[RISCV] Do a sign-extension in a compare-and-swap of 32 bit in RV64A
AtomicCmpSwapWithSuccess is legalised into an AtomicCmpSwap plus a comparison.
This requires an extension of the value which, by default, is a
zero-extension. When we later lower AtomicCmpSwap into a PseudoCmpXchg32 and then expanded in
RISCVExpandPseudoInsts.cpp, the lr.w instruction does a sign-extension.
This mismatch of extensions causes the comparison to fail when the compared
value is negative. This change overrides TargetLowering::getExtendForAtomicOps
for RISC-V so it does a sign-extension instead.
Differential Revision: https://reviews.llvm.org/D58829
Patch by Ferran Pallarès Roca.
llvm-svn: 355869
diff --git a/llvm/lib/Target/RISCV/RISCVISelLowering.h b/llvm/lib/Target/RISCV/RISCVISelLowering.h
index 4c9fd26..fc69682 100644
--- a/llvm/lib/Target/RISCV/RISCVISelLowering.h
+++ b/llvm/lib/Target/RISCV/RISCVISelLowering.h
@@ -106,6 +106,10 @@
Instruction *emitTrailingFence(IRBuilder<> &Builder, Instruction *Inst,
AtomicOrdering Ord) const override;
+ ISD::NodeType getExtendForAtomicOps() const override {
+ return ISD::SIGN_EXTEND;
+ }
+
private:
void analyzeInputArgs(MachineFunction &MF, CCState &CCInfo,
const SmallVectorImpl<ISD::InputArg> &Ins,
diff --git a/llvm/test/CodeGen/RISCV/atomic-cmpxchg-flag.ll b/llvm/test/CodeGen/RISCV/atomic-cmpxchg-flag.ll
new file mode 100644
index 0000000..e5d619d
--- /dev/null
+++ b/llvm/test/CodeGen/RISCV/atomic-cmpxchg-flag.ll
@@ -0,0 +1,29 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv64 -mattr=+a -verify-machineinstrs < %s \
+; RUN: | FileCheck -check-prefix=RV64IA %s
+
+; This test ensures that the output of the 'lr.w' instruction is sign-extended.
+; Previously, the default zero-extension was being used and 'cmp' parameter
+; higher bits were masked to zero for the comparison.
+
+define i1 @cmpxchg_i32_seq_cst_seq_cst(i32* %ptr, i32 signext %cmp,
+ i32 signext %val) {
+; RV64IA-LABEL: cmpxchg_i32_seq_cst_seq_cst:
+; RV64IA: # %bb.0: # %entry
+; RV64IA-NEXT: .LBB0_1: # %entry
+; RV64IA-NEXT: # =>This Inner Loop Header: Depth=1
+; RV64IA-NEXT: lr.w.aqrl a3, (a0)
+; RV64IA-NEXT: bne a3, a1, .LBB0_3
+; RV64IA-NEXT: # %bb.2: # %entry
+; RV64IA-NEXT: # in Loop: Header=BB0_1 Depth=1
+; RV64IA-NEXT: sc.w.aqrl a4, a2, (a0)
+; RV64IA-NEXT: bnez a4, .LBB0_1
+; RV64IA-NEXT: .LBB0_3: # %entry
+; RV64IA-NEXT: xor a0, a3, a1
+; RV64IA-NEXT: seqz a0, a0
+; RV64IA-NEXT: ret
+entry:
+ %0 = cmpxchg i32* %ptr, i32 %cmp, i32 %val seq_cst seq_cst
+ %1 = extractvalue { i32, i1 } %0, 1
+ ret i1 %1
+}