[all-commits] [llvm/llvm-project] 547bfd: [AArch64] Improve bcvtn2 and remove aarch64_neon_b...
David Green via All-commits
all-commits at lists.llvm.org
Tue Jan 21 01:16:27 PST 2025
Branch: refs/heads/main
Home: https://github.com/llvm/llvm-project
Commit: 547bfda56b2e3f3a4c6d2357d3566dcd3fa996ad
https://github.com/llvm/llvm-project/commit/547bfda56b2e3f3a4c6d2357d3566dcd3fa996ad
Author: David Green <david.green at arm.com>
Date: 2025-01-21 (Tue, 21 Jan 2025)
Changed paths:
M clang/include/clang/Basic/arm_neon.td
M clang/lib/CodeGen/CGBuiltin.cpp
M clang/test/CodeGen/arm-bf16-convert-intrinsics.c
M llvm/include/llvm/IR/IntrinsicsAArch64.td
M llvm/lib/IR/AutoUpgrade.cpp
M llvm/lib/Target/AArch64/AArch64InstrFormats.td
M llvm/lib/Target/AArch64/AArch64InstrInfo.td
M llvm/test/CodeGen/AArch64/bf16-convert-intrinsics.ll
M llvm/test/CodeGen/AArch64/bf16-v4-instructions.ll
M llvm/test/CodeGen/AArch64/bf16-v8-instructions.ll
Log Message:
-----------
[AArch64] Improve bcvtn2 and remove aarch64_neon_bfcvt intrinsics (#120363)
This started out as trying to combine bf16 fpround to BFCVT2
instructions, but ended up removing the aarch64.neon.nfcvt intrinsics in
favour of generating fpround instructions directly. This simplifies the
patterns and can lead to other optimizations. The BFCVT2 instruction is
adjusted to makes sure the types are valid, and a bfcvt2 is now
generated in more place. The old intrinsics are auto-upgraded to fptrunc
instructions too.
To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications
More information about the All-commits
mailing list