[llvm] [X86] Use NSW/NUW flags on ISD::TRUNCATE nodes to improve X86 PACKSS/PACKUS lowering (PR #123956)
via llvm-commits
llvm-commits at lists.llvm.org
Wed Jan 22 07:26:15 PST 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-x86
Author: Simon Pilgrim (RKSimon)
<details>
<summary>Changes</summary>
If the NSW/NUW flags are present, then we can assume the source value is within bounds and saturation will not occur with the PACKSS/PACKUS instructions.
Fixes #<!-- -->87485
---
Patch is 66.13 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/123956.diff
2 Files Affected:
- (modified) llvm/lib/Target/X86/X86ISelLowering.cpp (+18-17)
- (modified) llvm/test/CodeGen/X86/vector-trunc-nowrap.ll (+201-820)
``````````diff
diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index a956074e50d86f..faea2adf520892 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -20819,7 +20819,8 @@ static SDValue truncateVectorWithPACKSS(EVT DstVT, SDValue In, const SDLoc &DL,
static SDValue matchTruncateWithPACK(unsigned &PackOpcode, EVT DstVT,
SDValue In, const SDLoc &DL,
SelectionDAG &DAG,
- const X86Subtarget &Subtarget) {
+ const X86Subtarget &Subtarget,
+ const SDNodeFlags Flags = SDNodeFlags()) {
// Requires SSE2.
if (!Subtarget.hasSSE2())
return SDValue();
@@ -20865,7 +20866,8 @@ static SDValue matchTruncateWithPACK(unsigned &PackOpcode, EVT DstVT,
// e.g. Masks, zext_in_reg, etc.
// Pre-SSE41 we can only use PACKUSWB.
KnownBits Known = DAG.computeKnownBits(In);
- if ((NumSrcEltBits - NumPackedZeroBits) <= Known.countMinLeadingZeros()) {
+ if ((Flags.hasNoUnsignedWrap() && NumDstEltBits <= NumPackedZeroBits) ||
+ (NumSrcEltBits - NumPackedZeroBits) <= Known.countMinLeadingZeros()) {
PackOpcode = X86ISD::PACKUS;
return In;
}
@@ -20884,7 +20886,7 @@ static SDValue matchTruncateWithPACK(unsigned &PackOpcode, EVT DstVT,
return SDValue();
unsigned MinSignBits = NumSrcEltBits - NumPackedSignBits;
- if (MinSignBits < NumSignBits) {
+ if (Flags.hasNoSignedWrap() || MinSignBits < NumSignBits) {
PackOpcode = X86ISD::PACKSS;
return In;
}
@@ -20906,10 +20908,9 @@ static SDValue matchTruncateWithPACK(unsigned &PackOpcode, EVT DstVT,
/// This function lowers a vector truncation of 'extended sign-bits' or
/// 'extended zero-bits' values.
/// vXi16/vXi32/vXi64 to vXi8/vXi16/vXi32 into X86ISD::PACKSS/PACKUS operations.
-static SDValue LowerTruncateVecPackWithSignBits(MVT DstVT, SDValue In,
- const SDLoc &DL,
- const X86Subtarget &Subtarget,
- SelectionDAG &DAG) {
+static SDValue LowerTruncateVecPackWithSignBits(
+ MVT DstVT, SDValue In, const SDLoc &DL, const X86Subtarget &Subtarget,
+ SelectionDAG &DAG, const SDNodeFlags Flags = SDNodeFlags()) {
MVT SrcVT = In.getSimpleValueType();
MVT DstSVT = DstVT.getVectorElementType();
MVT SrcSVT = SrcVT.getVectorElementType();
@@ -20931,8 +20932,8 @@ static SDValue LowerTruncateVecPackWithSignBits(MVT DstVT, SDValue In,
}
unsigned PackOpcode;
- if (SDValue Src =
- matchTruncateWithPACK(PackOpcode, DstVT, In, DL, DAG, Subtarget))
+ if (SDValue Src = matchTruncateWithPACK(PackOpcode, DstVT, In, DL, DAG,
+ Subtarget, Flags))
return truncateVectorWithPACK(PackOpcode, DstVT, Src, DL, DAG, Subtarget);
return SDValue();
@@ -21102,8 +21103,8 @@ SDValue X86TargetLowering::LowerTRUNCATE(SDValue Op, SelectionDAG &DAG) const {
// Pre-AVX512 (or prefer-256bit) see if we can make use of PACKSS/PACKUS.
if (!Subtarget.hasAVX512() ||
(InVT.is512BitVector() && VT.is256BitVector()))
- if (SDValue SignPack =
- LowerTruncateVecPackWithSignBits(VT, In, DL, Subtarget, DAG))
+ if (SDValue SignPack = LowerTruncateVecPackWithSignBits(
+ VT, In, DL, Subtarget, DAG, Op->getFlags()))
return SignPack;
// Pre-AVX512 see if we can make use of PACKSS/PACKUS.
@@ -21120,8 +21121,8 @@ SDValue X86TargetLowering::LowerTRUNCATE(SDValue Op, SelectionDAG &DAG) const {
// Attempt to truncate with PACKUS/PACKSS even on AVX512 if we'd have to
// concat from subvectors to use VPTRUNC etc.
if (!Subtarget.hasAVX512() || isFreeToSplitVector(In.getNode(), DAG))
- if (SDValue SignPack =
- LowerTruncateVecPackWithSignBits(VT, In, DL, Subtarget, DAG))
+ if (SDValue SignPack = LowerTruncateVecPackWithSignBits(
+ VT, In, DL, Subtarget, DAG, Op->getFlags()))
return SignPack;
// vpmovqb/w/d, vpmovdb/w, vpmovwb
@@ -33578,10 +33579,10 @@ void X86TargetLowering::ReplaceNodeResults(SDNode *N,
// See if there are sufficient leading bits to perform a PACKUS/PACKSS.
unsigned PackOpcode;
- if (SDValue Src =
- matchTruncateWithPACK(PackOpcode, VT, In, dl, DAG, Subtarget)) {
- if (SDValue Res = truncateVectorWithPACK(PackOpcode, VT, Src,
- dl, DAG, Subtarget)) {
+ if (SDValue Src = matchTruncateWithPACK(PackOpcode, VT, In, dl, DAG,
+ Subtarget, N->getFlags())) {
+ if (SDValue Res =
+ truncateVectorWithPACK(PackOpcode, VT, Src, dl, DAG, Subtarget)) {
Res = widenSubVector(WidenVT, Res, false, Subtarget, DAG, dl);
Results.push_back(Res);
return;
diff --git a/llvm/test/CodeGen/X86/vector-trunc-nowrap.ll b/llvm/test/CodeGen/X86/vector-trunc-nowrap.ll
index 32c7e820c967b0..2b8eedfbbdc9c2 100644
--- a/llvm/test/CodeGen/X86/vector-trunc-nowrap.ll
+++ b/llvm/test/CodeGen/X86/vector-trunc-nowrap.ll
@@ -107,50 +107,28 @@ entry:
}
define <8 x i16> @trunc8i64_8i16_nsw(<8 x i64> %a) {
-; SSE2-SSSE3-LABEL: trunc8i64_8i16_nsw:
-; SSE2-SSSE3: # %bb.0: # %entry
-; SSE2-SSSE3-NEXT: shufps {{.*#+}} xmm2 = xmm2[0,2],xmm3[0,2]
-; SSE2-SSSE3-NEXT: pslld $16, %xmm2
-; SSE2-SSSE3-NEXT: psrad $16, %xmm2
-; SSE2-SSSE3-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
-; SSE2-SSSE3-NEXT: pslld $16, %xmm0
-; SSE2-SSSE3-NEXT: psrad $16, %xmm0
-; SSE2-SSSE3-NEXT: packssdw %xmm2, %xmm0
-; SSE2-SSSE3-NEXT: retq
-;
-; SSE41-LABEL: trunc8i64_8i16_nsw:
-; SSE41: # %bb.0: # %entry
-; SSE41-NEXT: pxor %xmm4, %xmm4
-; SSE41-NEXT: pblendw {{.*#+}} xmm3 = xmm3[0],xmm4[1,2,3],xmm3[4],xmm4[5,6,7]
-; SSE41-NEXT: pblendw {{.*#+}} xmm2 = xmm2[0],xmm4[1,2,3],xmm2[4],xmm4[5,6,7]
-; SSE41-NEXT: packusdw %xmm3, %xmm2
-; SSE41-NEXT: pblendw {{.*#+}} xmm1 = xmm1[0],xmm4[1,2,3],xmm1[4],xmm4[5,6,7]
-; SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0],xmm4[1,2,3],xmm0[4],xmm4[5,6,7]
-; SSE41-NEXT: packusdw %xmm1, %xmm0
-; SSE41-NEXT: packusdw %xmm2, %xmm0
-; SSE41-NEXT: retq
+; SSE-LABEL: trunc8i64_8i16_nsw:
+; SSE: # %bb.0: # %entry
+; SSE-NEXT: packssdw %xmm3, %xmm2
+; SSE-NEXT: packssdw %xmm1, %xmm0
+; SSE-NEXT: packssdw %xmm2, %xmm0
+; SSE-NEXT: retq
;
; AVX1-LABEL: trunc8i64_8i16_nsw:
; AVX1: # %bb.0: # %entry
-; AVX1-NEXT: vbroadcastsd {{.*#+}} ymm2 = [65535,65535,65535,65535]
-; AVX1-NEXT: vandps %ymm2, %ymm1, %ymm1
-; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm3
-; AVX1-NEXT: vpackusdw %xmm3, %xmm1, %xmm1
-; AVX1-NEXT: vandps %ymm2, %ymm0, %ymm0
+; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
+; AVX1-NEXT: vpackssdw %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
-; AVX1-NEXT: vpackusdw %xmm2, %xmm0, %xmm0
-; AVX1-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
+; AVX1-NEXT: vpackssdw %xmm2, %xmm0, %xmm0
+; AVX1-NEXT: vpackssdw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc8i64_8i16_nsw:
; AVX2: # %bb.0: # %entry
-; AVX2-NEXT: vpxor %xmm2, %xmm2, %xmm2
-; AVX2-NEXT: vpblendw {{.*#+}} ymm1 = ymm1[0],ymm2[1,2,3],ymm1[4],ymm2[5,6,7],ymm1[8],ymm2[9,10,11],ymm1[12],ymm2[13,14,15]
-; AVX2-NEXT: vpblendw {{.*#+}} ymm0 = ymm0[0],ymm2[1,2,3],ymm0[4],ymm2[5,6,7],ymm0[8],ymm2[9,10,11],ymm0[12],ymm2[13,14,15]
-; AVX2-NEXT: vpackusdw %ymm1, %ymm0, %ymm0
+; AVX2-NEXT: vpackssdw %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
-; AVX2-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
+; AVX2-NEXT: vpackssdw %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,1,3]
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
@@ -179,23 +157,15 @@ define <8 x i16> @trunc8i64_8i16_nuw(<8 x i64> %a) {
;
; SSE41-LABEL: trunc8i64_8i16_nuw:
; SSE41: # %bb.0: # %entry
-; SSE41-NEXT: pxor %xmm4, %xmm4
-; SSE41-NEXT: pblendw {{.*#+}} xmm3 = xmm3[0],xmm4[1,2,3],xmm3[4],xmm4[5,6,7]
-; SSE41-NEXT: pblendw {{.*#+}} xmm2 = xmm2[0],xmm4[1,2,3],xmm2[4],xmm4[5,6,7]
; SSE41-NEXT: packusdw %xmm3, %xmm2
-; SSE41-NEXT: pblendw {{.*#+}} xmm1 = xmm1[0],xmm4[1,2,3],xmm1[4],xmm4[5,6,7]
-; SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0],xmm4[1,2,3],xmm0[4],xmm4[5,6,7]
; SSE41-NEXT: packusdw %xmm1, %xmm0
; SSE41-NEXT: packusdw %xmm2, %xmm0
; SSE41-NEXT: retq
;
; AVX1-LABEL: trunc8i64_8i16_nuw:
; AVX1: # %bb.0: # %entry
-; AVX1-NEXT: vbroadcastsd {{.*#+}} ymm2 = [65535,65535,65535,65535]
-; AVX1-NEXT: vandps %ymm2, %ymm1, %ymm1
-; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm3
-; AVX1-NEXT: vpackusdw %xmm3, %xmm1, %xmm1
-; AVX1-NEXT: vandps %ymm2, %ymm0, %ymm0
+; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
+; AVX1-NEXT: vpackusdw %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vpackusdw %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
@@ -204,9 +174,6 @@ define <8 x i16> @trunc8i64_8i16_nuw(<8 x i64> %a) {
;
; AVX2-LABEL: trunc8i64_8i16_nuw:
; AVX2: # %bb.0: # %entry
-; AVX2-NEXT: vpxor %xmm2, %xmm2, %xmm2
-; AVX2-NEXT: vpblendw {{.*#+}} ymm1 = ymm1[0],ymm2[1,2,3],ymm1[4],ymm2[5,6,7],ymm1[8],ymm2[9,10,11],ymm1[12],ymm2[13,14,15]
-; AVX2-NEXT: vpblendw {{.*#+}} ymm0 = ymm0[0],ymm2[1,2,3],ymm0[4],ymm2[5,6,7],ymm0[8],ymm2[9,10,11],ymm0[12],ymm2[13,14,15]
; AVX2-NEXT: vpackusdw %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
@@ -225,59 +192,34 @@ entry:
}
define void @trunc8i64_8i8_nsw(<8 x i64> %a) {
-; SSE2-SSSE3-LABEL: trunc8i64_8i8_nsw:
-; SSE2-SSSE3: # %bb.0: # %entry
-; SSE2-SSSE3-NEXT: movdqa {{.*#+}} xmm4 = [255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0]
-; SSE2-SSSE3-NEXT: pand %xmm4, %xmm3
-; SSE2-SSSE3-NEXT: pand %xmm4, %xmm2
-; SSE2-SSSE3-NEXT: packuswb %xmm3, %xmm2
-; SSE2-SSSE3-NEXT: pand %xmm4, %xmm1
-; SSE2-SSSE3-NEXT: pand %xmm4, %xmm0
-; SSE2-SSSE3-NEXT: packuswb %xmm1, %xmm0
-; SSE2-SSSE3-NEXT: packuswb %xmm2, %xmm0
-; SSE2-SSSE3-NEXT: packuswb %xmm0, %xmm0
-; SSE2-SSSE3-NEXT: movq %xmm0, (%rax)
-; SSE2-SSSE3-NEXT: retq
-;
-; SSE41-LABEL: trunc8i64_8i8_nsw:
-; SSE41: # %bb.0: # %entry
-; SSE41-NEXT: pmovzxbq {{.*#+}} xmm4 = [255,255]
-; SSE41-NEXT: pand %xmm4, %xmm3
-; SSE41-NEXT: pand %xmm4, %xmm2
-; SSE41-NEXT: packusdw %xmm3, %xmm2
-; SSE41-NEXT: pand %xmm4, %xmm1
-; SSE41-NEXT: pand %xmm4, %xmm0
-; SSE41-NEXT: packusdw %xmm1, %xmm0
-; SSE41-NEXT: packusdw %xmm2, %xmm0
-; SSE41-NEXT: packuswb %xmm0, %xmm0
-; SSE41-NEXT: movq %xmm0, (%rax)
-; SSE41-NEXT: retq
+; SSE-LABEL: trunc8i64_8i8_nsw:
+; SSE: # %bb.0: # %entry
+; SSE-NEXT: packssdw %xmm3, %xmm2
+; SSE-NEXT: packssdw %xmm1, %xmm0
+; SSE-NEXT: packssdw %xmm2, %xmm0
+; SSE-NEXT: packsswb %xmm0, %xmm0
+; SSE-NEXT: movq %xmm0, (%rax)
+; SSE-NEXT: retq
;
; AVX1-LABEL: trunc8i64_8i8_nsw:
; AVX1: # %bb.0: # %entry
-; AVX1-NEXT: vbroadcastsd {{.*#+}} ymm2 = [255,255,255,255]
-; AVX1-NEXT: vandps %ymm2, %ymm1, %ymm1
-; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm3
-; AVX1-NEXT: vpackusdw %xmm3, %xmm1, %xmm1
-; AVX1-NEXT: vandps %ymm2, %ymm0, %ymm0
+; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
+; AVX1-NEXT: vpackssdw %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
-; AVX1-NEXT: vpackusdw %xmm2, %xmm0, %xmm0
-; AVX1-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
-; AVX1-NEXT: vpackuswb %xmm0, %xmm0, %xmm0
+; AVX1-NEXT: vpackssdw %xmm2, %xmm0, %xmm0
+; AVX1-NEXT: vpackssdw %xmm1, %xmm0, %xmm0
+; AVX1-NEXT: vpacksswb %xmm0, %xmm0, %xmm0
; AVX1-NEXT: vmovq %xmm0, (%rax)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc8i64_8i8_nsw:
; AVX2: # %bb.0: # %entry
-; AVX2-NEXT: vpbroadcastq {{.*#+}} ymm2 = [255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0]
-; AVX2-NEXT: vpand %ymm2, %ymm1, %ymm1
-; AVX2-NEXT: vpand %ymm2, %ymm0, %ymm0
-; AVX2-NEXT: vpackusdw %ymm1, %ymm0, %ymm0
+; AVX2-NEXT: vpackssdw %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
-; AVX2-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
+; AVX2-NEXT: vpackssdw %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,1,3]
-; AVX2-NEXT: vpackuswb %xmm0, %xmm0, %xmm0
+; AVX2-NEXT: vpacksswb %xmm0, %xmm0, %xmm0
; AVX2-NEXT: vmovq %xmm0, (%rax)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
@@ -296,12 +238,7 @@ entry:
define void @trunc8i64_8i8_nuw(<8 x i64> %a) {
; SSE2-SSSE3-LABEL: trunc8i64_8i8_nuw:
; SSE2-SSSE3: # %bb.0: # %entry
-; SSE2-SSSE3-NEXT: movdqa {{.*#+}} xmm4 = [255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0]
-; SSE2-SSSE3-NEXT: pand %xmm4, %xmm3
-; SSE2-SSSE3-NEXT: pand %xmm4, %xmm2
; SSE2-SSSE3-NEXT: packuswb %xmm3, %xmm2
-; SSE2-SSSE3-NEXT: pand %xmm4, %xmm1
-; SSE2-SSSE3-NEXT: pand %xmm4, %xmm0
; SSE2-SSSE3-NEXT: packuswb %xmm1, %xmm0
; SSE2-SSSE3-NEXT: packuswb %xmm2, %xmm0
; SSE2-SSSE3-NEXT: packuswb %xmm0, %xmm0
@@ -310,12 +247,7 @@ define void @trunc8i64_8i8_nuw(<8 x i64> %a) {
;
; SSE41-LABEL: trunc8i64_8i8_nuw:
; SSE41: # %bb.0: # %entry
-; SSE41-NEXT: pmovzxbq {{.*#+}} xmm4 = [255,255]
-; SSE41-NEXT: pand %xmm4, %xmm3
-; SSE41-NEXT: pand %xmm4, %xmm2
; SSE41-NEXT: packusdw %xmm3, %xmm2
-; SSE41-NEXT: pand %xmm4, %xmm1
-; SSE41-NEXT: pand %xmm4, %xmm0
; SSE41-NEXT: packusdw %xmm1, %xmm0
; SSE41-NEXT: packusdw %xmm2, %xmm0
; SSE41-NEXT: packuswb %xmm0, %xmm0
@@ -324,11 +256,8 @@ define void @trunc8i64_8i8_nuw(<8 x i64> %a) {
;
; AVX1-LABEL: trunc8i64_8i8_nuw:
; AVX1: # %bb.0: # %entry
-; AVX1-NEXT: vbroadcastsd {{.*#+}} ymm2 = [255,255,255,255]
-; AVX1-NEXT: vandps %ymm2, %ymm1, %ymm1
-; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm3
-; AVX1-NEXT: vpackusdw %xmm3, %xmm1, %xmm1
-; AVX1-NEXT: vandps %ymm2, %ymm0, %ymm0
+; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
+; AVX1-NEXT: vpackusdw %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vpackusdw %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
@@ -339,9 +268,6 @@ define void @trunc8i64_8i8_nuw(<8 x i64> %a) {
;
; AVX2-LABEL: trunc8i64_8i8_nuw:
; AVX2: # %bb.0: # %entry
-; AVX2-NEXT: vpbroadcastq {{.*#+}} ymm2 = [255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0]
-; AVX2-NEXT: vpand %ymm2, %ymm1, %ymm1
-; AVX2-NEXT: vpand %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vpackusdw %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
@@ -363,44 +289,22 @@ entry:
}
define <8 x i16> @trunc8i32_8i16_nsw(<8 x i32> %a) {
-; SSE2-LABEL: trunc8i32_8i16_nsw:
-; SSE2: # %bb.0: # %entry
-; SSE2-NEXT: pslld $16, %xmm1
-; SSE2-NEXT: psrad $16, %xmm1
-; SSE2-NEXT: pslld $16, %xmm0
-; SSE2-NEXT: psrad $16, %xmm0
-; SSE2-NEXT: packssdw %xmm1, %xmm0
-; SSE2-NEXT: retq
-;
-; SSSE3-LABEL: trunc8i32_8i16_nsw:
-; SSSE3: # %bb.0: # %entry
-; SSSE3-NEXT: movdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
-; SSSE3-NEXT: pshufb %xmm2, %xmm1
-; SSSE3-NEXT: pshufb %xmm2, %xmm0
-; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
-; SSSE3-NEXT: retq
-;
-; SSE41-LABEL: trunc8i32_8i16_nsw:
-; SSE41: # %bb.0: # %entry
-; SSE41-NEXT: pxor %xmm2, %xmm2
-; SSE41-NEXT: pblendw {{.*#+}} xmm1 = xmm1[0],xmm2[1],xmm1[2],xmm2[3],xmm1[4],xmm2[5],xmm1[6],xmm2[7]
-; SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0],xmm2[1],xmm0[2],xmm2[3],xmm0[4],xmm2[5],xmm0[6],xmm2[7]
-; SSE41-NEXT: packusdw %xmm1, %xmm0
-; SSE41-NEXT: retq
+; SSE-LABEL: trunc8i32_8i16_nsw:
+; SSE: # %bb.0: # %entry
+; SSE-NEXT: packssdw %xmm1, %xmm0
+; SSE-NEXT: retq
;
; AVX1-LABEL: trunc8i32_8i16_nsw:
; AVX1: # %bb.0: # %entry
-; AVX1-NEXT: vandps {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %ymm0, %ymm0
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
+; AVX1-NEXT: vpackssdw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc8i32_8i16_nsw:
; AVX2: # %bb.0: # %entry
-; AVX2-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,u,u,u,u,u,u,u,u,16,17,20,21,24,25,28,29,u,u,u,u,u,u,u,u]
-; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX2-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
+; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
+; AVX2-NEXT: vpackssdw %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
@@ -456,15 +360,11 @@ define <8 x i16> @trunc8i32_8i16_nuw(<8 x i32> %a) {
;
; SSE41-LABEL: trunc8i32_8i16_nuw:
; SSE41: # %bb.0: # %entry
-; SSE41-NEXT: pxor %xmm2, %xmm2
-; SSE41-NEXT: pblendw {{.*#+}} xmm1 = xmm1[0],xmm2[1],xmm1[2],xmm2[3],xmm1[4],xmm2[5],xmm1[6],xmm2[7]
-; SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0],xmm2[1],xmm0[2],xmm2[3],xmm0[4],xmm2[5],xmm0[6],xmm2[7]
; SSE41-NEXT: packusdw %xmm1, %xmm0
; SSE41-NEXT: retq
;
; AVX1-LABEL: trunc8i32_8i16_nuw:
; AVX1: # %bb.0: # %entry
-; AVX1-NEXT: vandps {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %ymm0, %ymm0
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
@@ -472,9 +372,8 @@ define <8 x i16> @trunc8i32_8i16_nuw(<8 x i32> %a) {
;
; AVX2-LABEL: trunc8i32_8i16_nuw:
; AVX2: # %bb.0: # %entry
-; AVX2-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,u,u,u,u,u,u,u,u,16,17,20,21,24,25,28,29,u,u,u,u,u,u,u,u]
-; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX2-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
+; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
+; AVX2-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
@@ -511,33 +410,18 @@ entry:
}
define void @trunc8i32_8i8_nsw(<8 x i32> %a) {
-; SSE2-SSSE3-LABEL: trunc8i32_8i8_nsw:
-; SSE2-SSSE3: # %bb.0: # %entry
-; SSE2-SSSE3-NEXT: movdqa {{.*#+}} xmm2 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
-; SSE2-SSSE3-NEXT: pand %xmm2, %xmm1
-; SSE2-SSSE3-NEXT: pand %xmm2, %xmm0
-; SSE2-SSSE3-NEXT: packuswb %xmm1, %xmm0
-; SSE2-SSSE3-NEXT: packuswb %xmm0, %xmm0
-; SSE2-SSSE3-NEXT: movq %xmm0, (%rax)
-; SSE2-SSSE3-NEXT: retq
-;
-; SSE41-LABEL: trunc8i32_8i8_nsw:
-; SSE41: # %bb.0: # %entry
-; SSE41-NEXT: pmovzxbd {{.*#+}} xmm2 = [255,255,255,255]
-; SSE41-NEXT: pand %xmm2, %xmm1
-; SSE41-NEXT: pand %xmm2, %xmm0
-; SSE41-NEXT: packusdw %xmm1, %xmm0
-; SSE41-NEXT: packuswb %xmm0, %xmm0
-; SSE41-NEXT: movq %xmm0, (%rax)
-; SSE41-NEXT: retq
+; SSE-LABEL: trunc8i32_8i8_nsw:
+; SSE: # %bb.0: # %entry
+; SSE-NEXT: packssdw %xmm1, %xmm0
+; SSE-NEXT: packsswb %xmm0, %xmm0
+; SSE-NEXT: movq %xmm0, (%rax)
+; SSE-NEXT: retq
;
; AVX1-LABEL: trunc8i32_8i8_nsw:
; AVX1: # %bb.0: # %entry
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT: vmovd {{.*#+}} xmm2 = [0,4,8,12,0,0,0,0,0,0,0,0,0,0,0,0]
-; AVX1-NEXT: vpshufb %xmm2, %xmm1, %xmm1
-; AVX1-NEXT: vpshufb %xmm2, %xmm0, %xmm0
-; AVX1-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; AVX1-NEXT: vpackssdw %xmm1, %xmm0, %xmm0
+; AVX1-NEXT: vpacksswb %xmm0, %xmm0, %xmm0
; AVX1-NEXT: vmovq %xmm0, (%rax)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
@@ -545,10 +429,8 @@ define void @trunc8i32_8i8_nsw(<8 x i32> %a) {
; AVX2-LABEL: trunc8i32_8i8_nsw:
; AVX2: # %bb.0: # %entry
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
-; AVX2-NEXT: vmovd {{.*#+}} xmm2 = [0,4,8,12,0,0,0,0,0,0,0,0,0,0,0,0]
-; AVX2-NEXT: vpshufb %xmm2, %xmm1, %xmm1
-; AVX2-NEXT: vpshufb %xmm2, %xmm0, %xmm0
-; AVX2-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; AVX2-NEXT: vpackssdw %xmm1, %xmm0, %xmm0
+; AVX2-NEXT: vpacksswb %xmm0, %xmm0, %xmm0
; AVX2-NEXT: vmovq %xmm0, (%rax)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
@@ -589,9 +471,6 @@ entry:
define void @trunc8i32_8i8_nuw(<8 x i32> %a) {
; SSE2-SSSE3-LABEL: trunc8i32_8i8_nuw:
; SSE2-SSSE3:...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/123956
More information about the llvm-commits
mailing list