Page MenuHomePhabricator

harsh (Harsh Menon)
User

Projects

User does not belong to any projects.

User Details

User Since
Jan 20 2021, 1:24 PM (26 w, 6 d)

Recent Activity

Mon, Jun 28

harsh added a comment to D104884: Order parallel indices before transposing the input in multireductions.

Thanks and feel free to merge because I don't have merge priveleges.

Mon, Jun 28, 5:09 PM · Restricted Project
harsh updated the diff for D104884: Order parallel indices before transposing the input in multireductions.

Address comments and linting errors

Mon, Jun 28, 4:11 PM · Restricted Project
harsh added inline comments to D104884: Order parallel indices before transposing the input in multireductions.
Mon, Jun 28, 4:10 PM · Restricted Project
harsh added a comment to D104884: Order parallel indices before transposing the input in multireductions.

@ThomasRaoux - yes I just uploaded it.

Mon, Jun 28, 3:02 PM · Restricted Project
harsh updated the diff for D104884: Order parallel indices before transposing the input in multireductions.

Fixed as per comments

Mon, Jun 28, 2:59 PM · Restricted Project
harsh added a comment to D104884: Order parallel indices before transposing the input in multireductions.

Thanks @ThomasRaoux , @asaadaldien , @nicolasvasilache for the comments. @nicolasvasilache I have modified the patch as per your changes but kept the current patch to just handle moving reductions to the inner most dimensions. I will put up another patch to handle moving reductions to the outermost dimensions and based on the performance of inner vs outer, we can decide which path we want to take.

Mon, Jun 28, 2:44 PM · Restricted Project

Jun 24 2021

harsh updated the diff for D104884: Order parallel indices before transposing the input in multireductions.

Fixed lint changes

Jun 24 2021, 6:19 PM · Restricted Project
harsh requested review of D104884: Order parallel indices before transposing the input in multireductions.
Jun 24 2021, 4:33 PM · Restricted Project

May 26 2021

harsh updated the diff for D103207: Add n-D vector lowering to LLVM for cast ops.

Add support for fpext, fptrunc and trunci

May 26 2021, 3:11 PM · Restricted Project
harsh updated the diff for D103207: Add n-D vector lowering to LLVM for cast ops.

Updated commit message

May 26 2021, 2:53 PM · Restricted Project
harsh updated the diff for D103207: Add n-D vector lowering to LLVM for cast ops.

Added support for more casting ops

May 26 2021, 2:52 PM · Restricted Project
harsh requested review of D103207: Add n-D vector lowering to LLVM for cast ops.
May 26 2021, 2:29 PM · Restricted Project

Jan 27 2021

harsh abandoned D95549: [X86][AVX] Handle vperm2x128 shuffling of a subvector splat..

Apologies I was just attempting to cherry pick someone else's change and am new to arcanist.

Jan 27 2021, 11:08 AM · Restricted Project
harsh requested review of D95549: [X86][AVX] Handle vperm2x128 shuffling of a subvector splat..
Jan 27 2021, 11:05 AM · Restricted Project