[llvm] a5212b5 - [X86][SSE] combineSubToSubus - remove SSE2 early-out.
Simon Pilgrim via llvm-commits
llvm-commits at lists.llvm.org
Tue Jan 12 04:52:57 PST 2021
Author: Simon Pilgrim
Date: 2021-01-12T12:52:11Z
New Revision: a5212b5c91cc699052125b8a3428ffe0c123837d
URL: https://github.com/llvm/llvm-project/commit/a5212b5c91cc699052125b8a3428ffe0c123837d
DIFF: https://github.com/llvm/llvm-project/commit/a5212b5c91cc699052125b8a3428ffe0c123837d.diff
LOG: [X86][SSE] combineSubToSubus - remove SSE2 early-out.
SSE2 truncation codegen has improved over the past few years (mainly due to better shuffle lowering/combining and computeKnownBits) - its no longer necessary to early-out from v8i32/v8i64 truncations.
This was noticed while looking at completing PR40111 and moving combineSubToSubus to DAGCombine entirely.
Added:
Modified:
llvm/lib/Target/X86/X86ISelLowering.cpp
llvm/test/CodeGen/X86/psubus.ll
Removed:
################################################################################
diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index 2f9de876a87f..e3a94f1c23ab 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -48754,11 +48754,10 @@ static SDValue combineSubToSubus(SDNode *N, SelectionDAG &DAG,
if (!VT.isVector())
return SDValue();
- // PSUBUS is supported, starting from SSE2, but truncation for v8i32
- // is only worth it with SSSE3 (PSHUFB).
+ // PSUBUS is supported, starting from SSE2.
EVT EltVT = VT.getVectorElementType();
- if (!(Subtarget.hasSSE2() && (EltVT == MVT::i8 || EltVT == MVT::i16)) &&
- !(Subtarget.hasSSSE3() && (VT == MVT::v8i32 || VT == MVT::v8i64)) &&
+ if (!(Subtarget.hasSSE2() && (EltVT == MVT::i8 || EltVT == MVT::i16 ||
+ VT == MVT::v8i32 || VT == MVT::v8i64)) &&
!(Subtarget.useBWIRegs() && (VT == MVT::v16i32)))
return SDValue();
@@ -48795,8 +48794,8 @@ static SDValue combineSubToSubus(SDNode *N, SelectionDAG &DAG,
SDValue MinLHS = Op1.getOperand(0).getOperand(0);
SDValue MinRHS = Op1.getOperand(0).getOperand(1);
EVT TruncVT = Op1.getOperand(0).getValueType();
- if (!(Subtarget.hasSSSE3() && (TruncVT == MVT::v8i32 ||
- TruncVT == MVT::v8i64)) &&
+ if (!(Subtarget.hasSSE2() &&
+ (TruncVT == MVT::v8i32 || TruncVT == MVT::v8i64)) &&
!(Subtarget.useBWIRegs() && (TruncVT == MVT::v16i32)))
return SDValue();
SDValue OpToSaturate;
@@ -48835,7 +48834,7 @@ static SDValue combineSubToSubus(SDNode *N, SelectionDAG &DAG,
// values, or first 48 bits for 64 bit values.
KnownBits Known = DAG.computeKnownBits(SubusLHS);
unsigned NumZeros = Known.countMinLeadingZeros();
- if ((VT == MVT::v8i64 && NumZeros < 48) || NumZeros < 16)
+ if (NumZeros < (VT.getScalarSizeInBits() - 16))
return SDValue();
EVT ExtType = SubusLHS.getValueType();
diff --git a/llvm/test/CodeGen/X86/psubus.ll b/llvm/test/CodeGen/X86/psubus.ll
index 92283dba25b8..906af5e17211 100644
--- a/llvm/test/CodeGen/X86/psubus.ll
+++ b/llvm/test/CodeGen/X86/psubus.ll
@@ -1382,33 +1382,32 @@ vector.ph:
define <8 x i16> @psubus_8i32_max(<8 x i16> %x, <8 x i32> %y) nounwind {
; SSE2-LABEL: psubus_8i32_max:
; SSE2: # %bb.0: # %vector.ph
-; SSE2-NEXT: movdqa %xmm0, %xmm3
-; SSE2-NEXT: pxor %xmm4, %xmm4
-; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1],xmm0[2],xmm4[2],xmm0[3],xmm4[3]
-; SSE2-NEXT: punpckhwd {{.*#+}} xmm3 = xmm3[4],xmm4[4],xmm3[5],xmm4[5],xmm3[6],xmm4[6],xmm3[7],xmm4[7]
-; SSE2-NEXT: movdqa {{.*#+}} xmm5 = [2147483648,2147483648,2147483648,2147483648]
-; SSE2-NEXT: movdqa %xmm2, %xmm6
-; SSE2-NEXT: pxor %xmm5, %xmm6
-; SSE2-NEXT: movdqa %xmm3, %xmm4
-; SSE2-NEXT: por %xmm5, %xmm4
-; SSE2-NEXT: pcmpgtd %xmm6, %xmm4
-; SSE2-NEXT: pand %xmm4, %xmm3
-; SSE2-NEXT: pandn %xmm2, %xmm4
-; SSE2-NEXT: por %xmm3, %xmm4
-; SSE2-NEXT: movdqa %xmm1, %xmm3
-; SSE2-NEXT: pxor %xmm5, %xmm3
-; SSE2-NEXT: por %xmm0, %xmm5
+; SSE2-NEXT: movdqa {{.*#+}} xmm3 = [2147483648,2147483648,2147483648,2147483648]
+; SSE2-NEXT: movdqa %xmm2, %xmm4
+; SSE2-NEXT: pxor %xmm3, %xmm4
+; SSE2-NEXT: movdqa {{.*#+}} xmm5 = [2147549183,2147549183,2147549183,2147549183]
+; SSE2-NEXT: movdqa %xmm5, %xmm6
+; SSE2-NEXT: pcmpgtd %xmm4, %xmm6
+; SSE2-NEXT: pcmpeqd %xmm4, %xmm4
+; SSE2-NEXT: pand %xmm6, %xmm2
+; SSE2-NEXT: pxor %xmm4, %xmm6
+; SSE2-NEXT: por %xmm2, %xmm6
+; SSE2-NEXT: pslld $16, %xmm6
+; SSE2-NEXT: psrad $16, %xmm6
+; SSE2-NEXT: pxor %xmm1, %xmm3
; SSE2-NEXT: pcmpgtd %xmm3, %xmm5
-; SSE2-NEXT: pand %xmm5, %xmm0
-; SSE2-NEXT: pandn %xmm1, %xmm5
-; SSE2-NEXT: por %xmm5, %xmm0
-; SSE2-NEXT: psubd %xmm1, %xmm0
-; SSE2-NEXT: psubd %xmm2, %xmm4
-; SSE2-NEXT: pslld $16, %xmm4
-; SSE2-NEXT: psrad $16, %xmm4
-; SSE2-NEXT: pslld $16, %xmm0
+; SSE2-NEXT: pxor %xmm5, %xmm4
+; SSE2-NEXT: pand %xmm1, %xmm5
+; SSE2-NEXT: por %xmm4, %xmm5
+; SSE2-NEXT: pslld $16, %xmm5
+; SSE2-NEXT: psrad $16, %xmm5
+; SSE2-NEXT: packssdw %xmm6, %xmm5
+; SSE2-NEXT: psubusw %xmm5, %xmm0
+; SSE2-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
+; SSE2-NEXT: psrad $16, %xmm1
+; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
; SSE2-NEXT: psrad $16, %xmm0
-; SSE2-NEXT: packssdw %xmm4, %xmm0
+; SSE2-NEXT: packssdw %xmm1, %xmm0
; SSE2-NEXT: retq
;
; SSSE3-LABEL: psubus_8i32_max:
@@ -1483,91 +1482,72 @@ vector.ph:
define <8 x i16> @psubus_8i64_max(<8 x i16> %x, <8 x i64> %y) nounwind {
; SSE2-LABEL: psubus_8i64_max:
; SSE2: # %bb.0: # %vector.ph
-; SSE2-NEXT: pxor %xmm5, %xmm5
-; SSE2-NEXT: movdqa %xmm0, %xmm10
-; SSE2-NEXT: punpckhwd {{.*#+}} xmm10 = xmm10[4],xmm5[4],xmm10[5],xmm5[5],xmm10[6],xmm5[6],xmm10[7],xmm5[7]
-; SSE2-NEXT: movdqa %xmm10, %xmm8
-; SSE2-NEXT: punpckldq {{.*#+}} xmm8 = xmm8[0],xmm5[0],xmm8[1],xmm5[1]
-; SSE2-NEXT: punpckhdq {{.*#+}} xmm10 = xmm10[2],xmm5[2],xmm10[3],xmm5[3]
-; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm5[0],xmm0[1],xmm5[1],xmm0[2],xmm5[2],xmm0[3],xmm5[3]
-; SSE2-NEXT: movdqa %xmm0, %xmm9
-; SSE2-NEXT: punpckldq {{.*#+}} xmm9 = xmm9[0],xmm5[0],xmm9[1],xmm5[1]
-; SSE2-NEXT: punpckhdq {{.*#+}} xmm0 = xmm0[2],xmm5[2],xmm0[3],xmm5[3]
-; SSE2-NEXT: movdqa {{.*#+}} xmm11 = [9223372039002259456,9223372039002259456]
-; SSE2-NEXT: movdqa %xmm2, %xmm6
-; SSE2-NEXT: pxor %xmm11, %xmm6
-; SSE2-NEXT: movdqa %xmm0, %xmm7
-; SSE2-NEXT: por %xmm11, %xmm7
-; SSE2-NEXT: movdqa %xmm7, %xmm5
-; SSE2-NEXT: pcmpgtd %xmm6, %xmm5
-; SSE2-NEXT: pshufd {{.*#+}} xmm12 = xmm5[0,0,2,2]
-; SSE2-NEXT: pcmpeqd %xmm6, %xmm7
-; SSE2-NEXT: pshufd {{.*#+}} xmm7 = xmm7[1,1,3,3]
-; SSE2-NEXT: pand %xmm12, %xmm7
-; SSE2-NEXT: pshufd {{.*#+}} xmm13 = xmm5[1,1,3,3]
-; SSE2-NEXT: por %xmm7, %xmm13
-; SSE2-NEXT: pand %xmm13, %xmm0
-; SSE2-NEXT: pandn %xmm2, %xmm13
-; SSE2-NEXT: por %xmm0, %xmm13
-; SSE2-NEXT: movdqa %xmm1, %xmm0
-; SSE2-NEXT: pxor %xmm11, %xmm0
-; SSE2-NEXT: movdqa %xmm9, %xmm5
-; SSE2-NEXT: por %xmm11, %xmm5
-; SSE2-NEXT: movdqa %xmm5, %xmm7
-; SSE2-NEXT: pcmpgtd %xmm0, %xmm7
-; SSE2-NEXT: pshufd {{.*#+}} xmm12 = xmm7[0,0,2,2]
-; SSE2-NEXT: pcmpeqd %xmm0, %xmm5
-; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm5[1,1,3,3]
-; SSE2-NEXT: pand %xmm12, %xmm5
-; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm7[1,1,3,3]
-; SSE2-NEXT: por %xmm5, %xmm0
-; SSE2-NEXT: pand %xmm0, %xmm9
-; SSE2-NEXT: pandn %xmm1, %xmm0
-; SSE2-NEXT: por %xmm9, %xmm0
-; SSE2-NEXT: movdqa %xmm4, %xmm5
-; SSE2-NEXT: pxor %xmm11, %xmm5
-; SSE2-NEXT: movdqa %xmm10, %xmm7
-; SSE2-NEXT: por %xmm11, %xmm7
-; SSE2-NEXT: movdqa %xmm7, %xmm6
-; SSE2-NEXT: pcmpgtd %xmm5, %xmm6
-; SSE2-NEXT: pshufd {{.*#+}} xmm9 = xmm6[0,0,2,2]
-; SSE2-NEXT: pcmpeqd %xmm5, %xmm7
-; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm7[1,1,3,3]
-; SSE2-NEXT: pand %xmm9, %xmm5
-; SSE2-NEXT: pshufd {{.*#+}} xmm7 = xmm6[1,1,3,3]
-; SSE2-NEXT: por %xmm5, %xmm7
-; SSE2-NEXT: pand %xmm7, %xmm10
-; SSE2-NEXT: pandn %xmm4, %xmm7
-; SSE2-NEXT: por %xmm10, %xmm7
-; SSE2-NEXT: movdqa %xmm3, %xmm5
-; SSE2-NEXT: pxor %xmm11, %xmm5
-; SSE2-NEXT: por %xmm8, %xmm11
-; SSE2-NEXT: movdqa %xmm11, %xmm6
-; SSE2-NEXT: pcmpgtd %xmm5, %xmm6
+; SSE2-NEXT: movdqa {{.*#+}} xmm5 = [9223372039002259456,9223372039002259456]
+; SSE2-NEXT: movdqa %xmm2, %xmm7
+; SSE2-NEXT: pxor %xmm5, %xmm7
+; SSE2-NEXT: movdqa {{.*#+}} xmm8 = [9223372039002324991,9223372039002324991]
+; SSE2-NEXT: movdqa %xmm8, %xmm6
+; SSE2-NEXT: pcmpgtd %xmm7, %xmm6
; SSE2-NEXT: pshufd {{.*#+}} xmm9 = xmm6[0,0,2,2]
-; SSE2-NEXT: pcmpeqd %xmm5, %xmm11
-; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm11[1,1,3,3]
-; SSE2-NEXT: pand %xmm9, %xmm5
+; SSE2-NEXT: pcmpeqd %xmm8, %xmm7
+; SSE2-NEXT: pshufd {{.*#+}} xmm7 = xmm7[1,1,3,3]
+; SSE2-NEXT: pand %xmm9, %xmm7
; SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm6[1,1,3,3]
-; SSE2-NEXT: por %xmm5, %xmm6
-; SSE2-NEXT: pand %xmm6, %xmm8
-; SSE2-NEXT: pandn %xmm3, %xmm6
-; SSE2-NEXT: por %xmm8, %xmm6
-; SSE2-NEXT: psubq %xmm3, %xmm6
-; SSE2-NEXT: psubq %xmm4, %xmm7
-; SSE2-NEXT: psubq %xmm1, %xmm0
-; SSE2-NEXT: psubq %xmm2, %xmm13
-; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm13[0,2,2,3]
+; SSE2-NEXT: por %xmm7, %xmm6
+; SSE2-NEXT: movdqa {{.*#+}} xmm9 = [65535,65535]
+; SSE2-NEXT: pand %xmm6, %xmm2
+; SSE2-NEXT: pandn %xmm9, %xmm6
+; SSE2-NEXT: por %xmm2, %xmm6
+; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm6[0,2,2,3]
+; SSE2-NEXT: pshuflw {{.*#+}} xmm10 = xmm2[0,2,2,3,4,5,6,7]
+; SSE2-NEXT: movdqa %xmm1, %xmm6
+; SSE2-NEXT: pxor %xmm5, %xmm6
+; SSE2-NEXT: movdqa %xmm8, %xmm7
+; SSE2-NEXT: pcmpgtd %xmm6, %xmm7
+; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm7[0,0,2,2]
+; SSE2-NEXT: pcmpeqd %xmm8, %xmm6
+; SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm6[1,1,3,3]
+; SSE2-NEXT: pand %xmm2, %xmm6
+; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm7[1,1,3,3]
+; SSE2-NEXT: por %xmm6, %xmm2
+; SSE2-NEXT: pand %xmm2, %xmm1
+; SSE2-NEXT: pandn %xmm9, %xmm2
+; SSE2-NEXT: por %xmm1, %xmm2
+; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm2[0,2,2,3]
; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
-; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
-; SSE2-NEXT: pshuflw {{.*#+}} xmm2 = xmm0[0,2,2,3,4,5,6,7]
-; SSE2-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
-; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm7[0,2,2,3]
-; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm0[0,1,0,2,4,5,6,7]
-; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm6[0,2,2,3]
-; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,1,0,2,4,5,6,7]
-; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
-; SSE2-NEXT: movsd {{.*#+}} xmm0 = xmm2[0],xmm0[1]
+; SSE2-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm10[0],xmm1[1],xmm10[1]
+; SSE2-NEXT: movdqa %xmm4, %xmm2
+; SSE2-NEXT: pxor %xmm5, %xmm2
+; SSE2-NEXT: movdqa %xmm8, %xmm6
+; SSE2-NEXT: pcmpgtd %xmm2, %xmm6
+; SSE2-NEXT: pshufd {{.*#+}} xmm7 = xmm6[0,0,2,2]
+; SSE2-NEXT: pcmpeqd %xmm8, %xmm2
+; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[1,1,3,3]
+; SSE2-NEXT: pand %xmm7, %xmm2
+; SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm6[1,1,3,3]
+; SSE2-NEXT: por %xmm2, %xmm6
+; SSE2-NEXT: pand %xmm6, %xmm4
+; SSE2-NEXT: pandn %xmm9, %xmm6
+; SSE2-NEXT: por %xmm4, %xmm6
+; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm6[0,2,2,3]
+; SSE2-NEXT: pshuflw {{.*#+}} xmm2 = xmm2[0,1,0,2,4,5,6,7]
+; SSE2-NEXT: pxor %xmm3, %xmm5
+; SSE2-NEXT: movdqa %xmm8, %xmm4
+; SSE2-NEXT: pcmpgtd %xmm5, %xmm4
+; SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm4[0,0,2,2]
+; SSE2-NEXT: pcmpeqd %xmm8, %xmm5
+; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm5[1,1,3,3]
+; SSE2-NEXT: pand %xmm6, %xmm5
+; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm4[1,1,3,3]
+; SSE2-NEXT: por %xmm5, %xmm4
+; SSE2-NEXT: pand %xmm4, %xmm3
+; SSE2-NEXT: pandn %xmm9, %xmm4
+; SSE2-NEXT: por %xmm3, %xmm4
+; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm4[0,2,2,3]
+; SSE2-NEXT: pshuflw {{.*#+}} xmm3 = xmm3[0,1,0,2,4,5,6,7]
+; SSE2-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm2[0],xmm3[1],xmm2[1]
+; SSE2-NEXT: movsd {{.*#+}} xmm3 = xmm1[0],xmm3[1]
+; SSE2-NEXT: psubusw %xmm3, %xmm0
; SSE2-NEXT: retq
;
; SSSE3-LABEL: psubus_8i64_max:
@@ -1943,35 +1923,32 @@ vector.ph:
define <8 x i16> @psubus_i16_i32_max_swapped(<8 x i16> %x, <8 x i32> %y) nounwind {
; SSE2-LABEL: psubus_i16_i32_max_swapped:
; SSE2: # %bb.0: # %vector.ph
-; SSE2-NEXT: pxor %xmm3, %xmm3
-; SSE2-NEXT: movdqa %xmm0, %xmm4
-; SSE2-NEXT: punpcklwd {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1],xmm4[2],xmm3[2],xmm4[3],xmm3[3]
-; SSE2-NEXT: punpckhwd {{.*#+}} xmm0 = xmm0[4],xmm3[4],xmm0[5],xmm3[5],xmm0[6],xmm3[6],xmm0[7],xmm3[7]
-; SSE2-NEXT: movdqa {{.*#+}} xmm5 = [2147483648,2147483648,2147483648,2147483648]
-; SSE2-NEXT: movdqa %xmm2, %xmm3
-; SSE2-NEXT: pxor %xmm5, %xmm3
-; SSE2-NEXT: movdqa %xmm0, %xmm6
-; SSE2-NEXT: por %xmm5, %xmm6
-; SSE2-NEXT: pcmpgtd %xmm6, %xmm3
-; SSE2-NEXT: movdqa %xmm2, %xmm6
-; SSE2-NEXT: pand %xmm3, %xmm6
-; SSE2-NEXT: pandn %xmm0, %xmm3
-; SSE2-NEXT: por %xmm6, %xmm3
-; SSE2-NEXT: movdqa %xmm1, %xmm0
-; SSE2-NEXT: pxor %xmm5, %xmm0
+; SSE2-NEXT: movdqa {{.*#+}} xmm3 = [2147483648,2147483648,2147483648,2147483648]
+; SSE2-NEXT: movdqa %xmm2, %xmm4
+; SSE2-NEXT: pxor %xmm3, %xmm4
+; SSE2-NEXT: movdqa {{.*#+}} xmm5 = [2147549183,2147549183,2147549183,2147549183]
+; SSE2-NEXT: movdqa %xmm5, %xmm6
+; SSE2-NEXT: pcmpgtd %xmm4, %xmm6
+; SSE2-NEXT: pcmpeqd %xmm4, %xmm4
+; SSE2-NEXT: pand %xmm6, %xmm2
+; SSE2-NEXT: pxor %xmm4, %xmm6
+; SSE2-NEXT: por %xmm2, %xmm6
+; SSE2-NEXT: pslld $16, %xmm6
+; SSE2-NEXT: psrad $16, %xmm6
+; SSE2-NEXT: pxor %xmm1, %xmm3
+; SSE2-NEXT: pcmpgtd %xmm3, %xmm5
+; SSE2-NEXT: pxor %xmm5, %xmm4
+; SSE2-NEXT: pand %xmm1, %xmm5
; SSE2-NEXT: por %xmm4, %xmm5
-; SSE2-NEXT: pcmpgtd %xmm5, %xmm0
-; SSE2-NEXT: movdqa %xmm1, %xmm5
-; SSE2-NEXT: pand %xmm0, %xmm5
-; SSE2-NEXT: pandn %xmm4, %xmm0
-; SSE2-NEXT: por %xmm5, %xmm0
-; SSE2-NEXT: psubd %xmm1, %xmm0
-; SSE2-NEXT: psubd %xmm2, %xmm3
-; SSE2-NEXT: pslld $16, %xmm3
-; SSE2-NEXT: psrad $16, %xmm3
-; SSE2-NEXT: pslld $16, %xmm0
+; SSE2-NEXT: pslld $16, %xmm5
+; SSE2-NEXT: psrad $16, %xmm5
+; SSE2-NEXT: packssdw %xmm6, %xmm5
+; SSE2-NEXT: psubusw %xmm5, %xmm0
+; SSE2-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
+; SSE2-NEXT: psrad $16, %xmm1
+; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
; SSE2-NEXT: psrad $16, %xmm0
-; SSE2-NEXT: packssdw %xmm3, %xmm0
+; SSE2-NEXT: packssdw %xmm1, %xmm0
; SSE2-NEXT: retq
;
; SSSE3-LABEL: psubus_i16_i32_max_swapped:
@@ -2046,33 +2023,27 @@ vector.ph:
define <8 x i16> @psubus_i16_i32_min(<8 x i16> %x, <8 x i32> %y) nounwind {
; SSE2-LABEL: psubus_i16_i32_min:
; SSE2: # %bb.0: # %vector.ph
-; SSE2-NEXT: pxor %xmm3, %xmm3
-; SSE2-NEXT: movdqa %xmm0, %xmm4
-; SSE2-NEXT: punpckhwd {{.*#+}} xmm4 = xmm4[4],xmm3[4],xmm4[5],xmm3[5],xmm4[6],xmm3[6],xmm4[7],xmm3[7]
-; SSE2-NEXT: movdqa %xmm0, %xmm5
-; SSE2-NEXT: punpcklwd {{.*#+}} xmm5 = xmm5[0],xmm3[0],xmm5[1],xmm3[1],xmm5[2],xmm3[2],xmm5[3],xmm3[3]
-; SSE2-NEXT: movdqa {{.*#+}} xmm6 = [2147483648,2147483648,2147483648,2147483648]
-; SSE2-NEXT: movdqa %xmm1, %xmm3
-; SSE2-NEXT: pxor %xmm6, %xmm3
-; SSE2-NEXT: movdqa %xmm5, %xmm7
-; SSE2-NEXT: por %xmm6, %xmm7
-; SSE2-NEXT: pcmpgtd %xmm7, %xmm3
-; SSE2-NEXT: pand %xmm3, %xmm5
-; SSE2-NEXT: pandn %xmm1, %xmm3
-; SSE2-NEXT: por %xmm5, %xmm3
-; SSE2-NEXT: movdqa %xmm2, %xmm1
-; SSE2-NEXT: pxor %xmm6, %xmm1
-; SSE2-NEXT: por %xmm4, %xmm6
-; SSE2-NEXT: pcmpgtd %xmm6, %xmm1
-; SSE2-NEXT: pand %xmm1, %xmm4
-; SSE2-NEXT: pandn %xmm2, %xmm1
-; SSE2-NEXT: por %xmm4, %xmm1
-; SSE2-NEXT: pslld $16, %xmm1
-; SSE2-NEXT: psrad $16, %xmm1
-; SSE2-NEXT: pslld $16, %xmm3
-; SSE2-NEXT: psrad $16, %xmm3
-; SSE2-NEXT: packssdw %xmm1, %xmm3
-; SSE2-NEXT: psubw %xmm3, %xmm0
+; SSE2-NEXT: movdqa {{.*#+}} xmm3 = [2147483648,2147483648,2147483648,2147483648]
+; SSE2-NEXT: movdqa %xmm2, %xmm4
+; SSE2-NEXT: pxor %xmm3, %xmm4
+; SSE2-NEXT: movdqa {{.*#+}} xmm5 = [2147549183,2147549183,2147549183,2147549183]
+; SSE2-NEXT: movdqa %xmm5, %xmm6
+; SSE2-NEXT: pcmpgtd %xmm4, %xmm6
+; SSE2-NEXT: pcmpeqd %xmm4, %xmm4
+; SSE2-NEXT: pand %xmm6, %xmm2
+; SSE2-NEXT: pxor %xmm4, %xmm6
+; SSE2-NEXT: por %xmm2, %xmm6
+; SSE2-NEXT: pslld $16, %xmm6
+; SSE2-NEXT: psrad $16, %xmm6
+; SSE2-NEXT: pxor %xmm1, %xmm3
+; SSE2-NEXT: pcmpgtd %xmm3, %xmm5
+; SSE2-NEXT: pxor %xmm5, %xmm4
+; SSE2-NEXT: pand %xmm1, %xmm5
+; SSE2-NEXT: por %xmm4, %xmm5
+; SSE2-NEXT: pslld $16, %xmm5
+; SSE2-NEXT: psrad $16, %xmm5
+; SSE2-NEXT: packssdw %xmm6, %xmm5
+; SSE2-NEXT: psubusw %xmm5, %xmm0
; SSE2-NEXT: retq
;
; SSSE3-LABEL: psubus_i16_i32_min:
More information about the llvm-commits
mailing list