================
@@ -2474,7 +2474,7 @@ uint32x4_t test_vmaxq_u32(uint32x4_t v1, uint32x4_t v2) {
// LLVM: [[TMP1:%.*]] = bitcast <4 x i32> [[V2]] to <16 x i8>
// LLVM: [[VMAXQ_V_I:%.*]] = bitcast <16 x i8> [[TMP0]] to <4 x i32>
// LLVM: [[VMAXQ_V1_I:%.*]] = bitcast <16 x i8> [[TMP1]] to <4 x i32>
- // LLVM: [[VMAXQ_V2_I:%.*]] = call <4 x i32> @llvm.aarch64.neon.umax.v4i32(<4
x i32> [[VMAXQ_V_I]], <4 x i32> [[VMAXQ_V1_I]])
+ // LLVM: [[VMAXQ_V2_I:%.*]] = call <4 x i32> @llvm.umax.v4i32(<4 x i32>
[[VMAXQ_V_I]], <4 x i32> [[VMAXQ_V1_I]])
----------------
osa1 wrote:
Right, I just realized that I misunderstood what `AutoUpgrade` is about. (I was
compiling my benchmarks from IR and thought `AutoUpgrade` runs on all IRs, not
just when reading from text IR or bitcode)
I'll update this PR to make clang emit the same instructions that we upgrade
here. Converting to draft for now.
https://github.com/llvm/llvm-project/pull/225339
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
