summary refs log tree commit diff stats
path: root/results/classifier/gemma3:12b/assembly/1590336
diff options
context:
space:
mode:
authorChristian Krinitsin <mail@krinitsin.com>2025-07-03 07:27:52 +0000
committerChristian Krinitsin <mail@krinitsin.com>2025-07-03 07:27:52 +0000
commitd0c85e36e4de67af628d54e9ab577cc3fad7796a (patch)
treef8f784b0f04343b90516a338d6df81df3a85dfa2 /results/classifier/gemma3:12b/assembly/1590336
parent7f4364274750eb8cb39a3e7493132fca1c01232e (diff)
downloadqemu-analysis-d0c85e36e4de67af628d54e9ab577cc3fad7796a.tar.gz
qemu-analysis-d0c85e36e4de67af628d54e9ab577cc3fad7796a.zip
add deepseek and gemma results
Diffstat (limited to 'results/classifier/gemma3:12b/assembly/1590336')
-rw-r--r--results/classifier/gemma3:12b/assembly/159033616
1 files changed, 16 insertions, 0 deletions
diff --git a/results/classifier/gemma3:12b/assembly/1590336 b/results/classifier/gemma3:12b/assembly/1590336
new file mode 100644
index 000000000..e2c646d0f
--- /dev/null
+++ b/results/classifier/gemma3:12b/assembly/1590336
@@ -0,0 +1,16 @@
+
+qemu-arm does not reject vrintz on non-v8 cpu
+
+Hello,
+
+It seems that qemu-arm does not reject some v8-only instructions as it should, but executes them "correctly".
+
+For instance, while compiling/running some of the GCC ARM instrinsics tests, we noticed that
+vrintz should be rejected on cortex-a9 for instance, while it is executed as if the instruction was supported.
+
+objdump says:
+   1074c:       f3fa05a0        vrintz.f32      d16, d16
+and qemu -d in_asm says:
+0x0001074c:  f3fa05a0      vabal.u<illegal width 64>    q8, d26, d16
+
+The problem is still present in qemu-2.6.0
\ No newline at end of file