[NVPTX] Fix segfault with i128 types in arrays

[vvchernov]

• Process i128 array with custom ComputePTXValueVTs. The i128 elements should be handled and split into i64 types in the recursion.
• Add corresponding tests

[github-actions]

Thank you for submitting a Pull Request (PR) to the LLVM Project!

This PR will be automatically labeled and the relevant teams will be notified.

If you wish to, you can add reviewers by using the "Reviewers" section on this page.

If this is not working for you, it is probably because you do not have write permissions for the repository. In which case you can instead tag reviewers by name in a comment by using @ followed by their GitHub username.

If you have received no comments on your PR for a week, you can request a review by "ping"ing the PR by adding a comment “Ping”. The common courtesy "ping" rate is once a week. Please remember that you are asking for valuable time from other developers.

If you have further questions, they may be answered by the LLVM GitHub User Guide.

You can also ask questions in a comment on this PR, on the LLVM Discord or on the forums.

[vvchernov]

cc @Artem-B

[llvmbot]

@llvm/pr-subscribers-backend-nvptx

Author: Valery Chernov (vvchernov)

Changes

• Process i128 array with custom ComputePTXValueVTs. The i128 elements should be handled and split into i64 types in the recursion.
• Add corresponding test

---

Full diff: https://github.com/llvm/llvm-project/pull/120562.diff

2 Files Affected:

• (modified) llvm/lib/Target/NVPTX/NVPTXISelLowering.cpp (+11)
• (added) llvm/test/CodeGen/NVPTX/i128-array.ll (+25)

diff --git a/llvm/lib/Target/NVPTX/NVPTXISelLowering.cpp b/llvm/lib/Target/NVPTX/NVPTXISelLowering.cpp
index ce94dded815b8f..4282965c3cddea 100644
--- a/llvm/lib/Target/NVPTX/NVPTXISelLowering.cpp
+++ b/llvm/lib/Target/NVPTX/NVPTXISelLowering.cpp
@@ -198,6 +198,17 @@ static void ComputePTXValueVTs(const TargetLowering &TLI, const DataLayout &DL,
     return;
   }
 
+  // Given an array type, recursively traverse the elements with custom ComputePTXValueVTs.
+  if (ArrayType *ATy = dyn_cast<ArrayType>(Ty)) {
+    Type *EltTy = ATy->getElementType();
+    uint64_t EltSize = DL.getTypeAllocSize(EltTy);
+    for (unsigned i = 0, e = ATy->getNumElements(); i != e; ++i) {
+      ComputePTXValueVTs(TLI, DL, EltTy, ValueVTs, Offsets,
+                         StartingOffset + i * EltSize);
+    }
+    return;
+  }
+
   ComputeValueVTs(TLI, DL, Ty, TempVTs, &TempOffsets, StartingOffset);
   for (unsigned i = 0, e = TempVTs.size(); i != e; ++i) {
     EVT VT = TempVTs[i];
diff --git a/llvm/test/CodeGen/NVPTX/i128-array.ll b/llvm/test/CodeGen/NVPTX/i128-array.ll
new file mode 100644
index 00000000000000..4054d721d04863
--- /dev/null
+++ b/llvm/test/CodeGen/NVPTX/i128-array.ll
@@ -0,0 +1,25 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
+; RUN: llc < %s -O0 -march=nvptx64 -mcpu=sm_20 | FileCheck %s
+
+define [2 x i128] @foo(i64 %a, i32 %b) {
+; CHECK-LABEL: foo(
+; CHECK:       {
+; CHECK-NEXT:    .reg .b32 %r<2>;
+; CHECK-NEXT:    .reg .b64 %rd<5>;
+; CHECK-EMPTY:
+; CHECK-NEXT:  // %bb.0:
+; CHECK-NEXT:    ld.param.u32 %r1, [foo_param_1];
+; CHECK-NEXT:    ld.param.u64 %rd1, [foo_param_0];
+; CHECK-NEXT:    shr.s64 %rd2, %rd1, 63;
+; CHECK-NEXT:    cvt.s64.s32 %rd3, %r1;
+; CHECK-NEXT:    shr.s64 %rd4, %rd3, 63;
+; CHECK-NEXT:    st.param.v2.b64 [func_retval0], {%rd1, %rd2};
+; CHECK-NEXT:    st.param.v2.b64 [func_retval0+16], {%rd3, %rd4};
+; CHECK-NEXT:    ret;
+  %1 = sext i64 %a to i128
+  %2 = sext i32 %b to i128
+  %3 = insertvalue [ 2 x i128 ] undef, i128 %1, 0
+  %4 = insertvalue [ 2 x i128 ] %3, i128 %2, 1
+
+  ret [ 2 x i128 ] %4
+}

[Artem-B]

Thank you for the fix. LGTM in principle with a couple of minor nits.

[Artem-B]

Few more nits.

[vvchernov]

Hello @Artem-B! It fails on Windows with the issue I'm sure not related to this patch. There is another patch with the same failure. What should be done with the issue?

[Artem-B]

The failed test is LLVM :: tools/llvm-gsymutil/ARM_AArch64/macho-merged-funcs-dwarf.yaml and it has nothing to do with this patch. It's Ok to ignore it.

[justinfargnoli]

Merged at @vvchernov's offline request.

[github-actions]

@vvchernov Congratulations on having your first Pull Request (PR) merged into the LLVM Project!

Your changes will be combined with recent changes from other authors, then tested by our build bots. If there is a problem with a build, you may receive a report in an email or a comment on this PR.

Please check whether problems have been caused by your change specifically, as the builds can include changes from many authors. It is not uncommon for your change to be included in a build that fails due to someone else's changes, or infrastructure issues.

How to do this, and the rest of the post-merge process, is covered in detail here.

If your change does cause a problem, it may be reverted, or you can revert it yourself. This is a normal part of LLVM development. You can fix your changes and open a new PR to merge them again.

If you don't get any reports, no action is required from you. Your changes are working as expected, well done!