Grafico dei commit
3 Commit
Autore SHA1 Messaggio Data
Jay Cornwall e2c353dc0d Allocate EOP queue local to GPU
On discrete GPUs place the EOP queue in VRAM. The reader/writer of this
queue is the CP and the size is small. Dispatch latency improves
through lower read latency in AQL completion phase.

Change-Id: Id8351dcddbd21fd7c7d699803c96434c9132db71
Signed-off-by: Jay Cornwall <Jay.Cornwall@amd.com>
2018-02-22 18:14:05 -05:00
Jay Cornwall 4fbffcdd9c Always allocate space for control stack at beginning of save area
Hardware block testing is done with the workgroup state offset
initialized to the control stack size on all ASICs. MEC microcode
assumes this space is available when the workgroup state offset is
reset after a context restore event.

Fixes context save area overrun when the full save area is used.

Change-Id: I8eeb62f97140c6fe409fe78b4497d833584feea8
Signed-off-by: Jay Cornwall <Jay.Cornwall@amd.com>
2017-07-04 10:12:02 -04:00
Jay Cornwall 5493ae420b Disable GPUVM-mapped doorbell on gfx802
gfx802 requires a workaround for a VM TLB bug in which lookups use
the ACTIVE bit of the 8th PTE within any aligned group of 8 PTEs.
Until this is fixed in amdgpu the GPUVM doorbell logic will fail.

Change-Id: I5ec7b1fcd8b7677011a141d27cfc486c45d9a415
Signed-off-by: Jay Cornwall <Jay.Cornwall@amd.com>
2016-10-10 18:39:31 -05:00