Loops
kai_matmul_clamp_f32_qsi8d32p4x8_qsi4c32p4x8_16x4_neon_i8mm.c: 131 - 223.69 %
| Run orig_default | Run gcc_default | Run gcc_5 | |||||||||||||||
| 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 (%) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2423 | 0.01 | 0.00 | 0.14 | 32.79 | 30.39 | 2092 | 0.41 | 1.51 | 82.07 | 28.14 | 27.69 | 1960 | 0.00 | 0.00 | 0.13 | 32.79 | 30.39 |
| 2426 | 0.40 | 0.90 | 60.68 | 28.14 | 27.69 | 2089 | 0.00 | 0.00 | 0.02 | 32.79 | 30.39 | 1963 | 0.41 | 1.42 | 80.65 | 28.14 | 27.69 |
| Sum on 2 analyzed binary loops (libggml-cpu.so - 2423, libggml-cpu.so - 2426) | Sum on 1 analyzed binary loop (libggml-cpu.so - 2092) | Sum on 1 analyzed binary loop (libggml-cpu.so - 1963) | |||||||||||||||
| 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 - 2.56 %
| Run orig_default | Run gcc_default | Run gcc_5 | |||||||||||||||
| 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 (%) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 908 | 0.01 | 0.01 | 0.82 | 68.18 | 79.76 | 766 | 0.01 | 0.01 | 0.81 | 80 | 97.59 | 752 | 0.01 | 0.02 | 0.93 | 88.89 | 97.32 |
| Sum on 1 analyzed binary loop (libggml-cpu.so - 908) | Sum on 1 analyzed binary loop (libggml-cpu.so - 766) | Sum on 1 analyzed binary loop (libggml-cpu.so - 752) | |||||||||||||||
| Analysis | Count | Analysis | Count | Analysis | Count | ||||||||||||
| Loop Computation Issues | Loop Computation Issues | Loop Computation Issues | |||||||||||||||
| Presence of expensive FP instructions | 1 | Presence of expensive FP instructions | 1 | Presence of expensive FP instructions | 1 | ||||||||||||
| 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 | ||||||||||||
kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 96 - 1.09 %
| Run orig_default | Run gcc_default | Run gcc_5 | |||||||||||||||
| 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 (%) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2389 | 0.01 | 0.01 | 0.35 | 77.23 | 48.22 | 2060 | 0.01 | 0.01 | 0.42 | 69.7 | 48.55 | 1933 | 0.01 | 0.01 | 0.32 | 69.7 | 48.55 |
| Sum on 1 analyzed binary loop (libggml-cpu.so - 2389) | Sum on 1 analyzed binary loop (libggml-cpu.so - 2060) | No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count. | |||||||||||||||
| Analysis | Count | Analysis | Count | Analysis | Count | ||||||||||||
| Loop Computation Issues | Loop Computation Issues | ||||||||||||||||
| Presence of expensive FP instructions | 1 | Presence of expensive FP instructions | 1 | ||||||||||||||
| Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA | 1 | Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA | 1 | ||||||||||||||
| 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 | ||||||||||||||
binary-ops.cpp: 10 - 0.82 %
| Run orig_default | Run gcc_default | Run gcc_5 | |||||||||||||||
| 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 (%) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 433 | 0.01 | 0.00 | 0.12 | 0 | 12.5 | 410 | 0.01 | 0.01 | 0.39 | 25 | 50 | 437 | 0.01 | 0.01 | 0.32 | 0 | 9.38 |
| 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 | ||||||||||||
quants.c: 2506 - 0.77 %
| Run orig_default | Run gcc_default | Run gcc_5 | |||||||||||||||
| 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 (%) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2308 | 0.00 | 0.00 | 0.01 | 50.56 | 33.98 | 1968 | 0.00 | 0.01 | 0.40 | 49.18 | 36.04 | 1841 | 0.00 | 0.01 | 0.35 | 48.65 | 35.94 |
| 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 - 1968) | 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 | |||||||||||||||||
| Presence of constant non-unit stride data access | 1 | ||||||||||||||||
| Vectorization Roadblocks | |||||||||||||||||
| Presence of constant non-unit stride data access | 1 | ||||||||||||||||
ggml-cpu.c: 3228 - 0.69 %
| Run orig_default | Run gcc_default | Run gcc_5 | |||||||||||||||
| 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 | 0.01 | 0.00 | 0.06 | 86.36 | 95.61 | 4 | 0.01 | 0.00 | 0.15 | 93.18 | 94.03 | 1 | 0.01 | 0.01 | 0.47 | 0 | 9.23 |
| 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 - 1) | |||||||||||||||
| Analysis | Count | Analysis | Count | Analysis | Count | ||||||||||||
| Loop Computation Issues | |||||||||||||||||
| Presence of a large number of scalar integer instructions | 1 | ||||||||||||||||
ops.cpp: 4325 - 0.57 %
| Run orig_default | Run gcc_default | Run gcc_5 | |||||||||||||||
| 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 (%) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1278 | 0.01 | 0.00 | 0.12 | 94.12 | 95.59 | 1132 | 0.01 | 0.00 | 0.25 | 0 | 13.28 | 1091 | 0.01 | 0.00 | 0.20 | 0 | 13.28 |
| 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 | ||||||||||||
vec.h: 411 - 0.54 %
| Run orig_default | Run gcc_default | Run gcc_5 | |||||||||||||||
| 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 (%) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1753 | 0.01 | 0.00 | 0.09 | 100 | 100 | 1470 | 0.00 | 0.00 | 0.24 | 100 | 100 | 1405 | 0.01 | 0.00 | 0.22 | 100 | 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 | ||||||||||||
binary-ops.cpp: 18 - 0.48 %
| Run orig_default | Run gcc_default | Run gcc_5 | |||||||||||||||
| 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 (%) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 538 | 0.01 | 0.00 | 0.13 | 0 | 11.84 | 494 | 0.00 | 0.00 | 0.13 | 25 | 50 | 507 | 0.00 | 0.00 | 0.22 | 0 | 9.38 |
| 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 | ||||||||||||
vec.cpp: 231 - 0.31 %
| Run orig_default | Run gcc_default | Run gcc_5 | |||||||||||||||
| 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 (%) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 901 | 0.01 | 0.00 | 0.10 | 96 | 97 | 763 | 0.00 | 0.00 | 0.08 | 100 | 100 | 749 | 0.01 | 0.00 | 0.12 | 100 | 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 | ||||||||||||
vec.h: 646 - 0.08 %
| Run orig_default | Run gcc_default | Run gcc_5 | |||||||||||||||
| 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 (%) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1756 | 0.00 | 0.00 | 0.01 | 100 | 100 | 1466 | 0.00 | 0.00 | 0.02 | 100 | 100 | 1094 | 0.00 | 0.00 | 0.02 | 100 | 100 |
| 1131 | 0.00 | 0.00 | 0.03 | 100 | 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 | ||||||||||||
basic_string.h: 194 - 0.05 %
| Run orig_default | Run gcc_default | Run gcc_5 | |||||||||||||||
| 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 (%) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2483 | 0.01 | 0.00 | 0.01 | 0 | 23.43 | 3728 | 0.00 | 0.00 | 0.02 | 0 | 25 | 3790 | 0.01 | 0.00 | 0.02 | 0 | 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 | ||||||||||||