[PATCH] D25020: [ARM] Fix 26% performance regression on Cortex-A9 caused by not using VMLA/VMLS

Renato Golin via llvm-commits llvm-commits at lists.llvm.org
Tue Oct 4 06:00:59 PDT 2016

Previous message: [PATCH] D25020: [ARM] Fix 26% performance regression on Cortex-A9 caused by not using VMLA/VMLS
Next message: [PATCH] D25020: [ARM] Fix 26% performance regression on Cortex-A9 caused by not using VMLA/VMLS
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

rengolin added a reviewer: rovka.
rengolin added a comment.

Hi,

Adding Diana, as she was looking into the VMLA hazard a few weeks ago in an attempt to remove a few CPU-specific flags. This review will need a deeper look in relation to the `isLikeA9` check.

cheers,
--renato


https://reviews.llvm.org/D25020

Previous message: [PATCH] D25020: [ARM] Fix 26% performance regression on Cortex-A9 caused by not using VMLA/VMLS
Next message: [PATCH] D25020: [ARM] Fix 26% performance regression on Cortex-A9 caused by not using VMLA/VMLS
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

More information about the llvm-commits mailing list