summaryrefslogtreecommitdiffstats
path: root/debug/risc-v-gsp-rm-vm/tests/test_probe.py
diff options
context:
space:
mode:
authorArthur Hanson Rasmusson <arthur@vgpu.io>2026-10-22 23:54:35 -0400
committerArthur Hanson Rasmusson <arthur@vgpu.io>2026-10-22 23:54:35 -0400
commit78a4db29e527a59dbff3ad6857440d64208dfba1 (patch)
tree6eac2d5975e59052b24281202a42862e317d54d2 /debug/risc-v-gsp-rm-vm/tests/test_probe.py
parente756d4fad97a6768f83f8e84d62a26673e0b37f3 (diff)
downloadopen-iov-78a4db29e527a59dbff3ad6857440d64208dfba1.tar.gz
open-iov-78a4db29e527a59dbff3ad6857440d64208dfba1.zip
r507o walk the CE channels before the GR channels: enforce the client's stream order in the pump itself
The streams order their H2D copies before the kernel that consumes them, but the channels register in handle order (the RM's GR channel early, the copy-CE channels later) and the pump walked them in that order; a pass that decoded the GR launch before the CE channel's entries ran let the forward workqueue execute the launch's copy-in against pre-copy data (r480-sep: copy-in 115 ms before its stream's H2D soft copies; r481 proved no host semaphore links the two). The CE copies execute on the same service thread, so consuming the CE entries first fixes the inversion without any cross-channel hold. Stable partition of the pass snapshot; relative order within each class is preserved.
Diffstat (limited to 'debug/risc-v-gsp-rm-vm/tests/test_probe.py')
0 files changed, 0 insertions, 0 deletions