index
:
open-iov.git
archive/pre-squash
bigpath
cs-share
dual
golden-replay
gr-forwarding
lottery
lottery-m156-gate-attempt
m31
m32
m32reorder
m33
master
refactor/host-gsp-emulation
reg-probe
stallfree
v7-user-lane
Open-IOV vGPU-IO: host-side GSP emulation for unmodified NVIDIA guest drivers
root
summary
refs
log
tree
commit
diff
stats
log msg
author
committer
range
Commit message (
Expand
)
Author
Age
*
tools/cuda-ab/run: the egl_frame guest GL probe binary (committed for the GL ...
Arthur Hanson Rasmusson
3 hours
*
gitignore: never track demo/release .mp4 videos (the 0.9.9 release preview wi...
Arthur Hanson Rasmusson
3 hours
*
r489b CONTINUATION_RECORD from the driver is one-way data (the tail of a mult...
Arthur Hanson Rasmusson
4 hours
*
r489 the proper large-reply framing for GSP_RM_CONTROL: replies beyond the dr...
Arthur Hanson Rasmusson
4 hours
*
r487b tighten the RM_CONTROL reply clamp margin: the guest rejected rpc.lengt...
Arthur Hanson Rasmusson
4 hours
*
r487 THE GL/VULKAN VASPACE WALL: clamp RM_CONTROL replies to the 64 KB wire r...
Arthur Hanson Rasmusson
4 hours
*
r484 the staging-drain completion edge: when the acquire gate holds an entry ...
Arthur Hanson Rasmusson
5 hours
*
r481c sema_push_raw: lower the call-site threshold to 512 bytes so launch pus...
Arthur Hanson Rasmusson
5 hours
*
r481b sema_push_raw walk fix: handle op!=1 method groups (data runs, scans) a...
Arthur Hanson Rasmusson
5 hours
*
r481 sema_push_raw diagnostic: dump the decoded method stream of the first N ...
Arthur Hanson Rasmusson
6 hours
*
r471 the counter-publish clamp: never advance the guest's completion word pas...
Arthur Hanson Rasmusson
7 hours
*
r470 the narrow streams_events stale-ring fix: an ALL-ZERO push page (ring en...
Arthur Hanson Rasmusson
8 hours
*
Revert "r469 THE streams_events staging-reuse corruption root cause: a GR ent...
Arthur Hanson Rasmusson
8 hours
*
r469 THE streams_events staging-reuse corruption root cause: a GR entry whose...
Arthur Hanson Rasmusson
8 hours
*
tools/cuda-ab/run: the r458-r459 probe binaries (memset2d_probe, streams_even...
Arthur Hanson Rasmusson
9 hours
*
r459 THE mid-boot degradation root cause: the 8-slot VA-space table filled wi...
Arthur Hanson Rasmusson
10 hours
*
tools/cuda-ab: isolation probes from the transformer/streams_events forensics
Arthur Hanson Rasmusson
10 hours
*
pin_gr_stream: the demand-loop regex never matched the kernel's stalled-VA li...
Arthur Hanson Rasmusson
11 hours
*
r458 THE memset2d root cause: the CE copy decode read only LINE_LENGTH_IN and...
Arthur Hanson Rasmusson
11 hours
*
r457 free the copy staging snapshot only on consumption/slot-reuse/skip/TTL (...
Arthur Hanson Rasmusson
14 hours
*
r456 keep the copy staging snapshot alive across opdef retries (the r455 oper...
Arthur Hanson Rasmusson
14 hours
*
tools/cuda-ab/run: add the r451-r453 probe binaries (ip_probe*, ip4/5/6, stre...
Arthur Hanson Rasmusson
15 hours
*
tools/cuda-ab: the r451-r453 probe suite that cracked the deterministic class...
Arthur Hanson Rasmusson
15 hours
*
docs/vEP: record the r452 copy-out fingerprint rule (a change-detection finge...
Arthur Hanson Rasmusson
15 hours
*
r453 rel_mod=1 default: route the forwarded QMD release0 to the module semaph...
Arthur Hanson Rasmusson
15 hours
*
r452 change-detection fingerprint fix: the 32-bit ADDITIVE page checksum used...
Arthur Hanson Rasmusson
16 hours
*
r449 shader-constant-cache invalidate experiment (gsp_phys_gr_ccache_inv, def...
Arthur Hanson Rasmusson
18 hours
*
tools/soak.sh: fix the present-clients probe (the for-loop's exit status was ...
Arthur Hanson Rasmusson
19 hours
*
r445b wedge hard re-arm trigger: the r445 battery shows every post-dispatch n...
Arthur Hanson Rasmusson
20 hours
*
r445 wedge hard re-arm experiment (gsp_phys_gr_wedge_rearm, default off): on ...
Arthur Hanson Rasmusson
20 hours
*
r444 copy-snapshot ownership: key the fail4 held-copy staging snapshot by (ch...
Arthur Hanson Rasmusson
20 hours
*
docs: SESSION 13 handoff (transformer=wedge class, four negative wedge experi...
Arthur Hanson Rasmusson
21 hours
*
r441 zero the guest-visible release words on the FIRST attempt too (not only ...
Arthur Hanson Rasmusson
21 hours
*
r436 full sysmem PTE aperture/VOL matrix: gsp_phys_rmcall_pte_coh becomes a 4...
Arthur Hanson Rasmusson
23 hours
*
r434 wedge instrumentation + CWD-slot path: post-retire QMD64 dump (hardware-...
Arthur Hanson Rasmusson
24 hours
*
r433 RELEASE_MEMBAR_TYPE A/B: gsp_phys_gr_rel_membar forces QMD word11 bit14 ...
Arthur Hanson Rasmusson
24 hours
*
r431b revert the coherent-PTE default: the clean-boot A/B showed aperture 2 (...
Arthur Hanson Rasmusson
25 hours
*
r431 sysmem leaf-PTE aperture fix (root-cause candidate): map every host dma_...
Arthur Hanson Rasmusson
25 hours
*
r430 wedge dispatch-window sampling: skedrec samples every poll iteration (th...
Arthur Hanson Rasmusson
25 hours
*
r427 idempotent fast-accept: a zero-write launch whose identity (QMD minus re...
Arthur Hanson Rasmusson
26 hours
*
r425 wedge diagnostics + init-once A/B: SKED/FECS/TPC/CWD register witnesses ...
Arthur Hanson Rasmusson
27 hours
*
tools: frame_reader picks the largest kvmfr shm (a stray empty 'kvmfr-*' file...
Arthur Hanson Rasmusson
28 hours
*
tools/lg + docs: guest frame producer path (CUDA -> ivshmem -> host) and the ...
Arthur Hanson Rasmusson
29 hours
*
sema: r420d bounded 2D-copy geometry witness (sema-op2d)
Arthur Hanson Rasmusson
29 hours
*
tools/cuda-ab: wedge_bisect - bisect the no-execute wedge trigger by inter-la...
Arthur Hanson Rasmusson
30 hours
*
sema: r420c 2D fills/copies with pitch == row length cover all rows
Arthur Hanson Rasmusson
30 hours
*
gr: r420b author the guest QMD release on every outcome when release0 is redi...
Arthur Hanson Rasmusson
30 hours
*
gr/sema: r420 pause completion deadlines under the backend wedge-quiet hold
Arthur Hanson Rasmusson
30 hours
*
gr: r411 sticky wedge episode - quiet the first retry of any zero-write launc...
Arthur Hanson Rasmusson
31 hours
*
gr: default wedge quiet window 40 s (r417 live: a 20 s host hold did not heal...
Arthur Hanson Rasmusson
32 hours
[next]