[llvm] [X86] combineCONCAT_VECTORS - fold concat(extract_subvector(X,0),extract_subvector(Y,0)) --> shuffle(X,Y) (PR #135985)
Simon Pilgrim via llvm-commits
llvm-commits at lists.llvm.org
Wed Apr 16 09:48:43 PDT 2025
https://github.com/RKSimon created https://github.com/llvm/llvm-project/pull/135985
This is a simple duplicate version of combineConcatVectorOfExtracts, which only runs generically pre-vector legalization.
I'm open to alternatives on how to handle this - we could go with this; we could add a TLI hook to allow combineConcatVectorOfExtracts to run after legalization; or we could move combineConcatVectorOfExtracts into TargetLowering so we can call it from x86 combineCONCAT_VECTORS when we want. Any thoughts?
>From a003be96f73bc4706a1860482b103339f31e5b9f Mon Sep 17 00:00:00 2001
From: Simon Pilgrim <llvm-dev at redking.me.uk>
Date: Wed, 16 Apr 2025 17:47:41 +0100
Subject: [PATCH] [X86] combineCONCAT_VECTORS - fold
concat(extract_subvector(X,0),extract_subvector(Y,0)) --> shuffle(X,Y)
This is a simple duplicate version of combineConcatVectorOfExtracts, which only runs generically pre-vector legalization.
I'm open to alternatives on how to handle this - we could go with this; we could add a TLI hook to allow combineConcatVectorOfExtracts to run after legalization; or we could move combineConcatVectorOfExtracts into TargetLowering so we can call it from x86 combineCONCAT_VECTORS when we want. Any thoughts?
---
llvm/lib/Target/X86/X86ISelLowering.cpp | 22 +++
llvm/test/CodeGen/X86/combine-pmuldq.ll | 14 +-
llvm/test/CodeGen/X86/masked_store_trunc.ll | 5 +-
.../CodeGen/X86/masked_store_trunc_ssat.ll | 5 +-
.../CodeGen/X86/masked_store_trunc_usat.ll | 5 +-
llvm/test/CodeGen/X86/pr40891.ll | 5 +-
llvm/test/CodeGen/X86/psubus.ll | 154 +++++-------------
.../CodeGen/X86/vector-reduce-xor-bool.ll | 5 +-
llvm/test/CodeGen/X86/vector-trunc-nowrap.ll | 148 ++++-------------
llvm/test/CodeGen/X86/vector-trunc-packus.ll | 74 ++-------
llvm/test/CodeGen/X86/vector-trunc-ssat.ll | 74 ++-------
llvm/test/CodeGen/X86/vector-trunc-usat.ll | 70 ++------
llvm/test/CodeGen/X86/vector-trunc.ll | 110 +++----------
13 files changed, 178 insertions(+), 513 deletions(-)
diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index 3adeb4628eabf..26bf076271f8e 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -58911,6 +58911,28 @@ static SDValue combineCONCAT_VECTORS(SDNode *N, SelectionDAG &DAG,
return R;
}
+ // Fold concat(extract_subvector(X,0),extract_subvector(Y,0))
+ // --> shuffle(X,Y)
+ // This is a more limited version of combineConcatVectorOfExtracts for use
+ // after legalization.
+ if (Ops.size() == 2 && TLI.isTypeLegal(VT)) {
+ SDValue Lo = Ops[0], Hi = Ops[1];
+ if (Lo.getOpcode() == ISD::EXTRACT_SUBVECTOR &&
+ Hi.getOpcode() == ISD::EXTRACT_SUBVECTOR &&
+ Lo.getOperand(0).getValueSizeInBits() == VT.getSizeInBits() &&
+ Hi.getOperand(0).getValueSizeInBits() == VT.getSizeInBits() &&
+ isNullConstant(Lo.getOperand(1)) && isNullConstant(Hi.getOperand(1))) {
+ unsigned NumElts = VT.getVectorNumElements();
+ unsigned HalfElts = NumElts / 2;
+ SmallVector<int, 8> ConcatMask(NumElts);
+ std::iota(ConcatMask.begin(), ConcatMask.begin() + HalfElts, 0);
+ std::iota(ConcatMask.begin() + HalfElts, ConcatMask.end(), NumElts);
+ return DAG.getVectorShuffle(
+ VT, SDLoc(N), DAG.getBitcast(VT, Lo.getOperand(0)),
+ DAG.getBitcast(VT, Hi.getOperand(0)), ConcatMask);
+ }
+ }
+
return SDValue();
}
diff --git a/llvm/test/CodeGen/X86/combine-pmuldq.ll b/llvm/test/CodeGen/X86/combine-pmuldq.ll
index 0748ca626bcf8..70335f834291d 100644
--- a/llvm/test/CodeGen/X86/combine-pmuldq.ll
+++ b/llvm/test/CodeGen/X86/combine-pmuldq.ll
@@ -396,9 +396,8 @@ define <8 x i32> @PR49658_zext(ptr %ptr, i32 %mul) {
; AVX2-NEXT: vpmovzxdq {{.*#+}} ymm3 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
; AVX2-NEXT: vpmuludq %ymm3, %ymm1, %ymm3
; AVX2-NEXT: vpmuludq %ymm2, %ymm1, %ymm2
-; AVX2-NEXT: vperm2i128 {{.*#+}} ymm4 = ymm3[2,3],ymm2[2,3]
-; AVX2-NEXT: vinserti128 $1, %xmm2, %ymm3, %ymm2
-; AVX2-NEXT: vshufps {{.*#+}} ymm2 = ymm2[1,3],ymm4[1,3],ymm2[5,7],ymm4[5,7]
+; AVX2-NEXT: vshufps {{.*#+}} ymm2 = ymm2[1,3],ymm3[1,3],ymm2[5,7],ymm3[5,7]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm2 = ymm2[0,2,1,3]
; AVX2-NEXT: vpaddd %ymm0, %ymm2, %ymm0
; AVX2-NEXT: subq $-128, %rax
; AVX2-NEXT: jne .LBB7_1
@@ -568,13 +567,12 @@ define <8 x i32> @PR49658_sext(ptr %ptr, i32 %mul) {
; AVX2-NEXT: .p2align 4
; AVX2-NEXT: .LBB8_1: # %loop
; AVX2-NEXT: # =>This Inner Loop Header: Depth=1
-; AVX2-NEXT: vpmovsxdq 2097168(%rdi,%rax), %ymm2
-; AVX2-NEXT: vpmovsxdq 2097152(%rdi,%rax), %ymm3
+; AVX2-NEXT: vpmovsxdq 2097152(%rdi,%rax), %ymm2
+; AVX2-NEXT: vpmovsxdq 2097168(%rdi,%rax), %ymm3
; AVX2-NEXT: vpmuldq %ymm3, %ymm1, %ymm3
; AVX2-NEXT: vpmuldq %ymm2, %ymm1, %ymm2
-; AVX2-NEXT: vperm2i128 {{.*#+}} ymm4 = ymm3[2,3],ymm2[2,3]
-; AVX2-NEXT: vinserti128 $1, %xmm2, %ymm3, %ymm2
-; AVX2-NEXT: vshufps {{.*#+}} ymm2 = ymm2[1,3],ymm4[1,3],ymm2[5,7],ymm4[5,7]
+; AVX2-NEXT: vshufps {{.*#+}} ymm2 = ymm2[1,3],ymm3[1,3],ymm2[5,7],ymm3[5,7]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm2 = ymm2[0,2,1,3]
; AVX2-NEXT: vpaddd %ymm0, %ymm2, %ymm0
; AVX2-NEXT: subq $-128, %rax
; AVX2-NEXT: jne .LBB8_1
diff --git a/llvm/test/CodeGen/X86/masked_store_trunc.ll b/llvm/test/CodeGen/X86/masked_store_trunc.ll
index 1e56f346030ca..2f0d419132492 100644
--- a/llvm/test/CodeGen/X86/masked_store_trunc.ll
+++ b/llvm/test/CodeGen/X86/masked_store_trunc.ll
@@ -172,9 +172,8 @@ define void @truncstore_v8i64_v8i32(<8 x i64> %x, ptr %p, <8 x i32> %mask) {
; AVX2-NEXT: vpcmpeqd %ymm3, %ymm2, %ymm2
; AVX2-NEXT: vpcmpeqd %ymm3, %ymm3, %ymm3
; AVX2-NEXT: vpxor %ymm3, %ymm2, %ymm2
-; AVX2-NEXT: vperm2f128 {{.*#+}} ymm3 = ymm0[2,3],ymm1[2,3]
-; AVX2-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm3[0,2],ymm0[4,6],ymm3[4,6]
+; AVX2-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX2-NEXT: vpmaskmovd %ymm0, %ymm2, (%rdi)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
diff --git a/llvm/test/CodeGen/X86/masked_store_trunc_ssat.ll b/llvm/test/CodeGen/X86/masked_store_trunc_ssat.ll
index 31ef44bd6b42b..c950ce64e8883 100644
--- a/llvm/test/CodeGen/X86/masked_store_trunc_ssat.ll
+++ b/llvm/test/CodeGen/X86/masked_store_trunc_ssat.ll
@@ -334,9 +334,8 @@ define void @truncstore_v8i64_v8i32(<8 x i64> %x, ptr %p, <8 x i32> %mask) {
; AVX2-NEXT: vblendvpd %ymm4, %ymm1, %ymm3, %ymm1
; AVX2-NEXT: vpcmpgtq %ymm3, %ymm0, %ymm4
; AVX2-NEXT: vblendvpd %ymm4, %ymm0, %ymm3, %ymm0
-; AVX2-NEXT: vperm2f128 {{.*#+}} ymm3 = ymm0[2,3],ymm1[2,3]
-; AVX2-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm3[0,2],ymm0[4,6],ymm3[4,6]
+; AVX2-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX2-NEXT: vpmaskmovd %ymm0, %ymm2, (%rdi)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
diff --git a/llvm/test/CodeGen/X86/masked_store_trunc_usat.ll b/llvm/test/CodeGen/X86/masked_store_trunc_usat.ll
index 590f090c59596..da057dd084b36 100644
--- a/llvm/test/CodeGen/X86/masked_store_trunc_usat.ll
+++ b/llvm/test/CodeGen/X86/masked_store_trunc_usat.ll
@@ -266,9 +266,8 @@ define void @truncstore_v8i64_v8i32(<8 x i64> %x, ptr %p, <8 x i32> %mask) {
; AVX2-NEXT: vpxor %ymm4, %ymm0, %ymm4
; AVX2-NEXT: vpcmpgtq %ymm4, %ymm6, %ymm4
; AVX2-NEXT: vblendvpd %ymm4, %ymm0, %ymm3, %ymm0
-; AVX2-NEXT: vperm2f128 {{.*#+}} ymm3 = ymm0[2,3],ymm1[2,3]
-; AVX2-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm3[0,2],ymm0[4,6],ymm3[4,6]
+; AVX2-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX2-NEXT: vpmaskmovd %ymm0, %ymm2, (%rdi)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
diff --git a/llvm/test/CodeGen/X86/pr40891.ll b/llvm/test/CodeGen/X86/pr40891.ll
index 24f644683c286..73327491c4151 100644
--- a/llvm/test/CodeGen/X86/pr40891.ll
+++ b/llvm/test/CodeGen/X86/pr40891.ll
@@ -8,9 +8,8 @@ define <8 x i32> @foo(<8 x i64> %x, <4 x i64> %y) {
; CHECK: # %bb.0:
; CHECK-NEXT: vandps %ymm2, %ymm0, %ymm0
; CHECK-NEXT: vandps {{\.?LCPI[0-9]+_[0-9]+}}, %ymm1, %ymm1
-; CHECK-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm0[2,3],ymm1[2,3]
-; CHECK-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; CHECK-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm2[0,2],ymm0[4,6],ymm2[4,6]
+; CHECK-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
+; CHECK-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
; CHECK-NEXT: retl
%a = shufflevector <4 x i64> %y, <4 x i64> <i64 12345, i64 67890, i64 13579, i64 24680>, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
%b = and <8 x i64> %x, %a
diff --git a/llvm/test/CodeGen/X86/psubus.ll b/llvm/test/CodeGen/X86/psubus.ll
index 61e3611dcedc9..73ee28a7fd247 100644
--- a/llvm/test/CodeGen/X86/psubus.ll
+++ b/llvm/test/CodeGen/X86/psubus.ll
@@ -3,9 +3,9 @@
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+ssse3 | FileCheck %s --check-prefixes=SSE,SSE2OR3,SSSE3
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefixes=SSE,SSE41
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefixes=AVX,AVX1
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=AVX,AVX2,AVX2-SLOW
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2,+fast-variable-crosslane-shuffle,+fast-variable-perlane-shuffle | FileCheck %s --check-prefixes=AVX,AVX2,AVX2-FAST-ALL
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2,+fast-variable-perlane-shuffle | FileCheck %s --check-prefixes=AVX,AVX2,AVX2-FAST-PERLANE
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=AVX,AVX2
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2,+fast-variable-crosslane-shuffle,+fast-variable-perlane-shuffle | FileCheck %s --check-prefixes=AVX,AVX2
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2,+fast-variable-perlane-shuffle | FileCheck %s --check-prefixes=AVX,AVX2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw,+avx512vl,+fast-variable-crosslane-shuffle,+fast-variable-perlane-shuffle | FileCheck %s --check-prefixes=AVX,AVX512
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw,+avx512vl,+fast-variable-perlane-shuffle | FileCheck %s --check-prefixes=AVX,AVX512
@@ -2846,60 +2846,22 @@ define <8 x i32> @test33(<8 x i32> %a0, <8 x i64> %a1) {
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
; AVX1-NEXT: retq
;
-; AVX2-SLOW-LABEL: test33:
-; AVX2-SLOW: # %bb.0:
-; AVX2-SLOW-NEXT: vpbroadcastq {{.*#+}} ymm3 = [9223372036854775808,9223372036854775808,9223372036854775808,9223372036854775808]
-; AVX2-SLOW-NEXT: vpxor %ymm3, %ymm2, %ymm4
-; AVX2-SLOW-NEXT: vpbroadcastq {{.*#+}} ymm5 = [9223372041149743103,9223372041149743103,9223372041149743103,9223372041149743103]
-; AVX2-SLOW-NEXT: vpcmpgtq %ymm4, %ymm5, %ymm4
-; AVX2-SLOW-NEXT: vbroadcastsd {{.*#+}} ymm6 = [4294967295,4294967295,4294967295,4294967295]
-; AVX2-SLOW-NEXT: vblendvpd %ymm4, %ymm2, %ymm6, %ymm2
-; AVX2-SLOW-NEXT: vpxor %ymm3, %ymm1, %ymm3
-; AVX2-SLOW-NEXT: vpcmpgtq %ymm3, %ymm5, %ymm3
-; AVX2-SLOW-NEXT: vblendvpd %ymm3, %ymm1, %ymm6, %ymm1
-; AVX2-SLOW-NEXT: vperm2f128 {{.*#+}} ymm3 = ymm1[2,3],ymm2[2,3]
-; AVX2-SLOW-NEXT: vinsertf128 $1, %xmm2, %ymm1, %ymm1
-; AVX2-SLOW-NEXT: vshufps {{.*#+}} ymm1 = ymm1[0,2],ymm3[0,2],ymm1[4,6],ymm3[4,6]
-; AVX2-SLOW-NEXT: vpmaxud %ymm1, %ymm0, %ymm0
-; AVX2-SLOW-NEXT: vpsubd %ymm1, %ymm0, %ymm0
-; AVX2-SLOW-NEXT: retq
-;
-; AVX2-FAST-ALL-LABEL: test33:
-; AVX2-FAST-ALL: # %bb.0:
-; AVX2-FAST-ALL-NEXT: vpbroadcastq {{.*#+}} ymm3 = [9223372036854775808,9223372036854775808,9223372036854775808,9223372036854775808]
-; AVX2-FAST-ALL-NEXT: vpxor %ymm3, %ymm1, %ymm4
-; AVX2-FAST-ALL-NEXT: vpbroadcastq {{.*#+}} ymm5 = [9223372041149743103,9223372041149743103,9223372041149743103,9223372041149743103]
-; AVX2-FAST-ALL-NEXT: vpcmpgtq %ymm4, %ymm5, %ymm4
-; AVX2-FAST-ALL-NEXT: vbroadcastsd {{.*#+}} ymm6 = [4294967295,4294967295,4294967295,4294967295]
-; AVX2-FAST-ALL-NEXT: vblendvpd %ymm4, %ymm1, %ymm6, %ymm1
-; AVX2-FAST-ALL-NEXT: vmovapd {{.*#+}} ymm4 = [0,2,4,6,4,6,6,7]
-; AVX2-FAST-ALL-NEXT: vpermps %ymm1, %ymm4, %ymm1
-; AVX2-FAST-ALL-NEXT: vpxor %ymm3, %ymm2, %ymm3
-; AVX2-FAST-ALL-NEXT: vpcmpgtq %ymm3, %ymm5, %ymm3
-; AVX2-FAST-ALL-NEXT: vblendvpd %ymm3, %ymm2, %ymm6, %ymm2
-; AVX2-FAST-ALL-NEXT: vpermps %ymm2, %ymm4, %ymm2
-; AVX2-FAST-ALL-NEXT: vinsertf128 $1, %xmm2, %ymm1, %ymm1
-; AVX2-FAST-ALL-NEXT: vpmaxud %ymm1, %ymm0, %ymm0
-; AVX2-FAST-ALL-NEXT: vpsubd %ymm1, %ymm0, %ymm0
-; AVX2-FAST-ALL-NEXT: retq
-;
-; AVX2-FAST-PERLANE-LABEL: test33:
-; AVX2-FAST-PERLANE: # %bb.0:
-; AVX2-FAST-PERLANE-NEXT: vpbroadcastq {{.*#+}} ymm3 = [9223372036854775808,9223372036854775808,9223372036854775808,9223372036854775808]
-; AVX2-FAST-PERLANE-NEXT: vpxor %ymm3, %ymm2, %ymm4
-; AVX2-FAST-PERLANE-NEXT: vpbroadcastq {{.*#+}} ymm5 = [9223372041149743103,9223372041149743103,9223372041149743103,9223372041149743103]
-; AVX2-FAST-PERLANE-NEXT: vpcmpgtq %ymm4, %ymm5, %ymm4
-; AVX2-FAST-PERLANE-NEXT: vbroadcastsd {{.*#+}} ymm6 = [4294967295,4294967295,4294967295,4294967295]
-; AVX2-FAST-PERLANE-NEXT: vblendvpd %ymm4, %ymm2, %ymm6, %ymm2
-; AVX2-FAST-PERLANE-NEXT: vpxor %ymm3, %ymm1, %ymm3
-; AVX2-FAST-PERLANE-NEXT: vpcmpgtq %ymm3, %ymm5, %ymm3
-; AVX2-FAST-PERLANE-NEXT: vblendvpd %ymm3, %ymm1, %ymm6, %ymm1
-; AVX2-FAST-PERLANE-NEXT: vperm2f128 {{.*#+}} ymm3 = ymm1[2,3],ymm2[2,3]
-; AVX2-FAST-PERLANE-NEXT: vinsertf128 $1, %xmm2, %ymm1, %ymm1
-; AVX2-FAST-PERLANE-NEXT: vshufps {{.*#+}} ymm1 = ymm1[0,2],ymm3[0,2],ymm1[4,6],ymm3[4,6]
-; AVX2-FAST-PERLANE-NEXT: vpmaxud %ymm1, %ymm0, %ymm0
-; AVX2-FAST-PERLANE-NEXT: vpsubd %ymm1, %ymm0, %ymm0
-; AVX2-FAST-PERLANE-NEXT: retq
+; AVX2-LABEL: test33:
+; AVX2: # %bb.0:
+; AVX2-NEXT: vpbroadcastq {{.*#+}} ymm3 = [9223372036854775808,9223372036854775808,9223372036854775808,9223372036854775808]
+; AVX2-NEXT: vpxor %ymm3, %ymm2, %ymm4
+; AVX2-NEXT: vpbroadcastq {{.*#+}} ymm5 = [9223372041149743103,9223372041149743103,9223372041149743103,9223372041149743103]
+; AVX2-NEXT: vpcmpgtq %ymm4, %ymm5, %ymm4
+; AVX2-NEXT: vbroadcastsd {{.*#+}} ymm6 = [4294967295,4294967295,4294967295,4294967295]
+; AVX2-NEXT: vblendvpd %ymm4, %ymm2, %ymm6, %ymm2
+; AVX2-NEXT: vpxor %ymm3, %ymm1, %ymm3
+; AVX2-NEXT: vpcmpgtq %ymm3, %ymm5, %ymm3
+; AVX2-NEXT: vblendvpd %ymm3, %ymm1, %ymm6, %ymm1
+; AVX2-NEXT: vshufps {{.*#+}} ymm1 = ymm1[0,2],ymm2[0,2],ymm1[4,6],ymm2[4,6]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm1 = ymm1[0,2,1,3]
+; AVX2-NEXT: vpmaxud %ymm1, %ymm0, %ymm0
+; AVX2-NEXT: vpsubd %ymm1, %ymm0, %ymm0
+; AVX2-NEXT: retq
;
; AVX512-LABEL: test33:
; AVX512: # %bb.0:
@@ -3070,66 +3032,24 @@ define <8 x i32> @test34(<8 x i32> %a0, <8 x i64> %a1) {
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
; AVX1-NEXT: retq
;
-; AVX2-SLOW-LABEL: test34:
-; AVX2-SLOW: # %bb.0:
-; AVX2-SLOW-NEXT: vpbroadcastd {{.*#+}} ymm3 = [1,1,1,1,1,1,1,1]
-; AVX2-SLOW-NEXT: vpand %ymm3, %ymm0, %ymm0
-; AVX2-SLOW-NEXT: vpbroadcastq {{.*#+}} ymm3 = [9223372036854775808,9223372036854775808,9223372036854775808,9223372036854775808]
-; AVX2-SLOW-NEXT: vpxor %ymm3, %ymm2, %ymm4
-; AVX2-SLOW-NEXT: vpbroadcastq {{.*#+}} ymm5 = [9223372041149743103,9223372041149743103,9223372041149743103,9223372041149743103]
-; AVX2-SLOW-NEXT: vpcmpgtq %ymm4, %ymm5, %ymm4
-; AVX2-SLOW-NEXT: vbroadcastsd {{.*#+}} ymm6 = [4294967295,4294967295,4294967295,4294967295]
-; AVX2-SLOW-NEXT: vblendvpd %ymm4, %ymm2, %ymm6, %ymm2
-; AVX2-SLOW-NEXT: vpxor %ymm3, %ymm1, %ymm3
-; AVX2-SLOW-NEXT: vpcmpgtq %ymm3, %ymm5, %ymm3
-; AVX2-SLOW-NEXT: vblendvpd %ymm3, %ymm1, %ymm6, %ymm1
-; AVX2-SLOW-NEXT: vperm2f128 {{.*#+}} ymm3 = ymm1[2,3],ymm2[2,3]
-; AVX2-SLOW-NEXT: vinsertf128 $1, %xmm2, %ymm1, %ymm1
-; AVX2-SLOW-NEXT: vshufps {{.*#+}} ymm1 = ymm1[0,2],ymm3[0,2],ymm1[4,6],ymm3[4,6]
-; AVX2-SLOW-NEXT: vpmaxud %ymm1, %ymm0, %ymm0
-; AVX2-SLOW-NEXT: vpsubd %ymm1, %ymm0, %ymm0
-; AVX2-SLOW-NEXT: retq
-;
-; AVX2-FAST-ALL-LABEL: test34:
-; AVX2-FAST-ALL: # %bb.0:
-; AVX2-FAST-ALL-NEXT: vpbroadcastd {{.*#+}} ymm3 = [1,1,1,1,1,1,1,1]
-; AVX2-FAST-ALL-NEXT: vpand %ymm3, %ymm0, %ymm0
-; AVX2-FAST-ALL-NEXT: vpbroadcastq {{.*#+}} ymm3 = [9223372036854775808,9223372036854775808,9223372036854775808,9223372036854775808]
-; AVX2-FAST-ALL-NEXT: vpxor %ymm3, %ymm1, %ymm4
-; AVX2-FAST-ALL-NEXT: vpbroadcastq {{.*#+}} ymm5 = [9223372041149743103,9223372041149743103,9223372041149743103,9223372041149743103]
-; AVX2-FAST-ALL-NEXT: vpcmpgtq %ymm4, %ymm5, %ymm4
-; AVX2-FAST-ALL-NEXT: vbroadcastsd {{.*#+}} ymm6 = [4294967295,4294967295,4294967295,4294967295]
-; AVX2-FAST-ALL-NEXT: vblendvpd %ymm4, %ymm1, %ymm6, %ymm1
-; AVX2-FAST-ALL-NEXT: vmovapd {{.*#+}} ymm4 = [0,2,4,6,4,6,6,7]
-; AVX2-FAST-ALL-NEXT: vpermps %ymm1, %ymm4, %ymm1
-; AVX2-FAST-ALL-NEXT: vpxor %ymm3, %ymm2, %ymm3
-; AVX2-FAST-ALL-NEXT: vpcmpgtq %ymm3, %ymm5, %ymm3
-; AVX2-FAST-ALL-NEXT: vblendvpd %ymm3, %ymm2, %ymm6, %ymm2
-; AVX2-FAST-ALL-NEXT: vpermps %ymm2, %ymm4, %ymm2
-; AVX2-FAST-ALL-NEXT: vinsertf128 $1, %xmm2, %ymm1, %ymm1
-; AVX2-FAST-ALL-NEXT: vpmaxud %ymm1, %ymm0, %ymm0
-; AVX2-FAST-ALL-NEXT: vpsubd %ymm1, %ymm0, %ymm0
-; AVX2-FAST-ALL-NEXT: retq
-;
-; AVX2-FAST-PERLANE-LABEL: test34:
-; AVX2-FAST-PERLANE: # %bb.0:
-; AVX2-FAST-PERLANE-NEXT: vpbroadcastd {{.*#+}} ymm3 = [1,1,1,1,1,1,1,1]
-; AVX2-FAST-PERLANE-NEXT: vpand %ymm3, %ymm0, %ymm0
-; AVX2-FAST-PERLANE-NEXT: vpbroadcastq {{.*#+}} ymm3 = [9223372036854775808,9223372036854775808,9223372036854775808,9223372036854775808]
-; AVX2-FAST-PERLANE-NEXT: vpxor %ymm3, %ymm2, %ymm4
-; AVX2-FAST-PERLANE-NEXT: vpbroadcastq {{.*#+}} ymm5 = [9223372041149743103,9223372041149743103,9223372041149743103,9223372041149743103]
-; AVX2-FAST-PERLANE-NEXT: vpcmpgtq %ymm4, %ymm5, %ymm4
-; AVX2-FAST-PERLANE-NEXT: vbroadcastsd {{.*#+}} ymm6 = [4294967295,4294967295,4294967295,4294967295]
-; AVX2-FAST-PERLANE-NEXT: vblendvpd %ymm4, %ymm2, %ymm6, %ymm2
-; AVX2-FAST-PERLANE-NEXT: vpxor %ymm3, %ymm1, %ymm3
-; AVX2-FAST-PERLANE-NEXT: vpcmpgtq %ymm3, %ymm5, %ymm3
-; AVX2-FAST-PERLANE-NEXT: vblendvpd %ymm3, %ymm1, %ymm6, %ymm1
-; AVX2-FAST-PERLANE-NEXT: vperm2f128 {{.*#+}} ymm3 = ymm1[2,3],ymm2[2,3]
-; AVX2-FAST-PERLANE-NEXT: vinsertf128 $1, %xmm2, %ymm1, %ymm1
-; AVX2-FAST-PERLANE-NEXT: vshufps {{.*#+}} ymm1 = ymm1[0,2],ymm3[0,2],ymm1[4,6],ymm3[4,6]
-; AVX2-FAST-PERLANE-NEXT: vpmaxud %ymm1, %ymm0, %ymm0
-; AVX2-FAST-PERLANE-NEXT: vpsubd %ymm1, %ymm0, %ymm0
-; AVX2-FAST-PERLANE-NEXT: retq
+; AVX2-LABEL: test34:
+; AVX2: # %bb.0:
+; AVX2-NEXT: vpbroadcastd {{.*#+}} ymm3 = [1,1,1,1,1,1,1,1]
+; AVX2-NEXT: vpand %ymm3, %ymm0, %ymm0
+; AVX2-NEXT: vpbroadcastq {{.*#+}} ymm3 = [9223372036854775808,9223372036854775808,9223372036854775808,9223372036854775808]
+; AVX2-NEXT: vpxor %ymm3, %ymm2, %ymm4
+; AVX2-NEXT: vpbroadcastq {{.*#+}} ymm5 = [9223372041149743103,9223372041149743103,9223372041149743103,9223372041149743103]
+; AVX2-NEXT: vpcmpgtq %ymm4, %ymm5, %ymm4
+; AVX2-NEXT: vbroadcastsd {{.*#+}} ymm6 = [4294967295,4294967295,4294967295,4294967295]
+; AVX2-NEXT: vblendvpd %ymm4, %ymm2, %ymm6, %ymm2
+; AVX2-NEXT: vpxor %ymm3, %ymm1, %ymm3
+; AVX2-NEXT: vpcmpgtq %ymm3, %ymm5, %ymm3
+; AVX2-NEXT: vblendvpd %ymm3, %ymm1, %ymm6, %ymm1
+; AVX2-NEXT: vshufps {{.*#+}} ymm1 = ymm1[0,2],ymm2[0,2],ymm1[4,6],ymm2[4,6]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm1 = ymm1[0,2,1,3]
+; AVX2-NEXT: vpmaxud %ymm1, %ymm0, %ymm0
+; AVX2-NEXT: vpsubd %ymm1, %ymm0, %ymm0
+; AVX2-NEXT: retq
;
; AVX512-LABEL: test34:
; AVX512: # %bb.0:
diff --git a/llvm/test/CodeGen/X86/vector-reduce-xor-bool.ll b/llvm/test/CodeGen/X86/vector-reduce-xor-bool.ll
index 80b4f4614383f..320dce840ea57 100644
--- a/llvm/test/CodeGen/X86/vector-reduce-xor-bool.ll
+++ b/llvm/test/CodeGen/X86/vector-reduce-xor-bool.ll
@@ -585,9 +585,8 @@ define i1 @trunc_v8i64_v8i1(<8 x i64>) nounwind {
;
; AVX2-LABEL: trunc_v8i64_v8i1:
; AVX2: # %bb.0:
-; AVX2-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm0[2,3],ymm1[2,3]
-; AVX2-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm2[0,2],ymm0[4,6],ymm2[4,6]
+; AVX2-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX2-NEXT: vpslld $31, %ymm0, %ymm0
; AVX2-NEXT: vmovmskps %ymm0, %eax
; AVX2-NEXT: testb %al, %al
diff --git a/llvm/test/CodeGen/X86/vector-trunc-nowrap.ll b/llvm/test/CodeGen/X86/vector-trunc-nowrap.ll
index 85cca4f6f9a57..a47e6de2a8cef 100644
--- a/llvm/test/CodeGen/X86/vector-trunc-nowrap.ll
+++ b/llvm/test/CodeGen/X86/vector-trunc-nowrap.ll
@@ -3,9 +3,9 @@
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+ssse3 | FileCheck %s --check-prefixes=SSE,SSE2-SSSE3,SSSE3
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefixes=SSE,SSE41
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefixes=AVX,AVX1
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=AVX,AVX2,AVX2-SLOW
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2,+fast-variable-crosslane-shuffle,+fast-variable-perlane-shuffle | FileCheck %s --check-prefixes=AVX,AVX2,AVX2-FAST-ALL
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2,+fast-variable-perlane-shuffle | FileCheck %s --check-prefixes=AVX,AVX2,AVX2-FAST-PERLANE
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=AVX,AVX2
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2,+fast-variable-crosslane-shuffle,+fast-variable-perlane-shuffle | FileCheck %s --check-prefixes=AVX,AVX2
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2,+fast-variable-perlane-shuffle | FileCheck %s --check-prefixes=AVX,AVX2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f | FileCheck %s --check-prefix=AVX512 --check-prefix=AVX512F
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512vl,+fast-variable-crosslane-shuffle,+fast-variable-perlane-shuffle | FileCheck %s --check-prefixes=AVX512,AVX512VL
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512vl,+fast-variable-perlane-shuffle | FileCheck %s --check-prefixes=AVX512,AVX512VL
@@ -29,27 +29,11 @@ define <8 x i32> @trunc8i64_8i32_nsw(<8 x i64> %a) {
; AVX1-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm2[0,2],ymm0[4,6],ymm2[4,6]
; AVX1-NEXT: retq
;
-; AVX2-SLOW-LABEL: trunc8i64_8i32_nsw:
-; AVX2-SLOW: # %bb.0: # %entry
-; AVX2-SLOW-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm0[2,3],ymm1[2,3]
-; AVX2-SLOW-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-SLOW-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm2[0,2],ymm0[4,6],ymm2[4,6]
-; AVX2-SLOW-NEXT: retq
-;
-; AVX2-FAST-ALL-LABEL: trunc8i64_8i32_nsw:
-; AVX2-FAST-ALL: # %bb.0: # %entry
-; AVX2-FAST-ALL-NEXT: vmovaps {{.*#+}} ymm2 = [0,2,4,6,4,6,6,7]
-; AVX2-FAST-ALL-NEXT: vpermps %ymm0, %ymm2, %ymm0
-; AVX2-FAST-ALL-NEXT: vpermps %ymm1, %ymm2, %ymm1
-; AVX2-FAST-ALL-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-FAST-ALL-NEXT: retq
-;
-; AVX2-FAST-PERLANE-LABEL: trunc8i64_8i32_nsw:
-; AVX2-FAST-PERLANE: # %bb.0: # %entry
-; AVX2-FAST-PERLANE-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm0[2,3],ymm1[2,3]
-; AVX2-FAST-PERLANE-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-FAST-PERLANE-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm2[0,2],ymm0[4,6],ymm2[4,6]
-; AVX2-FAST-PERLANE-NEXT: retq
+; AVX2-LABEL: trunc8i64_8i32_nsw:
+; AVX2: # %bb.0: # %entry
+; AVX2-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
+; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc8i64_8i32_nsw:
; AVX512: # %bb.0: # %entry
@@ -75,27 +59,11 @@ define <8 x i32> @trunc8i64_8i32_nuw(<8 x i64> %a) {
; AVX1-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm2[0,2],ymm0[4,6],ymm2[4,6]
; AVX1-NEXT: retq
;
-; AVX2-SLOW-LABEL: trunc8i64_8i32_nuw:
-; AVX2-SLOW: # %bb.0: # %entry
-; AVX2-SLOW-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm0[2,3],ymm1[2,3]
-; AVX2-SLOW-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-SLOW-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm2[0,2],ymm0[4,6],ymm2[4,6]
-; AVX2-SLOW-NEXT: retq
-;
-; AVX2-FAST-ALL-LABEL: trunc8i64_8i32_nuw:
-; AVX2-FAST-ALL: # %bb.0: # %entry
-; AVX2-FAST-ALL-NEXT: vmovaps {{.*#+}} ymm2 = [0,2,4,6,4,6,6,7]
-; AVX2-FAST-ALL-NEXT: vpermps %ymm0, %ymm2, %ymm0
-; AVX2-FAST-ALL-NEXT: vpermps %ymm1, %ymm2, %ymm1
-; AVX2-FAST-ALL-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-FAST-ALL-NEXT: retq
-;
-; AVX2-FAST-PERLANE-LABEL: trunc8i64_8i32_nuw:
-; AVX2-FAST-PERLANE: # %bb.0: # %entry
-; AVX2-FAST-PERLANE-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm0[2,3],ymm1[2,3]
-; AVX2-FAST-PERLANE-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-FAST-PERLANE-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm2[0,2],ymm0[4,6],ymm2[4,6]
-; AVX2-FAST-PERLANE-NEXT: retq
+; AVX2-LABEL: trunc8i64_8i32_nuw:
+; AVX2: # %bb.0: # %entry
+; AVX2-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
+; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc8i64_8i32_nuw:
; AVX512: # %bb.0: # %entry
@@ -996,27 +964,11 @@ define <8 x i32> @trunc2x4i64_8i32_nsw(<4 x i64> %a, <4 x i64> %b) {
; AVX1-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm2[0,2],ymm0[4,6],ymm2[4,6]
; AVX1-NEXT: retq
;
-; AVX2-SLOW-LABEL: trunc2x4i64_8i32_nsw:
-; AVX2-SLOW: # %bb.0: # %entry
-; AVX2-SLOW-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm0[2,3],ymm1[2,3]
-; AVX2-SLOW-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-SLOW-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm2[0,2],ymm0[4,6],ymm2[4,6]
-; AVX2-SLOW-NEXT: retq
-;
-; AVX2-FAST-ALL-LABEL: trunc2x4i64_8i32_nsw:
-; AVX2-FAST-ALL: # %bb.0: # %entry
-; AVX2-FAST-ALL-NEXT: vmovaps {{.*#+}} ymm2 = [0,2,4,6,4,6,6,7]
-; AVX2-FAST-ALL-NEXT: vpermps %ymm0, %ymm2, %ymm0
-; AVX2-FAST-ALL-NEXT: vpermps %ymm1, %ymm2, %ymm1
-; AVX2-FAST-ALL-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-FAST-ALL-NEXT: retq
-;
-; AVX2-FAST-PERLANE-LABEL: trunc2x4i64_8i32_nsw:
-; AVX2-FAST-PERLANE: # %bb.0: # %entry
-; AVX2-FAST-PERLANE-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm0[2,3],ymm1[2,3]
-; AVX2-FAST-PERLANE-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-FAST-PERLANE-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm2[0,2],ymm0[4,6],ymm2[4,6]
-; AVX2-FAST-PERLANE-NEXT: retq
+; AVX2-LABEL: trunc2x4i64_8i32_nsw:
+; AVX2: # %bb.0: # %entry
+; AVX2-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
+; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc2x4i64_8i32_nsw:
; AVX512: # %bb.0: # %entry
@@ -1046,27 +998,11 @@ define <8 x i32> @trunc2x4i64_8i32_nuw(<4 x i64> %a, <4 x i64> %b) {
; AVX1-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm2[0,2],ymm0[4,6],ymm2[4,6]
; AVX1-NEXT: retq
;
-; AVX2-SLOW-LABEL: trunc2x4i64_8i32_nuw:
-; AVX2-SLOW: # %bb.0: # %entry
-; AVX2-SLOW-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm0[2,3],ymm1[2,3]
-; AVX2-SLOW-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-SLOW-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm2[0,2],ymm0[4,6],ymm2[4,6]
-; AVX2-SLOW-NEXT: retq
-;
-; AVX2-FAST-ALL-LABEL: trunc2x4i64_8i32_nuw:
-; AVX2-FAST-ALL: # %bb.0: # %entry
-; AVX2-FAST-ALL-NEXT: vmovaps {{.*#+}} ymm2 = [0,2,4,6,4,6,6,7]
-; AVX2-FAST-ALL-NEXT: vpermps %ymm0, %ymm2, %ymm0
-; AVX2-FAST-ALL-NEXT: vpermps %ymm1, %ymm2, %ymm1
-; AVX2-FAST-ALL-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-FAST-ALL-NEXT: retq
-;
-; AVX2-FAST-PERLANE-LABEL: trunc2x4i64_8i32_nuw:
-; AVX2-FAST-PERLANE: # %bb.0: # %entry
-; AVX2-FAST-PERLANE-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm0[2,3],ymm1[2,3]
-; AVX2-FAST-PERLANE-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-FAST-PERLANE-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm2[0,2],ymm0[4,6],ymm2[4,6]
-; AVX2-FAST-PERLANE-NEXT: retq
+; AVX2-LABEL: trunc2x4i64_8i32_nuw:
+; AVX2: # %bb.0: # %entry
+; AVX2-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
+; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc2x4i64_8i32_nuw:
; AVX512: # %bb.0: # %entry
@@ -1611,37 +1547,13 @@ define void @foo(<4 x i64> %a, <4 x i64> %b, ptr %p) "min-legal-vector-width"="2
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
-; AVX2-SLOW-LABEL: foo:
-; AVX2-SLOW: # %bb.0: # %entry
-; AVX2-SLOW-NEXT: vextractf128 $1, %ymm0, %xmm2
-; AVX2-SLOW-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm2[0,2]
-; AVX2-SLOW-NEXT: vextractf128 $1, %ymm1, %xmm2
-; AVX2-SLOW-NEXT: vshufps {{.*#+}} xmm1 = xmm1[0,2],xmm2[0,2]
-; AVX2-SLOW-NEXT: vmovaps %xmm1, 16(%rdi)
-; AVX2-SLOW-NEXT: vmovaps %xmm0, (%rdi)
-; AVX2-SLOW-NEXT: vzeroupper
-; AVX2-SLOW-NEXT: retq
-;
-; AVX2-FAST-ALL-LABEL: foo:
-; AVX2-FAST-ALL: # %bb.0: # %entry
-; AVX2-FAST-ALL-NEXT: vmovaps {{.*#+}} ymm2 = [0,2,4,6,4,6,6,7]
-; AVX2-FAST-ALL-NEXT: vpermps %ymm0, %ymm2, %ymm0
-; AVX2-FAST-ALL-NEXT: vpermps %ymm1, %ymm2, %ymm1
-; AVX2-FAST-ALL-NEXT: vmovaps %xmm1, 16(%rdi)
-; AVX2-FAST-ALL-NEXT: vmovaps %xmm0, (%rdi)
-; AVX2-FAST-ALL-NEXT: vzeroupper
-; AVX2-FAST-ALL-NEXT: retq
-;
-; AVX2-FAST-PERLANE-LABEL: foo:
-; AVX2-FAST-PERLANE: # %bb.0: # %entry
-; AVX2-FAST-PERLANE-NEXT: vextractf128 $1, %ymm0, %xmm2
-; AVX2-FAST-PERLANE-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm2[0,2]
-; AVX2-FAST-PERLANE-NEXT: vextractf128 $1, %ymm1, %xmm2
-; AVX2-FAST-PERLANE-NEXT: vshufps {{.*#+}} xmm1 = xmm1[0,2],xmm2[0,2]
-; AVX2-FAST-PERLANE-NEXT: vmovaps %xmm1, 16(%rdi)
-; AVX2-FAST-PERLANE-NEXT: vmovaps %xmm0, (%rdi)
-; AVX2-FAST-PERLANE-NEXT: vzeroupper
-; AVX2-FAST-PERLANE-NEXT: retq
+; AVX2-LABEL: foo:
+; AVX2: # %bb.0: # %entry
+; AVX2-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
+; AVX2-NEXT: vmovups %ymm0, (%rdi)
+; AVX2-NEXT: vzeroupper
+; AVX2-NEXT: retq
;
; AVX512F-LABEL: foo:
; AVX512F: # %bb.0: # %entry
diff --git a/llvm/test/CodeGen/X86/vector-trunc-packus.ll b/llvm/test/CodeGen/X86/vector-trunc-packus.ll
index cdb1026452691..da8a3f3fa0d4e 100644
--- a/llvm/test/CodeGen/X86/vector-trunc-packus.ll
+++ b/llvm/test/CodeGen/X86/vector-trunc-packus.ll
@@ -698,63 +698,23 @@ define <8 x i32> @trunc_packus_v8i64_v8i32(ptr %p0) "min-legal-vector-width"="25
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: retq
;
-; AVX2-SLOW-LABEL: trunc_packus_v8i64_v8i32:
-; AVX2-SLOW: # %bb.0:
-; AVX2-SLOW-NEXT: vmovdqa (%rdi), %ymm0
-; AVX2-SLOW-NEXT: vmovdqa 32(%rdi), %ymm1
-; AVX2-SLOW-NEXT: vpbroadcastq {{.*#+}} ymm2 = [4294967295,4294967295,4294967295,4294967295]
-; AVX2-SLOW-NEXT: vpcmpgtq %ymm0, %ymm2, %ymm3
-; AVX2-SLOW-NEXT: vblendvpd %ymm3, %ymm0, %ymm2, %ymm0
-; AVX2-SLOW-NEXT: vpcmpgtq %ymm1, %ymm2, %ymm3
-; AVX2-SLOW-NEXT: vblendvpd %ymm3, %ymm1, %ymm2, %ymm1
-; AVX2-SLOW-NEXT: vpxor %xmm2, %xmm2, %xmm2
-; AVX2-SLOW-NEXT: vpcmpgtq %ymm2, %ymm1, %ymm3
-; AVX2-SLOW-NEXT: vpand %ymm1, %ymm3, %ymm1
-; AVX2-SLOW-NEXT: vpcmpgtq %ymm2, %ymm0, %ymm2
-; AVX2-SLOW-NEXT: vpand %ymm0, %ymm2, %ymm0
-; AVX2-SLOW-NEXT: vperm2i128 {{.*#+}} ymm2 = ymm0[2,3],ymm1[2,3]
-; AVX2-SLOW-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-SLOW-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm2[0,2],ymm0[4,6],ymm2[4,6]
-; AVX2-SLOW-NEXT: retq
-;
-; AVX2-FAST-ALL-LABEL: trunc_packus_v8i64_v8i32:
-; AVX2-FAST-ALL: # %bb.0:
-; AVX2-FAST-ALL-NEXT: vmovdqa (%rdi), %ymm0
-; AVX2-FAST-ALL-NEXT: vmovdqa 32(%rdi), %ymm1
-; AVX2-FAST-ALL-NEXT: vpbroadcastq {{.*#+}} ymm2 = [4294967295,4294967295,4294967295,4294967295]
-; AVX2-FAST-ALL-NEXT: vpcmpgtq %ymm0, %ymm2, %ymm3
-; AVX2-FAST-ALL-NEXT: vblendvpd %ymm3, %ymm0, %ymm2, %ymm0
-; AVX2-FAST-ALL-NEXT: vpcmpgtq %ymm1, %ymm2, %ymm3
-; AVX2-FAST-ALL-NEXT: vblendvpd %ymm3, %ymm1, %ymm2, %ymm1
-; AVX2-FAST-ALL-NEXT: vpxor %xmm2, %xmm2, %xmm2
-; AVX2-FAST-ALL-NEXT: vpcmpgtq %ymm2, %ymm1, %ymm3
-; AVX2-FAST-ALL-NEXT: vpand %ymm1, %ymm3, %ymm1
-; AVX2-FAST-ALL-NEXT: vpcmpgtq %ymm2, %ymm0, %ymm2
-; AVX2-FAST-ALL-NEXT: vpand %ymm0, %ymm2, %ymm0
-; AVX2-FAST-ALL-NEXT: vpmovsxbd {{.*#+}} ymm2 = [0,2,4,6,4,6,6,7]
-; AVX2-FAST-ALL-NEXT: vpermd %ymm0, %ymm2, %ymm0
-; AVX2-FAST-ALL-NEXT: vpermd %ymm1, %ymm2, %ymm1
-; AVX2-FAST-ALL-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-FAST-ALL-NEXT: retq
-;
-; AVX2-FAST-PERLANE-LABEL: trunc_packus_v8i64_v8i32:
-; AVX2-FAST-PERLANE: # %bb.0:
-; AVX2-FAST-PERLANE-NEXT: vmovdqa (%rdi), %ymm0
-; AVX2-FAST-PERLANE-NEXT: vmovdqa 32(%rdi), %ymm1
-; AVX2-FAST-PERLANE-NEXT: vpbroadcastq {{.*#+}} ymm2 = [4294967295,4294967295,4294967295,4294967295]
-; AVX2-FAST-PERLANE-NEXT: vpcmpgtq %ymm0, %ymm2, %ymm3
-; AVX2-FAST-PERLANE-NEXT: vblendvpd %ymm3, %ymm0, %ymm2, %ymm0
-; AVX2-FAST-PERLANE-NEXT: vpcmpgtq %ymm1, %ymm2, %ymm3
-; AVX2-FAST-PERLANE-NEXT: vblendvpd %ymm3, %ymm1, %ymm2, %ymm1
-; AVX2-FAST-PERLANE-NEXT: vpxor %xmm2, %xmm2, %xmm2
-; AVX2-FAST-PERLANE-NEXT: vpcmpgtq %ymm2, %ymm1, %ymm3
-; AVX2-FAST-PERLANE-NEXT: vpand %ymm1, %ymm3, %ymm1
-; AVX2-FAST-PERLANE-NEXT: vpcmpgtq %ymm2, %ymm0, %ymm2
-; AVX2-FAST-PERLANE-NEXT: vpand %ymm0, %ymm2, %ymm0
-; AVX2-FAST-PERLANE-NEXT: vperm2i128 {{.*#+}} ymm2 = ymm0[2,3],ymm1[2,3]
-; AVX2-FAST-PERLANE-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-FAST-PERLANE-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm2[0,2],ymm0[4,6],ymm2[4,6]
-; AVX2-FAST-PERLANE-NEXT: retq
+; AVX2-LABEL: trunc_packus_v8i64_v8i32:
+; AVX2: # %bb.0:
+; AVX2-NEXT: vmovdqa (%rdi), %ymm0
+; AVX2-NEXT: vmovdqa 32(%rdi), %ymm1
+; AVX2-NEXT: vpbroadcastq {{.*#+}} ymm2 = [4294967295,4294967295,4294967295,4294967295]
+; AVX2-NEXT: vpcmpgtq %ymm0, %ymm2, %ymm3
+; AVX2-NEXT: vblendvpd %ymm3, %ymm0, %ymm2, %ymm0
+; AVX2-NEXT: vpcmpgtq %ymm1, %ymm2, %ymm3
+; AVX2-NEXT: vblendvpd %ymm3, %ymm1, %ymm2, %ymm1
+; AVX2-NEXT: vpxor %xmm2, %xmm2, %xmm2
+; AVX2-NEXT: vpcmpgtq %ymm2, %ymm1, %ymm3
+; AVX2-NEXT: vpand %ymm1, %ymm3, %ymm1
+; AVX2-NEXT: vpcmpgtq %ymm2, %ymm0, %ymm2
+; AVX2-NEXT: vpand %ymm0, %ymm2, %ymm0
+; AVX2-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
+; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc_packus_v8i64_v8i32:
; AVX512: # %bb.0:
diff --git a/llvm/test/CodeGen/X86/vector-trunc-ssat.ll b/llvm/test/CodeGen/X86/vector-trunc-ssat.ll
index b6557e929a5fd..d0cdbf1e3f08d 100644
--- a/llvm/test/CodeGen/X86/vector-trunc-ssat.ll
+++ b/llvm/test/CodeGen/X86/vector-trunc-ssat.ll
@@ -720,63 +720,23 @@ define <8 x i32> @trunc_ssat_v8i64_v8i32(ptr %p0) "min-legal-vector-width"="256"
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: retq
;
-; AVX2-SLOW-LABEL: trunc_ssat_v8i64_v8i32:
-; AVX2-SLOW: # %bb.0:
-; AVX2-SLOW-NEXT: vmovdqa (%rdi), %ymm0
-; AVX2-SLOW-NEXT: vmovdqa 32(%rdi), %ymm1
-; AVX2-SLOW-NEXT: vpbroadcastq {{.*#+}} ymm2 = [2147483647,2147483647,2147483647,2147483647]
-; AVX2-SLOW-NEXT: vpcmpgtq %ymm0, %ymm2, %ymm3
-; AVX2-SLOW-NEXT: vblendvpd %ymm3, %ymm0, %ymm2, %ymm0
-; AVX2-SLOW-NEXT: vpcmpgtq %ymm1, %ymm2, %ymm3
-; AVX2-SLOW-NEXT: vblendvpd %ymm3, %ymm1, %ymm2, %ymm1
-; AVX2-SLOW-NEXT: vpbroadcastq {{.*#+}} ymm2 = [18446744071562067968,18446744071562067968,18446744071562067968,18446744071562067968]
-; AVX2-SLOW-NEXT: vpcmpgtq %ymm2, %ymm1, %ymm3
-; AVX2-SLOW-NEXT: vblendvpd %ymm3, %ymm1, %ymm2, %ymm1
-; AVX2-SLOW-NEXT: vpcmpgtq %ymm2, %ymm0, %ymm3
-; AVX2-SLOW-NEXT: vblendvpd %ymm3, %ymm0, %ymm2, %ymm0
-; AVX2-SLOW-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm0[2,3],ymm1[2,3]
-; AVX2-SLOW-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-SLOW-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm2[0,2],ymm0[4,6],ymm2[4,6]
-; AVX2-SLOW-NEXT: retq
-;
-; AVX2-FAST-ALL-LABEL: trunc_ssat_v8i64_v8i32:
-; AVX2-FAST-ALL: # %bb.0:
-; AVX2-FAST-ALL-NEXT: vmovdqa (%rdi), %ymm0
-; AVX2-FAST-ALL-NEXT: vmovdqa 32(%rdi), %ymm1
-; AVX2-FAST-ALL-NEXT: vpbroadcastq {{.*#+}} ymm2 = [2147483647,2147483647,2147483647,2147483647]
-; AVX2-FAST-ALL-NEXT: vpcmpgtq %ymm0, %ymm2, %ymm3
-; AVX2-FAST-ALL-NEXT: vblendvpd %ymm3, %ymm0, %ymm2, %ymm0
-; AVX2-FAST-ALL-NEXT: vpcmpgtq %ymm1, %ymm2, %ymm3
-; AVX2-FAST-ALL-NEXT: vblendvpd %ymm3, %ymm1, %ymm2, %ymm1
-; AVX2-FAST-ALL-NEXT: vpbroadcastq {{.*#+}} ymm2 = [18446744071562067968,18446744071562067968,18446744071562067968,18446744071562067968]
-; AVX2-FAST-ALL-NEXT: vpcmpgtq %ymm2, %ymm1, %ymm3
-; AVX2-FAST-ALL-NEXT: vblendvpd %ymm3, %ymm1, %ymm2, %ymm1
-; AVX2-FAST-ALL-NEXT: vpcmpgtq %ymm2, %ymm0, %ymm3
-; AVX2-FAST-ALL-NEXT: vblendvpd %ymm3, %ymm0, %ymm2, %ymm0
-; AVX2-FAST-ALL-NEXT: vmovapd {{.*#+}} ymm2 = [0,2,4,6,4,6,6,7]
-; AVX2-FAST-ALL-NEXT: vpermps %ymm0, %ymm2, %ymm0
-; AVX2-FAST-ALL-NEXT: vpermps %ymm1, %ymm2, %ymm1
-; AVX2-FAST-ALL-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-FAST-ALL-NEXT: retq
-;
-; AVX2-FAST-PERLANE-LABEL: trunc_ssat_v8i64_v8i32:
-; AVX2-FAST-PERLANE: # %bb.0:
-; AVX2-FAST-PERLANE-NEXT: vmovdqa (%rdi), %ymm0
-; AVX2-FAST-PERLANE-NEXT: vmovdqa 32(%rdi), %ymm1
-; AVX2-FAST-PERLANE-NEXT: vpbroadcastq {{.*#+}} ymm2 = [2147483647,2147483647,2147483647,2147483647]
-; AVX2-FAST-PERLANE-NEXT: vpcmpgtq %ymm0, %ymm2, %ymm3
-; AVX2-FAST-PERLANE-NEXT: vblendvpd %ymm3, %ymm0, %ymm2, %ymm0
-; AVX2-FAST-PERLANE-NEXT: vpcmpgtq %ymm1, %ymm2, %ymm3
-; AVX2-FAST-PERLANE-NEXT: vblendvpd %ymm3, %ymm1, %ymm2, %ymm1
-; AVX2-FAST-PERLANE-NEXT: vpbroadcastq {{.*#+}} ymm2 = [18446744071562067968,18446744071562067968,18446744071562067968,18446744071562067968]
-; AVX2-FAST-PERLANE-NEXT: vpcmpgtq %ymm2, %ymm1, %ymm3
-; AVX2-FAST-PERLANE-NEXT: vblendvpd %ymm3, %ymm1, %ymm2, %ymm1
-; AVX2-FAST-PERLANE-NEXT: vpcmpgtq %ymm2, %ymm0, %ymm3
-; AVX2-FAST-PERLANE-NEXT: vblendvpd %ymm3, %ymm0, %ymm2, %ymm0
-; AVX2-FAST-PERLANE-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm0[2,3],ymm1[2,3]
-; AVX2-FAST-PERLANE-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-FAST-PERLANE-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm2[0,2],ymm0[4,6],ymm2[4,6]
-; AVX2-FAST-PERLANE-NEXT: retq
+; AVX2-LABEL: trunc_ssat_v8i64_v8i32:
+; AVX2: # %bb.0:
+; AVX2-NEXT: vmovdqa (%rdi), %ymm0
+; AVX2-NEXT: vmovdqa 32(%rdi), %ymm1
+; AVX2-NEXT: vpbroadcastq {{.*#+}} ymm2 = [2147483647,2147483647,2147483647,2147483647]
+; AVX2-NEXT: vpcmpgtq %ymm0, %ymm2, %ymm3
+; AVX2-NEXT: vblendvpd %ymm3, %ymm0, %ymm2, %ymm0
+; AVX2-NEXT: vpcmpgtq %ymm1, %ymm2, %ymm3
+; AVX2-NEXT: vblendvpd %ymm3, %ymm1, %ymm2, %ymm1
+; AVX2-NEXT: vpbroadcastq {{.*#+}} ymm2 = [18446744071562067968,18446744071562067968,18446744071562067968,18446744071562067968]
+; AVX2-NEXT: vpcmpgtq %ymm2, %ymm1, %ymm3
+; AVX2-NEXT: vblendvpd %ymm3, %ymm1, %ymm2, %ymm1
+; AVX2-NEXT: vpcmpgtq %ymm2, %ymm0, %ymm3
+; AVX2-NEXT: vblendvpd %ymm3, %ymm0, %ymm2, %ymm0
+; AVX2-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
+; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc_ssat_v8i64_v8i32:
; AVX512: # %bb.0:
diff --git a/llvm/test/CodeGen/X86/vector-trunc-usat.ll b/llvm/test/CodeGen/X86/vector-trunc-usat.ll
index 23af4283dc79a..65916aaf52f9e 100644
--- a/llvm/test/CodeGen/X86/vector-trunc-usat.ll
+++ b/llvm/test/CodeGen/X86/vector-trunc-usat.ll
@@ -477,60 +477,22 @@ define <8 x i32> @trunc_usat_v8i64_v8i32(ptr %p0) {
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: retq
;
-; AVX2-SLOW-LABEL: trunc_usat_v8i64_v8i32:
-; AVX2-SLOW: # %bb.0:
-; AVX2-SLOW-NEXT: vmovdqa (%rdi), %ymm0
-; AVX2-SLOW-NEXT: vmovdqa 32(%rdi), %ymm1
-; AVX2-SLOW-NEXT: vbroadcastsd {{.*#+}} ymm2 = [4294967295,4294967295,4294967295,4294967295]
-; AVX2-SLOW-NEXT: vpbroadcastq {{.*#+}} ymm3 = [9223372036854775808,9223372036854775808,9223372036854775808,9223372036854775808]
-; AVX2-SLOW-NEXT: vpxor %ymm3, %ymm1, %ymm4
-; AVX2-SLOW-NEXT: vpbroadcastq {{.*#+}} ymm5 = [9223372041149743103,9223372041149743103,9223372041149743103,9223372041149743103]
-; AVX2-SLOW-NEXT: vpcmpgtq %ymm4, %ymm5, %ymm4
-; AVX2-SLOW-NEXT: vblendvpd %ymm4, %ymm1, %ymm2, %ymm1
-; AVX2-SLOW-NEXT: vpxor %ymm3, %ymm0, %ymm3
-; AVX2-SLOW-NEXT: vpcmpgtq %ymm3, %ymm5, %ymm3
-; AVX2-SLOW-NEXT: vblendvpd %ymm3, %ymm0, %ymm2, %ymm0
-; AVX2-SLOW-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm0[2,3],ymm1[2,3]
-; AVX2-SLOW-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-SLOW-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm2[0,2],ymm0[4,6],ymm2[4,6]
-; AVX2-SLOW-NEXT: retq
-;
-; AVX2-FAST-ALL-LABEL: trunc_usat_v8i64_v8i32:
-; AVX2-FAST-ALL: # %bb.0:
-; AVX2-FAST-ALL-NEXT: vmovdqa (%rdi), %ymm0
-; AVX2-FAST-ALL-NEXT: vmovdqa 32(%rdi), %ymm1
-; AVX2-FAST-ALL-NEXT: vbroadcastsd {{.*#+}} ymm2 = [4294967295,4294967295,4294967295,4294967295]
-; AVX2-FAST-ALL-NEXT: vpbroadcastq {{.*#+}} ymm3 = [9223372036854775808,9223372036854775808,9223372036854775808,9223372036854775808]
-; AVX2-FAST-ALL-NEXT: vpxor %ymm3, %ymm1, %ymm4
-; AVX2-FAST-ALL-NEXT: vpbroadcastq {{.*#+}} ymm5 = [9223372041149743103,9223372041149743103,9223372041149743103,9223372041149743103]
-; AVX2-FAST-ALL-NEXT: vpcmpgtq %ymm4, %ymm5, %ymm4
-; AVX2-FAST-ALL-NEXT: vblendvpd %ymm4, %ymm1, %ymm2, %ymm1
-; AVX2-FAST-ALL-NEXT: vpxor %ymm3, %ymm0, %ymm3
-; AVX2-FAST-ALL-NEXT: vpcmpgtq %ymm3, %ymm5, %ymm3
-; AVX2-FAST-ALL-NEXT: vblendvpd %ymm3, %ymm0, %ymm2, %ymm0
-; AVX2-FAST-ALL-NEXT: vmovapd {{.*#+}} ymm2 = [0,2,4,6,4,6,6,7]
-; AVX2-FAST-ALL-NEXT: vpermps %ymm0, %ymm2, %ymm0
-; AVX2-FAST-ALL-NEXT: vpermps %ymm1, %ymm2, %ymm1
-; AVX2-FAST-ALL-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-FAST-ALL-NEXT: retq
-;
-; AVX2-FAST-PERLANE-LABEL: trunc_usat_v8i64_v8i32:
-; AVX2-FAST-PERLANE: # %bb.0:
-; AVX2-FAST-PERLANE-NEXT: vmovdqa (%rdi), %ymm0
-; AVX2-FAST-PERLANE-NEXT: vmovdqa 32(%rdi), %ymm1
-; AVX2-FAST-PERLANE-NEXT: vbroadcastsd {{.*#+}} ymm2 = [4294967295,4294967295,4294967295,4294967295]
-; AVX2-FAST-PERLANE-NEXT: vpbroadcastq {{.*#+}} ymm3 = [9223372036854775808,9223372036854775808,9223372036854775808,9223372036854775808]
-; AVX2-FAST-PERLANE-NEXT: vpxor %ymm3, %ymm1, %ymm4
-; AVX2-FAST-PERLANE-NEXT: vpbroadcastq {{.*#+}} ymm5 = [9223372041149743103,9223372041149743103,9223372041149743103,9223372041149743103]
-; AVX2-FAST-PERLANE-NEXT: vpcmpgtq %ymm4, %ymm5, %ymm4
-; AVX2-FAST-PERLANE-NEXT: vblendvpd %ymm4, %ymm1, %ymm2, %ymm1
-; AVX2-FAST-PERLANE-NEXT: vpxor %ymm3, %ymm0, %ymm3
-; AVX2-FAST-PERLANE-NEXT: vpcmpgtq %ymm3, %ymm5, %ymm3
-; AVX2-FAST-PERLANE-NEXT: vblendvpd %ymm3, %ymm0, %ymm2, %ymm0
-; AVX2-FAST-PERLANE-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm0[2,3],ymm1[2,3]
-; AVX2-FAST-PERLANE-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-FAST-PERLANE-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm2[0,2],ymm0[4,6],ymm2[4,6]
-; AVX2-FAST-PERLANE-NEXT: retq
+; AVX2-LABEL: trunc_usat_v8i64_v8i32:
+; AVX2: # %bb.0:
+; AVX2-NEXT: vmovdqa (%rdi), %ymm0
+; AVX2-NEXT: vmovdqa 32(%rdi), %ymm1
+; AVX2-NEXT: vbroadcastsd {{.*#+}} ymm2 = [4294967295,4294967295,4294967295,4294967295]
+; AVX2-NEXT: vpbroadcastq {{.*#+}} ymm3 = [9223372036854775808,9223372036854775808,9223372036854775808,9223372036854775808]
+; AVX2-NEXT: vpxor %ymm3, %ymm1, %ymm4
+; AVX2-NEXT: vpbroadcastq {{.*#+}} ymm5 = [9223372041149743103,9223372041149743103,9223372041149743103,9223372041149743103]
+; AVX2-NEXT: vpcmpgtq %ymm4, %ymm5, %ymm4
+; AVX2-NEXT: vblendvpd %ymm4, %ymm1, %ymm2, %ymm1
+; AVX2-NEXT: vpxor %ymm3, %ymm0, %ymm3
+; AVX2-NEXT: vpcmpgtq %ymm3, %ymm5, %ymm3
+; AVX2-NEXT: vblendvpd %ymm3, %ymm0, %ymm2, %ymm0
+; AVX2-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
+; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc_usat_v8i64_v8i32:
; AVX512: # %bb.0:
diff --git a/llvm/test/CodeGen/X86/vector-trunc.ll b/llvm/test/CodeGen/X86/vector-trunc.ll
index 732cc445ddcd8..9470e83b05dc4 100644
--- a/llvm/test/CodeGen/X86/vector-trunc.ll
+++ b/llvm/test/CodeGen/X86/vector-trunc.ll
@@ -3,9 +3,9 @@
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+ssse3 | FileCheck %s --check-prefixes=SSE,SSE2-SSSE3,SSSE3
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefixes=SSE,SSE41
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefixes=AVX,AVX1
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=AVX,AVX2,AVX2-SLOW
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2,+fast-variable-crosslane-shuffle,+fast-variable-perlane-shuffle | FileCheck %s --check-prefixes=AVX,AVX2,AVX2-FAST-ALL
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2,+fast-variable-perlane-shuffle | FileCheck %s --check-prefixes=AVX,AVX2,AVX2-FAST-PERLANE
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=AVX,AVX2
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2,+fast-variable-crosslane-shuffle,+fast-variable-perlane-shuffle | FileCheck %s --check-prefixes=AVX,AVX2
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2,+fast-variable-perlane-shuffle | FileCheck %s --check-prefixes=AVX,AVX2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f | FileCheck %s --check-prefix=AVX512 --check-prefix=AVX512F
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512vl,+fast-variable-crosslane-shuffle,+fast-variable-perlane-shuffle | FileCheck %s --check-prefixes=AVX512,AVX512VL
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512vl,+fast-variable-perlane-shuffle | FileCheck %s --check-prefixes=AVX512,AVX512VL
@@ -29,27 +29,11 @@ define <8 x i32> @trunc8i64_8i32(<8 x i64> %a) {
; AVX1-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm2[0,2],ymm0[4,6],ymm2[4,6]
; AVX1-NEXT: retq
;
-; AVX2-SLOW-LABEL: trunc8i64_8i32:
-; AVX2-SLOW: # %bb.0: # %entry
-; AVX2-SLOW-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm0[2,3],ymm1[2,3]
-; AVX2-SLOW-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-SLOW-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm2[0,2],ymm0[4,6],ymm2[4,6]
-; AVX2-SLOW-NEXT: retq
-;
-; AVX2-FAST-ALL-LABEL: trunc8i64_8i32:
-; AVX2-FAST-ALL: # %bb.0: # %entry
-; AVX2-FAST-ALL-NEXT: vmovaps {{.*#+}} ymm2 = [0,2,4,6,4,6,6,7]
-; AVX2-FAST-ALL-NEXT: vpermps %ymm0, %ymm2, %ymm0
-; AVX2-FAST-ALL-NEXT: vpermps %ymm1, %ymm2, %ymm1
-; AVX2-FAST-ALL-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-FAST-ALL-NEXT: retq
-;
-; AVX2-FAST-PERLANE-LABEL: trunc8i64_8i32:
-; AVX2-FAST-PERLANE: # %bb.0: # %entry
-; AVX2-FAST-PERLANE-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm0[2,3],ymm1[2,3]
-; AVX2-FAST-PERLANE-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-FAST-PERLANE-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm2[0,2],ymm0[4,6],ymm2[4,6]
-; AVX2-FAST-PERLANE-NEXT: retq
+; AVX2-LABEL: trunc8i64_8i32:
+; AVX2: # %bb.0: # %entry
+; AVX2-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
+; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc8i64_8i32:
; AVX512: # %bb.0: # %entry
@@ -75,27 +59,11 @@ define <8 x i32> @trunc8i64_8i32_ashr(<8 x i64> %a) {
; AVX1-NEXT: vshufps {{.*#+}} ymm0 = ymm0[1,3],ymm2[1,3],ymm0[5,7],ymm2[5,7]
; AVX1-NEXT: retq
;
-; AVX2-SLOW-LABEL: trunc8i64_8i32_ashr:
-; AVX2-SLOW: # %bb.0: # %entry
-; AVX2-SLOW-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm0[2,3],ymm1[2,3]
-; AVX2-SLOW-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-SLOW-NEXT: vshufps {{.*#+}} ymm0 = ymm0[1,3],ymm2[1,3],ymm0[5,7],ymm2[5,7]
-; AVX2-SLOW-NEXT: retq
-;
-; AVX2-FAST-ALL-LABEL: trunc8i64_8i32_ashr:
-; AVX2-FAST-ALL: # %bb.0: # %entry
-; AVX2-FAST-ALL-NEXT: vmovaps {{.*#+}} xmm2 = [1,3,5,7]
-; AVX2-FAST-ALL-NEXT: vpermps %ymm0, %ymm2, %ymm0
-; AVX2-FAST-ALL-NEXT: vpermps %ymm1, %ymm2, %ymm1
-; AVX2-FAST-ALL-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-FAST-ALL-NEXT: retq
-;
-; AVX2-FAST-PERLANE-LABEL: trunc8i64_8i32_ashr:
-; AVX2-FAST-PERLANE: # %bb.0: # %entry
-; AVX2-FAST-PERLANE-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm0[2,3],ymm1[2,3]
-; AVX2-FAST-PERLANE-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-FAST-PERLANE-NEXT: vshufps {{.*#+}} ymm0 = ymm0[1,3],ymm2[1,3],ymm0[5,7],ymm2[5,7]
-; AVX2-FAST-PERLANE-NEXT: retq
+; AVX2-LABEL: trunc8i64_8i32_ashr:
+; AVX2: # %bb.0: # %entry
+; AVX2-NEXT: vshufps {{.*#+}} ymm0 = ymm0[1,3],ymm1[1,3],ymm0[5,7],ymm1[5,7]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
+; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc8i64_8i32_ashr:
; AVX512: # %bb.0: # %entry
@@ -123,27 +91,11 @@ define <8 x i32> @trunc8i64_8i32_lshr(<8 x i64> %a) {
; AVX1-NEXT: vshufps {{.*#+}} ymm0 = ymm0[1,3],ymm2[1,3],ymm0[5,7],ymm2[5,7]
; AVX1-NEXT: retq
;
-; AVX2-SLOW-LABEL: trunc8i64_8i32_lshr:
-; AVX2-SLOW: # %bb.0: # %entry
-; AVX2-SLOW-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm0[2,3],ymm1[2,3]
-; AVX2-SLOW-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-SLOW-NEXT: vshufps {{.*#+}} ymm0 = ymm0[1,3],ymm2[1,3],ymm0[5,7],ymm2[5,7]
-; AVX2-SLOW-NEXT: retq
-;
-; AVX2-FAST-ALL-LABEL: trunc8i64_8i32_lshr:
-; AVX2-FAST-ALL: # %bb.0: # %entry
-; AVX2-FAST-ALL-NEXT: vmovaps {{.*#+}} xmm2 = [1,3,5,7]
-; AVX2-FAST-ALL-NEXT: vpermps %ymm0, %ymm2, %ymm0
-; AVX2-FAST-ALL-NEXT: vpermps %ymm1, %ymm2, %ymm1
-; AVX2-FAST-ALL-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-FAST-ALL-NEXT: retq
-;
-; AVX2-FAST-PERLANE-LABEL: trunc8i64_8i32_lshr:
-; AVX2-FAST-PERLANE: # %bb.0: # %entry
-; AVX2-FAST-PERLANE-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm0[2,3],ymm1[2,3]
-; AVX2-FAST-PERLANE-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-FAST-PERLANE-NEXT: vshufps {{.*#+}} ymm0 = ymm0[1,3],ymm2[1,3],ymm0[5,7],ymm2[5,7]
-; AVX2-FAST-PERLANE-NEXT: retq
+; AVX2-LABEL: trunc8i64_8i32_lshr:
+; AVX2: # %bb.0: # %entry
+; AVX2-NEXT: vshufps {{.*#+}} ymm0 = ymm0[1,3],ymm1[1,3],ymm0[5,7],ymm1[5,7]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
+; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc8i64_8i32_lshr:
; AVX512: # %bb.0: # %entry
@@ -1273,27 +1225,11 @@ define <8 x i32> @trunc2x4i64_8i32(<4 x i64> %a, <4 x i64> %b) {
; AVX1-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm2[0,2],ymm0[4,6],ymm2[4,6]
; AVX1-NEXT: retq
;
-; AVX2-SLOW-LABEL: trunc2x4i64_8i32:
-; AVX2-SLOW: # %bb.0: # %entry
-; AVX2-SLOW-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm0[2,3],ymm1[2,3]
-; AVX2-SLOW-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-SLOW-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm2[0,2],ymm0[4,6],ymm2[4,6]
-; AVX2-SLOW-NEXT: retq
-;
-; AVX2-FAST-ALL-LABEL: trunc2x4i64_8i32:
-; AVX2-FAST-ALL: # %bb.0: # %entry
-; AVX2-FAST-ALL-NEXT: vmovaps {{.*#+}} ymm2 = [0,2,4,6,4,6,6,7]
-; AVX2-FAST-ALL-NEXT: vpermps %ymm0, %ymm2, %ymm0
-; AVX2-FAST-ALL-NEXT: vpermps %ymm1, %ymm2, %ymm1
-; AVX2-FAST-ALL-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-FAST-ALL-NEXT: retq
-;
-; AVX2-FAST-PERLANE-LABEL: trunc2x4i64_8i32:
-; AVX2-FAST-PERLANE: # %bb.0: # %entry
-; AVX2-FAST-PERLANE-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm0[2,3],ymm1[2,3]
-; AVX2-FAST-PERLANE-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-FAST-PERLANE-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm2[0,2],ymm0[4,6],ymm2[4,6]
-; AVX2-FAST-PERLANE-NEXT: retq
+; AVX2-LABEL: trunc2x4i64_8i32:
+; AVX2: # %bb.0: # %entry
+; AVX2-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
+; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc2x4i64_8i32:
; AVX512: # %bb.0: # %entry
More information about the llvm-commits
mailing list