llvm/llvm-project

[X86][SSE] Improve ISD::FP_TO_*INT_SAT vector lowering

Open

#51,923 opened on Nov 22, 2021

View on GitHub
 (7 comments) (0 reactions) (1 assignee)C++ (10,782 forks)batch import
backend:X86bugzillagood first issue

Repository metrics

Stars
 (26,378 stars)
PR merge metrics
 (Avg merge 1d 2h) (1,000 merged PRs in 30d)

Description
Bugzilla Link 52581
Version trunk
OS Windows NT
CC @topperc,@DMG862,@RKSimon,@phoebewang,@rotateright

Extended Description

https://gcc.godbolt.org/z/3q7KGs6h5

We currently scalarize these cases, but we should be able to make use of SSE behaviour for out-of-range integer results to keep these fully vectorized.

Contributor guide

Research direction
Examine the current scalarization implementation for vector FP TO *INT SAT lowering and identify how SSE's native behavior for out of range integer results can be leveraged to keep the operations vectorized without scalarization.
Tech stack
cpp
Domain
backend
Issue type
Performance
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
3-5 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Mostly clear
Prerequisites
C++LLVMSSE
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
40