Loops
kai_matmul_clamp_f32_qsi8d32p4x8_qsi4c32p4x8_16x4_neon_i8mm.c: 131 - 261.56 %
| 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 (%) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2426 | 2.90 | 3.54 | 84.56 | 28.14 | 27.69 | 2092 | 2.90 | 3.97 | 88.53 | 28.14 | 27.69 | 2067 | 2.91 | 3.99 | 88.46 | 28.14 | 27.69 |
| Sum on 1 analyzed binary loop (libggml-cpu.so - 2426) | Sum on 1 analyzed binary loop (libggml-cpu.so - 2092) | Sum on 1 analyzed binary loop (libggml-cpu.so - 2067) | |||||||||||||||
| 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 - 2.97 %
| 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 (%) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 908 | 0.06 | 0.05 | 1.12 | 68.18 | 79.76 | 766 | 0.06 | 0.04 | 0.93 | 80 | 97.59 | 779 | 0.06 | 0.04 | 0.92 | 90 | 98.62 |
| 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 - 779) | |||||||||||||||
| 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 | |||||||||||||
| 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 | |||||||||||||
kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 96 - 1.40 %
| 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 (%) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2389 | 0.05 | 0.02 | 0.43 | 77.23 | 48.22 | 2060 | 0.03 | 0.02 | 0.49 | 69.7 | 48.55 | 2035 | 0.05 | 0.02 | 0.48 | 69.7 | 48.55 |
| Sum on 1 analyzed binary loop (libggml-cpu.so - 2389) | Sum on 1 analyzed binary loop (libggml-cpu.so - 2060) | Sum on 1 analyzed binary loop (libggml-cpu.so - 2035) | |||||||||||||||
| 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 | ||||||||||||
| 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 | Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA | 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 | ||||||||||||
ops.cpp: 4325 - 1.11 %
| 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 (%) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1278 | 0.03 | 0.02 | 0.39 | 94.12 | 95.59 | 1132 | 0.04 | 0.02 | 0.41 | 0 | 13.28 | 1153 | 0.03 | 0.01 | 0.30 | 90.91 | 75.04 |
| Sum on 1 analyzed binary loop (libggml-cpu.so - 1278) | Sum on 1 analyzed binary loop (libggml-cpu.so - 1132) | Sum on 1 analyzed binary loop (libggml-cpu.so - 1153) | |||||||||||||||
| Analysis | Count | Analysis | Count | Analysis | Count | ||||||||||||
| Loop Computation Issues | Loop Computation Issues | Loop Computation Issues | |||||||||||||||
| 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 | Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA | 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 | Presence of constant non-unit stride data access | ||||||||||||||
| Vectorization Roadblocks | Vectorization Roadblocks | Vectorization Roadblocks | |||||||||||||||
| Presence of constant non-unit stride data access | 1 | Presence of constant non-unit stride data access | Presence of constant non-unit stride data access | ||||||||||||||
binary-ops.cpp: 18 - 0.91 %
| 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 (%) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 538 | 0.03 | 0.01 | 0.29 | 0 | 11.84 | 494 | 0.03 | 0.01 | 0.32 | 25 | 50 | 498 | 0.03 | 0.01 | 0.30 | 25 | 50 |
| Sum on 1 analyzed binary loop (libggml-cpu.so - 538) | Sum on 1 analyzed binary loop (libggml-cpu.so - 494) | Sum on 1 analyzed binary loop (libggml-cpu.so - 498) | |||||||||||||||
| Analysis | Count | Analysis | Count | Analysis | Count | ||||||||||||
| Loop Computation Issues | Loop Computation Issues | Loop Computation Issues | |||||||||||||||
| 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 | Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA | 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 | ||||||||||||
binary-ops.cpp: 10 - 0.90 %
| 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 (%) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 433 | 0.03 | 0.01 | 0.32 | 0 | 12.5 | 410 | 0.03 | 0.01 | 0.28 | 25 | 50 | 412 | 0.03 | 0.01 | 0.30 | 25 | 50 |
| Sum on 1 analyzed binary loop (libggml-cpu.so - 433) | Sum on 1 analyzed binary loop (libggml-cpu.so - 410) | Sum on 1 analyzed binary loop (libggml-cpu.so - 412) | |||||||||||||||
| Analysis | Count | Analysis | Count | Analysis | Count | ||||||||||||
| Loop Computation Issues | Loop Computation Issues | Loop Computation Issues | |||||||||||||||
| 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 | Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA | 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 | ||||||||||||
ggml-cpu.c: 3228 - 0.57 %
| 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 | 0.01 | 0.23 | 86.36 | 95.61 | 4 | 0.03 | 0.01 | 0.17 | 93.18 | 94.03 | 0 | 0.03 | 0.01 | 0.17 | 92.11 | 93.09 |
| Sum on 1 analyzed binary loop (libggml-cpu.so - 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. | |||||||||||||||
| 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 constant non-unit stride data access | 1 | ||||||||||||||||
| Vectorization Roadblocks | |||||||||||||||||
| Presence of constant non-unit stride data access | 1 | ||||||||||||||||
quants.c: 2506 - 0.52 %
| 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 (%) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2308 | 0.01 | 0.01 | 0.15 | 50.56 | 33.98 | 1968 | 0.01 | 0.01 | 0.22 | 49.18 | 36.04 | 1941 | 0.01 | 0.01 | 0.16 | 48.65 | 35.94 |
| 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 - 0.19 %
| 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 (%) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1437 | 0.01 | 0.00 | 0.07 | 0 | 12.5 | 799 | 0.01 | 0.00 | 0.04 | 37.5 | 40.63 | 828 | 0.02 | 0.00 | 0.08 | 42.55 | 63.3 |
| 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 - 0.16 %
| 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 (%) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1282 | 0.01 | 0.00 | 0.04 | 100 | 100 | 1131 | 0.01 | 0.00 | 0.06 | 100 | 100 | 1156 | 0.01 | 0.00 | 0.04 | 100 | 100 |
| 1489 | 0.01 | 0.00 | 0.02 | 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 | ||||||||||||