Help is available by moving the cursor above any 
symbol or by checking MAQAO website.
| Metric | r0 | r1 | r2 | r3 | r4 | r5 | |
|---|---|---|---|---|---|---|---|
| Total Time (s) | 6.68 | 6.70 | 8.80 | 8.73 | 9.88 | 9.88 | |
| Max (Thread Active Time) (s) | 6.66 | 6.69 | 8.80 | 8.73 | 9.87 | 9.88 | |
| Average Active Time (s) | 6.66 | 6.69 | 8.80 | 8.73 | 9.87 | 9.88 | |
| Activity Ratio (%) | 99.6 | 99.9 | 99.9 | 100.0 | 99.9 | 99.9 | |
| Average number of active threads | 0.996 | 0.999 | 0.999 | 1.000 | 0.999 | 0.999 | |
| Affinity Stability (%) | 99.6 | 99.9 | 99.9 | 99.9 | 99.9 | 99.9 | |
| Time in analyzed loops (%) | 90.4 | 89.7 | 88.7 | 90.4 | 91.8 | 91.3 | |
| Time in analyzed innermost loops (%) | 85.5 | 84.1 | 76.9 | 78.0 | 82.9 | 82.8 | |
| Time in user code (%) | 90.8 | 89.8 | 88.9 | 90.5 | 92.0 | 91.4 | |
| Compilation Options Score (%) | 75.0 | 75.0 | 100 | 100 | 100 | 100 | |
| Array Access Efficiency (%) | 46.4 | 45.4 | 75.3 | 75.5 | 71.4 | 74.8 | |
| Potential Speedups | | ||||||
| Perfect Flow Complexity | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | |
| Perfect OpenMP/MPI/Pthread/TBB | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | |
| Perfect OpenMP/MPI/Pthread/TBB + Perfect Load Distribution | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | |
| No Scalar Integer | Potential Speedup | 1.02 | 1.02 | 1.08 | 1.08 | 1.03 | 1.04 |
| Nb Loops to get 80% | 5 | 4 | 3 | 3 | 6 | 3 | |
| FP Vectorised | Potential Speedup | 1.71 | 1.71 | 1.61 | 1.49 | 1.78 | 1.65 |
| Nb Loops to get 80% | 5 | 5 | 5 | 4 | 5 | 4 | |
| Fully Vectorised | Potential Speedup | 6.10 | 5.89 | 5.50 | 4.39 | 6.22 | 4.86 |
| Nb Loops to get 80% | 8 | 8 | 8 | 7 | 8 | 6 | |
| Only FP Arithmetic | Potential Speedup | 1.02 | 1.02 | 1.11 | 1.11 | 1.05 | 1.06 |
| Nb Loops to get 80% | 5 | 5 | 5 | 6 | 6 | 6 | |
| Source Object | Issue |
|---|---|
| ▼attention-gcc-znver5-256 | |
| ▼random.tcc | |
| ○ | -funroll-loops is missing. |
| ▼attention_v2.cpp | |
| ○ | -funroll-loops is missing. |
| r0 | r1 | r2 | r3 | r4 | r5 | |
|---|---|---|---|---|---|---|
| Experiment Name | ||||||
| Application | ./attention-gcc-znver5-256 | ./attention-gcc-znver5-512 | ./attention-clang-znver5-256 | ./attention-clang-znver5-512 | ./attention-aocc-znver5-256 | ./attention-aocc-znver5-512 |
| Timestamp | 2026-06-22 16:25:56 | 2026-06-22 16:26:23 | 2026-06-22 18:08:29 | 2026-06-22 18:09:10 | 2026-06-22 16:31:51 | 2026-06-22 16:31:07 |
| Experiment Type | Sequential | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Machine | gmz12.benchmarkcenter.megware.com | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Architecture | x86_64 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Micro Architecture | ZEN_V5 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Model Name | AMD EPYC 9655 96-Core Processor | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Cache Size | 1024 KB | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Number of Cores | 96 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Maximal Frequency | 4.51 GHz | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| OS Version | Linux 5.14.0-611.54.6.el9_7.x86_64 #1 SMP PREEMPT_DYNAMIC Fri May 15 04:23:18 EDT 2026 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Architecture used during static analysis | x86_64 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Micro Architecture used during static analysis | ZEN_V5 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Compilation Options | attention-gcc-znver5-256: GNU C++17 15.1.0 -march=znver5 -mmmx -mpopcnt -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -mavx -mavx2 -msse4a -mno-fma4 -mno-xop -mfma -mavx512f -mbmi -mbmi2 -maes -mpclmul -mavx512vl -mavx512bw -mavx512dq -mavx512cd -mavx512vbmi -mavx512ifma -mavx512vpopcntdq -mavx512vbmi2 -mgfni -mvpclmulqdq -mavx512vnni -mavx512bitalg -mavx512bf16 -mavx512vp2intersect -mno-3dnow -madx -mabm -mno-cldemote -mclflushopt -mclwb -mclzero -mcx16 -mno-enqcmd -mf16c -mfsgsbase -mfxsr -mno-hle -msahf -mno-lwp -mlzcnt -mmovbe -mmovdir64b -mmovdiri -mmwaitx -mno-pconfig -mpku -mprfchw -mno-ptwrite -mrdpid -mrdrnd -mrdseed -mno-rtm -mno-serialize -mno-sgx -msha -mshstk -mno-tbm -mno-tsxldtrk -mvaes -mno-waitpkg -mwbnoinvd -mxsave -mxsavec -mxsaveopt -mxsaves -mno-amx-tile -mno-amx-int8 -mno-amx-bf16 -mno-uintr -mno-hreset -mno-kl -mno-widekl -mavxvnni -mno-avx512fp16 -mno-avxifma -mno-avxvnniint8 -mno-avxneconvert -mno-cmpccxadd -mno-amx-fp16 -mno-prefetchi -mno-raoint -mno-amx-complex -mno-avxvnniint16 -mno-sm3 -mno-sha512 -mno-sm4 -mno-apxf -mno-usermsr -mno-avx10.2 -mno-amx-avx512 -mno-amx-tf32 -mno-amx-transpose -mno-amx-fp8 -mno-movrs -mno-amx-movrs --param=l1-cache-size=48 --param=l1-cache-line-size=64 --param=l2-cache-size=1024 -mtune=znver5 -mprefer-vector-width=256 -g -O3 -fno-omit-frame-pointer -fno-math-errno -ffinite-math-only -fassociative-math -fno-signed-zeros | attention-gcc-znver5-512: GNU C++17 15.1.0 -march=znver5 -mmmx -mpopcnt -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -mavx -mavx2 -msse4a -mno-fma4 -mno-xop -mfma -mavx512f -mbmi -mbmi2 -maes -mpclmul -mavx512vl -mavx512bw -mavx512dq -mavx512cd -mavx512vbmi -mavx512ifma -mavx512vpopcntdq -mavx512vbmi2 -mgfni -mvpclmulqdq -mavx512vnni -mavx512bitalg -mavx512bf16 -mavx512vp2intersect -mno-3dnow -madx -mabm -mno-cldemote -mclflushopt -mclwb -mclzero -mcx16 -mno-enqcmd -mf16c -mfsgsbase -mfxsr -mno-hle -msahf -mno-lwp -mlzcnt -mmovbe -mmovdir64b -mmovdiri -mmwaitx -mno-pconfig -mpku -mprfchw -mno-ptwrite -mrdpid -mrdrnd -mrdseed -mno-rtm -mno-serialize -mno-sgx -msha -mshstk -mno-tbm -mno-tsxldtrk -mvaes -mno-waitpkg -mwbnoinvd -mxsave -mxsavec -mxsaveopt -mxsaves -mno-amx-tile -mno-amx-int8 -mno-amx-bf16 -mno-uintr -mno-hreset -mno-kl -mno-widekl -mavxvnni -mno-avx512fp16 -mno-avxifma -mno-avxvnniint8 -mno-avxneconvert -mno-cmpccxadd -mno-amx-fp16 -mno-prefetchi -mno-raoint -mno-amx-complex -mno-avxvnniint16 -mno-sm3 -mno-sha512 -mno-sm4 -mno-apxf -mno-usermsr -mno-avx10.2 -mno-amx-avx512 -mno-amx-tf32 -mno-amx-transpose -mno-amx-fp8 -mno-movrs -mno-amx-movrs --param=l1-cache-size=48 --param=l1-cache-line-size=64 --param=l2-cache-size=1024 -mtune=znver5 -mprefer-vector-width=512 -g -O3 -fno-omit-frame-pointer -fno-math-errno -ffinite-math-only -fassociative-math -fno-signed-zeros | attention-clang-znver5-256: clang version 21.1.8 /beegfs/hackathon/users/eoseret/spack-install/linux-zen4/llvm-21.1.8-bfvz545rqe5kvs5h24gj6hdamlfpj3u2/bin/clang-21 --gcc-install-dir=/usr/lib/gcc/x86_64-redhat-linux/11 --driver-mode=g++ -O3 -g -fno-omit-frame-pointer -grecord-command-line -march=native -mprefer-vector-width=256 -fapprox-func -fno-math-errno -ffinite-math-only -fassociative-math -fno-signed-zeros attention_v2.cpp -o attention-clang-znver5-256 -dumpdir attention-clang-znver5-256- | attention-clang-znver5-512: clang version 21.1.8 /beegfs/hackathon/users/eoseret/spack-install/linux-zen4/llvm-21.1.8-bfvz545rqe5kvs5h24gj6hdamlfpj3u2/bin/clang-21 --gcc-install-dir=/usr/lib/gcc/x86_64-redhat-linux/11 --driver-mode=g++ -O3 -g -fno-omit-frame-pointer -grecord-command-line -march=native -mprefer-vector-width=512 -fapprox-func -fno-math-errno -ffinite-math-only -fassociative-math -fno-signed-zeros attention_v2.cpp -o attention-clang-znver5-512 -dumpdir attention-clang-znver5-512- | attention-aocc-znver5-256: AMD clang version 17.0.6 (CLANG: AOCC_5.1.0-Build#1994 2025_12_23) /cluster/comp/aocc/5.1.0/bin/clang-17 --driver-mode=g++ -O3 -g -fno-omit-frame-pointer -grecord-command-line -march=native -mprefer-vector-width=256 -fapprox-func -fno-math-errno -ffinite-math-only -fassociative-math -fno-signed-zeros attention_v2.cpp -o attention-aocc-znver5-256 -dumpdir attention-aocc-znver5-256- | attention-aocc-znver5-512: AMD clang version 17.0.6 (CLANG: AOCC_5.1.0-Build#1994 2025_12_23) /cluster/comp/aocc/5.1.0/bin/clang-17 --driver-mode=g++ -O3 -g -fno-omit-frame-pointer -grecord-command-line -march=native -mprefer-vector-width=512 -fapprox-func -fno-math-errno -ffinite-math-only -fassociative-math -fno-signed-zeros attention_v2.cpp -o attention-aocc-znver5-512 -dumpdir attention-aocc-znver5-512- |
| Number of processes observed | 1 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Number of threads observed | 1 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Frequency Driver | amd-pstate-epp | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Frequency Governor | performance | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Huge Pages | always | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Hyperthreading | on | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Number of sockets | 2 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Number of cores per socket | 96 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| MAQAO version | 2026.0.1 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| MAQAO build | 5913ca57b6edfb4b485a73198a6fcad282267733::20260622-042016 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Comments | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |