[PATCH] D131265: Fixed sm version for .and bmma operator.

[Jack Kirk via Phabricator via cfe-commits]

JackAKirk created this revision.
JackAKirk added a reviewer: tra.
Herald added subscribers: mattd, gchakrabarti, asavonic.
Herald added a project: All.
JackAKirk requested review of this revision.
Herald added subscribers: cfe-commits, jholewinski.
Herald added a project: clang.

As stated here (https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#warp-level-matrix-instructions-wmma-mma):

".and operation in single-bit wmma requires sm_80 or higher."


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D131265

Files:
  clang/include/clang/Basic/BuiltinsNVPTX.def


Index: clang/include/clang/Basic/BuiltinsNVPTX.def
===================================================================
--- clang/include/clang/Basic/BuiltinsNVPTX.def
+++ clang/include/clang/Basic/BuiltinsNVPTX.def
@@ -853,7 +853,7 @@
 TARGET_BUILTIN(__bmma_m8n8k128_ld_a_b1, "vi*iC*UiIi", "", AND(SM_75,PTX63))
 TARGET_BUILTIN(__bmma_m8n8k128_ld_b_b1, "vi*iC*UiIi", "", AND(SM_75,PTX63))
 TARGET_BUILTIN(__bmma_m8n8k128_ld_c, "vi*iC*UiIi", "", AND(SM_75,PTX63))
-TARGET_BUILTIN(__bmma_m8n8k128_mma_and_popc_b1, "vi*iC*iC*iC*Ii", "", AND(SM_75,PTX71))
+TARGET_BUILTIN(__bmma_m8n8k128_mma_and_popc_b1, "vi*iC*iC*iC*Ii", "", AND(SM_80,PTX71))
 TARGET_BUILTIN(__bmma_m8n8k128_mma_xor_popc_b1, "vi*iC*iC*iC*Ii", "", AND(SM_75,PTX63))
 TARGET_BUILTIN(__bmma_m8n8k128_st_c_i32, "vi*iC*UiIi", "", AND(SM_75,PTX63))
 TARGET_BUILTIN(__imma_m16n16k16_ld_a_s8, "vi*iC*UiIi", "", AND(SM_72,PTX63))


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D131265.450302.patch
Type: text/x-patch
Size: 886 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20220805/fe617004/attachment.bin>