diff options
| author | Shilei Tian <i@tianshilei.me> | 2022-02-10 18:07:39 -0500 |
|---|---|---|
| committer | Shilei Tian <i@tianshilei.me> | 2022-02-10 18:07:46 -0500 |
| commit | aca33b0b37b706a013625c92c4713b3a329d90d0 (patch) | |
| tree | 1dd933fa53c16334829c83694ed1586126b113af /llvm/lib/Transforms/Utils/LoopVersioning.cpp | |
| parent | 93d1a623cecb6f732db7900baf230a13e6ac6c6a (diff) | |
| download | llvm-aca33b0b37b706a013625c92c4713b3a329d90d0.zip llvm-aca33b0b37b706a013625c92c4713b3a329d90d0.tar.gz llvm-aca33b0b37b706a013625c92c4713b3a329d90d0.tar.bz2 | |
[OpenMP][CUDA] Remove the hard team limit
Currently we have a hard team limit, which is set to 65536. It says no matter whether the device can support more teams, or users set more teams, as long as it is larger than that hard limit, the final number to launch the kernel will always be that hard limit. It is way less than the actual hardware limit. For example, my workstation has GTX2080, and the hardware limit of grid size is 2147483647, which is exactly the largest number a `int32_t` can represent. There is no limitation mentioned in the spec. This patch simply removes it.
Reviewed By: jdoerfert
Differential Revision: https://reviews.llvm.org/D119313
Diffstat (limited to 'llvm/lib/Transforms/Utils/LoopVersioning.cpp')
0 files changed, 0 insertions, 0 deletions