https://github.com/jofrn updated
https://github.com/llvm/llvm-project/pull/120598
>From 768b1a91595c23b3902aee20b8142b2897ac3840 Mon Sep 17 00:00:00 2001
From: jofrn <jofer...@amd.com>
Date: Thu, 19 Dec 2024 11:19:39 -0500
Subject: [PATCH] [SelectionDAG] Widen <2 x T> vector types for atomic load
Vector types of 2 elements must be widened. This change does this
for vector types of atomic load in SelectionDAG
so that it can translate aligned vectors of >1 size.
commit-id:2894ccd1
---
llvm/lib/CodeGen/SelectionDAG/LegalizeTypes.h | 1 +
.../SelectionDAG/LegalizeVectorTypes.cpp | 97 ++++--
llvm/test/CodeGen/X86/atomic-load-store.ll | 286 ++++++++++++++++++
3 files changed, 361 insertions(+), 23 deletions(-)
diff --git a/llvm/lib/CodeGen/SelectionDAG/LegalizeTypes.h
b/llvm/lib/CodeGen/SelectionDAG/LegalizeTypes.h
index d24b4517a460d..b6e018ba0e454 100644
--- a/llvm/lib/CodeGen/SelectionDAG/LegalizeTypes.h
+++ b/llvm/lib/CodeGen/SelectionDAG/LegalizeTypes.h
@@ -1068,6 +1068,7 @@ class LLVM_LIBRARY_VISIBILITY DAGTypeLegalizer {
SDValue WidenVecRes_EXTRACT_SUBVECTOR(SDNode* N);
SDValue WidenVecRes_INSERT_SUBVECTOR(SDNode *N);
SDValue WidenVecRes_INSERT_VECTOR_ELT(SDNode* N);
+ SDValue WidenVecRes_ATOMIC_LOAD(AtomicSDNode *N);
SDValue WidenVecRes_LOAD(SDNode* N);
SDValue WidenVecRes_VP_LOAD(VPLoadSDNode *N);
SDValue WidenVecRes_VP_STRIDED_LOAD(VPStridedLoadSDNode *N);
diff --git a/llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
b/llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
index d6cbf2211f053..42763aab5bb55 100644
--- a/llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
@@ -4622,6 +4622,9 @@ void DAGTypeLegalizer::WidenVectorResult(SDNode *N,
unsigned ResNo) {
break;
case ISD::EXTRACT_SUBVECTOR: Res = WidenVecRes_EXTRACT_SUBVECTOR(N); break;
case ISD::INSERT_VECTOR_ELT: Res = WidenVecRes_INSERT_VECTOR_ELT(N); break;
+ case ISD::ATOMIC_LOAD:
+ Res = WidenVecRes_ATOMIC_LOAD(cast<AtomicSDNode>(N));
+ break;
case ISD::LOAD: Res = WidenVecRes_LOAD(N); break;
case ISD::STEP_VECTOR:
case ISD::SPLAT_VECTOR:
@@ -6003,6 +6006,74 @@ SDValue
DAGTypeLegalizer::WidenVecRes_INSERT_VECTOR_ELT(SDNode *N) {
N->getOperand(1), N->getOperand(2));
}
+/// Either return the same load or provide appropriate casts
+/// from the load and return that.
+static SDValue coerceLoadedValue(SDValue LdOp, EVT FirstVT, EVT WidenVT,
+ TypeSize LdWidth, TypeSize FirstVTWidth,
+ SDLoc dl, SelectionDAG &DAG) {
+ assert(TypeSize::isKnownLE(LdWidth, FirstVTWidth));
+ TypeSize WidenWidth = WidenVT.getSizeInBits();
+ if (!FirstVT.isVector()) {
+ unsigned NumElts =
+ WidenWidth.getFixedValue() / FirstVTWidth.getFixedValue();
+ EVT NewVecVT = EVT::getVectorVT(*DAG.getContext(), FirstVT, NumElts);
+ SDValue VecOp = DAG.getNode(ISD::SCALAR_TO_VECTOR, dl, NewVecVT, LdOp);
+ return DAG.getNode(ISD::BITCAST, dl, WidenVT, VecOp);
+ }
+ assert(FirstVT == WidenVT);
+ return LdOp;
+}
+
+static std::optional<EVT> findMemType(SelectionDAG &DAG,
+ const TargetLowering &TLI, unsigned
Width,
+ EVT WidenVT, unsigned Align,
+ unsigned WidenEx);
+
+SDValue DAGTypeLegalizer::WidenVecRes_ATOMIC_LOAD(AtomicSDNode *LD) {
+ EVT WidenVT =
+ TLI.getTypeToTransformTo(*DAG.getContext(), LD->getValueType(0));
+ EVT LdVT = LD->getMemoryVT();
+ SDLoc dl(LD);
+ assert(LdVT.isVector() && WidenVT.isVector() && "Expected vectors");
+ assert(LdVT.isScalableVector() == WidenVT.isScalableVector() &&
+ "Must be scalable");
+ assert(LdVT.getVectorElementType() == WidenVT.getVectorElementType() &&
+ "Expected equivalent element types");
+
+ // Load information
+ SDValue Chain = LD->getChain();
+ SDValue BasePtr = LD->getBasePtr();
+ MachineMemOperand::Flags MMOFlags = LD->getMemOperand()->getFlags();
+ AAMDNodes AAInfo = LD->getAAInfo();
+
+ TypeSize LdWidth = LdVT.getSizeInBits();
+ TypeSize WidenWidth = WidenVT.getSizeInBits();
+ TypeSize WidthDiff = WidenWidth - LdWidth;
+
+ // Find the vector type that can load from.
+ std::optional<EVT> FirstVT =
+ findMemType(DAG, TLI, LdWidth.getKnownMinValue(), WidenVT, /*LdAlign=*/0,
+ WidthDiff.getKnownMinValue());
+
+ if (!FirstVT)
+ return SDValue();
+
+ SmallVector<EVT, 8> MemVTs;
+ TypeSize FirstVTWidth = FirstVT->getSizeInBits();
+
+ SDValue LdOp = DAG.getAtomicLoad(ISD::NON_EXTLOAD, dl, *FirstVT, *FirstVT,
+ Chain, BasePtr, LD->getMemOperand());
+
+ // Load the element with one instruction.
+ SDValue Result = coerceLoadedValue(LdOp, *FirstVT, WidenVT, LdWidth,
+ FirstVTWidth, dl, DAG);
+
+ // Modified the chain - switch anything that used the old chain to use
+ // the new one.
+ ReplaceValueWith(SDValue(LD, 1), LdOp.getValue(1));
+ return Result;
+}
+
SDValue DAGTypeLegalizer::WidenVecRes_LOAD(SDNode *N) {
LoadSDNode *LD = cast<LoadSDNode>(N);
ISD::LoadExtType ExtType = LD->getExtensionType();
@@ -7894,29 +7965,9 @@ SDValue
DAGTypeLegalizer::GenWidenVectorLoads(SmallVectorImpl<SDValue> &LdChain,
LdChain.push_back(LdOp.getValue(1));
// Check if we can load the element with one instruction.
- if (MemVTs.empty()) {
- assert(TypeSize::isKnownLE(LdWidth, FirstVTWidth));
- if (!FirstVT->isVector()) {
- unsigned NumElts =
- WidenWidth.getFixedValue() / FirstVTWidth.getFixedValue();
- EVT NewVecVT = EVT::getVectorVT(*DAG.getContext(), *FirstVT, NumElts);
- SDValue VecOp = DAG.getNode(ISD::SCALAR_TO_VECTOR, dl, NewVecVT, LdOp);
- return DAG.getNode(ISD::BITCAST, dl, WidenVT, VecOp);
- }
- if (FirstVT == WidenVT)
- return LdOp;
-
- // TODO: We don't currently have any tests that exercise this code path.
- assert(WidenWidth.getFixedValue() % FirstVTWidth.getFixedValue() == 0);
- unsigned NumConcat =
- WidenWidth.getFixedValue() / FirstVTWidth.getFixedValue();
- SmallVector<SDValue, 16> ConcatOps(NumConcat);
- SDValue UndefVal = DAG.getUNDEF(*FirstVT);
- ConcatOps[0] = LdOp;
- for (unsigned i = 1; i != NumConcat; ++i)
- ConcatOps[i] = UndefVal;
- return DAG.getNode(ISD::CONCAT_VECTORS, dl, WidenVT, ConcatOps);
- }
+ if (MemVTs.empty())
+ return coerceLoadedValue(LdOp, *FirstVT, WidenVT, LdWidth, FirstVTWidth,
dl,
+ DAG);
// Load vector by using multiple loads from largest vector to scalar.
SmallVector<SDValue, 16> LdOps;
diff --git a/llvm/test/CodeGen/X86/atomic-load-store.ll
b/llvm/test/CodeGen/X86/atomic-load-store.ll
index 3e7b73a65fe07..ff5391f44bbe3 100644
--- a/llvm/test/CodeGen/X86/atomic-load-store.ll
+++ b/llvm/test/CodeGen/X86/atomic-load-store.ll
@@ -270,6 +270,212 @@ define <1 x i64> @atomic_vec1_i64_align(ptr %x) nounwind {
ret <1 x i64> %ret
}
+define <2 x i8> @atomic_vec2_i8(ptr %x) {
+; CHECK-O3-LABEL: atomic_vec2_i8:
+; CHECK-O3: # %bb.0:
+; CHECK-O3-NEXT: movzwl (%rdi), %eax
+; CHECK-O3-NEXT: movd %eax, %xmm0
+; CHECK-O3-NEXT: retq
+;
+; CHECK-SSE-O3-LABEL: atomic_vec2_i8:
+; CHECK-SSE-O3: # %bb.0:
+; CHECK-SSE-O3-NEXT: movzwl (%rdi), %eax
+; CHECK-SSE-O3-NEXT: movd %eax, %xmm0
+; CHECK-SSE-O3-NEXT: retq
+;
+; CHECK-AVX-O3-LABEL: atomic_vec2_i8:
+; CHECK-AVX-O3: # %bb.0:
+; CHECK-AVX-O3-NEXT: movzwl (%rdi), %eax
+; CHECK-AVX-O3-NEXT: vmovd %eax, %xmm0
+; CHECK-AVX-O3-NEXT: retq
+;
+; CHECK-O0-LABEL: atomic_vec2_i8:
+; CHECK-O0: # %bb.0:
+; CHECK-O0-NEXT: movw (%rdi), %cx
+; CHECK-O0-NEXT: # implicit-def: $eax
+; CHECK-O0-NEXT: movw %cx, %ax
+; CHECK-O0-NEXT: movd %eax, %xmm0
+; CHECK-O0-NEXT: retq
+;
+; CHECK-SSE-O0-LABEL: atomic_vec2_i8:
+; CHECK-SSE-O0: # %bb.0:
+; CHECK-SSE-O0-NEXT: movw (%rdi), %cx
+; CHECK-SSE-O0-NEXT: # implicit-def: $eax
+; CHECK-SSE-O0-NEXT: movw %cx, %ax
+; CHECK-SSE-O0-NEXT: movd %eax, %xmm0
+; CHECK-SSE-O0-NEXT: retq
+;
+; CHECK-AVX-O0-LABEL: atomic_vec2_i8:
+; CHECK-AVX-O0: # %bb.0:
+; CHECK-AVX-O0-NEXT: movw (%rdi), %cx
+; CHECK-AVX-O0-NEXT: # implicit-def: $eax
+; CHECK-AVX-O0-NEXT: movw %cx, %ax
+; CHECK-AVX-O0-NEXT: vmovd %eax, %xmm0
+; CHECK-AVX-O0-NEXT: retq
+ %ret = load atomic <2 x i8>, ptr %x acquire, align 4
+ ret <2 x i8> %ret
+}
+
+define <2 x i16> @atomic_vec2_i16(ptr %x) {
+; CHECK-O3-LABEL: atomic_vec2_i16:
+; CHECK-O3: # %bb.0:
+; CHECK-O3-NEXT: movl (%rdi), %eax
+; CHECK-O3-NEXT: movd %eax, %xmm0
+; CHECK-O3-NEXT: retq
+;
+; CHECK-SSE-O3-LABEL: atomic_vec2_i16:
+; CHECK-SSE-O3: # %bb.0:
+; CHECK-SSE-O3-NEXT: movl (%rdi), %eax
+; CHECK-SSE-O3-NEXT: movd %eax, %xmm0
+; CHECK-SSE-O3-NEXT: retq
+;
+; CHECK-AVX-O3-LABEL: atomic_vec2_i16:
+; CHECK-AVX-O3: # %bb.0:
+; CHECK-AVX-O3-NEXT: movl (%rdi), %eax
+; CHECK-AVX-O3-NEXT: vmovd %eax, %xmm0
+; CHECK-AVX-O3-NEXT: retq
+;
+; CHECK-O0-LABEL: atomic_vec2_i16:
+; CHECK-O0: # %bb.0:
+; CHECK-O0-NEXT: movl (%rdi), %eax
+; CHECK-O0-NEXT: movd %eax, %xmm0
+; CHECK-O0-NEXT: retq
+;
+; CHECK-SSE-O0-LABEL: atomic_vec2_i16:
+; CHECK-SSE-O0: # %bb.0:
+; CHECK-SSE-O0-NEXT: movl (%rdi), %eax
+; CHECK-SSE-O0-NEXT: movd %eax, %xmm0
+; CHECK-SSE-O0-NEXT: retq
+;
+; CHECK-AVX-O0-LABEL: atomic_vec2_i16:
+; CHECK-AVX-O0: # %bb.0:
+; CHECK-AVX-O0-NEXT: movl (%rdi), %eax
+; CHECK-AVX-O0-NEXT: vmovd %eax, %xmm0
+; CHECK-AVX-O0-NEXT: retq
+ %ret = load atomic <2 x i16>, ptr %x acquire, align 4
+ ret <2 x i16> %ret
+}
+
+define <2 x ptr addrspace(270)> @atomic_vec2_ptr270(ptr %x) {
+; CHECK-O3-LABEL: atomic_vec2_ptr270:
+; CHECK-O3: # %bb.0:
+; CHECK-O3-NEXT: movq (%rdi), %rax
+; CHECK-O3-NEXT: movq %rax, %xmm0
+; CHECK-O3-NEXT: retq
+;
+; CHECK-SSE-O3-LABEL: atomic_vec2_ptr270:
+; CHECK-SSE-O3: # %bb.0:
+; CHECK-SSE-O3-NEXT: movq (%rdi), %rax
+; CHECK-SSE-O3-NEXT: movq %rax, %xmm0
+; CHECK-SSE-O3-NEXT: retq
+;
+; CHECK-AVX-O3-LABEL: atomic_vec2_ptr270:
+; CHECK-AVX-O3: # %bb.0:
+; CHECK-AVX-O3-NEXT: movq (%rdi), %rax
+; CHECK-AVX-O3-NEXT: vmovq %rax, %xmm0
+; CHECK-AVX-O3-NEXT: retq
+;
+; CHECK-O0-LABEL: atomic_vec2_ptr270:
+; CHECK-O0: # %bb.0:
+; CHECK-O0-NEXT: movq (%rdi), %rax
+; CHECK-O0-NEXT: movq %rax, %xmm0
+; CHECK-O0-NEXT: retq
+;
+; CHECK-SSE-O0-LABEL: atomic_vec2_ptr270:
+; CHECK-SSE-O0: # %bb.0:
+; CHECK-SSE-O0-NEXT: movq (%rdi), %rax
+; CHECK-SSE-O0-NEXT: movq %rax, %xmm0
+; CHECK-SSE-O0-NEXT: retq
+;
+; CHECK-AVX-O0-LABEL: atomic_vec2_ptr270:
+; CHECK-AVX-O0: # %bb.0:
+; CHECK-AVX-O0-NEXT: movq (%rdi), %rax
+; CHECK-AVX-O0-NEXT: vmovq %rax, %xmm0
+; CHECK-AVX-O0-NEXT: retq
+ %ret = load atomic <2 x ptr addrspace(270)>, ptr %x acquire, align 8
+ ret <2 x ptr addrspace(270)> %ret
+}
+
+define <2 x i32> @atomic_vec2_i32_align(ptr %x) {
+; CHECK-O3-LABEL: atomic_vec2_i32_align:
+; CHECK-O3: # %bb.0:
+; CHECK-O3-NEXT: movq (%rdi), %rax
+; CHECK-O3-NEXT: movq %rax, %xmm0
+; CHECK-O3-NEXT: retq
+;
+; CHECK-SSE-O3-LABEL: atomic_vec2_i32_align:
+; CHECK-SSE-O3: # %bb.0:
+; CHECK-SSE-O3-NEXT: movq (%rdi), %rax
+; CHECK-SSE-O3-NEXT: movq %rax, %xmm0
+; CHECK-SSE-O3-NEXT: retq
+;
+; CHECK-AVX-O3-LABEL: atomic_vec2_i32_align:
+; CHECK-AVX-O3: # %bb.0:
+; CHECK-AVX-O3-NEXT: movq (%rdi), %rax
+; CHECK-AVX-O3-NEXT: vmovq %rax, %xmm0
+; CHECK-AVX-O3-NEXT: retq
+;
+; CHECK-O0-LABEL: atomic_vec2_i32_align:
+; CHECK-O0: # %bb.0:
+; CHECK-O0-NEXT: movq (%rdi), %rax
+; CHECK-O0-NEXT: movq %rax, %xmm0
+; CHECK-O0-NEXT: retq
+;
+; CHECK-SSE-O0-LABEL: atomic_vec2_i32_align:
+; CHECK-SSE-O0: # %bb.0:
+; CHECK-SSE-O0-NEXT: movq (%rdi), %rax
+; CHECK-SSE-O0-NEXT: movq %rax, %xmm0
+; CHECK-SSE-O0-NEXT: retq
+;
+; CHECK-AVX-O0-LABEL: atomic_vec2_i32_align:
+; CHECK-AVX-O0: # %bb.0:
+; CHECK-AVX-O0-NEXT: movq (%rdi), %rax
+; CHECK-AVX-O0-NEXT: vmovq %rax, %xmm0
+; CHECK-AVX-O0-NEXT: retq
+ %ret = load atomic <2 x i32>, ptr %x acquire, align 8
+ ret <2 x i32> %ret
+}
+
+define <2 x float> @atomic_vec2_float_align(ptr %x) {
+; CHECK-O3-LABEL: atomic_vec2_float_align:
+; CHECK-O3: # %bb.0:
+; CHECK-O3-NEXT: movq (%rdi), %rax
+; CHECK-O3-NEXT: movq %rax, %xmm0
+; CHECK-O3-NEXT: retq
+;
+; CHECK-SSE-O3-LABEL: atomic_vec2_float_align:
+; CHECK-SSE-O3: # %bb.0:
+; CHECK-SSE-O3-NEXT: movq (%rdi), %rax
+; CHECK-SSE-O3-NEXT: movq %rax, %xmm0
+; CHECK-SSE-O3-NEXT: retq
+;
+; CHECK-AVX-O3-LABEL: atomic_vec2_float_align:
+; CHECK-AVX-O3: # %bb.0:
+; CHECK-AVX-O3-NEXT: movq (%rdi), %rax
+; CHECK-AVX-O3-NEXT: vmovq %rax, %xmm0
+; CHECK-AVX-O3-NEXT: retq
+;
+; CHECK-O0-LABEL: atomic_vec2_float_align:
+; CHECK-O0: # %bb.0:
+; CHECK-O0-NEXT: movq (%rdi), %rax
+; CHECK-O0-NEXT: movq %rax, %xmm0
+; CHECK-O0-NEXT: retq
+;
+; CHECK-SSE-O0-LABEL: atomic_vec2_float_align:
+; CHECK-SSE-O0: # %bb.0:
+; CHECK-SSE-O0-NEXT: movq (%rdi), %rax
+; CHECK-SSE-O0-NEXT: movq %rax, %xmm0
+; CHECK-SSE-O0-NEXT: retq
+;
+; CHECK-AVX-O0-LABEL: atomic_vec2_float_align:
+; CHECK-AVX-O0: # %bb.0:
+; CHECK-AVX-O0-NEXT: movq (%rdi), %rax
+; CHECK-AVX-O0-NEXT: vmovq %rax, %xmm0
+; CHECK-AVX-O0-NEXT: retq
+ %ret = load atomic <2 x float>, ptr %x acquire, align 8
+ ret <2 x float> %ret
+}
+
define <1 x ptr> @atomic_vec1_ptr(ptr %x) nounwind {
; CHECK-O3-LABEL: atomic_vec1_ptr:
; CHECK-O3: # %bb.0:
@@ -691,6 +897,86 @@ define <2 x i32> @atomic_vec2_i32(ptr %x) nounwind {
ret <2 x i32> %ret
}
+define <4 x i8> @atomic_vec4_i8(ptr %x) nounwind {
+; CHECK-O3-LABEL: atomic_vec4_i8:
+; CHECK-O3: # %bb.0:
+; CHECK-O3-NEXT: movl (%rdi), %eax
+; CHECK-O3-NEXT: movd %eax, %xmm0
+; CHECK-O3-NEXT: retq
+;
+; CHECK-SSE-O3-LABEL: atomic_vec4_i8:
+; CHECK-SSE-O3: # %bb.0:
+; CHECK-SSE-O3-NEXT: movl (%rdi), %eax
+; CHECK-SSE-O3-NEXT: movd %eax, %xmm0
+; CHECK-SSE-O3-NEXT: retq
+;
+; CHECK-AVX-O3-LABEL: atomic_vec4_i8:
+; CHECK-AVX-O3: # %bb.0:
+; CHECK-AVX-O3-NEXT: movl (%rdi), %eax
+; CHECK-AVX-O3-NEXT: vmovd %eax, %xmm0
+; CHECK-AVX-O3-NEXT: retq
+;
+; CHECK-O0-LABEL: atomic_vec4_i8:
+; CHECK-O0: # %bb.0:
+; CHECK-O0-NEXT: movl (%rdi), %eax
+; CHECK-O0-NEXT: movd %eax, %xmm0
+; CHECK-O0-NEXT: retq
+;
+; CHECK-SSE-O0-LABEL: atomic_vec4_i8:
+; CHECK-SSE-O0: # %bb.0:
+; CHECK-SSE-O0-NEXT: movl (%rdi), %eax
+; CHECK-SSE-O0-NEXT: movd %eax, %xmm0
+; CHECK-SSE-O0-NEXT: retq
+;
+; CHECK-AVX-O0-LABEL: atomic_vec4_i8:
+; CHECK-AVX-O0: # %bb.0:
+; CHECK-AVX-O0-NEXT: movl (%rdi), %eax
+; CHECK-AVX-O0-NEXT: vmovd %eax, %xmm0
+; CHECK-AVX-O0-NEXT: retq
+ %ret = load atomic <4 x i8>, ptr %x acquire, align 4
+ ret <4 x i8> %ret
+}
+
+define <4 x i16> @atomic_vec4_i16(ptr %x) nounwind {
+; CHECK-O3-LABEL: atomic_vec4_i16:
+; CHECK-O3: # %bb.0:
+; CHECK-O3-NEXT: movq (%rdi), %rax
+; CHECK-O3-NEXT: movq %rax, %xmm0
+; CHECK-O3-NEXT: retq
+;
+; CHECK-SSE-O3-LABEL: atomic_vec4_i16:
+; CHECK-SSE-O3: # %bb.0:
+; CHECK-SSE-O3-NEXT: movq (%rdi), %rax
+; CHECK-SSE-O3-NEXT: movq %rax, %xmm0
+; CHECK-SSE-O3-NEXT: retq
+;
+; CHECK-AVX-O3-LABEL: atomic_vec4_i16:
+; CHECK-AVX-O3: # %bb.0:
+; CHECK-AVX-O3-NEXT: movq (%rdi), %rax
+; CHECK-AVX-O3-NEXT: vmovq %rax, %xmm0
+; CHECK-AVX-O3-NEXT: retq
+;
+; CHECK-O0-LABEL: atomic_vec4_i16:
+; CHECK-O0: # %bb.0:
+; CHECK-O0-NEXT: movq (%rdi), %rax
+; CHECK-O0-NEXT: movq %rax, %xmm0
+; CHECK-O0-NEXT: retq
+;
+; CHECK-SSE-O0-LABEL: atomic_vec4_i16:
+; CHECK-SSE-O0: # %bb.0:
+; CHECK-SSE-O0-NEXT: movq (%rdi), %rax
+; CHECK-SSE-O0-NEXT: movq %rax, %xmm0
+; CHECK-SSE-O0-NEXT: retq
+;
+; CHECK-AVX-O0-LABEL: atomic_vec4_i16:
+; CHECK-AVX-O0: # %bb.0:
+; CHECK-AVX-O0-NEXT: movq (%rdi), %rax
+; CHECK-AVX-O0-NEXT: vmovq %rax, %xmm0
+; CHECK-AVX-O0-NEXT: retq
+ %ret = load atomic <4 x i16>, ptr %x acquire, align 8
+ ret <4 x i16> %ret
+}
+
define <4 x float> @atomic_vec4_float(ptr %x) nounwind {
; CHECK-O3-LABEL: atomic_vec4_float:
; CHECK-O3: # %bb.0:
_______________________________________________
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
