[llvm] [RISCV] Fix crash when unrolling loop containing vector instructions (PR #83384)
via llvm-commits
llvm-commits at lists.llvm.org
Wed Feb 28 23:11:19 PST 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-llvm-analysis
@llvm/pr-subscribers-backend-risc-v
Author: Shih-Po Hung (arcbbb)
<details>
<summary>Changes</summary>
When MVT is not a vector type, TCK_CodeSize should return an invalid cost. This patch adds a check in the beginning to make sure all cost kinds return invalid costs consistently.
Before this patch, TCK_CodeSize returns a valid cost on scalar MVT but other cost kinds doesn't.
This fixes the issue #<!-- -->83294 where a loop contains vector instructions and MVT is scalar after type legalization when the vector extension is not enabled,
---
Full diff: https://github.com/llvm/llvm-project/pull/83384.diff
2 Files Affected:
- (modified) llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp (+3)
- (added) llvm/test/Analysis/CostModel/RISCV/rvv-invalid-cost.ll (+53)
``````````diff
diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
index f04968d82e86e2..54c7402e4444cd 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -37,6 +37,9 @@ static cl::opt<unsigned> SLPMaxVF(
InstructionCost
RISCVTTIImpl::getRISCVInstructionCost(ArrayRef<unsigned> OpCodes, MVT VT,
TTI::TargetCostKind CostKind) {
+ // Check if the type is valid for all CostKind
+ if (!VT.isVector())
+ return InstructionCost::getInvalid();
size_t NumInstr = OpCodes.size();
if (CostKind == TTI::TCK_CodeSize)
return NumInstr;
diff --git a/llvm/test/Analysis/CostModel/RISCV/rvv-invalid-cost.ll b/llvm/test/Analysis/CostModel/RISCV/rvv-invalid-cost.ll
new file mode 100644
index 00000000000000..8df26d88f52898
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/RISCV/rvv-invalid-cost.ll
@@ -0,0 +1,53 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 4
+; RUN: opt < %s -mtriple=riscv64 -mattr=+f,+d --passes=loop-unroll-full -S | FileCheck %s
+
+; Check it doesn' crash when the vector extension is not enabled.
+define void @foo() {
+; CHECK-LABEL: define void @foo(
+; CHECK-SAME: ) #[[ATTR0:[0-9]+]] {
+; CHECK-NEXT: entry:
+; CHECK-NEXT: br label [[FOR_BODY:%.*]]
+; CHECK: for.body:
+; CHECK-NEXT: [[INDVARS_IV1:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT: [[TMP0:%.*]] = load float, ptr null, align 4
+; CHECK-NEXT: [[SPLAT_SPLAT_I_I_I:%.*]] = shufflevector <2 x float> zeroinitializer, <2 x float> zeroinitializer, <2 x i32> zeroinitializer
+; CHECK-NEXT: [[CMP1_I_I_I:%.*]] = fcmp ogt <2 x float> zeroinitializer, zeroinitializer
+; CHECK-NEXT: [[SPLAT_SPLAT3_I_I_I:%.*]] = shufflevector <2 x i32> zeroinitializer, <2 x i32> zeroinitializer, <2 x i32> zeroinitializer
+; CHECK-NEXT: [[XOR3_I_I_I_I_I:%.*]] = select <2 x i1> zeroinitializer, <2 x i32> zeroinitializer, <2 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP1:%.*]] = load float, ptr null, align 4
+; CHECK-NEXT: [[SPLAT_SPLAT8_I_I_I:%.*]] = shufflevector <2 x float> zeroinitializer, <2 x float> zeroinitializer, <2 x i32> zeroinitializer
+; CHECK-NEXT: [[SUB_I_I_I:%.*]] = fsub <2 x float> zeroinitializer, zeroinitializer
+; CHECK-NEXT: [[MUL_I_I_I:%.*]] = shl i64 0, 0
+; CHECK-NEXT: [[TMP2:%.*]] = load float, ptr null, align 4
+; CHECK-NEXT: [[SPLAT_SPLAT_I_I_I_I:%.*]] = shufflevector <2 x float> zeroinitializer, <2 x float> zeroinitializer, <2 x i32> zeroinitializer
+; CHECK-NEXT: [[XOR3_I_I_I_V_I_I:%.*]] = select <2 x i1> zeroinitializer, <2 x float> zeroinitializer, <2 x float> zeroinitializer
+; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add i64 [[INDVARS_IV1]], 1
+; CHECK-NEXT: [[EXITCOND:%.*]] = icmp ne i64 [[INDVARS_IV1]], 8
+; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_BODY]], label [[EXIT:%.*]]
+; CHECK: exit:
+; CHECK-NEXT: ret void
+;
+entry:
+ br label %for.body
+
+for.body: ; preds = %for.body, %entry
+ %indvars.iv1 = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
+ %0 = load float, ptr null, align 4
+ %splat.splat.i.i.i = shufflevector <2 x float> zeroinitializer, <2 x float> zeroinitializer, <2 x i32> zeroinitializer
+ %cmp1.i.i.i = fcmp ogt <2 x float> zeroinitializer, zeroinitializer
+ %splat.splat3.i.i.i = shufflevector <2 x i32> zeroinitializer, <2 x i32> zeroinitializer, <2 x i32> zeroinitializer
+ %xor3.i.i.i.i.i = select <2 x i1> zeroinitializer, <2 x i32> zeroinitializer, <2 x i32> zeroinitializer
+ %1 = load float, ptr null, align 4
+ %splat.splat8.i.i.i = shufflevector <2 x float> zeroinitializer, <2 x float> zeroinitializer, <2 x i32> zeroinitializer
+ %sub.i.i.i = fsub <2 x float> zeroinitializer, zeroinitializer
+ %mul.i.i.i = shl i64 0, 0
+ %2 = load float, ptr null, align 4
+ %splat.splat.i.i.i.i = shufflevector <2 x float> zeroinitializer, <2 x float> zeroinitializer, <2 x i32> zeroinitializer
+ %xor3.i.i.i.v.i.i = select <2 x i1> zeroinitializer, <2 x float> zeroinitializer, <2 x float> zeroinitializer
+ %indvars.iv.next = add i64 %indvars.iv1, 1
+ %exitcond = icmp ne i64 %indvars.iv1, 8
+ br i1 %exitcond, label %for.body, label %exit
+
+exit: ; preds = %for.body
+ ret void
+}
``````````
</details>
https://github.com/llvm/llvm-project/pull/83384
More information about the llvm-commits
mailing list