diff options
Diffstat (limited to 'results/classifier/zero-shot-user-mode/output/instruction/1901')
| -rw-r--r-- | results/classifier/zero-shot-user-mode/output/instruction/1901 | 25 |
1 files changed, 0 insertions, 25 deletions
diff --git a/results/classifier/zero-shot-user-mode/output/instruction/1901 b/results/classifier/zero-shot-user-mode/output/instruction/1901 deleted file mode 100644 index 13a696bd..00000000 --- a/results/classifier/zero-shot-user-mode/output/instruction/1901 +++ /dev/null @@ -1,25 +0,0 @@ -instruction: 0.890 -runtime: 0.081 -syscall: 0.030 - - - -qemu-sparc64 / sparc32plus apparent wrong results from VIS fmul8x16 instruction -Description of problem: -Experimenting with SPARC emulation, I noticed that the results of the UltraSparc fmul8x16 instruction don't appear to match the behaviour of real silicon (aka it doesn't appear to work at all -- in the test program, the result seems to be always 0). Other VIS instructions I tried seem to be OK (I have not tried all of them). - -The same problem is observed both in 64-bit (qemu-sparc64) and 32-bit (qemu-sparc32plus) applications. -Steps to reproduce: -1. Compile the attached test program (which exhaustively tests all possible combinations of 16-bit and 8-bit inputs) with gcc: - ``` - sparc64-unknown-linux-gnu-gcc -static -Os -mcpu=ultrasparc -mvis -o test_fmul8x16 test_fmul8x16.c - ``` -2. Run it in qemu-sparc64: - ``` - qemu-sparc64 -cpu 'TI UltraSparc II' ./test_fmul8x16 - ``` -3. Observe almost all tests fail. - - Running the exact same compiled binary on a real UltraSparc II CPU gives all pass results. -Additional information: -[test_fmul8x16.c](/uploads/2bf68e53652fba2ed69ac3ebb3f4b5e9/test_fmul8x16.c) |