diff options
| author | Christian Krinitsin <mail@krinitsin.com> | 2025-07-07 17:18:14 +0000 |
|---|---|---|
| committer | Christian Krinitsin <mail@krinitsin.com> | 2025-07-07 17:18:14 +0000 |
| commit | 61361f925d4914a6608a0076e64cc2399311ed5f (patch) | |
| tree | 6f717c2ff0b11d7493e60da9757818d119cfb541 /results/classifier/phi4:14b/reasoning/manual-review/1620 | |
| parent | 238ec2b7cc1557d6f34c33cc482e4d0cd3e266dd (diff) | |
| download | qemu-analysis-61361f925d4914a6608a0076e64cc2399311ed5f.tar.gz qemu-analysis-61361f925d4914a6608a0076e64cc2399311ed5f.zip | |
add new results
Diffstat (limited to 'results/classifier/phi4:14b/reasoning/manual-review/1620')
| -rw-r--r-- | results/classifier/phi4:14b/reasoning/manual-review/1620 | 5 |
1 files changed, 5 insertions, 0 deletions
diff --git a/results/classifier/phi4:14b/reasoning/manual-review/1620 b/results/classifier/phi4:14b/reasoning/manual-review/1620 new file mode 100644 index 000000000..bf0a388a0 --- /dev/null +++ b/results/classifier/phi4:14b/reasoning/manual-review/1620 @@ -0,0 +1,5 @@ +Instruction + +The issue revolves around the SME FMOPA outer product instruction giving incorrect results when using tile 1 (za1.s). The expected behavior of producing a matrix filled with 1.0 is not achieved, indicating a problem with how the instruction handles elements in that specific tile configuration. + +This classification is based on the bug report's focus on a specific SIMD instruction (`fmopa`) and its interaction with SME tiles, rather than issues related to system calls or general runtime errors outside of this context. \ No newline at end of file |