Deepak Nibade
278ec56a6f
gpu: nvgpu: move ops.gr.get_pmm_per_chiplet_offset() HAL to PERF unit
...
g->ops.gr.get_pmm_per_chiplet_offset() HAL operation accesses registers
owned by PERF unit, hence move this HAL to PERF unit as
g->ops.perf.get_pmm_per_chiplet_offset()
Jira NVGPU-2894
Change-Id: I8fb1160329829dc50326aad4b7d1a59e088bba9f
Signed-off-by: Deepak Nibade <dnibade@nvidia.com >
Reviewed-on: https://git-master.nvidia.com/r/2030693
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com >
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com >
2019-03-05 02:50:21 -08:00
Debarshi Dutta
6c8be7cfe2
gpu: nvgpu: move header location of gk20a.h
...
Change path corresponding to gk20a.h to <nvgpu/gk20a.h> corresponding
to files in the following directories.
gk20a/
vgpu/
gv100/
tu104/
common/bus/
common/fb/
common/ltc/
common/mc/
common/perf/
Jira NVGPU-597
Change-Id: I7b4f5e5ea3d13a4d1810c5db35fbc26fe5da443e
Signed-off-by: Debarshi Dutta <ddutta@nvidia.com >
Reviewed-on: https://git-master.nvidia.com/r/1846826
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com >
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com >
2018-10-24 23:16:10 -07:00
Deepak Nibade
362f9a7371
gpu: nvgpu: use MC hals to get MC reset mask in perf unit
...
In common/perf/perf_*.c we right now include MC h/w headers to get
MC reset mask for perfmon
Use MC HAL gops.mc.reset_mask() to get reset mask instead of using
direct MC register headers
Jira NVGPU-1102
Change-Id: I06f0b3638775c07c9e4e7ac80efd479871322d50
Signed-off-by: Deepak Nibade <dnibade@nvidia.com >
Reviewed-on: https://git-master.nvidia.com/r/1852620
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com >
Reviewed-by: svc-misra-checker <svc-misra-checker@nvidia.com >
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com >
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com >
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com >
2018-10-12 17:35:08 +05:30
Deepak Nibade
71a4ca9935
gpu: nvgpu: add separate unit for perf
...
Add separate unit for perf under common/perf/ to provide accesses to h/w
unit hw_perf_*_.c
Implement below HALs in gm20b and gv11b specific h/w files and set them to
appropriate chips
gops.perf.enable_membuf()
gops.perf.disable_membuf()
gops.perf.membuf_reset_streaming()
gops.perf.get_membuf_pending_bytes()
gops.perf.set_membuf_handled_bytes()
gops.perf.get_membuf_overflow_status()
Jira NVGPU-1102
Change-Id: I161990fdb7283f33c0fb2ab6a8051f4bfc3bb181
Signed-off-by: Deepak Nibade <dnibade@nvidia.com >
Reviewed-on: https://git-master.nvidia.com/r/1819302
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com >
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com >
2018-10-12 17:35:08 +05:30
