Author: JackAKirk Date: 2022-01-25T11:29:19-08:00 New Revision: 0ad19a833177861be55fefaff725ab89c8695d01
URL: https://github.com/llvm/llvm-project/commit/0ad19a833177861be55fefaff725ab89c8695d01 DIFF: https://github.com/llvm/llvm-project/commit/0ad19a833177861be55fefaff725ab89c8695d01.diff LOG: [CUDA,NVPTX] Corrected fragment size for tf32 LD B matrix. Signed-off-by: JackAKirk <jack.k...@codeplay.com> Reviewed By: tra Differential Revision: https://reviews.llvm.org/D118023 Added: Modified: clang/lib/CodeGen/CGBuiltin.cpp Removed: ################################################################################ diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp index cd35e7cbe76f7..a80a55e054a3b 100644 --- a/clang/lib/CodeGen/CGBuiltin.cpp +++ b/clang/lib/CodeGen/CGBuiltin.cpp @@ -17190,7 +17190,7 @@ static NVPTXMmaLdstInfo getNVPTXMmaLdstInfo(unsigned BuiltinID) { case NVPTX::BI__mma_tf32_m16n16k8_ld_a: return MMA_LDST(4, m16n16k8_load_a_tf32); case NVPTX::BI__mma_tf32_m16n16k8_ld_b: - return MMA_LDST(2, m16n16k8_load_b_tf32); + return MMA_LDST(4, m16n16k8_load_b_tf32); case NVPTX::BI__mma_tf32_m16n16k8_ld_c: return MMA_LDST(8, m16n16k8_load_c_f32); _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
