diff options
| author | Marek Olsak <marek.olsak@amd.com> | 2018-04-09 16:56:32 +0000 |
|---|---|---|
| committer | Marek Olsak <marek.olsak@amd.com> | 2018-04-09 16:56:32 +0000 |
| commit | 52b033b82721af150a9bf986feacb9948cefd8c0 (patch) | |
| tree | d00ab06803adeaa84934b9cc38faae55f4f16aa4 /llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h | |
| parent | c65901282b22f92b34f933005f8b409d2e3651d3 (diff) | |
| download | bcm5719-llvm-52b033b82721af150a9bf986feacb9948cefd8c0.tar.gz bcm5719-llvm-52b033b82721af150a9bf986feacb9948cefd8c0.zip | |
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).
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=105464
llvm-svn: 329591
Diffstat (limited to 'llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h')
| -rw-r--r-- | llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h | 5 |
1 files changed, 3 insertions, 2 deletions
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h b/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h index e3455d34324..cd080263c5a 100644 --- a/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h +++ b/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h @@ -133,6 +133,7 @@ protected: bool EnableLoadStoreOpt; bool EnableUnsafeDSOffsetFolding; bool EnableSIScheduler; + bool EnableDS128; bool DumpCode; // Subtarget statically properties set by tablegen @@ -412,8 +413,8 @@ public: /// \returns If target supports ds_read/write_b128 and user enables generation /// of ds_read/write_b128. - bool useDS128(bool UserEnable) const { - return CIInsts && UserEnable; + bool useDS128() const { + return CIInsts && EnableDS128; } /// \returns If MUBUF instructions always perform range checking, even for |

