2-SLOW-NEXT:    vpsubb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-SLOW-NEXT:    vzeroupper
 ; AVX2-SLOW-NEXT:    retq
 ;
 ; AVX2-FAST-LABEL: trunc_sub_const_v16i64_v16i8:
 ; AVX2-FAST:       # %bb.0:
-; AVX2-FAST-NEXT:    vpsubq {{.*}}(%rip), %ymm1, %ymm1
-; AVX2-FAST-NEXT:    vpsubq {{.*}}(%rip), %ymm0, %ymm0
-; AVX2-FAST-NEXT:    vpsubq {{.*}}(%rip), %ymm3, %ymm3
-; AVX2-FAST-NEXT:    vpsubq {{.*}}(%rip), %ymm2, %ymm2
 ; AVX2-FAST-NEXT:    vmovdqa {{.*#+}} ymm4 = [0,2,4,6,4,6,6,7]
 ; AVX2-FAST-NEXT:    vpermd %ymm2, %ymm4, %ymm2
 ; AVX2-FAST-NEXT:    vpermd %ymm3, %ymm4, %ymm3
 ; AVX2-FAST-NEXT:    vinserti128 $1, %xmm3, %ymm2, %ymm2
 ; AVX2-FAST-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
 ; AVX2-FAST-NEXT:    vpshufb %ymm3, %ymm2, %ymm2
 ; AVX2-FAST-NEXT:    vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
 ; AVX2-FAST-NEXT:    vmovdqa {{.*#+}} xmm5 = [255,255,255,255,255,255,255,255]
 ; AVX2-FAST-NEXT:    vpand %xmm5, %xmm2, %xmm2
 ; AVX2-FAST-NEXT:    vpermd %ymm0, %ymm4, %ymm0
 ; AVX2-FAST-NEXT:    vpermd %ymm1, %ymm4, %ymm1
 ; AVX2-FAST-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
 ; AVX2-FAST-NEXT:    vpshufb %ymm3, %ymm0, %ymm0
 ; AVX2-FAST-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
 ; AVX2-FAST-NEXT:    vpand %xmm5, %xmm0, %xmm0
 ; AVX2-FAST-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
+; AVX2-FAST-NEXT:    vpsubb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-FAST-NEXT:    vzeroupper
 ; AVX2-FAST-NEXT:    retq
 ;
 ; AVX512-LABEL: trunc_sub_const_v16i64_v16i8:
 ; AVX512:       # %bb.0:
-; AVX512-NEXT:    vpsubq {{.*}}(%rip), %zmm1, %zmm1
-; AVX512-NEXT:    vpsubq {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512-NEXT:    vpmovqd %zmm0, %ymm0
 ; AVX512-NEXT:    vpmovqd %zmm1, %ymm1
 ; AVX512-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
 ; AVX512-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512-NEXT:    vpsubb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
   %1 = sub <16 x i64> %a0, <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11, i64 12, i64 13, i64 14, i64 15>
   %2 = trunc <16 x i64> %1 to <16 x i8>
   ret <16 x i8> %2
 }
 
 define <16 x i8> @trunc_sub_const_v16i32_v16i8(<16 x i32> %a0) nounwind {
 ; SSE-LABEL: trunc_sub_const_v16i32_v16i8:
 ; SSE:       # %bb.0:
-; SSE-NEXT:    psubd {{.*}}(%rip), %xmm0
-; SSE-NEXT:    psubd {{.*}}(%rip), %xmm1
-; SSE-NEXT:    psubd {{.*}}(%rip), %xmm2
-; SSE-NEXT:    psubd {{.*}}(%rip), %xmm3
 ; SSE-NEXT:    movdqa {{.*#+}} xmm4 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
 ; SSE-NEXT:    pand %xmm4, %xmm3
 ; SSE-NEXT:    pand %xmm4, %xmm2
 ; SSE-NEXT:    packuswb %xmm3, %xmm2
 ; SSE-NEXT:    pand %xmm4, %xmm1
 ; SSE-NEXT:    pand %xmm4, %xmm0
 ; SSE-NEXT:    packuswb %xmm1, %xmm0
 ; SSE-NEXT:    packuswb %xmm2, %xmm0
+; SSE-NEXT:    psubb {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_sub_const_v16i32_v16i8:
 ; AVX1:       # %bb.0:
-; AVX1-NEXT:    vpsubd {{.*}}(%rip), %xmm0, %xmm2
-; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpsubd {{.*}}(%rip), %xmm0, %xmm0
-; AVX1-NEXT:    vpsubd {{.*}}(%rip), %xmm1, %xmm3
-; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm1
-; AVX1-NEXT:    vpsubd {{.*}}(%rip), %xmm1, %xmm1
-; AVX1-NEXT:    vbroadcastss {{.*#+}} xmm4 = [3.57331108E-43,3.57331108E-43,3.57331108E-43,3.57331108E-43]
-; AVX1-NEXT:    vpand %xmm4, %xmm1, %xmm1
-; AVX1-NEXT:    vpand %xmm4, %xmm3, %xmm3
-; AVX1-NEXT:    vpackusdw %xmm1, %xmm3, %xmm1
-; AVX1-NEXT:    vpand %xmm4, %xmm0, %xmm0
-; AVX1-NEXT:    vpand %xmm4, %xmm2, %xmm2
-; AVX1-NEXT:    vpackusdw %xmm0, %xmm2, %xmm0
+; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
+; AVX1-NEXT:    vbroadcastss {{.*#+}} xmm3 = [3.57331108E-43,3.57331108E-43,3.57331108E-43,3.57331108E-43]
+; AVX1-NEXT:    vandps %xmm3, %xmm2, %xmm2
+; AVX1-NEXT:    vandps %xmm3, %xmm1, %xmm1
+; AVX1-NEXT:    vpackusdw %xmm2, %xmm1, %xmm1
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
+; AVX1-NEXT:    vandps %xmm3, %xmm2, %xmm2
+; AVX1-NEXT:    vandps %xmm3, %xmm0, %xmm0
+; AVX1-NEXT:    vpackusdw %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vpackuswb %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpsubb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_sub_const_v16i32_v16i8:
 ; AVX2:       # %bb.0:
-; AVX2-NEXT:    vpsubd {{.*}}(%rip), %ymm0, %ymm0
-; AVX2-NEXT:    vpsubd {{.*}}(%rip), %ymm1, %ymm1
 ; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
 ; AVX2-NEXT:    vpshufb %ymm2, %ymm1, %ymm1
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
 ; AVX2-NEXT:    vmovdqa {{.*#+}} xmm3 = [255,255,255,255,255,255,255,255]
 ; AVX2-NEXT:    vpand %xmm3, %xmm1, %xmm1
 ; AVX2-NEXT:    vpshufb %ymm2, %ymm0, %ymm0
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
 ; AVX2-NEXT:    vpand %xmm3, %xmm0, %xmm0
 ; AVX2-NEXT:    vpackuswb %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpsubb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: trunc_sub_const_v16i32_v16i8:
 ; AVX512:       # %bb.0:
-; AVX512-NEXT:    vpsubd {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512-NEXT:    vpsubb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
   %1 = sub <16 x i32> %a0, <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
   %2 = trunc <16 x i32> %1 to <16 x i8>
   ret <16 x i8> %2
 }
 
 define <16 x i8> @trunc_sub_const_v16i16_v16i8(<16 x i16> %a0) nounwind {
 ; SSE-LABEL: trunc_sub_const_v16i16_v16i8:
 ; SSE:       # %bb.0:
-; SSE-NEXT:    psubw {{.*}}(%rip), %xmm0
-; SSE-NEXT:    psubw {{.*}}(%rip), %xmm1
 ; SSE-NEXT:    movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255]
 ; SSE-NEXT:    pand %xmm2, %xmm1
 ; SSE-NEXT:    pand %xmm2, %xmm0
 ; SSE-NEXT:    packuswb %xmm1, %xmm0
+; SSE-NEXT:    psubb {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_sub_const_v16i16_v16i8:
 ; AVX1:       # %bb.0:
-; AVX1-NEXT:    vpsubw {{.*}}(%rip), %xmm0, %xmm1
-; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpsubw {{.*}}(%rip), %xmm0, %xmm0
-; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255]
-; AVX1-NEXT:    vpand %xmm2, %xmm0, %xmm0
-; AVX1-NEXT:    vpand %xmm2, %xmm1, %xmm1
-; AVX1-NEXT:    vpackuswb %xmm0, %xmm1, %xmm0
+; AVX1-NEXT:    vandps {{.*}}(%rip), %ymm0, %ymm0
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
+; AVX1-NEXT:    vpackuswb %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpsubb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_sub_const_v16i16_v16i8:
 ; AVX2:       # %bb.0:
-; AVX2-NEXT:    vpsubw {{.*}}(%rip), %ymm0, %ymm0
 ; AVX2-NEXT:    vpand {{.*}}(%rip), %ymm0, %ymm0
 ; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm1
 ; AVX2-NEXT:    vpackuswb %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpsubb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512F-LABEL: trunc_sub_const_v16i16_v16i8:
 ; AVX512F:       # %bb.0:
-; AVX512F-NEXT:    vpsubw {{.*}}(%rip), %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, %xmm0
+; AVX512F-NEXT:    vpsubb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512F-NEXT:    vzeroupper
 ; AVX512F-NEXT:    retq
 ;
 ; AVX512BW-LABEL: trunc_sub_const_v16i16_v16i8:
 ; AVX512BW:       # %bb.0:
-; AVX512BW-NEXT:    vpsubw {{.*}}(%rip), %ymm0, %ymm0
+; AVX512BW-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
 ; AVX512BW-NEXT:    vpmovwb %zmm0, %ymm0
-; AVX512BW-NEXT:    # kill: def $xmm0 killed $xmm0 killed $ymm0
+; AVX512BW-NEXT:    vpsubb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512BW-NEXT:    vzeroupper
 ; AVX512BW-NEXT:    retq
 ;
 ; AVX512DQ-LABEL: trunc_sub_const_v16i16_v16i8:
 ; AVX512DQ:       # %bb.0:
-; AVX512DQ-NEXT:    vpsubw {{.*}}(%rip), %ymm0, %ymm0
 ; AVX512DQ-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
 ; AVX512DQ-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512DQ-NEXT:    vpsubb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512DQ-NEXT:    vzeroupper
 ; AVX512DQ-NEXT:    retq
   %1 = sub <16 x i16> %a0, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15>
   %2 = trunc <16 x i16> %1 to <16 x i8>
   ret <16 x i8> %2
 }
 
 define <16 x i8> @trunc_ext_sub_const_rhs_v16i16_v16i8(<16 x i8> %x) {