AMDGPU: enable 128-bit for local addr space under an option
Author: Samuel Pitoiset
ds_read_b128 and ds_write_b128 have been recently enabled
under the amdgpu-ds128 option because the performance benefit
is unclear.
Though, using 128-bit loads/stores for the local address space
appears to introduce regressions in tessellation shaders. Not
sure what is broken, but as ds_read_b128/ds_write_b128 are not
enabled by default, just introduce a global option and enable
128-bit only if requested (until it's fixed/used correctly).
v2: - fix regressions in merge-stores.ll and multiple_tails.ll
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=105464
llvm-svn: 329764
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
index 9f097cd..bf560a9 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
@@ -265,11 +265,13 @@
return 512;
}
- if (AddrSpace == AS.FLAT_ADDRESS ||
- AddrSpace == AS.LOCAL_ADDRESS ||
- AddrSpace == AS.REGION_ADDRESS)
+ if (AddrSpace == AS.FLAT_ADDRESS)
return 128;
+ if (AddrSpace == AS.LOCAL_ADDRESS ||
+ AddrSpace == AS.REGION_ADDRESS)
+ return ST->useDS128() ? 128 : 64;
+
if (AddrSpace == AS.PRIVATE_ADDRESS)
return 8 * ST->getMaxPrivateElementSize();