radeonsi: Use llvm.amdgcn.mbcnt.* intrinsics instead of llvm.SI.tid
authorTom Stellard <thomas.stellard@amd.com>
Fri, 15 Apr 2016 22:53:38 +0000 (22:53 +0000)
committerTom Stellard <thomas.stellard@amd.com>
Fri, 22 Apr 2016 23:48:43 +0000 (23:48 +0000)
commit128267d781ffa9cb986cb3d79a356492abc21df4
tree2ea099bb9592c0e64649e7c35f5194da0ac14b8f
parentd3427412a335ec64d05e09e040a2ddb2b9552563
radeonsi: Use llvm.amdgcn.mbcnt.* intrinsics instead of llvm.SI.tid

We're trying to move to more of the new style intrinsics with include
the correct target name, and map directly to ISA instructions.

v2:
  - Only do this with LLVM 3.8 and newer.

Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
src/gallium/drivers/radeonsi/si_shader.c