<feed xmlns='http://www.w3.org/2005/Atom'>
<title>open-iov.git/tools/cuda-ab/memset2d_probe.cu, branch master</title>
<subtitle>Open-IOV vGPU-IO: host-side GSP emulation for unmodified NVIDIA guest drivers
</subtitle>
<id>https://git.vgpu.io/open-iov.git/atom?h=master</id>
<link rel='self' href='https://git.vgpu.io/open-iov.git/atom?h=master'/>
<link rel='alternate' type='text/html' href='https://git.vgpu.io/open-iov.git/'/>
<updated>2026-10-22T13:40:06+00:00</updated>
<entry>
<title>tools/cuda-ab: isolation probes from the transformer/streams_events forensics</title>
<updated>2026-10-22T13:40:06+00:00</updated>
<author>
<name>Arthur Hanson Rasmusson</name>
<email>arthur@vgpu.io</email>
</author>
<published>2026-10-22T13:40:06+00:00</published>
<link rel='alternate' type='text/html' href='https://git.vgpu.io/open-iov.git/commit/?id=7df79840ceae3b0b05720c489afe35d471fa7e49'/>
<id>urn:sha1:7df79840ceae3b0b05720c489afe35d471fa7e49</id>
<content type='text'>
- tgemm_probe: minimal X[64x256]xW[256x256] GEMM isolation. Found the
  deterministic first-page corruption: after a forwarded launch (and
  sometimes already after the H2D upload) the FIRST 8 bytes of the first
  data-window page are replaced by that page's bytes at offset 8
  (X[0..1] &lt;- X[2..3]; vidmem dump confirms; OUT-UNCH shows chunk==guest),
  which corrupts GEMM row 0 for all 256 columns (bad=256/pass, identical
  across 3 passes). Not rel_mod-dependent (A/B at runtime).
- streams_events_probe: per-buffer DPTRS + per-buffer bad + first-8
  expected/actual for the 3-stream event chain (green on a clean boot,
  bad=131072 after several clients - the client-switch resolution class).
- memset2d_probe: per-phase bad/PHIST for victory_memset2d (verified the
  r458 LINE_COUNT fix: bad_total=0, all three phases).
</content>
</entry>
</feed>
