counted-float 0.9.5__tar.gz → 0.9.6__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {counted_float-0.9.5 → counted_float-0.9.6}/PKG-INFO +80 -59
- {counted_float-0.9.5 → counted_float-0.9.6}/README.md +79 -58
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/__init__.py +1 -11
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/_core/_cli.py +3 -2
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/_core/benchmarking/__init__.py +2 -2
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/_core/benchmarking/flops/__init__.py +1 -1
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/_core/benchmarking/flops/_flops_benchmark_suite.py +3 -3
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/_core/benchmarking/micro/_micro_benchmark.py +8 -4
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/_core/counting/_builtin_data.py +4 -6
- counted_float-0.9.6/counted_float/_core/models/__init__.py +9 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/_core/models/_flops_benchmark_meta_data.py +6 -4
- counted_float-0.9.5/counted_float/_core/models/_flops_benchmark_result_v2.py → counted_float-0.9.6/counted_float/_core/models/_flops_benchmark_result.py +1 -1
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/_core/models/_instruction_latencies.py +36 -47
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/_core/utils/__init__.py +1 -0
- counted_float-0.9.6/counted_float/_core/utils/_cpu_freq.py +46 -0
- counted_float-0.9.6/counted_float/_core/utils/_latency.py +3 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/_core/utils/_missing_data.py +5 -1
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/benchmarking/__init__.py +2 -2
- counted_float-0.9.6/counted_float/data/arm/v8_x/benchmarks/apple_m3_max_mbp16.json +196 -0
- counted_float-0.9.6/counted_float/data/arm/v8_x/benchmarks/apple_m3_mba15.json +196 -0
- counted_float-0.9.6/counted_float/data/arm/v8_x/benchmarks/ec2_m6g_xlarge_graviton_2_neoverse_n1.json +196 -0
- counted_float-0.9.6/counted_float/data/arm/v8_x/benchmarks/ec2_m7g_xlarge_graviton_3_neoverse_v1.json +196 -0
- counted_float-0.9.6/counted_float/data/arm/v8_x/benchmarks/gh_apple_m1.json +196 -0
- counted_float-0.9.6/counted_float/data/arm/v9_0/benchmarks/ec2_m8g_xlarge_graviton_4_neoverse_v2.json +196 -0
- counted_float-0.9.6/counted_float/data/arm/v9_0/benchmarks/gh_azure_cobalt_100_neoverse_n2.json +196 -0
- counted_float-0.9.6/counted_float/data/arm/v9_2/benchmarks/apple_m4_pro_mbp16.json +196 -0
- counted_float-0.9.6/counted_float/data/x86/amd/2017_zen1/benchmark_ryzen_1700x.json +196 -0
- counted_float-0.9.6/counted_float/data/x86/amd/2020_zen3/benchmark_gh_amd_epyc_7763_linux.json +196 -0
- counted_float-0.9.6/counted_float/data/x86/amd/2020_zen3/benchmark_gh_amd_epyc_7763_windows.json +196 -0
- counted_float-0.9.6/counted_float/data/x86/amd/2022_zen4/benchmark_ec2_m7a_xlarge_zen4.json +196 -0
- counted_float-0.9.6/counted_float/data/x86/amd/2024_zen5/benchmark_ec2_m8a_xlarge_zen5.json +196 -0
- counted_float-0.9.6/counted_float/data/x86/intel/2017_coffee_lake_gen_8/benchmark_gh_intel_i7_8550U_windows.json +196 -0
- counted_float-0.9.6/counted_float/data/x86/intel/2017_coffee_lake_gen_8/benchmark_gh_intel_i7_8700B_macos.json +196 -0
- counted_float-0.9.6/counted_float/data/x86/intel/2019_sunny_cove_gen_10/benchmark_ec2_m6i_xlarge_ice_lake.json +196 -0
- counted_float-0.9.6/counted_float/data/x86/intel/2021_golden_cove_gen_12/benchmark_ec2_m7i_xlarge_sapphire_rapids.json +196 -0
- counted_float-0.9.6/counted_float/data/x86/intel/2022_raptor_cove_gen_13_14/benchmark_ec2_i7i_xlarge_emerald_rapids.json +196 -0
- counted_float-0.9.6/counted_float/data/x86/intel/2023_redwood_cove_ultra_1/benchmark_ec2_m8i_xlarge_granite_rapids.json +196 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/pyproject.toml +1 -1
- counted_float-0.9.5/counted_float/_core/models/__init__.py +0 -18
- counted_float-0.9.5/counted_float/_core/models/_flops_benchmark_result_v1.py +0 -42
- counted_float-0.9.5/counted_float/_core/utils/_latency.py +0 -3
- counted_float-0.9.5/counted_float/data/arm/v8_x/benchmarks/m3_max_macbook_pro_16.json +0 -106
- counted_float-0.9.5/counted_float/data/arm/v8_x/benchmarks/m3_max_macbook_pro_16_v2.json +0 -196
- counted_float-0.9.5/counted_float/data/x86/amd/2017_zen1/benchmark_ryzen_1700x.json +0 -106
- counted_float-0.9.5/counted_float/data/x86/intel/2021_golden_cove_gen_12/benchmark_core_i7_1265u.json +0 -106
- {counted_float-0.9.5 → counted_float-0.9.6}/.gitignore +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/LICENSE +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/_core/__init__.py +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/_core/benchmarking/flops/_array_generator.py +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/_core/benchmarking/flops/_flops_micro_benchmark.py +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/_core/benchmarking/micro/__init__.py +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/_core/compatibility/__init__.py +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/_core/compatibility/_numba.py +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/_core/counting/__init__.py +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/_core/counting/_context_managers.py +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/_core/counting/_counted_float.py +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/_core/counting/_global_counter.py +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/_core/counting/config/__init__.py +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/_core/counting/config/_config.py +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/_core/counting/config/_defaults.py +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/_core/models/_base.py +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/_core/models/_flop_counts.py +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/_core/models/_flop_type.py +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/_core/models/_flop_weights.py +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/_core/models/_flops_benchmark_type.py +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/_core/models/_micro_benchmark_result.py +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/_core/utils/_formatting.py +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/_core/utils/_geo_mean.py +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/_core/utils/_timer.py +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/config/__init__.py +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/data/arm/v8_x/specs/arm_v8_cortex_a76.json +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/data/arm/v8_x/specs/arm_v9_cortex_x1.json +0 -0
- /counted_float-0.9.5/counted_float/data/arm/v8_x/specs/arm_v9_cortex_n1.json → /counted_float-0.9.6/counted_float/data/arm/v8_x/specs/arm_v9_neoverse_n1.json +0 -0
- /counted_float-0.9.5/counted_float/data/arm/v8_x/specs/arm_v9_cortex_v1.json → /counted_float-0.9.6/counted_float/data/arm/v8_x/specs/arm_v9_neoverse_v1.json +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/data/arm/v9_0/specs/arm_v9_cortex_x2.json +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/data/arm/v9_0/specs/arm_v9_cortex_x3.json +0 -0
- /counted_float-0.9.5/counted_float/data/arm/v9_0/specs/arm_v9_cortex_n2.json → /counted_float-0.9.6/counted_float/data/arm/v9_0/specs/arm_v9_neoverse_n2.json +0 -0
- /counted_float-0.9.5/counted_float/data/arm/v9_0/specs/arm_v9_cortex_v2.json → /counted_float-0.9.6/counted_float/data/arm/v9_0/specs/arm_v9_neoverse_v2.json +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/data/arm/v9_2/specs/arm_v9_cortex_x4.json +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/data/arm/v9_2/specs/arm_v9_cortex_x925.json +0 -0
- /counted_float-0.9.5/counted_float/data/arm/v9_2/specs/arm_v9_cortex_v3.json → /counted_float-0.9.6/counted_float/data/arm/v9_2/specs/arm_v9_neoverse_v3.json +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/data/x86/amd/2017_zen1/analysis_uops_info_zen1+.json +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/data/x86/amd/2020_zen3/analysis_agner_fog_r7_5800x.json +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/data/x86/amd/2020_zen3/analysis_uops_info_zen3.json +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/data/x86/amd/2022_zen4/analysis_agner_fog_r9_7900x.json +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/data/x86/amd/2022_zen4/analysis_uops_info_zen4.json +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/data/x86/amd/2022_zen4/specs_amd.json +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/data/x86/amd/2024_zen5/analysis_agner_fog_r7_9800x3d.json +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/data/x86/amd/2024_zen5/specs_amd.json +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/data/x86/intel/2017_coffee_lake_gen_8/analysis_agner_fog_coffee_lake.json +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/data/x86/intel/2017_coffee_lake_gen_8/analysis_uops_info_coffee_lake.json +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/data/x86/intel/2019_sunny_cove_gen_10/analysis_agner_fog_ice_lake.json +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/data/x86/intel/2019_sunny_cove_gen_10/analysis_uops_info_ice_lake.json +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/data/x86/intel/2019_sunny_cove_gen_10/analysis_uops_info_tiger_lake.json +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/data/x86/intel/2021_golden_cove_gen_12/analysis_uops_info_alder_lake_p.json +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/data/x86/intel/2021_golden_cove_gen_12/specs_intel.json +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/data/x86/intel/2022_raptor_cove_gen_13_14/specs_intel.json +0 -0
- {counted_float-0.9.5 → counted_float-0.9.6}/counted_float/data/x86/intel/2023_redwood_cove_ultra_1/specs_intel.json +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: counted-float
|
|
3
|
-
Version: 0.9.
|
|
3
|
+
Version: 0.9.6
|
|
4
4
|
Summary: Count floating-point operations in Python code & benchmark relative flop costs.
|
|
5
5
|
Project-URL: Source, https://github.com/bertpl/counted-float
|
|
6
6
|
Project-URL: ChangeLog, https://github.com/bertpl/counted-float/blob/develop/CHANGELOG.md
|
|
@@ -21,9 +21,9 @@ Description-Content-Type: text/markdown
|
|
|
21
21
|
|
|
22
22
|
<!--START_SECTION:images-->
|
|
23
23
|
|
|
24
|
-
|
|
25
|
+
|
|
26
|
+
|
|
27
27
|
<!--END_SECTION:images-->
|
|
28
28
|
|
|
29
29
|
# counted-float
|
|
@@ -36,6 +36,10 @@ The target application area is evaluation of research prototypes of numerical al
|
|
|
36
36
|
useful for estimating total computational cost, in cases where benchmarking a compiled version (C, Rust, ...) is not
|
|
37
37
|
feasible or desirable.
|
|
38
38
|
|
|
39
|
+
Flop weights are computed using a highly curated dataset spanning a wide range of modern CPUs:
|
|
40
|
+
- 19 benchmarks, 16 spec sheets, 12 third party measurements (Agner Fog, uops.info)
|
|
41
|
+
- covering x86 (Intel, AMD) and ARM (Apple, AWS, Azure) architectures
|
|
42
|
+
|
|
39
43
|
# 1. Installation
|
|
40
44
|
|
|
41
45
|
Use you favorite package manager such as `uv` or `pip`:
|
|
@@ -381,61 +385,78 @@ after which the results will be shown as .json.
|
|
|
381
385
|
|
|
382
386
|
```
|
|
383
387
|
[~] counted_float show-data
|
|
384
|
-
|
|
385
|
-
|
|
386
|
-
|
|
387
|
-
├─
|
|
388
|
-
│ ├─
|
|
389
|
-
│ │ ├─
|
|
390
|
-
│ │ │ ├─
|
|
391
|
-
│ │ │
|
|
392
|
-
│ │
|
|
393
|
-
│ │
|
|
394
|
-
│ │
|
|
395
|
-
│ │ ├─
|
|
396
|
-
│ │
|
|
397
|
-
│ ├─
|
|
398
|
-
│ │
|
|
399
|
-
│
|
|
400
|
-
│ │
|
|
401
|
-
│ │
|
|
402
|
-
│ │
|
|
403
|
-
│ └─
|
|
404
|
-
│
|
|
405
|
-
│
|
|
406
|
-
│
|
|
407
|
-
│
|
|
408
|
-
└─
|
|
409
|
-
|
|
410
|
-
|
|
411
|
-
|
|
412
|
-
|
|
413
|
-
|
|
414
|
-
|
|
415
|
-
|
|
416
|
-
|
|
417
|
-
│
|
|
418
|
-
│ │ ├─
|
|
419
|
-
│ │ └─
|
|
420
|
-
│
|
|
421
|
-
│
|
|
422
|
-
│
|
|
423
|
-
|
|
424
|
-
|
|
425
|
-
|
|
426
|
-
|
|
427
|
-
|
|
428
|
-
|
|
429
|
-
|
|
430
|
-
|
|
431
|
-
|
|
432
|
-
|
|
433
|
-
|
|
434
|
-
|
|
435
|
-
├─
|
|
436
|
-
│
|
|
437
|
-
|
|
438
|
-
|
|
388
|
+
MINUS ABS COMP SUB ADD MUL RND F2I I2F DIV SQRT EXP2 EXP LOG LOG2 EXP10 LOG10 SIN COS POW TAN CBRT
|
|
389
|
+
ALL 0.47 0.70 0.97 1.00 1.00 1.40 1.77 1.91 1.92 5.53 7.36 15.86 17.52 19.00 22.38 23.03 24.66 30.41 31.39 41.81 42.16 44.32
|
|
390
|
+
├─arm 0.89 1.05 0.64 1.01 1.00 1.50 1.61 1.49 1.59 6.15 7.60 15.98 18.57 19.60 20.86 23.30 24.26 32.32 34.08 42.28 42.85 44.97
|
|
391
|
+
│ ├─v8_x 0.83 1.00 0.67 1.01 1.00 1.48 1.50 1.56 1.91 5.90 7.42 15.45 17.86 19.06 20.80 22.92 22.90 32.43 33.47 41.19 42.99 44.71
|
|
392
|
+
│ │ ├─benchmarks 0.70 1.01 0.45 1.01 1.00 1.46 1.50 / / 4.65 6.68 13.93 16.10 17.18 18.75 20.66 20.65 29.23 30.17 37.13 38.76 40.30
|
|
393
|
+
│ │ │ ├─apple_m3_max_mbp16 0.90 0.90 1.64 1.00 1.00 1.40 1.25 / / 4.00 5.28 16.69 17.42 17.59 18.15 21.06 17.31 28.77 29.17 37.93 39.04 39.48
|
|
394
|
+
│ │ │ ├─apple_m3_mba15 0.90 0.90 1.68 1.00 1.00 1.53 1.24 / / 4.06 5.27 16.68 17.43 17.56 18.09 21.07 17.29 28.63 29.06 38.46 32.32 39.43
|
|
395
|
+
│ │ │ ├─ec2_m6g_xlarge_graviton_2_neoverse_n1 0.46 1.47 0.38 1.00 1.00 1.38 2.01 / / 5.42 8.76 10.21 14.17 15.98 17.91 22.65 25.25 28.68 29.63 33.95 41.90 40.25
|
|
396
|
+
│ │ │ ├─ec2_m7g_xlarge_graviton_3_neoverse_v1 0.51 1.00 0.01 1.00 1.00 1.50 1.99 / / 6.03 9.58 11.89 14.81 17.49 19.20 19.09 27.67 30.26 31.49 36.85 42.45 40.96
|
|
397
|
+
│ │ │ └─gh_apple_m1 0.86 0.86 1.73 1.06 1.00 1.48 1.22 / / 4.07 5.70 15.50 16.98 17.33 20.52 19.61 17.95 29.86 31.59 38.67 38.97 41.44
|
|
398
|
+
│ │ └─specs 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.73 2.12 7.50 8.25 / / / / / / / / / / /
|
|
399
|
+
│ │ ├─arm_v8_cortex_a76 1.00 1.00 1.00 1.00 1.00 1.50 1.50 2.00 3.00 7.50 8.50 / / / / / / / / / / /
|
|
400
|
+
│ │ ├─arm_v9_cortex_x1 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
|
|
401
|
+
│ │ ├─arm_v9_neoverse_n1 1.00 1.00 1.00 1.00 1.00 1.50 1.50 2.00 3.00 7.50 8.50 / / / / / / / / / / /
|
|
402
|
+
│ │ └─arm_v9_neoverse_v1 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
|
|
403
|
+
│ ├─v9_0 0.74 1.00 0.25 1.00 1.00 1.51 1.80 1.27 1.27 6.78 8.83 14.32 17.90 20.66 22.09 24.04 32.41 35.53 37.31 44.86 52.70 48.30
|
|
404
|
+
│ │ ├─benchmarks 0.54 1.00 0.06 1.00 1.00 1.52 2.16 / / 6.14 9.75 12.12 15.15 17.49 18.70 20.35 27.44 30.08 31.59 37.98 44.62 40.89
|
|
405
|
+
│ │ │ ├─ec2_m8g_xlarge_graviton_4_neoverse_v2 0.52 1.00 0.01 1.00 1.00 1.50 2.05 / / 6.04 9.49 12.66 14.40 17.66 18.54 19.86 27.12 28.76 30.11 36.90 42.70 38.65
|
|
406
|
+
│ │ │ └─gh_azure_cobalt_100_neoverse_n2 0.57 1.00 0.33 1.00 1.00 1.53 2.28 / / 6.23 10.02 11.61 15.94 17.33 18.87 20.85 27.76 31.46 33.15 39.09 46.62 43.26
|
|
407
|
+
│ │ └─specs 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
|
|
408
|
+
│ │ ├─arm_v9_cortex_x2 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
|
|
409
|
+
│ │ ├─arm_v9_cortex_x3 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
|
|
410
|
+
│ │ ├─arm_v9_neoverse_n2 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
|
|
411
|
+
│ │ └─arm_v9_neoverse_v2 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
|
|
412
|
+
│ └─v9_2 1.16 1.16 1.55 1.02 1.00 1.51 1.55 1.66 1.66 5.80 6.70 18.44 20.04 19.11 19.75 22.96 19.23 29.29 31.69 40.89 34.73 42.11
|
|
413
|
+
│ ├─benchmarks 1.35 1.35 2.40 1.03 1.00 1.51 1.84 / / 5.32 7.10 20.38 22.15 21.13 21.83 25.38 21.25 32.38 35.03 45.20 38.39 46.55
|
|
414
|
+
│ │ └─apple_m4_pro_mbp16 1.35 1.35 2.40 1.03 1.00 1.51 1.84 / / 5.32 7.10 20.38 22.15 21.13 21.83 25.38 21.25 32.38 35.03 45.20 38.39 46.55
|
|
415
|
+
│ └─specs 1.00 1.00 1.00 1.00 1.00 1.50 1.31 1.50 1.50 6.33 6.33 / / / / / / / / / / /
|
|
416
|
+
│ ├─arm_v9_cortex_x4 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 6.50 6.50 / / / / / / / / / / /
|
|
417
|
+
│ ├─arm_v9_cortex_x925 1.00 1.00 1.00 1.00 1.00 1.50 1.00 1.50 1.50 6.00 6.00 / / / / / / / / / / /
|
|
418
|
+
│ └─arm_v9_neoverse_v3 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 6.50 6.50 / / / / / / / / / / /
|
|
419
|
+
└─x86 0.24 0.47 1.47 0.99 1.00 1.31 1.95 2.47 2.32 4.98 7.12 15.74 16.52 18.43 24.01 22.76 25.06 28.61 28.92 41.35 41.47 43.69
|
|
420
|
+
├─amd 0.29 0.43 1.51 0.99 1.00 1.19 1.21 2.42 2.54 4.74 7.39 18.48 16.73 18.23 24.93 24.05 24.46 28.42 28.69 42.99 40.87 45.73
|
|
421
|
+
│ ├─2017_zen1 0.34 0.34 1.16 1.00 1.00 1.29 1.34 3.07 3.07 4.18 6.44 63.95 19.71 17.05 32.24 43.83 18.79 30.58 30.27 57.99 39.24 66.55
|
|
422
|
+
│ │ ├─analysis_uops_info_zen1+ 0.33 0.33 2.33 1.00 1.00 1.33 1.33 3.33 3.33 4.33 6.67 / / / / / / / / / / /
|
|
423
|
+
│ │ └─benchmark_ryzen_1700x 0.35 0.35 0.58 1.01 1.00 1.24 1.34 / / 4.03 6.23 58.90 18.16 15.70 29.69 40.37 17.30 28.16 27.88 53.41 36.14 61.29
|
|
424
|
+
│ ├─2020_zen3 0.18 0.34 1.16 1.00 1.00 1.03 1.00 2.15 2.33 4.36 6.76 11.76 15.94 17.09 22.60 19.44 21.26 24.19 24.21 38.36 38.26 39.30
|
|
425
|
+
│ │ ├─analysis_agner_fog_r7_5800x 0.33 0.33 1.67 1.00 1.00 / 1.00 2.00 2.33 4.50 6.67 / / / / / / / / / / /
|
|
426
|
+
│ │ ├─analysis_uops_info_zen3 0.33 0.33 2.33 1.00 1.00 1.00 1.00 3.00 3.00 4.33 6.67 / / / / / / / / / / /
|
|
427
|
+
│ │ ├─benchmark_gh_amd_epyc_7763_linux 0.10 0.34 0.68 1.00 1.00 1.00 1.00 / / 4.31 6.86 10.35 11.79 15.35 14.36 14.53 22.21 22.45 22.86 30.57 33.34 31.25
|
|
428
|
+
│ │ └─benchmark_gh_amd_epyc_7763_windows 0.10 0.34 0.68 1.00 1.00 1.00 1.00 / / 4.28 6.86 10.32 16.65 14.70 27.48 20.08 15.72 20.14 19.82 37.19 33.92 38.17
|
|
429
|
+
│ ├─2022_zen4 0.23 0.33 1.34 0.99 1.00 1.01 1.00 1.92 1.85 4.37 6.90 11.20 12.97 17.81 21.31 16.47 26.04 25.08 25.55 33.51 37.44 34.67
|
|
430
|
+
│ │ ├─analysis_agner_fog_r9_7900x 0.33 0.33 1.33 1.00 1.00 / 1.00 2.00 2.00 4.33 7.00 / / / / / / / / / / /
|
|
431
|
+
│ │ ├─analysis_uops_info_zen4 0.33 0.33 2.33 1.00 1.00 1.00 1.00 3.00 2.67 4.33 7.00 / / / / / / / / / / /
|
|
432
|
+
│ │ ├─benchmark_ec2_m7a_xlarge_zen4 0.07 0.33 1.57 0.97 1.00 0.98 0.99 / / 4.49 6.95 9.97 11.55 15.86 18.98 14.66 23.19 22.34 22.75 29.84 33.34 30.87
|
|
433
|
+
│ │ └─specs_amd 0.33 0.33 0.67 1.00 1.00 1.00 1.00 1.33 1.33 4.33 6.67 / / / / / / / / / / /
|
|
434
|
+
│ └─2024_zen5 0.47 0.91 2.87 0.97 1.00 1.51 1.62 2.69 3.14 6.37 9.89 13.84 19.21 21.29 24.85 23.87 34.44 35.17 36.16 45.83 49.62 48.23
|
|
435
|
+
│ ├─analysis_agner_fog_r7_9800x3d 1.00 1.00 3.00 1.00 1.00 / 1.50 3.00 3.50 6.50 10.00 / / / / / / / / / / /
|
|
436
|
+
│ ├─benchmark_ec2_m8a_xlarge_zen5 0.21 1.53 2.95 0.91 1.00 1.36 1.87 / / 6.12 9.69 13.33 18.50 20.50 23.94 22.98 33.17 33.87 34.83 44.14 47.79 46.45
|
|
437
|
+
│ └─specs_amd 0.50 0.50 / 1.00 1.00 1.50 1.50 / / 6.50 10.00 / / / / / / / / / / /
|
|
438
|
+
└─intel 0.21 0.50 1.43 0.99 1.00 1.44 3.13 2.51 2.12 5.22 6.86 13.40 16.32 18.63 23.13 21.53 25.68 28.79 29.16 39.77 42.08 41.74
|
|
439
|
+
├─2017_coffee_lake_gen_8 0.14 0.40 1.30 0.98 1.00 1.03 1.99 1.66 1.66 3.54 4.56 10.44 16.58 12.62 19.41 21.85 13.05 20.81 20.80 33.18 28.66 36.32
|
|
440
|
+
│ ├─analysis_agner_fog_coffee_lake 0.25 0.25 / 1.00 1.00 1.00 2.00 1.50 1.50 3.50 4.00 / / / / / / / / / / /
|
|
441
|
+
│ ├─analysis_uops_info_coffee_lake 0.25 0.25 0.75 1.00 1.00 1.00 2.00 1.75 1.75 3.75 4.75 / / / / / / / / / / /
|
|
442
|
+
│ ├─benchmark_gh_intel_i7_8550U_windows 0.08 0.44 1.69 1.01 1.00 1.01 2.00 / / 3.15 4.79 7.02 15.44 11.99 30.07 21.33 13.00 17.80 17.21 32.36 28.09 35.06
|
|
443
|
+
│ └─benchmark_gh_intel_i7_8700B_macos 0.08 0.91 1.77 0.92 1.00 1.10 1.97 / / 3.78 4.77 16.30 18.68 13.93 13.15 23.47 13.74 25.51 26.38 35.70 30.68 39.48
|
|
444
|
+
├─2019_sunny_cove_gen_10 0.16 0.29 0.78 0.98 1.00 0.99 1.97 1.63 1.63 3.62 4.51 12.52 9.62 14.29 17.52 13.66 20.63 19.62 20.22 29.29 30.32 29.53
|
|
445
|
+
│ ├─analysis_agner_fog_ice_lake 0.25 0.25 0.50 1.00 1.00 / 2.00 1.50 1.50 3.50 4.00 / / / / / / / / / / /
|
|
446
|
+
│ ├─analysis_uops_info_ice_lake 0.25 0.25 0.75 1.00 1.00 1.00 2.00 1.75 1.75 3.75 4.75 / / / / / / / / / / /
|
|
447
|
+
│ ├─analysis_uops_info_tiger_lake 0.25 0.25 0.75 1.00 1.00 1.00 2.00 1.75 1.75 3.75 4.75 / / / / / / / / / / /
|
|
448
|
+
│ └─benchmark_ec2_m6i_xlarge_ice_lake 0.04 0.44 1.30 0.91 1.00 1.00 1.89 / / 3.50 4.60 11.82 9.08 13.49 16.55 12.90 19.48 18.52 19.09 27.65 28.63 27.88
|
|
449
|
+
├─2021_golden_cove_gen_12 0.28 0.55 1.56 0.99 1.00 1.74 3.77 3.02 2.55 6.20 8.22 14.56 17.86 21.33 24.92 23.36 31.87 33.78 34.10 42.83 49.32 45.31
|
|
450
|
+
│ ├─analysis_uops_info_alder_lake_p 0.33 0.33 1.00 1.00 1.00 1.33 2.67 2.33 2.33 5.00 6.33 / / / / / / / / / / /
|
|
451
|
+
│ ├─benchmark_ec2_m7i_xlarge_sapphire_rapids 0.13 0.99 2.52 0.98 1.00 1.99 5.03 / / 6.80 9.74 16.28 19.97 23.84 27.86 26.11 35.63 37.76 38.12 47.88 55.14 50.65
|
|
452
|
+
│ └─specs_intel 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
|
|
453
|
+
├─2022_raptor_cove_gen_13_14 0.26 0.71 1.96 1.00 1.00 2.00 4.51 3.55 2.53 7.00 9.49 15.73 19.93 24.00 28.64 26.02 35.73 37.86 38.33 49.02 55.79 51.16
|
|
454
|
+
│ ├─benchmark_ec2_i7i_xlarge_emerald_rapids 0.13 1.00 2.55 1.00 1.00 2.00 5.08 / / 7.00 10.00 15.95 20.20 24.33 29.03 26.37 36.21 38.37 38.85 49.69 56.55 51.86
|
|
455
|
+
│ └─specs_intel 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
|
|
456
|
+
└─2023_redwood_cove_ultra_1 0.24 0.71 1.95 0.99 1.00 1.73 4.51 3.46 2.47 6.97 9.47 14.44 20.41 24.32 27.29 25.53 36.40 37.92 38.32 48.75 55.19 50.95
|
|
457
|
+
├─benchmark_ec2_m8i_xlarge_granite_rapids 0.12 1.01 2.53 0.98 1.00 1.50 5.09 / / 6.94 9.96 14.28 20.19 24.06 26.99 25.26 36.01 37.51 37.91 48.22 54.60 50.40
|
|
458
|
+
└─specs_intel 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
|
|
459
|
+
|
|
439
460
|
```
|
|
440
461
|
|
|
441
462
|
# 5. Known limitations
|
|
@@ -1,8 +1,8 @@
|
|
|
1
1
|
<!--START_SECTION:images-->
|
|
2
2
|
|
|
3
|
-
|
|
4
|
+
|
|
5
|
+
|
|
6
6
|
<!--END_SECTION:images-->
|
|
7
7
|
|
|
8
8
|
# counted-float
|
|
@@ -15,6 +15,10 @@ The target application area is evaluation of research prototypes of numerical al
|
|
|
15
15
|
useful for estimating total computational cost, in cases where benchmarking a compiled version (C, Rust, ...) is not
|
|
16
16
|
feasible or desirable.
|
|
17
17
|
|
|
18
|
+
Flop weights are computed using a highly curated dataset spanning a wide range of modern CPUs:
|
|
19
|
+
- 19 benchmarks, 16 spec sheets, 12 third party measurements (Agner Fog, uops.info)
|
|
20
|
+
- covering x86 (Intel, AMD) and ARM (Apple, AWS, Azure) architectures
|
|
21
|
+
|
|
18
22
|
# 1. Installation
|
|
19
23
|
|
|
20
24
|
Use you favorite package manager such as `uv` or `pip`:
|
|
@@ -360,61 +364,78 @@ after which the results will be shown as .json.
|
|
|
360
364
|
|
|
361
365
|
```
|
|
362
366
|
[~] counted_float show-data
|
|
363
|
-
|
|
364
|
-
|
|
365
|
-
|
|
366
|
-
├─
|
|
367
|
-
│ ├─
|
|
368
|
-
│ │ ├─
|
|
369
|
-
│ │ │ ├─
|
|
370
|
-
│ │ │
|
|
371
|
-
│ │
|
|
372
|
-
│ │
|
|
373
|
-
│ │
|
|
374
|
-
│ │ ├─
|
|
375
|
-
│ │
|
|
376
|
-
│ ├─
|
|
377
|
-
│ │
|
|
378
|
-
│
|
|
379
|
-
│ │
|
|
380
|
-
│ │
|
|
381
|
-
│ │
|
|
382
|
-
│ └─
|
|
383
|
-
│
|
|
384
|
-
│
|
|
385
|
-
│
|
|
386
|
-
│
|
|
387
|
-
└─
|
|
388
|
-
|
|
389
|
-
|
|
390
|
-
|
|
391
|
-
|
|
392
|
-
|
|
393
|
-
|
|
394
|
-
|
|
395
|
-
|
|
396
|
-
│
|
|
397
|
-
│ │ ├─
|
|
398
|
-
│ │ └─
|
|
399
|
-
│
|
|
400
|
-
│
|
|
401
|
-
│
|
|
402
|
-
|
|
403
|
-
|
|
404
|
-
|
|
405
|
-
|
|
406
|
-
|
|
407
|
-
|
|
408
|
-
|
|
409
|
-
|
|
410
|
-
|
|
411
|
-
|
|
412
|
-
|
|
413
|
-
|
|
414
|
-
├─
|
|
415
|
-
│
|
|
416
|
-
|
|
417
|
-
|
|
367
|
+
MINUS ABS COMP SUB ADD MUL RND F2I I2F DIV SQRT EXP2 EXP LOG LOG2 EXP10 LOG10 SIN COS POW TAN CBRT
|
|
368
|
+
ALL 0.47 0.70 0.97 1.00 1.00 1.40 1.77 1.91 1.92 5.53 7.36 15.86 17.52 19.00 22.38 23.03 24.66 30.41 31.39 41.81 42.16 44.32
|
|
369
|
+
├─arm 0.89 1.05 0.64 1.01 1.00 1.50 1.61 1.49 1.59 6.15 7.60 15.98 18.57 19.60 20.86 23.30 24.26 32.32 34.08 42.28 42.85 44.97
|
|
370
|
+
│ ├─v8_x 0.83 1.00 0.67 1.01 1.00 1.48 1.50 1.56 1.91 5.90 7.42 15.45 17.86 19.06 20.80 22.92 22.90 32.43 33.47 41.19 42.99 44.71
|
|
371
|
+
│ │ ├─benchmarks 0.70 1.01 0.45 1.01 1.00 1.46 1.50 / / 4.65 6.68 13.93 16.10 17.18 18.75 20.66 20.65 29.23 30.17 37.13 38.76 40.30
|
|
372
|
+
│ │ │ ├─apple_m3_max_mbp16 0.90 0.90 1.64 1.00 1.00 1.40 1.25 / / 4.00 5.28 16.69 17.42 17.59 18.15 21.06 17.31 28.77 29.17 37.93 39.04 39.48
|
|
373
|
+
│ │ │ ├─apple_m3_mba15 0.90 0.90 1.68 1.00 1.00 1.53 1.24 / / 4.06 5.27 16.68 17.43 17.56 18.09 21.07 17.29 28.63 29.06 38.46 32.32 39.43
|
|
374
|
+
│ │ │ ├─ec2_m6g_xlarge_graviton_2_neoverse_n1 0.46 1.47 0.38 1.00 1.00 1.38 2.01 / / 5.42 8.76 10.21 14.17 15.98 17.91 22.65 25.25 28.68 29.63 33.95 41.90 40.25
|
|
375
|
+
│ │ │ ├─ec2_m7g_xlarge_graviton_3_neoverse_v1 0.51 1.00 0.01 1.00 1.00 1.50 1.99 / / 6.03 9.58 11.89 14.81 17.49 19.20 19.09 27.67 30.26 31.49 36.85 42.45 40.96
|
|
376
|
+
│ │ │ └─gh_apple_m1 0.86 0.86 1.73 1.06 1.00 1.48 1.22 / / 4.07 5.70 15.50 16.98 17.33 20.52 19.61 17.95 29.86 31.59 38.67 38.97 41.44
|
|
377
|
+
│ │ └─specs 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.73 2.12 7.50 8.25 / / / / / / / / / / /
|
|
378
|
+
│ │ ├─arm_v8_cortex_a76 1.00 1.00 1.00 1.00 1.00 1.50 1.50 2.00 3.00 7.50 8.50 / / / / / / / / / / /
|
|
379
|
+
│ │ ├─arm_v9_cortex_x1 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
|
|
380
|
+
│ │ ├─arm_v9_neoverse_n1 1.00 1.00 1.00 1.00 1.00 1.50 1.50 2.00 3.00 7.50 8.50 / / / / / / / / / / /
|
|
381
|
+
│ │ └─arm_v9_neoverse_v1 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
|
|
382
|
+
│ ├─v9_0 0.74 1.00 0.25 1.00 1.00 1.51 1.80 1.27 1.27 6.78 8.83 14.32 17.90 20.66 22.09 24.04 32.41 35.53 37.31 44.86 52.70 48.30
|
|
383
|
+
│ │ ├─benchmarks 0.54 1.00 0.06 1.00 1.00 1.52 2.16 / / 6.14 9.75 12.12 15.15 17.49 18.70 20.35 27.44 30.08 31.59 37.98 44.62 40.89
|
|
384
|
+
│ │ │ ├─ec2_m8g_xlarge_graviton_4_neoverse_v2 0.52 1.00 0.01 1.00 1.00 1.50 2.05 / / 6.04 9.49 12.66 14.40 17.66 18.54 19.86 27.12 28.76 30.11 36.90 42.70 38.65
|
|
385
|
+
│ │ │ └─gh_azure_cobalt_100_neoverse_n2 0.57 1.00 0.33 1.00 1.00 1.53 2.28 / / 6.23 10.02 11.61 15.94 17.33 18.87 20.85 27.76 31.46 33.15 39.09 46.62 43.26
|
|
386
|
+
│ │ └─specs 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
|
|
387
|
+
│ │ ├─arm_v9_cortex_x2 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
|
|
388
|
+
│ │ ├─arm_v9_cortex_x3 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
|
|
389
|
+
│ │ ├─arm_v9_neoverse_n2 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
|
|
390
|
+
│ │ └─arm_v9_neoverse_v2 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
|
|
391
|
+
│ └─v9_2 1.16 1.16 1.55 1.02 1.00 1.51 1.55 1.66 1.66 5.80 6.70 18.44 20.04 19.11 19.75 22.96 19.23 29.29 31.69 40.89 34.73 42.11
|
|
392
|
+
│ ├─benchmarks 1.35 1.35 2.40 1.03 1.00 1.51 1.84 / / 5.32 7.10 20.38 22.15 21.13 21.83 25.38 21.25 32.38 35.03 45.20 38.39 46.55
|
|
393
|
+
│ │ └─apple_m4_pro_mbp16 1.35 1.35 2.40 1.03 1.00 1.51 1.84 / / 5.32 7.10 20.38 22.15 21.13 21.83 25.38 21.25 32.38 35.03 45.20 38.39 46.55
|
|
394
|
+
│ └─specs 1.00 1.00 1.00 1.00 1.00 1.50 1.31 1.50 1.50 6.33 6.33 / / / / / / / / / / /
|
|
395
|
+
│ ├─arm_v9_cortex_x4 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 6.50 6.50 / / / / / / / / / / /
|
|
396
|
+
│ ├─arm_v9_cortex_x925 1.00 1.00 1.00 1.00 1.00 1.50 1.00 1.50 1.50 6.00 6.00 / / / / / / / / / / /
|
|
397
|
+
│ └─arm_v9_neoverse_v3 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 6.50 6.50 / / / / / / / / / / /
|
|
398
|
+
└─x86 0.24 0.47 1.47 0.99 1.00 1.31 1.95 2.47 2.32 4.98 7.12 15.74 16.52 18.43 24.01 22.76 25.06 28.61 28.92 41.35 41.47 43.69
|
|
399
|
+
├─amd 0.29 0.43 1.51 0.99 1.00 1.19 1.21 2.42 2.54 4.74 7.39 18.48 16.73 18.23 24.93 24.05 24.46 28.42 28.69 42.99 40.87 45.73
|
|
400
|
+
│ ├─2017_zen1 0.34 0.34 1.16 1.00 1.00 1.29 1.34 3.07 3.07 4.18 6.44 63.95 19.71 17.05 32.24 43.83 18.79 30.58 30.27 57.99 39.24 66.55
|
|
401
|
+
│ │ ├─analysis_uops_info_zen1+ 0.33 0.33 2.33 1.00 1.00 1.33 1.33 3.33 3.33 4.33 6.67 / / / / / / / / / / /
|
|
402
|
+
│ │ └─benchmark_ryzen_1700x 0.35 0.35 0.58 1.01 1.00 1.24 1.34 / / 4.03 6.23 58.90 18.16 15.70 29.69 40.37 17.30 28.16 27.88 53.41 36.14 61.29
|
|
403
|
+
│ ├─2020_zen3 0.18 0.34 1.16 1.00 1.00 1.03 1.00 2.15 2.33 4.36 6.76 11.76 15.94 17.09 22.60 19.44 21.26 24.19 24.21 38.36 38.26 39.30
|
|
404
|
+
│ │ ├─analysis_agner_fog_r7_5800x 0.33 0.33 1.67 1.00 1.00 / 1.00 2.00 2.33 4.50 6.67 / / / / / / / / / / /
|
|
405
|
+
│ │ ├─analysis_uops_info_zen3 0.33 0.33 2.33 1.00 1.00 1.00 1.00 3.00 3.00 4.33 6.67 / / / / / / / / / / /
|
|
406
|
+
│ │ ├─benchmark_gh_amd_epyc_7763_linux 0.10 0.34 0.68 1.00 1.00 1.00 1.00 / / 4.31 6.86 10.35 11.79 15.35 14.36 14.53 22.21 22.45 22.86 30.57 33.34 31.25
|
|
407
|
+
│ │ └─benchmark_gh_amd_epyc_7763_windows 0.10 0.34 0.68 1.00 1.00 1.00 1.00 / / 4.28 6.86 10.32 16.65 14.70 27.48 20.08 15.72 20.14 19.82 37.19 33.92 38.17
|
|
408
|
+
│ ├─2022_zen4 0.23 0.33 1.34 0.99 1.00 1.01 1.00 1.92 1.85 4.37 6.90 11.20 12.97 17.81 21.31 16.47 26.04 25.08 25.55 33.51 37.44 34.67
|
|
409
|
+
│ │ ├─analysis_agner_fog_r9_7900x 0.33 0.33 1.33 1.00 1.00 / 1.00 2.00 2.00 4.33 7.00 / / / / / / / / / / /
|
|
410
|
+
│ │ ├─analysis_uops_info_zen4 0.33 0.33 2.33 1.00 1.00 1.00 1.00 3.00 2.67 4.33 7.00 / / / / / / / / / / /
|
|
411
|
+
│ │ ├─benchmark_ec2_m7a_xlarge_zen4 0.07 0.33 1.57 0.97 1.00 0.98 0.99 / / 4.49 6.95 9.97 11.55 15.86 18.98 14.66 23.19 22.34 22.75 29.84 33.34 30.87
|
|
412
|
+
│ │ └─specs_amd 0.33 0.33 0.67 1.00 1.00 1.00 1.00 1.33 1.33 4.33 6.67 / / / / / / / / / / /
|
|
413
|
+
│ └─2024_zen5 0.47 0.91 2.87 0.97 1.00 1.51 1.62 2.69 3.14 6.37 9.89 13.84 19.21 21.29 24.85 23.87 34.44 35.17 36.16 45.83 49.62 48.23
|
|
414
|
+
│ ├─analysis_agner_fog_r7_9800x3d 1.00 1.00 3.00 1.00 1.00 / 1.50 3.00 3.50 6.50 10.00 / / / / / / / / / / /
|
|
415
|
+
│ ├─benchmark_ec2_m8a_xlarge_zen5 0.21 1.53 2.95 0.91 1.00 1.36 1.87 / / 6.12 9.69 13.33 18.50 20.50 23.94 22.98 33.17 33.87 34.83 44.14 47.79 46.45
|
|
416
|
+
│ └─specs_amd 0.50 0.50 / 1.00 1.00 1.50 1.50 / / 6.50 10.00 / / / / / / / / / / /
|
|
417
|
+
└─intel 0.21 0.50 1.43 0.99 1.00 1.44 3.13 2.51 2.12 5.22 6.86 13.40 16.32 18.63 23.13 21.53 25.68 28.79 29.16 39.77 42.08 41.74
|
|
418
|
+
├─2017_coffee_lake_gen_8 0.14 0.40 1.30 0.98 1.00 1.03 1.99 1.66 1.66 3.54 4.56 10.44 16.58 12.62 19.41 21.85 13.05 20.81 20.80 33.18 28.66 36.32
|
|
419
|
+
│ ├─analysis_agner_fog_coffee_lake 0.25 0.25 / 1.00 1.00 1.00 2.00 1.50 1.50 3.50 4.00 / / / / / / / / / / /
|
|
420
|
+
│ ├─analysis_uops_info_coffee_lake 0.25 0.25 0.75 1.00 1.00 1.00 2.00 1.75 1.75 3.75 4.75 / / / / / / / / / / /
|
|
421
|
+
│ ├─benchmark_gh_intel_i7_8550U_windows 0.08 0.44 1.69 1.01 1.00 1.01 2.00 / / 3.15 4.79 7.02 15.44 11.99 30.07 21.33 13.00 17.80 17.21 32.36 28.09 35.06
|
|
422
|
+
│ └─benchmark_gh_intel_i7_8700B_macos 0.08 0.91 1.77 0.92 1.00 1.10 1.97 / / 3.78 4.77 16.30 18.68 13.93 13.15 23.47 13.74 25.51 26.38 35.70 30.68 39.48
|
|
423
|
+
├─2019_sunny_cove_gen_10 0.16 0.29 0.78 0.98 1.00 0.99 1.97 1.63 1.63 3.62 4.51 12.52 9.62 14.29 17.52 13.66 20.63 19.62 20.22 29.29 30.32 29.53
|
|
424
|
+
│ ├─analysis_agner_fog_ice_lake 0.25 0.25 0.50 1.00 1.00 / 2.00 1.50 1.50 3.50 4.00 / / / / / / / / / / /
|
|
425
|
+
│ ├─analysis_uops_info_ice_lake 0.25 0.25 0.75 1.00 1.00 1.00 2.00 1.75 1.75 3.75 4.75 / / / / / / / / / / /
|
|
426
|
+
│ ├─analysis_uops_info_tiger_lake 0.25 0.25 0.75 1.00 1.00 1.00 2.00 1.75 1.75 3.75 4.75 / / / / / / / / / / /
|
|
427
|
+
│ └─benchmark_ec2_m6i_xlarge_ice_lake 0.04 0.44 1.30 0.91 1.00 1.00 1.89 / / 3.50 4.60 11.82 9.08 13.49 16.55 12.90 19.48 18.52 19.09 27.65 28.63 27.88
|
|
428
|
+
├─2021_golden_cove_gen_12 0.28 0.55 1.56 0.99 1.00 1.74 3.77 3.02 2.55 6.20 8.22 14.56 17.86 21.33 24.92 23.36 31.87 33.78 34.10 42.83 49.32 45.31
|
|
429
|
+
│ ├─analysis_uops_info_alder_lake_p 0.33 0.33 1.00 1.00 1.00 1.33 2.67 2.33 2.33 5.00 6.33 / / / / / / / / / / /
|
|
430
|
+
│ ├─benchmark_ec2_m7i_xlarge_sapphire_rapids 0.13 0.99 2.52 0.98 1.00 1.99 5.03 / / 6.80 9.74 16.28 19.97 23.84 27.86 26.11 35.63 37.76 38.12 47.88 55.14 50.65
|
|
431
|
+
│ └─specs_intel 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
|
|
432
|
+
├─2022_raptor_cove_gen_13_14 0.26 0.71 1.96 1.00 1.00 2.00 4.51 3.55 2.53 7.00 9.49 15.73 19.93 24.00 28.64 26.02 35.73 37.86 38.33 49.02 55.79 51.16
|
|
433
|
+
│ ├─benchmark_ec2_i7i_xlarge_emerald_rapids 0.13 1.00 2.55 1.00 1.00 2.00 5.08 / / 7.00 10.00 15.95 20.20 24.33 29.03 26.37 36.21 38.37 38.85 49.69 56.55 51.86
|
|
434
|
+
│ └─specs_intel 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
|
|
435
|
+
└─2023_redwood_cove_ultra_1 0.24 0.71 1.95 0.99 1.00 1.73 4.51 3.46 2.47 6.97 9.47 14.44 20.41 24.32 27.29 25.53 36.40 37.92 38.32 48.75 55.19 50.95
|
|
436
|
+
├─benchmark_ec2_m8i_xlarge_granite_rapids 0.12 1.01 2.53 0.98 1.00 1.50 5.09 / / 6.94 9.96 14.28 20.19 24.06 26.99 25.26 36.01 37.51 37.91 48.22 54.60 50.40
|
|
437
|
+
└─specs_intel 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
|
|
438
|
+
|
|
418
439
|
```
|
|
419
440
|
|
|
420
441
|
# 5. Known limitations
|
|
@@ -2,15 +2,7 @@ import counted_float.benchmarking as benchmarking
|
|
|
2
2
|
import counted_float.config as config
|
|
3
3
|
|
|
4
4
|
from ._core.counting import BuiltInData, CountedFloat, FlopCountingContext, PauseFlopCounting
|
|
5
|
-
from ._core.models import
|
|
6
|
-
FlopCounts,
|
|
7
|
-
FlopsBenchmarkDurations,
|
|
8
|
-
FlopsBenchmarkResults_V1,
|
|
9
|
-
FlopType,
|
|
10
|
-
FlopWeights,
|
|
11
|
-
Quantiles,
|
|
12
|
-
SystemInfo,
|
|
13
|
-
)
|
|
5
|
+
from ._core.models import FlopCounts, FlopType, FlopWeights, Quantiles, SystemInfo
|
|
14
6
|
|
|
15
7
|
__all__ = [
|
|
16
8
|
"benchmarking",
|
|
@@ -18,8 +10,6 @@ __all__ = [
|
|
|
18
10
|
"CountedFloat",
|
|
19
11
|
"FlopCountingContext",
|
|
20
12
|
"FlopCounts",
|
|
21
|
-
"FlopsBenchmarkDurations",
|
|
22
|
-
"FlopsBenchmarkResults_V1",
|
|
23
13
|
"FlopType",
|
|
24
14
|
"FlopWeights",
|
|
25
15
|
"PauseFlopCounting",
|
|
@@ -19,5 +19,6 @@ def benchmark():
|
|
|
19
19
|
|
|
20
20
|
|
|
21
21
|
@cli.command(short_help="show all built-in data")
|
|
22
|
-
|
|
23
|
-
|
|
22
|
+
@click.option("--key_filter", default="", help="Optional key filter for built-in data")
|
|
23
|
+
def show_data(key_filter: str):
|
|
24
|
+
BuiltInData.show(key_filter=key_filter)
|
|
@@ -1,7 +1,7 @@
|
|
|
1
|
-
from .flops import
|
|
1
|
+
from .flops import FlopsBenchmarkResults, FlopsBenchmarkSuite
|
|
2
2
|
|
|
3
3
|
|
|
4
|
-
def run_flops_benchmark() ->
|
|
4
|
+
def run_flops_benchmark() -> FlopsBenchmarkResults:
|
|
5
5
|
"""Run the flops benchmark suite with default settings returns a FlopsBenchmarkResults object."""
|
|
6
6
|
|
|
7
7
|
benchmark_results = FlopsBenchmarkSuite().run()
|
|
@@ -6,7 +6,7 @@ import numpy as np
|
|
|
6
6
|
from counted_float._core.compatibility import is_numba_installed, numba
|
|
7
7
|
from counted_float._core.models import (
|
|
8
8
|
BenchmarkSettings,
|
|
9
|
-
|
|
9
|
+
FlopsBenchmarkResults,
|
|
10
10
|
FlopsBenchmarkType,
|
|
11
11
|
FlopType,
|
|
12
12
|
Quantiles,
|
|
@@ -29,7 +29,7 @@ class FlopsBenchmarkSuite:
|
|
|
29
29
|
n_runs_total: int = 40,
|
|
30
30
|
n_runs_warmup: int = 15,
|
|
31
31
|
n_seconds_per_run_target: float = 0.1,
|
|
32
|
-
) ->
|
|
32
|
+
) -> FlopsBenchmarkResults:
|
|
33
33
|
"""
|
|
34
34
|
Run entire flops benchmarking suite and return the results as a FlopsBenchmarkResults_V2 object.
|
|
35
35
|
"""
|
|
@@ -95,7 +95,7 @@ class FlopsBenchmarkSuite:
|
|
|
95
95
|
}
|
|
96
96
|
|
|
97
97
|
# put results in appropriate format
|
|
98
|
-
return
|
|
98
|
+
return FlopsBenchmarkResults(
|
|
99
99
|
system=SystemInfo.from_system(),
|
|
100
100
|
benchmark_settings=BenchmarkSettings(
|
|
101
101
|
array_size=array_size,
|