Benjamin Maxwell

Results 38 issues of Benjamin Maxwell

Using the path rasterizer here is much slower than simply drawing four lines. This also more accurately shows the (real) clip as the bounding box is truncated to an int...

👀 pr-needs-review

See related PR: https://github.com/llvm/llvm-project/pull/101645

This reduces the default AArch64 matmul tile sizes from (8, 16, 1) to (6, 16, 1). Originally, (8, 16, 1) was chosen to attempt to use all available vector registers...

benchmarks:comp-stats
benchmarks:android-cpu

**Demo Video:** This demo shows my intended workflow (which previously required a fair bit of copy/pasting): https://github.com/user-attachments/assets/0a01846f-15bf-48ba-81a8-b156e4be4b09 This adds (hacky) support for chaining the output from one compiler to the...

ui

This enables the LLVM IR filters for the output of `mlir-translate` (with `-mlir-to-llvmir`). The filters are still disabled for `mlir-opt` (which only outputs MLIR) as there's currently no support for...

lang-python
lang-ruby
lang-mlir
lang-jakt
lang-cobol
lang-vala

In streaming[-compatible] functions, use SVE for scalar FP conversions to/from integer types. This can help avoid moves between FPRs and GRPs, which could be costly. This patch also updates definitions...

backend:AArch64

See commits for details: Progression `rotated.pdf`: **Before**: **After**:

👀 pr-needs-review

The previous SelectionDAG lowering is still available via `-aarch64-new-sme-abi=false` (this will stay around until at least LLVM 23). In tests that contained `CHECK-NEWLOWERING` the checks have been updated so: *...

backend:AArch64