sci-libs/rocWMMA
library for accelerating mixed precision matrix multiply-accumulate operations
Screenshots
-
rocWMMA-6.3.2~amd64+amdgpu_targets_gfx908 +amdgpu_targets_gfx90a +amdgpu_targets_gfx940 +amdgpu_targets_gfx941 +amdgpu_targets_gfx942 +amdgpu_targets_gfx1100 +amdgpu_targets_gfx1101 +amdgpu_targets_gfx1102 test
View 
Download 
Browse License: MIT Overlay: gentoo -
rocWMMA-6.3.0~amd64+amdgpu_targets_gfx908 +amdgpu_targets_gfx90a +amdgpu_targets_gfx940 +amdgpu_targets_gfx941 +amdgpu_targets_gfx942 +amdgpu_targets_gfx1100 +amdgpu_targets_gfx1101 +amdgpu_targets_gfx1102 test
View Download Browse License: MIT Overlay: gentoo
USE Flags
+amdgpu_targets_gfx908
* This flag is undocumented *
+amdgpu_targets_gfx90a
* This flag is undocumented *
+amdgpu_targets_gfx940
* This flag is undocumented *
+amdgpu_targets_gfx941
* This flag is undocumented *
+amdgpu_targets_gfx942
* This flag is undocumented *
+amdgpu_targets_gfx1100
* This flag is undocumented *
+amdgpu_targets_gfx1101
* This flag is undocumented *
+amdgpu_targets_gfx1102
* This flag is undocumented *
test
Global: Workaround to pull in packages needed to run with FEATURES=test. Portage-2.1.2 handles this internally, so don't set it in make.conf/package.use anymore