Loops
kai_matmul_clamp_f32_qsi8d32p4x8_qsi4c32p4x8_16x4_neon_i8mm.c: 131 - 122.58 %
| Run orig_default | Run gcc_default | Run gcc_2 | |||||||||||||||
| 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 (%) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2582 | 0.03 | 0.02 | 0.56 | 28.14 | 55.37 | 2075 | 0.03 | 0.02 | 0.56 | 28.14 | 55.37 | 2076 | 1.24 | 1.50 | 40.75 | 32.79 | 60.77 |
| 2579 | 1.24 | 1.35 | 39.40 | 32.79 | 60.77 | 2072 | 1.19 | 1.57 | 40.78 | 32.79 | 60.77 | 2079 | 0.03 | 0.02 | 0.54 | 28.14 | 55.37 |
| Sum on 2 analyzed binary loops (libggml-cpu.so - 2582, libggml-cpu.so - 2579) | Sum on 2 analyzed binary loops (libggml-cpu.so - 2075, libggml-cpu.so - 2072) | Sum on 2 analyzed binary loops (libggml-cpu.so - 2076, libggml-cpu.so - 2079) | |||||||||||||||
| Analysis | Count | Analysis | Count | Analysis | Count | ||||||||||||
| Data Access Issues | Data Access Issues | Data Access Issues | |||||||||||||||
| Presence of constant non-unit stride data access | 1 | Presence of constant non-unit stride data access | 1 | Presence of constant non-unit stride data access | 1 | ||||||||||||
| Vectorization Roadblocks | Vectorization Roadblocks | Vectorization Roadblocks | |||||||||||||||
| Presence of constant non-unit stride data access | 1 | Presence of constant non-unit stride data access | 1 | Presence of constant non-unit stride data access | 1 | ||||||||||||
quants.c: 2506 - 14.71 %
| Run orig_default | Run gcc_default | Run gcc_2 | |||||||||||||||
| 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 (%) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2463 | 0.21 | 0.19 | 5.66 | 50 | 65.41 | 1951 | 0.16 | 0.18 | 4.66 | 48.91 | 69.52 | 1952 | 0.16 | 0.16 | 4.39 | 48.9 | 67.65 |
| Sum on 1 analyzed binary loop (libggml-cpu.so - 2463) | Sum on 1 analyzed binary loop (libggml-cpu.so - 1951) | Sum on 1 analyzed binary loop (libggml-cpu.so - 1952) | |||||||||||||||
| Analysis | Count | Analysis | Count | Analysis | Count | ||||||||||||
| Data Access Issues | Data Access Issues | Data Access Issues | |||||||||||||||
| Presence of constant non-unit stride data access | 1 | Presence of constant non-unit stride data access | 1 | Presence of constant non-unit stride data access | 1 | ||||||||||||
| Vectorization Roadblocks | Vectorization Roadblocks | Vectorization Roadblocks | |||||||||||||||
| Presence of constant non-unit stride data access | 1 | Presence of constant non-unit stride data access | 1 | Presence of constant non-unit stride data access | 1 | ||||||||||||
vec.cpp: 231 - 0.63 %
| Run orig_default | Run gcc_default | Run gcc_2 | |||||||||||||||
| 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 (%) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1007 | 0.02 | 0.01 | 0.15 | 100 | 100 | 764 | 0.04 | 0.01 | 0.26 | 100 | 100 | 788 | 0.02 | 0.01 | 0.22 | 100 | 100 |
| Sum on 1 analyzed binary loop (libggml-cpu.so - 1007) | Sum on 1 analyzed binary loop (libggml-cpu.so - 764) | Sum on 1 analyzed binary loop (libggml-cpu.so - 788) | |||||||||||||||
| Analysis | Count | Analysis | Count | Analysis | Count | ||||||||||||
| Data Access Issues | Data Access Issues | Data Access Issues | |||||||||||||||
| Presence of constant non-unit stride data access | 1 | Presence of constant non-unit stride data access | 1 | Presence of constant non-unit stride data access | 1 | ||||||||||||
| Vectorization Roadblocks | Vectorization Roadblocks | Vectorization Roadblocks | |||||||||||||||
| Presence of constant non-unit stride data access | 1 | Presence of constant non-unit stride data access | 1 | Presence of constant non-unit stride data access | 1 | ||||||||||||
vec.cpp: 385 - 0.61 %
| Run orig_default | Run gcc_default | Run gcc_2 | |||||||||||||||
| 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 (%) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1015 | 0.30 | 0.01 | 0.35 | 68.18 | 82.24 | 767 | 0.09 | 0.00 | 0.12 | 80 | 97.68 | 790 | 0.11 | 0.00 | 0.13 | 90 | 98.67 |
| Sum on 1 analyzed binary loop (libggml-cpu.so - 1015) | 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 - 790) | |||||||||||||||
| Analysis | Count | Analysis | Count | Analysis | Count | ||||||||||||
| Loop Computation Issues | Loop Computation Issues | ||||||||||||||||
| Presence of expensive FP instructions | 1 | Presence of expensive FP instructions | 1 | ||||||||||||||
vec.h: 411 - 0.44 %
| Run orig_default | Run gcc_default | Run gcc_2 | |||||||||||||||
| 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 (%) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1900 | 0.03 | 0.01 | 0.17 | 100 | 100 | 1454 | 0.02 | 0.01 | 0.16 | 100 | 100 | 1501 | 0.02 | 0.00 | 0.11 | 100 | 100 |
| Sum on 1 analyzed binary loop (libggml-cpu.so - 1900) | Sum on 1 analyzed binary loop (libggml-cpu.so - 1454) | No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count. | |||||||||||||||
| Analysis | Count | Analysis | Count | Analysis | Count | ||||||||||||
| Data Access Issues | Data Access Issues | ||||||||||||||||
| Presence of constant non-unit stride data access | 1 | Presence of constant non-unit stride data access | 1 | ||||||||||||||
| Vectorization Roadblocks | Vectorization Roadblocks | ||||||||||||||||
| Presence of constant non-unit stride data access | 1 | Presence of constant non-unit stride data access | 1 | ||||||||||||||
ggml-cpu.c: 3228 - 0.21 %
| Run orig_default | Run gcc_default | Run gcc_2 | |||||||||||||||
| 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 (%) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 0.02 | 0.00 | 0.06 | 92.5 | 98.75 | 6 | 0.03 | 0.00 | 0.12 | 0 | 18.47 | 1 | 0.01 | 0.00 | 0.03 | 72.6 | 83.56 |
| 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 | ||||||||||||
kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 96 - 0.19 %
| Run orig_default | Run gcc_default | Run gcc_2 | |||||||||||||||
| 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 (%) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2545 | 0.11 | 0.00 | 0.04 | 77.23 | 96.44 | 2043 | 0.20 | 0.00 | 0.08 | 69.7 | 97.1 | 2046 | 0.17 | 0.00 | 0.07 | 69.7 | 97.1 |
| 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 | ||||||||||||
ggml-cpu.c: 1125 - 0.11 %
| Run orig_default | Run gcc_default | Run gcc_2 | |||||||||||||||
| 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 (%) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 77 | 0.01 | 0.00 | 0.02 | 0 | 46.79 | 51 | 0.01 | 0.00 | 0.03 | 0 | 48.72 | 55 | 0.01 | 0.00 | 0.06 | 0 | 47.98 |
| 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 | ||||||||||||
binary-ops.cpp: 18 - 0.09 %
| Run orig_default | Run gcc_default | Run gcc_2 | |||||||||||||||
| 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 (%) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 551 | 0.03 | 0.00 | 0.04 | 0 | 23.68 | 495 | 0.03 | 0.00 | 0.03 | 25 | 100 | 501 | 0.02 | 0.00 | 0.02 | 25 | 100 |
| 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 | ||||||||||||
ops.cpp: 6446 - 0.07 %
| Run orig_default | Run gcc_default | Run gcc_2 | |||||||||||||||
| 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 (%) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1570 | 0.01 | 0.00 | 0.04 | 0 | 25 | 800 | 0.01 | 0.00 | 0.02 | 37.5 | 81.25 | 839 | 0.01 | 0.00 | 0.02 | 37.5 | 81.25 |
| 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 | ||||||||||||