AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
f7405b87395472ffccbf5209afd56c64b23e8e3e
rocm-systems/projects
T
History
alex-breslow-amd f7405b8739 Remove nontemporality from stores, put in casts to global address space (#1982) 
* Implements casting key loads and stores to address_space(1) so that vector global load and store instructions are emitted by the compiler instead of more costly flat loads and stores
* Removes nontemporality from some key stores for gfx950.

[ROCm/rccl commit: e69b11eba5]
2025-10-28 10:34:48 -07:00
..
rccl
Remove nontemporality from stores, put in casts to global address space (#1982)
2025-10-28 10:34:48 -07:00