[CUDA,NVPTX] Corrected fragment size for tf32 LD B matrix.
authorJackAKirk <jack.kirk@codeplay.com>
Mon, 24 Jan 2022 20:32:36 +0000 (12:32 -0800)
committerArtem Belevich <tra@google.com>
Tue, 25 Jan 2022 19:29:19 +0000 (11:29 -0800)
commit0ad19a833177861be55fefaff725ab89c8695d01
treec3778c1c131b61ce78b26a1fd90c95fe196a0a92
parentc39d22d1968cf07e54b5816ba76dccef8acaace1
[CUDA,NVPTX] Corrected fragment size for tf32 LD B matrix.

Signed-off-by: JackAKirk <jack.kirk@codeplay.com>
Reviewed By: tra

Differential Revision: https://reviews.llvm.org/D118023
clang/lib/CodeGen/CGBuiltin.cpp