Diff Detail
Diff Detail
Event Timeline
lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp | ||
---|---|---|
1146 | The amdgpu-32bit-address-high-bits function attribute determines the high 32 bits. They are not 0. |
Paths
| Differential D66388
AMDGPU/GlobalISel: Implement addrspacecast for 32-bit constant addrspace ClosedPublic Authored by arsenm on Aug 17 2019, 8:57 PM.
Diff Detail Event TimelineHerald added subscribers: Petar.Avramovic, t-tye, tpr and 6 others. · View Herald TranscriptAug 17 2019, 8:57 PM arsenm added a child revision: D66389: AMDGPU/GlobalISel: Legalize constant 32-bit loads.Aug 17 2019, 9:38 PM
arsenm added a parent revision: D66780: AMDGPU: Add amdgpu-32bit-address-high-bits to MIR serialization.Aug 26 2019, 9:12 PM This revision is now accepted and ready to land.Aug 27 2019, 2:59 PM
Revision Contents
Diff 217299 lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
test/CodeGen/AMDGPU/GlobalISel/legalize-addrspacecast.mir
|
The amdgpu-32bit-address-high-bits function attribute determines the high 32 bits. They are not 0.