llvm-project
[NVPTX] Vectorize and lower 256-bit global loads/stores for sm_100+/ptx88+
#139292
Merged
Overview
Commits
13
Changes
View On GitHub

[NVPTX] Vectorize and lower 256-bit global loads/stores for sm_100+/ptx88+ #139292

AlexMaclean merged 13 commits into llvm:main from dakersnar:github/dkersnar/256-bit
dakersnar
llvmbot llvmbot added backend:NVPTX
llvmbot llvmbot added llvm:transforms
llvmbot
AlexMaclean AlexMaclean requested a review from Artem-B Artem-B 1 year ago
AlexMaclean AlexMaclean requested a review from AlexMaclean AlexMaclean 1 year ago
github-actions
dakersnar
AlexMaclean
AlexMaclean commented on 2025-05-09
Artem-B
Artem-B commented on 2025-05-09
Artem-B
Artem-B commented on 2025-05-09
dakersnar
Artem-B
Artem-B approved these changes on 2025-05-09
AlexMaclean
AlexMaclean
AlexMaclean approved these changes on 2025-05-09
dakersnar
dakersnar [NVPTX] Vectorize and lower 256-bit global loads/stores for sm_100+ a…
f2d54032
dakersnar Clang format
293fb1f5
dakersnar Address reviewer feedback
852c7b79
dakersnar Clang format
25636fe8
dakersnar Replace std::nullopt with empty initializer list:
7a737f9c
dakersnar Make comments consistent
9ca5da5a
dakersnar Simplify loop
502c4379
dakersnar Fix issues with removal of VecType, all tests pass now
327459e3
dakersnar Update test checks to ld/st untyped data
7bc66d08
dakersnar dakersnar force pushed to 7bc66d08 1 year ago
dakersnar Update intirnsics to use untyped ld/st
adb299a9
dakersnar Merge branch 'main' into github/dkersnar/256-bit
83819e20
dakersnar
Artem-B
Artem-B approved these changes on 2025-05-13
dakersnar Simplify op append
65f3e735
dakersnar Merge branch 'main' into github/dkersnar/256-bit
49734db9
AlexMaclean AlexMaclean merged a1e1a84d into main 1 year ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
backend:NVPTX llvm:transforms
Milestone
No milestone
Terms Of Use Privacy Policy Refund Policy Impressum