From 04524a5b401c373fb72f014bab1026e3451b2227 Mon Sep 17 00:00:00 2001 From: Arthur Hanson Rasmusson Date: Sun, 18 Oct 2026 15:11:08 -0400 Subject: cuda-ab: ctaid_probe ground-truth revision - RAWA/RAWA2, 16 values per band, PROBE2B repeat r229 first run: PROBE1 (coordinate map) perfect; PROBE2 (flat A read) wrong at every element - band 0 read A's own values at wrong offsets (16382/16383 = A's last elements), bands >=1 read float-typed data. Before concluding engine-side, the probe now records ground truth in-band: - RAWA: A uploaded then copied straight back D2H with no kernel, first8/ last8 printed (the buffer itself must hold i); - RAWA2: same readback after both phases (input-corruption check); - every band prints its raw first 16 values; - PROBE2B: the same arow_read runs a second time into a fresh output buffer, so a first-attempt-only failure is the engine's per-launch lottery rather than addressing. The probe's own math re-checked: A is int32 everywhere, expected is row*256+col, and PROBE1's exact pass over the same output pipeline proves the harness itself is sound. Committed binary rebuilt static sm_75. --- tools/cuda-ab/run/ctaid_probe | Bin 829280 -> 829368 bytes 1 file changed, 0 insertions(+), 0 deletions(-) (limited to 'tools/cuda-ab/run') diff --git a/tools/cuda-ab/run/ctaid_probe b/tools/cuda-ab/run/ctaid_probe index a675ed1..d8d5498 100755 Binary files a/tools/cuda-ab/run/ctaid_probe and b/tools/cuda-ab/run/ctaid_probe differ -- cgit v1.2.3