Skip to content

[BACKEND] Fixing assert in shared encoding swizzling addresses calculation #2292

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ptillet merged 1 commit into from
Sep 13, 2023
Merged

[BACKEND] Fixing assert in shared encoding swizzling addresses calculation #2292

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions lib/Conversion/TritonGPUToLLVM/TritonGPUToLLVMBase.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -339,8 +339,9 @@ class ConvertTritonGPUOpToLLVMPatternBase {
// Order
auto inOrder = triton::gpu::getOrder(srcEncoding);
auto outOrder = triton::gpu::getOrder(resSharedLayout);
assert(outVec * (maxPhase - 1) <= srcShape[outOrder[0]] &&
"Swizzling would generate out of bounds memory accesses");
assert(maxPhase == 1 ||
outVec * maxPhase <= srcShape[outOrder[0]] &&
"Swizzling would generate out of bounds memory accesses");
// Tensor indices held by the current thread, as LLVM values
auto srcIndices = emitIndices(loc, rewriter, srcEncoding, srcTy, false);
// Swizzling with leading offsets (e.g. Hopper GMMA)
Expand Down