[llvm] [ARM] Use correct ABI for atomic functions (PR #128891)
via llvm-commits
llvm-commits at lists.llvm.org
Wed Feb 26 07:15:32 PST 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-arm
Author: Oliver Stannard (ostannard)
<details>
<summary>Changes</summary>
The AArch32 PCS passes small integer arguments in registers by zero- or sign-extending them in the caller, but we were previously generating calls to the __atomic and __sync functions which left other values in the high bits. This is important in practice for the atomic min/max functions, which have signed versions which expect the value to have been correctly sign-extended.
This bug existed in two places: the AtomicExpand IR pass, and in DAG ISel. For the firrst, the fix is to add the `zeroext` or `signext` attributes to the function arguments, and for the latter we insert the zero- or sign-extension functions when converting the DAG node to a function call.
While testing this, I noticed that AArch64 is doing this extension in some cases, but that isn't needed because in the AArch64 PCS the high bits are unspecified, the callee does the extension. There was already a target lowering hook to configure this, so I've set it correctly for AArch64.
Fixes #<!-- -->61880
---
Patch is 39.90 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/128891.diff
11 Files Affected:
- (modified) llvm/lib/CodeGen/AtomicExpandPass.cpp (+13)
- (modified) llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp (+30-7)
- (modified) llvm/lib/Target/AArch64/AArch64ISelLowering.h (+4)
- (modified) llvm/test/CodeGen/AArch64/atomicrmw-fadd.ll (+16-16)
- (modified) llvm/test/CodeGen/AArch64/atomicrmw-fmax.ll (+16-16)
- (modified) llvm/test/CodeGen/AArch64/atomicrmw-fmin.ll (+16-16)
- (modified) llvm/test/CodeGen/AArch64/atomicrmw-fsub.ll (+16-16)
- (modified) llvm/test/CodeGen/AArch64/strictfp_f16_abi_promote.ll (+7-10)
- (modified) llvm/test/CodeGen/ARM/atomic-cmpxchg.ll (+10-9)
- (modified) llvm/test/CodeGen/ARM/atomic-load-store.ll (+37-29)
- (modified) llvm/test/CodeGen/ARM/thumbv6m-atomic32.ll (+264)
``````````diff
diff --git a/llvm/lib/CodeGen/AtomicExpandPass.cpp b/llvm/lib/CodeGen/AtomicExpandPass.cpp
index a75fa688d87a8..b13d380ae7c7e 100644
--- a/llvm/lib/CodeGen/AtomicExpandPass.cpp
+++ b/llvm/lib/CodeGen/AtomicExpandPass.cpp
@@ -1999,6 +1999,19 @@ bool AtomicExpandImpl::expandAtomicOpToLibcall(
Value *IntValue =
Builder.CreateBitOrPointerCast(ValueOperand, SizedIntTy);
Args.push_back(IntValue);
+
+ // Set the zeroext/signext attributes on the parameter if needed to match
+ // the target's ABI.
+ if (TLI->shouldExtendTypeInLibCall(
+ TLI->getMemValueType(DL, SizedIntTy))) {
+ // The only atomic operations affected by signedness are min/max, and
+ // we don't have __atomic_ libcalls for them, so IsSigned is always
+ // false.
+ if (TLI->shouldSignExtendTypeInLibCall(SizedIntTy, false /*IsSigned*/))
+ Attr = Attr.addParamAttribute(Ctx, Args.size() - 1, Attribute::SExt);
+ else
+ Attr = Attr.addParamAttribute(Ctx, Args.size() - 1, Attribute::ZExt);
+ }
} else {
AllocaValue = AllocaBuilder.CreateAlloca(ValueOperand->getType());
AllocaValue->setAlignment(AllocaAlignment);
diff --git a/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp b/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp
index f56097fdbb51a..9cd4e42cfd062 100644
--- a/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp
@@ -4386,23 +4386,46 @@ void SelectionDAGLegalize::ConvertNodeToLibcall(SDNode *Node) {
AtomicOrdering Order = cast<AtomicSDNode>(Node)->getMergedOrdering();
RTLIB::Libcall LC = RTLIB::getOUTLINE_ATOMIC(Opc, Order, VT);
EVT RetVT = Node->getValueType(0);
+ SDValue ChainIn = Node->getOperand(0);
+ SDValue Pointer = Node->getOperand(1);
+ SDLoc dl(Node);
SmallVector<SDValue, 4> Ops;
+
+ // Zero/sign extend small operands if required by the target's ABI.
+ SmallVector<SDValue, 4> ExtendedOps;
+ for (auto Op = Node->op_begin() + 2, E = Node->op_end(); Op != E; ++Op) {
+ if (TLI.shouldExtendTypeInLibCall(VT)) {
+ bool IsSigned =
+ Opc == ISD::ATOMIC_LOAD_MIN || Opc == ISD::ATOMIC_LOAD_MAX;
+ if (TLI.shouldSignExtendTypeInLibCall(
+ EVT(VT).getTypeForEVT(*DAG.getContext()), IsSigned))
+ ExtendedOps.push_back(DAG.getNode(ISD::SIGN_EXTEND_INREG, dl,
+ Op->getValueType(), *Op,
+ DAG.getValueType(VT)));
+ else
+ ExtendedOps.push_back(DAG.getZeroExtendInReg(*Op, dl, VT));
+
+ } else {
+ ExtendedOps.push_back(*Op);
+ }
+ }
+
if (TLI.getLibcallName(LC)) {
// If outline atomic available, prepare its arguments and expand.
- Ops.append(Node->op_begin() + 2, Node->op_end());
- Ops.push_back(Node->getOperand(1));
+ Ops.append(ExtendedOps.begin(), ExtendedOps.end());
+ Ops.push_back(Pointer);
} else {
LC = RTLIB::getSYNC(Opc, VT);
assert(LC != RTLIB::UNKNOWN_LIBCALL &&
"Unexpected atomic op or value type!");
// Arguments for expansion to sync libcall
- Ops.append(Node->op_begin() + 1, Node->op_end());
+ Ops.push_back(Pointer);
+ Ops.append(ExtendedOps.begin(), ExtendedOps.end());
}
- std::pair<SDValue, SDValue> Tmp = TLI.makeLibCall(DAG, LC, RetVT,
- Ops, CallOptions,
- SDLoc(Node),
- Node->getOperand(0));
+
+ std::pair<SDValue, SDValue> Tmp =
+ TLI.makeLibCall(DAG, LC, RetVT, Ops, CallOptions, dl, ChainIn);
Results.push_back(Tmp.first);
Results.push_back(Tmp.second);
break;
diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.h b/llvm/lib/Target/AArch64/AArch64ISelLowering.h
index 1987c892ac080..9a009f0eb6980 100644
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.h
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.h
@@ -1378,6 +1378,10 @@ class AArch64TargetLowering : public TargetLowering {
bool shouldScalarizeBinop(SDValue VecOp) const override {
return VecOp.getOpcode() == ISD::SETCC;
}
+
+ bool shouldExtendTypeInLibCall(EVT Type) const override {
+ return false;
+ }
};
namespace AArch64 {
diff --git a/llvm/test/CodeGen/AArch64/atomicrmw-fadd.ll b/llvm/test/CodeGen/AArch64/atomicrmw-fadd.ll
index 21729b9dfd101..b650040617ecd 100644
--- a/llvm/test/CodeGen/AArch64/atomicrmw-fadd.ll
+++ b/llvm/test/CodeGen/AArch64/atomicrmw-fadd.ll
@@ -58,13 +58,13 @@ define half @test_atomicrmw_fadd_f16_seq_cst_align2(ptr %ptr, half %value) #0 {
; SOFTFP-NOLSE-NEXT: .LBB0_2: // %atomicrmw.start
; SOFTFP-NOLSE-NEXT: // =>This Loop Header: Depth=1
; SOFTFP-NOLSE-NEXT: // Child Loop BB0_3 Depth 2
-; SOFTFP-NOLSE-NEXT: mov w22, w0
-; SOFTFP-NOLSE-NEXT: and w0, w20, #0xffff
-; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
; SOFTFP-NOLSE-NEXT: mov w21, w0
-; SOFTFP-NOLSE-NEXT: and w0, w22, #0xffff
+; SOFTFP-NOLSE-NEXT: mov w0, w20
; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
-; SOFTFP-NOLSE-NEXT: mov w1, w21
+; SOFTFP-NOLSE-NEXT: mov w22, w0
+; SOFTFP-NOLSE-NEXT: mov w0, w21
+; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
+; SOFTFP-NOLSE-NEXT: mov w1, w22
; SOFTFP-NOLSE-NEXT: bl __addsf3
; SOFTFP-NOLSE-NEXT: bl __truncsfhf2
; SOFTFP-NOLSE-NEXT: mov w8, w0
@@ -72,7 +72,7 @@ define half @test_atomicrmw_fadd_f16_seq_cst_align2(ptr %ptr, half %value) #0 {
; SOFTFP-NOLSE-NEXT: // Parent Loop BB0_2 Depth=1
; SOFTFP-NOLSE-NEXT: // => This Inner Loop Header: Depth=2
; SOFTFP-NOLSE-NEXT: ldaxrh w0, [x19]
-; SOFTFP-NOLSE-NEXT: cmp w0, w22, uxth
+; SOFTFP-NOLSE-NEXT: cmp w0, w21, uxth
; SOFTFP-NOLSE-NEXT: b.ne .LBB0_1
; SOFTFP-NOLSE-NEXT: // %bb.4: // %cmpxchg.trystore
; SOFTFP-NOLSE-NEXT: // in Loop: Header=BB0_3 Depth=2
@@ -146,13 +146,13 @@ define half @test_atomicrmw_fadd_f16_seq_cst_align4(ptr %ptr, half %value) #0 {
; SOFTFP-NOLSE-NEXT: .LBB1_2: // %atomicrmw.start
; SOFTFP-NOLSE-NEXT: // =>This Loop Header: Depth=1
; SOFTFP-NOLSE-NEXT: // Child Loop BB1_3 Depth 2
-; SOFTFP-NOLSE-NEXT: mov w22, w0
-; SOFTFP-NOLSE-NEXT: and w0, w20, #0xffff
-; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
; SOFTFP-NOLSE-NEXT: mov w21, w0
-; SOFTFP-NOLSE-NEXT: and w0, w22, #0xffff
+; SOFTFP-NOLSE-NEXT: mov w0, w20
; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
-; SOFTFP-NOLSE-NEXT: mov w1, w21
+; SOFTFP-NOLSE-NEXT: mov w22, w0
+; SOFTFP-NOLSE-NEXT: mov w0, w21
+; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
+; SOFTFP-NOLSE-NEXT: mov w1, w22
; SOFTFP-NOLSE-NEXT: bl __addsf3
; SOFTFP-NOLSE-NEXT: bl __truncsfhf2
; SOFTFP-NOLSE-NEXT: mov w8, w0
@@ -160,7 +160,7 @@ define half @test_atomicrmw_fadd_f16_seq_cst_align4(ptr %ptr, half %value) #0 {
; SOFTFP-NOLSE-NEXT: // Parent Loop BB1_2 Depth=1
; SOFTFP-NOLSE-NEXT: // => This Inner Loop Header: Depth=2
; SOFTFP-NOLSE-NEXT: ldaxrh w0, [x19]
-; SOFTFP-NOLSE-NEXT: cmp w0, w22, uxth
+; SOFTFP-NOLSE-NEXT: cmp w0, w21, uxth
; SOFTFP-NOLSE-NEXT: b.ne .LBB1_1
; SOFTFP-NOLSE-NEXT: // %bb.4: // %cmpxchg.trystore
; SOFTFP-NOLSE-NEXT: // in Loop: Header=BB1_3 Depth=2
@@ -711,19 +711,19 @@ define <2 x half> @test_atomicrmw_fadd_v2f16_seq_cst_align4(ptr %ptr, <2 x half>
; SOFTFP-NOLSE-NEXT: .LBB7_2: // %atomicrmw.start
; SOFTFP-NOLSE-NEXT: // =>This Loop Header: Depth=1
; SOFTFP-NOLSE-NEXT: // Child Loop BB7_3 Depth 2
-; SOFTFP-NOLSE-NEXT: and w0, w19, #0xffff
+; SOFTFP-NOLSE-NEXT: mov w0, w19
; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
; SOFTFP-NOLSE-NEXT: mov w24, w0
-; SOFTFP-NOLSE-NEXT: and w0, w23, #0xffff
+; SOFTFP-NOLSE-NEXT: mov w0, w23
; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
; SOFTFP-NOLSE-NEXT: mov w1, w24
; SOFTFP-NOLSE-NEXT: bl __addsf3
; SOFTFP-NOLSE-NEXT: bl __truncsfhf2
; SOFTFP-NOLSE-NEXT: mov w24, w0
-; SOFTFP-NOLSE-NEXT: and w0, w21, #0xffff
+; SOFTFP-NOLSE-NEXT: mov w0, w21
; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
; SOFTFP-NOLSE-NEXT: mov w25, w0
-; SOFTFP-NOLSE-NEXT: and w0, w22, #0xffff
+; SOFTFP-NOLSE-NEXT: mov w0, w22
; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
; SOFTFP-NOLSE-NEXT: mov w1, w25
; SOFTFP-NOLSE-NEXT: bl __addsf3
diff --git a/llvm/test/CodeGen/AArch64/atomicrmw-fmax.ll b/llvm/test/CodeGen/AArch64/atomicrmw-fmax.ll
index 9b5e48d2b4217..41c5afe0f64a9 100644
--- a/llvm/test/CodeGen/AArch64/atomicrmw-fmax.ll
+++ b/llvm/test/CodeGen/AArch64/atomicrmw-fmax.ll
@@ -60,13 +60,13 @@ define half @test_atomicrmw_fmax_f16_seq_cst_align2(ptr %ptr, half %value) #0 {
; SOFTFP-NOLSE-NEXT: .LBB0_2: // %atomicrmw.start
; SOFTFP-NOLSE-NEXT: // =>This Loop Header: Depth=1
; SOFTFP-NOLSE-NEXT: // Child Loop BB0_3 Depth 2
-; SOFTFP-NOLSE-NEXT: mov w22, w0
-; SOFTFP-NOLSE-NEXT: and w0, w20, #0xffff
-; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
; SOFTFP-NOLSE-NEXT: mov w21, w0
-; SOFTFP-NOLSE-NEXT: and w0, w22, #0xffff
+; SOFTFP-NOLSE-NEXT: mov w0, w20
; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
-; SOFTFP-NOLSE-NEXT: mov w1, w21
+; SOFTFP-NOLSE-NEXT: mov w22, w0
+; SOFTFP-NOLSE-NEXT: mov w0, w21
+; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
+; SOFTFP-NOLSE-NEXT: mov w1, w22
; SOFTFP-NOLSE-NEXT: bl fmaxf
; SOFTFP-NOLSE-NEXT: bl __truncsfhf2
; SOFTFP-NOLSE-NEXT: mov w8, w0
@@ -74,7 +74,7 @@ define half @test_atomicrmw_fmax_f16_seq_cst_align2(ptr %ptr, half %value) #0 {
; SOFTFP-NOLSE-NEXT: // Parent Loop BB0_2 Depth=1
; SOFTFP-NOLSE-NEXT: // => This Inner Loop Header: Depth=2
; SOFTFP-NOLSE-NEXT: ldaxrh w0, [x19]
-; SOFTFP-NOLSE-NEXT: cmp w0, w22, uxth
+; SOFTFP-NOLSE-NEXT: cmp w0, w21, uxth
; SOFTFP-NOLSE-NEXT: b.ne .LBB0_1
; SOFTFP-NOLSE-NEXT: // %bb.4: // %cmpxchg.trystore
; SOFTFP-NOLSE-NEXT: // in Loop: Header=BB0_3 Depth=2
@@ -148,13 +148,13 @@ define half @test_atomicrmw_fmax_f16_seq_cst_align4(ptr %ptr, half %value) #0 {
; SOFTFP-NOLSE-NEXT: .LBB1_2: // %atomicrmw.start
; SOFTFP-NOLSE-NEXT: // =>This Loop Header: Depth=1
; SOFTFP-NOLSE-NEXT: // Child Loop BB1_3 Depth 2
-; SOFTFP-NOLSE-NEXT: mov w22, w0
-; SOFTFP-NOLSE-NEXT: and w0, w20, #0xffff
-; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
; SOFTFP-NOLSE-NEXT: mov w21, w0
-; SOFTFP-NOLSE-NEXT: and w0, w22, #0xffff
+; SOFTFP-NOLSE-NEXT: mov w0, w20
; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
-; SOFTFP-NOLSE-NEXT: mov w1, w21
+; SOFTFP-NOLSE-NEXT: mov w22, w0
+; SOFTFP-NOLSE-NEXT: mov w0, w21
+; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
+; SOFTFP-NOLSE-NEXT: mov w1, w22
; SOFTFP-NOLSE-NEXT: bl fmaxf
; SOFTFP-NOLSE-NEXT: bl __truncsfhf2
; SOFTFP-NOLSE-NEXT: mov w8, w0
@@ -162,7 +162,7 @@ define half @test_atomicrmw_fmax_f16_seq_cst_align4(ptr %ptr, half %value) #0 {
; SOFTFP-NOLSE-NEXT: // Parent Loop BB1_2 Depth=1
; SOFTFP-NOLSE-NEXT: // => This Inner Loop Header: Depth=2
; SOFTFP-NOLSE-NEXT: ldaxrh w0, [x19]
-; SOFTFP-NOLSE-NEXT: cmp w0, w22, uxth
+; SOFTFP-NOLSE-NEXT: cmp w0, w21, uxth
; SOFTFP-NOLSE-NEXT: b.ne .LBB1_1
; SOFTFP-NOLSE-NEXT: // %bb.4: // %cmpxchg.trystore
; SOFTFP-NOLSE-NEXT: // in Loop: Header=BB1_3 Depth=2
@@ -591,19 +591,19 @@ define <2 x half> @test_atomicrmw_fmax_v2f16_seq_cst_align4(ptr %ptr, <2 x half>
; SOFTFP-NOLSE-NEXT: .LBB6_2: // %atomicrmw.start
; SOFTFP-NOLSE-NEXT: // =>This Loop Header: Depth=1
; SOFTFP-NOLSE-NEXT: // Child Loop BB6_3 Depth 2
-; SOFTFP-NOLSE-NEXT: and w0, w19, #0xffff
+; SOFTFP-NOLSE-NEXT: mov w0, w19
; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
; SOFTFP-NOLSE-NEXT: mov w24, w0
-; SOFTFP-NOLSE-NEXT: and w0, w23, #0xffff
+; SOFTFP-NOLSE-NEXT: mov w0, w23
; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
; SOFTFP-NOLSE-NEXT: mov w1, w24
; SOFTFP-NOLSE-NEXT: bl fmaxf
; SOFTFP-NOLSE-NEXT: bl __truncsfhf2
; SOFTFP-NOLSE-NEXT: mov w24, w0
-; SOFTFP-NOLSE-NEXT: and w0, w21, #0xffff
+; SOFTFP-NOLSE-NEXT: mov w0, w21
; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
; SOFTFP-NOLSE-NEXT: mov w25, w0
-; SOFTFP-NOLSE-NEXT: and w0, w22, #0xffff
+; SOFTFP-NOLSE-NEXT: mov w0, w22
; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
; SOFTFP-NOLSE-NEXT: mov w1, w25
; SOFTFP-NOLSE-NEXT: bl fmaxf
diff --git a/llvm/test/CodeGen/AArch64/atomicrmw-fmin.ll b/llvm/test/CodeGen/AArch64/atomicrmw-fmin.ll
index f6c542fe7d407..a01bd182e61e6 100644
--- a/llvm/test/CodeGen/AArch64/atomicrmw-fmin.ll
+++ b/llvm/test/CodeGen/AArch64/atomicrmw-fmin.ll
@@ -60,13 +60,13 @@ define half @test_atomicrmw_fmin_f16_seq_cst_align2(ptr %ptr, half %value) #0 {
; SOFTFP-NOLSE-NEXT: .LBB0_2: // %atomicrmw.start
; SOFTFP-NOLSE-NEXT: // =>This Loop Header: Depth=1
; SOFTFP-NOLSE-NEXT: // Child Loop BB0_3 Depth 2
-; SOFTFP-NOLSE-NEXT: mov w22, w0
-; SOFTFP-NOLSE-NEXT: and w0, w20, #0xffff
-; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
; SOFTFP-NOLSE-NEXT: mov w21, w0
-; SOFTFP-NOLSE-NEXT: and w0, w22, #0xffff
+; SOFTFP-NOLSE-NEXT: mov w0, w20
; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
-; SOFTFP-NOLSE-NEXT: mov w1, w21
+; SOFTFP-NOLSE-NEXT: mov w22, w0
+; SOFTFP-NOLSE-NEXT: mov w0, w21
+; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
+; SOFTFP-NOLSE-NEXT: mov w1, w22
; SOFTFP-NOLSE-NEXT: bl fminf
; SOFTFP-NOLSE-NEXT: bl __truncsfhf2
; SOFTFP-NOLSE-NEXT: mov w8, w0
@@ -74,7 +74,7 @@ define half @test_atomicrmw_fmin_f16_seq_cst_align2(ptr %ptr, half %value) #0 {
; SOFTFP-NOLSE-NEXT: // Parent Loop BB0_2 Depth=1
; SOFTFP-NOLSE-NEXT: // => This Inner Loop Header: Depth=2
; SOFTFP-NOLSE-NEXT: ldaxrh w0, [x19]
-; SOFTFP-NOLSE-NEXT: cmp w0, w22, uxth
+; SOFTFP-NOLSE-NEXT: cmp w0, w21, uxth
; SOFTFP-NOLSE-NEXT: b.ne .LBB0_1
; SOFTFP-NOLSE-NEXT: // %bb.4: // %cmpxchg.trystore
; SOFTFP-NOLSE-NEXT: // in Loop: Header=BB0_3 Depth=2
@@ -148,13 +148,13 @@ define half @test_atomicrmw_fmin_f16_seq_cst_align4(ptr %ptr, half %value) #0 {
; SOFTFP-NOLSE-NEXT: .LBB1_2: // %atomicrmw.start
; SOFTFP-NOLSE-NEXT: // =>This Loop Header: Depth=1
; SOFTFP-NOLSE-NEXT: // Child Loop BB1_3 Depth 2
-; SOFTFP-NOLSE-NEXT: mov w22, w0
-; SOFTFP-NOLSE-NEXT: and w0, w20, #0xffff
-; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
; SOFTFP-NOLSE-NEXT: mov w21, w0
-; SOFTFP-NOLSE-NEXT: and w0, w22, #0xffff
+; SOFTFP-NOLSE-NEXT: mov w0, w20
; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
-; SOFTFP-NOLSE-NEXT: mov w1, w21
+; SOFTFP-NOLSE-NEXT: mov w22, w0
+; SOFTFP-NOLSE-NEXT: mov w0, w21
+; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
+; SOFTFP-NOLSE-NEXT: mov w1, w22
; SOFTFP-NOLSE-NEXT: bl fminf
; SOFTFP-NOLSE-NEXT: bl __truncsfhf2
; SOFTFP-NOLSE-NEXT: mov w8, w0
@@ -162,7 +162,7 @@ define half @test_atomicrmw_fmin_f16_seq_cst_align4(ptr %ptr, half %value) #0 {
; SOFTFP-NOLSE-NEXT: // Parent Loop BB1_2 Depth=1
; SOFTFP-NOLSE-NEXT: // => This Inner Loop Header: Depth=2
; SOFTFP-NOLSE-NEXT: ldaxrh w0, [x19]
-; SOFTFP-NOLSE-NEXT: cmp w0, w22, uxth
+; SOFTFP-NOLSE-NEXT: cmp w0, w21, uxth
; SOFTFP-NOLSE-NEXT: b.ne .LBB1_1
; SOFTFP-NOLSE-NEXT: // %bb.4: // %cmpxchg.trystore
; SOFTFP-NOLSE-NEXT: // in Loop: Header=BB1_3 Depth=2
@@ -591,19 +591,19 @@ define <2 x half> @test_atomicrmw_fmin_v2f16_seq_cst_align4(ptr %ptr, <2 x half>
; SOFTFP-NOLSE-NEXT: .LBB6_2: // %atomicrmw.start
; SOFTFP-NOLSE-NEXT: // =>This Loop Header: Depth=1
; SOFTFP-NOLSE-NEXT: // Child Loop BB6_3 Depth 2
-; SOFTFP-NOLSE-NEXT: and w0, w19, #0xffff
+; SOFTFP-NOLSE-NEXT: mov w0, w19
; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
; SOFTFP-NOLSE-NEXT: mov w24, w0
-; SOFTFP-NOLSE-NEXT: and w0, w23, #0xffff
+; SOFTFP-NOLSE-NEXT: mov w0, w23
; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
; SOFTFP-NOLSE-NEXT: mov w1, w24
; SOFTFP-NOLSE-NEXT: bl fminf
; SOFTFP-NOLSE-NEXT: bl __truncsfhf2
; SOFTFP-NOLSE-NEXT: mov w24, w0
-; SOFTFP-NOLSE-NEXT: and w0, w21, #0xffff
+; SOFTFP-NOLSE-NEXT: mov w0, w21
; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
; SOFTFP-NOLSE-NEXT: mov w25, w0
-; SOFTFP-NOLSE-NEXT: and w0, w22, #0xffff
+; SOFTFP-NOLSE-NEXT: mov w0, w22
; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
; SOFTFP-NOLSE-NEXT: mov w1, w25
; SOFTFP-NOLSE-NEXT: bl fminf
diff --git a/llvm/test/CodeGen/AArch64/atomicrmw-fsub.ll b/llvm/test/CodeGen/AArch64/atomicrmw-fsub.ll
index 82e0f14e68e26..01beb5c50afdd 100644
--- a/llvm/test/CodeGen/AArch64/atomicrmw-fsub.ll
+++ b/llvm/test/CodeGen/AArch64/atomicrmw-fsub.ll
@@ -58,13 +58,13 @@ define half @test_atomicrmw_fsub_f16_seq_cst_align2(ptr %ptr, half %value) #0 {
; SOFTFP-NOLSE-NEXT: .LBB0_2: // %atomicrmw.start
; SOFTFP-NOLSE-NEXT: // =>This Loop Header: Depth=1
; SOFTFP-NOLSE-NEXT: // Child Loop BB0_3 Depth 2
-; SOFTFP-NOLSE-NEXT: mov w22, w0
-; SOFTFP-NOLSE-NEXT: and w0, w20, #0xffff
-; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
; SOFTFP-NOLSE-NEXT: mov w21, w0
-; SOFTFP-NOLSE-NEXT: and w0, w22, #0xffff
+; SOFTFP-NOLSE-NEXT: mov w0, w20
; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
-; SOFTFP-NOLSE-NEXT: mov w1, w21
+; SOFTFP-NOLSE-NEXT: mov w22, w0
+; SOFTFP-NOLSE-NEXT: mov w0, w21
+; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
+; SOFTFP-NOLSE-NEXT: mov w1, w22
; SOFTFP-NOLSE-NEXT: bl __subsf3
; SOFTFP-NOLSE-NEXT: bl __truncsfhf2
; SOFTFP-NOLSE-NEXT: mov w8, w0
@@ -72,7 +72,7 @@ define half @test_atomicrmw_fsub_f16_seq_cst_align2(ptr %ptr, half %value) #0 {
; SOFTFP-NOLSE-NEXT: // Parent Loop BB0_2 Depth=1
; SOFTFP-NOLSE-NEXT: // => This Inner Loop Header: Depth=2
; SOFTFP-NOLSE-NEXT: ldaxrh w0, [x19]
-; SOFTFP-NOLSE-NEXT: cmp w0, w22, uxth
+; SOFTFP-NOLSE-NEXT: cmp w0, w21, uxth
; SOFTFP-NOLSE-NEXT: b.ne .LBB0_1
; SOFTFP-NOLSE-NEXT: // %bb.4: // %cmpxchg.trystore
; SOFTFP-NOLSE-NEXT: // in Loop: Header=BB0_3 Depth=2
@@ -146,13 +146,13 @@ define half @test_atomicrmw_fsub_f16_seq_cst_align4(ptr %ptr, half %value) #0 {
; SOFTFP-NOLSE-NEXT: .LBB1_2: // %atomicrmw.start
; SOFTFP-NOLSE-NEXT: // =>This Loop Header: Depth=1
; SOFTFP-NOLSE-NEXT: // Child Loop BB1_3 Depth 2
-; SOFTFP-NOLSE-NEXT: mov w22, w0
-; SOFTFP-NOLSE-NEXT: and w0, w20, #0xffff
-; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
; SOFTFP-NOLSE-NEXT: mov w21, w0
-; SOFTFP-NOLSE-NEXT: and w0, w22, #0xffff
+; SOFTFP-NOLSE-NEXT: mov w0, w20
; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
-; SOFTFP-NOLSE-NEXT: mov w1, w21
+; SOFTFP-NOLSE-NEXT: mov w22, w0
+; SOFTFP-NOLSE-NEXT: mov w0, w21
+; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
+; SOFTFP-NOLSE-NEXT: mov w1, w22
; SOFTFP-NOLSE-NEXT: bl __subsf3
; SOFTFP-NOLSE-NEXT: bl __truncsfhf2
; SOFTFP-NOLSE-NEXT: mov w8, w0
@@ -160,7 +160,7 @@ define half @test_atomicrmw_fsub_f16_seq_cst_align4(ptr %ptr, half %value) #0 {
; SOFTFP-NOLSE-NEXT: // Parent Loop BB1_2 Depth=1
; SOFTFP-NOLSE-NEXT: // => This Inner Loop Header: Depth=2
; SOFTFP-NOLSE-NEXT: ldaxrh w0, [x19]
-; SOFTFP-NOLSE-NEXT: cmp w0, w22, uxth
+; SOFTFP-NOLSE-NEXT: cmp w0, w21, uxth
; SOFTFP-NOLSE-NEXT: b.ne .LBB1_1
; SOFTFP-NOLSE-NEXT: // %bb.4: // %cmpxchg.trystore
; SOFTFP-NOLSE-NEXT: // in Loop: Header=BB1_3 Depth=2
@@ -711,19 +711,19 @@ define <2 x half> @test_atomicrmw_fsub_v2f16_seq_cst_align4(ptr %ptr, <2 x half>
; SOFTFP-NOLSE-NEXT: .LBB7_2: // %atomicrmw.start
; SOFTFP-NOLSE-NEXT: // =>This Loop Header: Depth=1
; SOFTFP-NOLSE-NEXT: // Child Loop BB7_3 Depth 2
-; SOFTFP-NOLSE-NEXT: and w0, w19, #0xffff
+; SOFTFP-NOLSE-NEXT: mov w0, w19
; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
; SOFTFP-NOLSE-NEXT: mov w24, w0
-; SOFTFP-NOLSE-NEXT: and w0, w23, #0xffff
+; SOFTFP-NOLSE-NEXT: mov w0, w23
; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
; SOFTFP-NOLSE-NEXT: mov w1, w24
; SOFTFP-NOLSE-NEXT: bl __subsf3
; SOFTFP-NOLSE-NEXT: bl __truncsfhf2
; SOFTFP-NOLSE-NEXT: mov w24, w0
-; SOFTFP-NOLSE-NEXT: and w0, w21, #0xffff
+; SOFTFP-NOLSE-NEXT: mov w0, w21
; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
; SOFTFP-NOLSE-NEXT: mov w25, w0
-; SOFTFP-NOLSE-NEXT: and w0, w22, #0xffff
+; SOFTFP-NOLSE-NEXT: mov w0, w22
; SOFTFP-NOLSE-NEXT: bl __extendhfsf2
; SOFTFP-NOLSE-NEXT: mov w1, w25
; SOFTFP-NOLSE-NEXT: bl __subsf3
diff --git a/llvm/test/CodeGen/AArch64/strictfp_f16_abi_promote.ll b/llvm/test/CodeGen/AArc...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/128891
More information about the llvm-commits
mailing list