| Run orig_default | Run icx_default | Run aocc_4 | Run icx_3 |
| Loop Source Regions | - /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 138-138
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 818-846
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1038-1038
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1044-1044
| Loop Source Regions | - /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 138-138
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 818-821
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 827-846
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 966-966
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1038-1038
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1044-1044
| Loop Source Regions | - /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 138-138
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 818-846
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1038-1038
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1044-1044
| Loop Source Regions | |
| ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) | ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) | ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) | ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) |
|---|
| 2365 | 0.08 | 0.05 | 0.43 | 0 | 0 | 2688 | 0.08 | 0.06 | 0.49 | 0 | 0 | 2224 | 0.07 | 0.05 | 0.43 | 0 | 0 | |
| | | |
| Sum on 1 analyzed binary loop (libggml-cpu.so - 2365) | Sum on 1 analyzed binary loop (libggml-cpu.so - 2688) | Sum on 1 analyzed binary loop (libggml-cpu.so - 2224) | No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count. |
| Analysis | Count | Analysis | Count | Analysis | Count | Analysis | Count |
|---|
| Run orig_default | Run icx_default | Run aocc_4 | Run icx_3 |
| Loop Source Regions | | Loop Source Regions | | Loop Source Regions | | Loop Source Regions | - /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 1066-1073
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130
|
| ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) | ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) | ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) | ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) |
|---|
| | | 4223 | 0.15 | 0.13 | 1.14 | 88.89 | 20.14 |
| | | |
| No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count. | No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count. | No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count. | Sum on 1 analyzed binary loop (libggml-cpu.so - 4223) |
| Analysis | Count | Analysis | Count | Analysis | Count | Analysis | Count |
|---|
| | | | | | Loop Computation Issues | |
| | | | | | Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA | 1 |
| | | | | | Data Access Issues | |
| | | | | | Presence of indirect access | 1 |
| | | | | | Presence of special instructions executing on a single port | 1 |
| | | | | | Vectorization Roadblocks | |
| | | | | | Presence of indirect access | 1 |
| | | | | | Inefficient Vectorization | |
| | | | | | Presence of special instructions executing on a single port | 1 |
| Run orig_default | Run icx_default | Run aocc_4 | Run icx_3 |
| Loop Source Regions | | Loop Source Regions | | Loop Source Regions | | Loop Source Regions | |
| ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) | ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) | ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) | ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) |
|---|
| 2640 | 0.00 | 0.00 | 0.00 | 0 | 0 | 2294 | 0.00 | 0.00 | 0.00 | 0 | 0 | 2713 | 0.01 | 0.00 | 0.00 | 0 | 0 | 4335 | 0.00 | 0.00 | 0.00 | 0 | 0 |
| 2842 | 0.00 | 0.00 | 0.00 | 0 | 0 | 1023 | 0.00 | 0.00 | 0.00 | 0 | 0 | 2710 | 0.01 | 0.00 | 0.00 | 0 | 0 | 4515 | 0.00 | 0.00 | 0.00 | 0 | 0 |
| 2638 | 0.00 | 0.00 | 0.00 | 0 | 0 | 2395 | 0.01 | 0.00 | 0.00 | 0 | 0 | 314 | 0.02 | 0.00 | 0.00 | 0 | 0 | 4520 | 0.00 | 0.00 | 0.00 | 0 | 0 |
| 2741 | 0.03 | 0.00 | 0.00 | 0 | 0 | 2155 | 0.00 | 0.00 | 0.00 | 0 | 0 | 1611 | 0.01 | 0.00 | 0.01 | 0 | 0 | 4518 | 0.03 | 0.00 | 0.00 | 0 | 0 |
| 317 | 0.04 | 0.00 | 0.00 | 0 | 0 | 2289 | 0.01 | 0.00 | 0.00 | 0 | 0 | 1148 | 0.02 | 0.00 | 0.03 | 0 | 0 | 4526 | 0.00 | 0.00 | 0.00 | 0 | 0 |
| 766 | 0.02 | 0.00 | 0.03 | 0 | 0 | 2298 | 0.00 | 0.00 | 0.00 | 0 | 0 | 1386 | 0.02 | 0.00 | 0.04 | 0 | 0 | 4540 | 0.00 | 0.00 | 0.00 | 0 | 0 |
| 99 | 0.01 | 0.00 | 0.00 | 0 | 0 | 372 | 0.04 | 0.00 | 0.00 | 0 | 0 | 386 | 0.02 | 0.00 | 0.03 | 0 | 0 | 1440 | 0.00 | 0.00 | 0.00 | 0 | 0 |
| 485 | 0.01 | 0.00 | 0.01 | 0 | 0 | 1948 | 0.01 | 0.00 | 0.00 | 0 | 0 | 1380 | 0.01 | 0.00 | 0.00 | 0 | 0 | 748 | 0.03 | 0.00 | 0.00 | 0 | 0 |
| 90 | 0.01 | 0.00 | 0.00 | 0 | 0 | 444 | 0.02 | 0.00 | 0.02 | 0 | 0 | 738 | 0.02 | 0.00 | 0.03 | 0 | 0 | 731 | 0.01 | 0.00 | 0.00 | 0 | 0 |
| 2528 | 0.01 | 0.00 | 0.01 | 0 | 0 | 114 | 0.00 | 0.00 | 0.00 | 0 | 0 | 462 | 0.02 | 0.00 | 0.02 | 0 | 0 | 1023 | 0.01 | 0.00 | 0.01 | 0 | 0 |
| 399 | 0.01 | 0.00 | 0.02 | 0 | 0 | 866 | 0.01 | 0.00 | 0.01 | 0 | 0 | 92 | 0.01 | 0.00 | 0.00 | 0 | 0 | 759 | 0.02 | 0.00 | 0.02 | 0 | 0 |
| 1710 | 0.01 | 0.00 | 0.01 | 0 | 0 | 124 | 0.00 | 0.00 | 0.00 | 0 | 0 | 732 | 0.01 | 0.00 | 0.01 | 0 | 0 | 115 | 0.01 | 0.00 | 0.00 | 0 | 0 |
| 1463 | 0.01 | 0.00 | 0.02 | 0 | 0 | 873 | 0.01 | 0.00 | 0.03 | 0 | 0 | 4 | 0.00 | 0.00 | 0.00 | 0 | 0 | 3825 | 0.01 | 0.00 | 0.00 | 0 | 0 |
| 1457 | 0.01 | 0.00 | 0.00 | 0 | 0 | 2099 | 0.01 | 0.00 | 0.00 | 0 | 0 | 350 | 0.00 | 0.00 | 0.00 | 0 | 0 | 3812 | 0.01 | 0.00 | 0.00 | 0 | 0 |
| 1724 | 0.01 | 0.00 | 0.02 | 0 | 0 | 6 | 0.01 | 0.00 | 0.01 | 0 | 0 | 1604 | 0.00 | 0.00 | 0.00 | 0 | 0 | 126 | 0.01 | 0.00 | 0.00 | 0 | 0 |
| 1196 | 0.03 | 0.00 | 0.03 | 0 | 0 | 1418 | 0.01 | 0.00 | 0.01 | 0 | 0 | 1149 | 0.00 | 0.00 | 0.00 | 0 | 0 | 2710 | 0.02 | 0.00 | 0.02 | 0 | 0 |
| 1197 | 0.01 | 0.00 | 0.00 | 0 | 0 | 1707 | 0.01 | 0.00 | 0.00 | 0 | 0 | 1622 | 0.02 | 0.00 | 0.03 | 0 | 0 | 127 | 0.00 | 0.00 | 0.00 | 0 | 0 |
| 2374 | 0.01 | 0.00 | 0.04 | 0 | 0 | 2702 | 0.01 | 0.00 | 0.04 | 0 | 0 | 1627 | 0.01 | 0.00 | 0.00 | 0 | 0 | 144 | 0.00 | 0.00 | 0.00 | 0 | 0 |
| 1375 | 0.01 | 0.00 | 0.00 | 0 | 0 | 558 | 0.01 | 0.00 | 0.01 | 0 | 0 | 2387 | 0.01 | 0.00 | 0.00 | 0 | 0 | 3808 | 0.01 | 0.00 | 0.00 | 0 | 0 |
| 1731 | 0.01 | 0.00 | 0.00 | 0 | 0 | 2918 | 0.01 | 0.00 | 0.00 | 0 | 0 | 2233 | 0.01 | 0.01 | 0.04 | 0 | 0 | 3142 | 0.01 | 0.00 | 0.02 | 0 | 0 |
| 5 | 0.01 | 0.00 | 0.00 | 0 | 0 | 2111 | 0.00 | 0.00 | 0.00 | 0 | 0 | | 3 | 0.01 | 0.00 | 0.01 | 0 | 0 |
| 762 | 0.01 | 0.00 | 0.01 | 0 | 0 | 1734 | 0.02 | 0.00 | 0.02 | 0 | 0 | | 1768 | 0.02 | 0.00 | 0.02 | 0 | 0 |
| 2109 | 0.02 | 0.00 | 0.02 | 0 | 0 | | 2708 | 0.01 | 0.00 | 0.01 | 0 | 0 |
| 1412 | 0.01 | 0.00 | 0.00 | 0 | 0 | | 3118 | 0.01 | 0.00 | 0.01 | 0 | 0 |
| 1605 | 0.00 | 0.00 | 0.00 | 0 | 0 | | |
| | | |
| No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count. | No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count. | No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count. | No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count. |
| Analysis | Count | Analysis | Count | Analysis | Count | Analysis | Count |
|---|
| Run orig_default | Run icx_default | Run aocc_4 | Run icx_3 |
| Loop Source Regions | | Loop Source Regions | | Loop Source Regions | | Loop Source Regions | - /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-389
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 399-404
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 508-509
|
| ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) | ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) | ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) | ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) |
|---|
| | | 3822 | 0.07 | 0.04 | 0.31 | 85.05 | 20.79 |
| | | |
| No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count. | No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count. | No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count. | Sum on 1 analyzed binary loop (libggml-cpu.so - 3822) |
| Analysis | Count | Analysis | Count | Analysis | Count | Analysis | Count |
|---|
| | | | | | Loop Computation Issues | |
| | | | | | Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA | 1 |
| | | | | | Data Access Issues | |
| | | | | | Presence of indirect access | 1 |
| | | | | | Presence of special instructions executing on a single port | 1 |
| | | | | | Vectorization Roadblocks | |
| | | | | | Presence of indirect access | 1 |
| | | | | | Inefficient Vectorization | |
| | | | | | Presence of special instructions executing on a single port | 1 |
| Run orig_default | Run icx_default | Run aocc_4 | Run icx_3 |
| Loop Source Regions | | Loop Source Regions | | Loop Source Regions | | Loop Source Regions | - /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 331-332
|
| ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) | ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) | ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) | ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) |
|---|
| | | 1754 | 0.03 | 0.02 | 0.14 | 5.88 | 8.82 |
| | | |
| No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count. | No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count. | No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count. | Sum on 1 analyzed binary loop (libggml-cpu.so - 1754) |
| Analysis | Count | Analysis | Count | Analysis | Count | Analysis | Count |
|---|
| | | | | | Loop Computation Issues | |
| | | | | | Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA | 1 |
| | | | | | Data Access Issues | |
| | | | | | Presence of indirect access | 1 |
| | | | | | Vectorization Roadblocks | |
| | | | | | Presence of indirect access | 1 |
