Bug 248549 - [WebAssembly SIMD] Support integer and floating-point arithmetic on Intel
Summary: [WebAssembly SIMD] Support integer and floating-point arithmetic on Intel
Status: RESOLVED FIXED
Alias: None
Product: WebKit
Classification: Unclassified
Component: WebAssembly (show other bugs)
Version: WebKit Nightly Build
Hardware: Unspecified Unspecified
: P2 Normal
Assignee: David Degazio
URL:
Keywords: InRadar
Depends on:
Blocks: 246345
  Show dependency tree / graph
 
Reported: 2022-11-30 13:04 PST by David Degazio
Modified: 2022-12-07 15:02 PST (History)
2 users (show)

See Also:

Attachments
Add an attachment (proposed patch, testcase, etc.)

Note You need to log in before you can comment on or make changes to this bug.
Description David Degazio 2022-11-30 13:04:29 PST 
Adds support for basic SIMD integer arithmetic and floating-point arithmetic instructions on Intel.
Comment 1 David Degazio 2022-11-30 13:33:13 PST 
Pull request: https://github.com/WebKit/WebKit/pull/6984
Comment 2 David Degazio 2022-12-01 16:49:07 PST 
For reference, this means adding support for the following instructions:

 - i8x16.add, i16x8.add, i32x4.add, i64x2.add
 - i8x16.sub, i16x8.sub, i32x4.sub, f64x2.sub
 - i16x8.mul, i32x4.mul, i64x2.mul
 - i32x4.dot_i16x8_s
 - i8x16.neg, i16x8.neg, i32x4.neg, i64x2.neg
 - f32x4.add, f64x2.add
 - f32x4.sub, f64x2.sub
 - f32x4.mul, f64x2.mul
 - f32x4.div, f64x2.div
 - f32x4.sqrt, f64x2.sqrt
 - f32x4.ceil, f64x2.ceil
 - f32x4.floor, f64x2.floor
 - f32x4.trunc, f64x2.trunc
 - f32x4.nearest, f64x2.nearest
Comment 3 Mark Lam 2022-12-07 10:56:45 PST 
<rdar://problem/103081491>
Comment 4 EWS 2022-12-07 15:02:35 PST 
Committed 257511@main (155740a50205): <https://commits.webkit.org/257511@main>

Reviewed commits have been landed. Closing PR #6984 and removing active labels.