================
@@ -87,6 +87,7 @@ class CGHLSLRuntime {
GENERATE_HLSL_INTRINSIC_FUNCTION(SDot, sdot)
GENERATE_HLSL_INTRINSIC_FUNCTION(UDot, udot)
GENERATE_HLSL_INTRINSIC_FUNCTION(WaveIsFirstLane, wave_is_first_lane)
+ GENERATE_HLSL_INTRINSIC_FUNCTION(WaveReadLaneAt, waveReadLaneAt)
----------------
llvm-beanz wrote:
The equivalent AMD GPU intrinsic is named `int_amdgcn_readlane`, which
translates to `llvm.amdgcn.readlane`. Having `dx.readlane` or
`dx.wave.readlane` seems like a preferable naming approach.
https://github.com/llvm/llvm-project/pull/111010
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
