counted-float 1.1.0__tar.gz → 1.1.1__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.
Files changed (97) hide show
  1. {counted_float-1.1.0 → counted_float-1.1.1}/PKG-INFO +53 -53
  2. {counted_float-1.1.0 → counted_float-1.1.1}/README.md +52 -52
  3. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/__init__.py +4 -2
  4. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/_cli.py +4 -4
  5. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/benchmarking/__init__.py +0 -1
  6. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/benchmarking/counted_float/_counted_float_benchmark.py +11 -11
  7. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/benchmarking/flops/_array_generator.py +10 -10
  8. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/benchmarking/flops/_flops_benchmark_suite.py +36 -37
  9. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/benchmarking/flops/_flops_micro_benchmark.py +10 -9
  10. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/benchmarking/micro/_micro_benchmark.py +17 -15
  11. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/compatibility/_numba.py +8 -8
  12. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/counting/_builtin_data.py +34 -31
  13. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/counting/_context_managers.py +30 -18
  14. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/counting/_counted_float.py +53 -52
  15. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/counting/_global_counter.py +33 -33
  16. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/counting/_math_patching.py +51 -59
  17. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/counting/config/_config.py +11 -13
  18. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/counting/config/_defaults.py +4 -6
  19. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/models/_base.py +3 -3
  20. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/models/_flop_counts.py +13 -10
  21. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/models/_flop_type.py +4 -4
  22. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/models/_flop_weights.py +18 -23
  23. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/models/_instruction_latencies.py +12 -14
  24. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/utils/_cpu_freq.py +10 -11
  25. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/utils/_formatting.py +9 -11
  26. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/utils/_geo_mean.py +5 -3
  27. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/utils/_latency.py +1 -1
  28. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/utils/_missing_data.py +5 -5
  29. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/utils/_rounding.py +9 -10
  30. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/utils/_timer.py +13 -9
  31. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/benchmarking/__init__.py +2 -0
  32. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/config/__init__.py +2 -0
  33. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/arm/v8_x/benchmarks/apple_m1_github_actions.json +1 -1
  34. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/arm/v8_x/benchmarks/apple_m3_max_mbp16.json +1 -1
  35. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/arm/v8_x/benchmarks/aws_graviton_2_neoverse_n1_ec2_m6g_xlarge.json +1 -1
  36. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/arm/v8_x/benchmarks/aws_graviton_3_neoverse_v1_ec2_m7g_xlarge.json +1 -1
  37. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/arm/v8_x/specs/arm_cortex_a76.json +1 -1
  38. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/arm/v8_x/specs/arm_cortex_x1.json +1 -1
  39. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/arm/v8_x/specs/arm_neoverse_n1.json +1 -1
  40. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/arm/v8_x/specs/arm_neoverse_v1.json +1 -1
  41. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/arm/v9_0/benchmarks/aws_graviton_4_neoverse_v2_ec2_m8g_xlarge.json +1 -1
  42. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/arm/v9_0/benchmarks/azure_cobalt_100_neoverse_n2_github_actions.json +1 -1
  43. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/arm/v9_0/specs/arm_cortex_x2.json +1 -1
  44. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/arm/v9_0/specs/arm_cortex_x3.json +1 -1
  45. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/arm/v9_0/specs/arm_neoverse_n2.json +1 -1
  46. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/arm/v9_0/specs/arm_neoverse_v2.json +1 -1
  47. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/arm/v9_2/specs/arm_cortex_x4.json +1 -1
  48. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/arm/v9_2/specs/arm_cortex_x925.json +1 -1
  49. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/arm/v9_2/specs/arm_neoverse_v3.json +1 -1
  50. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/x86/amd/2017_zen1/benchmarks/amd_ryzen_1700x.json +1 -1
  51. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/x86/amd/2017_zen1/other/analysis_uops_info_zen1+.json +1 -1
  52. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/x86/amd/2020_zen3/benchmark/amd_epyc_7763_linux_github.json +1 -1
  53. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/x86/amd/2020_zen3/benchmark/amd_epyc_7763_windows_github.json +1 -1
  54. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/x86/amd/2020_zen3/other/analysis_agner_fog_r7_5800x.json +1 -1
  55. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/x86/amd/2020_zen3/other/analysis_uops_info_zen3.json +1 -1
  56. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/x86/amd/2022_zen4/benchmark/amd_epyc_9r14_ec2_m7a_xlarge.json +1 -1
  57. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/x86/amd/2022_zen4/other/analysis_agner_fog_r9_7900x.json +1 -1
  58. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/x86/amd/2022_zen4/other/analysis_uops_info_zen4.json +1 -1
  59. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/x86/amd/2022_zen4/other/specs_amd.json +1 -1
  60. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/x86/amd/2024_zen5/benchmark/amd_epyc_9r45_ec2_m8a_xlarge.json +1 -1
  61. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/x86/amd/2024_zen5/other/analysis_agner_fog_r7_9800x3d.json +1 -1
  62. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/x86/amd/2024_zen5/other/specs_amd.json +1 -1
  63. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/x86/intel/2017_coffee_lake_gen_8/benchmarks/intel_i7_8550U_windows.json +1 -1
  64. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/x86/intel/2017_coffee_lake_gen_8/benchmarks/intel_i7_8700B_macos_github_actions.json +1 -1
  65. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/x86/intel/2017_coffee_lake_gen_8/other/analysis_agner_fog_coffee_lake.json +1 -1
  66. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/x86/intel/2017_coffee_lake_gen_8/other/analysis_uops_info_coffee_lake.json +1 -1
  67. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/x86/intel/2019_sunny_cove_gen_10/benchmarks/intel_xeon_8375c_ice_lake_ec2_m6i_xlarge.json +1 -1
  68. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/x86/intel/2019_sunny_cove_gen_10/other/analysis_agner_fog_ice_lake.json +1 -1
  69. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/x86/intel/2019_sunny_cove_gen_10/other/analysis_uops_info_ice_lake.json +1 -1
  70. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/x86/intel/2019_sunny_cove_gen_10/other/analysis_uops_info_tiger_lake.json +1 -1
  71. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/x86/intel/2021_golden_cove_gen_12/benchmarks/intel_xeon_8488c_sapphire_rapids_ec2_m7i_xlarge.json +1 -1
  72. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/x86/intel/2021_golden_cove_gen_12/other/analysis_uops_info_alder_lake_p.json +1 -1
  73. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/x86/intel/2021_golden_cove_gen_12/other/specs_intel.json +1 -1
  74. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/x86/intel/2022_raptor_cove_gen_13_14/benchmarks/intel_xeon_8559c_emerald_rapids_ec2_i7i_xlarge.json +1 -1
  75. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/x86/intel/2022_raptor_cove_gen_13_14/other/specs_intel.json +1 -1
  76. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/x86/intel/2023_redwood_cove_ultra_1/benchmarks/intel_xeon_6975p_granite_rapids_ec2_m8i_xlarge.json +1 -1
  77. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/x86/intel/2023_redwood_cove_ultra_1/other/specs_intel.json +1 -1
  78. counted_float-1.1.1/counted_float/py.typed +0 -0
  79. counted_float-1.1.1/pyproject.toml +134 -0
  80. counted_float-1.1.0/pyproject.toml +0 -69
  81. {counted_float-1.1.0 → counted_float-1.1.1}/.gitignore +0 -0
  82. {counted_float-1.1.0 → counted_float-1.1.1}/LICENSE +0 -0
  83. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/__init__.py +0 -0
  84. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/benchmarking/counted_float/__init__.py +0 -0
  85. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/benchmarking/flops/__init__.py +0 -0
  86. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/benchmarking/micro/__init__.py +0 -0
  87. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/compatibility/__init__.py +0 -0
  88. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/counting/__init__.py +0 -0
  89. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/counting/config/__init__.py +0 -0
  90. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/models/__init__.py +0 -0
  91. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/models/_flops_benchmark_meta_data.py +0 -0
  92. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/models/_flops_benchmark_result.py +0 -0
  93. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/models/_flops_benchmark_type.py +0 -0
  94. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/models/_micro_benchmark_result.py +0 -0
  95. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/utils/__init__.py +0 -0
  96. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/arm/v8_x/benchmarks/apple_m3_mba15.json +0 -0
  97. {counted_float-1.1.0 → counted_float-1.1.1}/counted_float/data/arm/v9_2/benchmarks/apple_m4_pro_mbp16.json +0 -0
{counted_float-1.1.0 → counted_float-1.1.1}/PKG-INFO RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: counted-float
3
- Version: 1.1.0
3
+ Version: 1.1.1
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/main/CHANGELOG.md
@@ -20,9 +20,9 @@ Requires-Dist: numba>=0.50; extra == 'numba'
20
20
  Description-Content-Type: text/markdown
21
21
 
22
22
  ![shields.io-python-versions](https://img.shields.io/badge/python-3.11%20%7C%203.12%20%7C%203.13-blue)
23
- ![genbadge-test-count](https://bertpl.github.io/counted-float/version_artifacts/develop/v1.1.0/badge-test-count.svg)
24
- ![genbadge-test-coverage](https://bertpl.github.io/counted-float/version_artifacts/develop/v1.1.0/badge-coverage.svg)
25
- ![counted_float logo](https://bertpl.github.io/counted-float/version_artifacts/develop/v1.1.0/splash.webp)
23
+ ![genbadge-test-count](https://bertpl.github.io/counted-float/version_artifacts/release/v1.1.1/badge-test-count.svg)
24
+ ![genbadge-test-coverage](https://bertpl.github.io/counted-float/version_artifacts/release/v1.1.1/badge-coverage.svg)
25
+ ![counted_float logo](https://bertpl.github.io/counted-float/version_artifacts/release/v1.1.1/splash.webp)
26
26
 
27
27
  # counted-float
28
28
 
@@ -30,8 +30,8 @@ This Python package provides functionality for...
30
30
  - **counting floating point operations** (FLOPs) of numerical algorithms implemented in plain Python, optionally weighted by their relative cost of execution
31
31
  - **running benchmarks** to estimate the relative cost of executing various floating-point operations (requires `numba` optional dependency for achieving accurate results)
32
32
 
33
- The target application area is evaluation of research prototypes of numerical algorithms where (weighted) flop counting can be
34
- useful for estimating total computational cost, in cases where benchmarking a compiled version (C, Rust, ...) is not
33
+ The target application area is evaluation of research prototypes of numerical algorithms where (weighted) flop counting can be
34
+ useful for estimating total computational cost, in cases where benchmarking a compiled version (C, Rust, ...) is not
35
35
  feasible or desirable.
36
36
 
37
37
  Flop weights are computed using a highly curated dataset spanning a wide range of modern CPUs:
@@ -190,7 +190,7 @@ counts.total_count() # 2
190
190
  ## 2.3. Weighted FLOP counting
191
191
 
192
192
  The `counted_float` package contains a set of default, built-in FLOP weights, based on both empirical measurements
193
- and theoretical estimates of the relative cost of different floating point operations.
193
+ and theoretical estimates of the relative cost of different floating point operations.
194
194
 
195
195
  See [fpu_data_sources.md](https://github.com/bertpl/counted-float/tree/develop/docs/analysis_methodology.md) for
196
196
  rationale behind choice of data sources and methodology.
@@ -241,7 +241,7 @@ with FlopCountingContext() as ctx:
241
241
  _ = cf1 + cf2
242
242
  _ = cf1 ** cf2
243
243
  _ = math.log2(cf2)
244
-
244
+
245
245
  flop_counts = ctx.flop_counts()
246
246
  total_cost = flop_counts.total_weighted_cost() # 1 + 40 + 22 = 63
247
247
  ```
@@ -343,7 +343,7 @@ from counted_float.config import get_builtin_flop_weights
343
343
 
344
344
  # 3. Benchmarking
345
345
 
346
- If the package is installed with the optional `numba` dependency, it provides the ability to micro-benchmark
346
+ If the package is installed with the optional `numba` dependency, it provides the ability to micro-benchmark
347
347
  floating point operations as follows:
348
348
 
349
349
  ```
@@ -381,7 +381,7 @@ div : wwwwwwwwwwwwwww.........................
381
381
  div_div : wwwwwwwwwwwwwww......................... [ 5.00 µs ± 0.2% | 20.3K cpu cycles ± 0.2% ] / 1000 iterations
382
382
  lte_addsub : wwwwwwwwwwwwwww......................... [ 1.71 µs ± 0.2% | 6.94K cpu cycles ± 0.2% ] / 1000 iterations
383
383
 
384
- >>> results.flop_weights().show()
384
+ >>> results.flop_weights().show()
385
385
 
386
386
  {
387
387
  FlopType.ABS [abs(x)] : 0.89904
@@ -441,86 +441,86 @@ ALL 0.44
441
441
  │ │ │ ├─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
442
442
  │ │ │ ├─aws_graviton_2_neoverse_n1_ec2_m6g_xlarge 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
443
443
  │ │ │ └─aws_graviton_3_neoverse_v1_ec2_m7g_xlarge 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
444
- │ │ └─specs 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.73 2.12 7.50 8.25 / / / / / / / / / / /
445
- │ │ ├─arm_cortex_a76 1.00 1.00 1.00 1.00 1.00 1.50 1.50 2.00 3.00 7.50 8.50 / / / / / / / / / / /
446
- │ │ ├─arm_cortex_x1 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
447
- │ │ ├─arm_neoverse_n1 1.00 1.00 1.00 1.00 1.00 1.50 1.50 2.00 3.00 7.50 8.50 / / / / / / / / / / /
448
- │ │ └─arm_neoverse_v1 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
444
+ │ │ └─specs 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.73 2.12 7.50 8.25 / / / / / / / / / / /
445
+ │ │ ├─arm_cortex_a76 1.00 1.00 1.00 1.00 1.00 1.50 1.50 2.00 3.00 7.50 8.50 / / / / / / / / / / /
446
+ │ │ ├─arm_cortex_x1 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
447
+ │ │ ├─arm_neoverse_n1 1.00 1.00 1.00 1.00 1.00 1.50 1.50 2.00 3.00 7.50 8.50 / / / / / / / / / / /
448
+ │ │ └─arm_neoverse_v1 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
449
449
  │ ├─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
450
450
  │ │ ├─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
451
451
  │ │ │ ├─aws_graviton_4_neoverse_v2_ec2_m8g_xlarge 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
452
452
  │ │ │ └─azure_cobalt_100_neoverse_n2_github_actions 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
453
- │ │ └─specs 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
454
- │ │ ├─arm_cortex_x2 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
455
- │ │ ├─arm_cortex_x3 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
456
- │ │ ├─arm_neoverse_n2 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
457
- │ │ └─arm_neoverse_v2 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
453
+ │ │ └─specs 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
454
+ │ │ ├─arm_cortex_x2 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
455
+ │ │ ├─arm_cortex_x3 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
456
+ │ │ ├─arm_neoverse_n2 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
457
+ │ │ └─arm_neoverse_v2 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
458
458
  │ └─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
459
459
  │ ├─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
460
460
  │ │ └─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
461
- │ └─specs 1.00 1.00 1.00 1.00 1.00 1.50 1.31 1.50 1.50 6.33 6.33 / / / / / / / / / / /
462
- │ ├─arm_cortex_x4 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 6.50 6.50 / / / / / / / / / / /
463
- │ ├─arm_cortex_x925 1.00 1.00 1.00 1.00 1.00 1.50 1.00 1.50 1.50 6.00 6.00 / / / / / / / / / / /
464
- │ └─arm_neoverse_v3 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 6.50 6.50 / / / / / / / / / / /
461
+ │ └─specs 1.00 1.00 1.00 1.00 1.00 1.50 1.31 1.50 1.50 6.33 6.33 / / / / / / / / / / /
462
+ │ ├─arm_cortex_x4 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 6.50 6.50 / / / / / / / / / / /
463
+ │ ├─arm_cortex_x925 1.00 1.00 1.00 1.00 1.00 1.50 1.00 1.50 1.50 6.00 6.00 / / / / / / / / / / /
464
+ │ └─arm_neoverse_v3 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 6.50 6.50 / / / / / / / / / / /
465
465
  └─x86 0.21 0.49 1.50 0.98 1.00 1.30 1.97 2.46 2.31 4.98 7.15 15.62 16.40 18.29 23.83 22.58 24.87 28.39 28.70 41.03 41.15 43.35
466
466
  ├─amd 0.25 0.45 1.52 0.99 1.00 1.17 1.22 2.39 2.51 4.74 7.38 18.22 16.50 17.98 24.59 23.73 24.13 28.04 28.30 42.41 40.31 45.11
467
467
  │ ├─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
468
468
  │ │ ├─benchmarks 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
469
469
  │ │ │ └─amd_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
470
- │ │ └─other 0.33 0.33 2.33 1.00 1.00 1.33 1.33 3.33 3.33 4.33 6.67 / / / / / / / / / / /
471
- │ │ └─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 / / / / / / / / / / /
470
+ │ │ └─other 0.33 0.33 2.33 1.00 1.00 1.33 1.33 3.33 3.33 4.33 6.67 / / / / / / / / / / /
471
+ │ │ └─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 / / / / / / / / / / /
472
472
  │ ├─2020_zen3 0.18 0.34 1.16 1.00 1.00 0.98 1.00 2.17 2.34 4.36 6.76 11.69 15.85 16.99 22.46 19.32 21.13 24.05 24.07 38.13 38.04 39.06
473
473
  │ │ ├─benchmark 0.10 0.34 0.68 1.00 1.00 1.00 1.00 / / 4.30 6.86 10.33 14.01 15.02 19.86 17.08 18.69 21.26 21.28 33.72 33.63 34.54
474
474
  │ │ │ ├─amd_epyc_7763_linux_github 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
475
475
  │ │ │ └─amd_epyc_7763_windows_github 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
476
- │ │ └─other 0.33 0.33 1.97 1.00 1.00 0.95 1.00 2.45 2.65 4.42 6.67 / / / / / / / / / / /
477
- │ │ ├─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 / / / / / / / / / / /
478
- │ │ └─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 / / / / / / / / / / /
476
+ │ │ └─other 0.33 0.33 1.97 1.00 1.00 0.95 1.00 2.45 2.65 4.42 6.67 / / / / / / / / / / /
477
+ │ │ ├─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 / / / / / / / / / / /
478
+ │ │ └─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 / / / / / / / / / / /
479
479
  │ ├─2022_zen4 0.15 0.33 1.41 0.99 1.00 0.99 1.00 1.85 1.78 4.41 6.92 10.77 12.47 17.12 20.49 15.83 25.03 24.11 24.56 32.21 35.99 33.32
480
480
  │ │ ├─benchmark 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
481
481
  │ │ │ └─amd_epyc_9r14_ec2_m7a_xlarge 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
482
- │ │ └─other 0.33 0.33 1.28 1.00 1.00 1.01 1.00 2.00 1.92 4.33 6.89 / / / / / / / / / / /
483
- │ │ ├─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 / / / / / / / / / / /
484
- │ │ ├─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 / / / / / / / / / / /
485
- │ │ └─specs_amd 0.33 0.33 0.67 1.00 1.00 1.00 1.00 1.33 1.33 4.33 6.67 / / / / / / / / / / /
482
+ │ │ └─other 0.33 0.33 1.28 1.00 1.00 1.01 1.00 2.00 1.92 4.33 6.89 / / / / / / / / / / /
483
+ │ │ ├─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 / / / / / / / / / / /
484
+ │ │ ├─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 / / / / / / / / / / /
485
+ │ │ └─specs_amd 0.33 0.33 0.67 1.00 1.00 1.00 1.00 1.33 1.33 4.33 6.67 / / / / / / / / / / /
486
486
  │ └─2024_zen5 0.39 1.04 2.83 0.95 1.00 1.50 1.68 2.64 3.08 6.31 9.84 13.71 19.04 21.09 24.62 23.64 34.12 34.84 35.83 45.40 49.16 47.78
487
487
  │ ├─benchmark 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
488
488
  │ │ └─amd_epyc_9r45_ec2_m8a_xlarge 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
489
- │ └─other 0.71 0.71 2.72 1.00 1.00 1.66 1.50 2.72 3.17 6.50 10.00 / / / / / / / / / / /
490
- │ ├─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 / / / / / / / / / / /
491
- │ └─specs_amd 0.50 0.50 / 1.00 1.00 1.50 1.50 / / 6.50 10.00 / / / / / / / / / / /
489
+ │ └─other 0.71 0.71 2.72 1.00 1.00 1.66 1.50 2.72 3.17 6.50 10.00 / / / / / / / / / / /
490
+ │ ├─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 / / / / / / / / / / /
491
+ │ └─specs_amd 0.50 0.50 / 1.00 1.00 1.50 1.50 / / 6.50 10.00 / / / / / / / / / / /
492
492
  └─intel 0.18 0.53 1.47 0.98 1.00 1.45 3.17 2.53 2.14 5.23 6.93 13.38 16.30 18.60 23.09 21.50 25.64 28.75 29.11 39.70 42.01 41.67
493
493
  ├─2017_coffee_lake_gen_8 0.14 0.40 1.12 0.98 1.00 1.03 1.99 1.69 1.69 3.54 4.56 10.27 16.31 12.42 19.10 21.50 12.84 20.48 20.47 32.65 28.21 35.74
494
494
  │ ├─benchmarks 0.08 0.63 1.73 0.96 1.00 1.05 1.99 / / 3.45 4.78 10.69 16.98 12.92 19.88 22.38 13.37 21.31 21.31 33.99 29.36 37.20
495
495
  │ │ ├─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
496
496
  │ │ └─intel_i7_8700B_macos_github_actions 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
497
- │ └─other 0.25 0.25 0.73 1.00 1.00 1.00 2.00 1.62 1.62 3.62 4.36 / / / / / / / / / / /
498
- │ ├─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 / / / / / / / / / / /
499
- │ └─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 / / / / / / / / / / /
497
+ │ └─other 0.25 0.25 0.73 1.00 1.00 1.00 2.00 1.62 1.62 3.62 4.36 / / / / / / / / / / /
498
+ │ ├─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 / / / / / / / / / / /
499
+ │ └─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 / / / / / / / / / / /
500
500
  ├─2019_sunny_cove_gen_10 0.10 0.33 0.92 0.95 1.00 0.98 1.94 1.60 1.60 3.58 4.54 12.27 9.43 14.01 17.18 13.39 20.23 19.23 19.83 28.71 29.72 28.95
501
501
  │ ├─benchmarks 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
502
502
  │ │ └─intel_xeon_8375c_ice_lake_ec2_m6i_xlarge 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
503
- │ └─other 0.25 0.25 0.66 1.00 1.00 0.97 2.00 1.66 1.66 3.66 4.49 / / / / / / / / / / /
504
- │ ├─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 / / / / / / / / / / /
505
- │ ├─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 / / / / / / / / / / /
506
- │ └─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 / / / / / / / / / / /
503
+ │ └─other 0.25 0.25 0.66 1.00 1.00 0.97 2.00 1.66 1.66 3.66 4.49 / / / / / / / / / / /
504
+ │ ├─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 / / / / / / / / / / /
505
+ │ ├─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 / / / / / / / / / / /
506
+ │ └─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 / / / / / / / / / / /
507
507
  ├─2021_golden_cove_gen_12 0.23 0.64 1.76 0.99 1.00 1.80 4.05 3.11 2.63 6.34 8.58 14.98 18.37 21.93 25.63 24.02 32.77 34.73 35.06 44.04 50.72 46.59
508
508
  │ ├─benchmarks 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
509
509
  │ │ └─intel_xeon_8488c_sapphire_rapids_ec2_m7i_xlarge 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
510
- │ └─other 0.41 0.41 1.22 1.00 1.00 1.63 3.27 2.86 2.42 5.92 7.55 / / / / / / / / / / /
511
- │ ├─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 / / / / / / / / / / /
512
- │ └─specs_intel 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
510
+ │ └─other 0.41 0.41 1.22 1.00 1.00 1.63 3.27 2.86 2.42 5.92 7.55 / / / / / / / / / / /
511
+ │ ├─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 / / / / / / / / / / /
512
+ │ └─specs_intel 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
513
513
  ├─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
514
514
  │ ├─benchmarks 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
515
515
  │ │ └─intel_xeon_8559c_emerald_rapids_ec2_i7i_xlarge 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
516
- │ └─other 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
517
- │ └─specs_intel 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
516
+ │ └─other 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
517
+ │ └─specs_intel 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
518
518
  └─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
519
519
  ├─benchmarks 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
520
520
  │ └─intel_xeon_6975p_granite_rapids_ec2_m8i_xlarge 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
521
- └─other 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
522
- └─specs_intel 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
523
-
521
+ └─other 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
522
+ └─specs_intel 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
523
+
524
524
 
525
525
  ```
526
526
 
@@ -557,7 +557,7 @@ CountedFloat is 37.3x slower than float
557
557
  - currently any non-Python-built-in math operations are not counted (e.g. `numpy`)
558
558
  - not all Python built-in math operations are counted (e.g. hyperbolic functions)
559
559
  - flop weights should be taken with a grain of salt and should only provide relative ballpark estimates w.r.t computational complexity. Production implementations in a compiled language could have vastly differing performance depending on cpu cache sizes, branch prediction misses, compiler optimizations using vector operations (AVX etc...), etc...
560
-
560
+
561
561
  # Appendix A - Flop counting / analysis details
562
562
 
563
563
  This appendix provides detailed information about how each floating-point operation (FLOP) type is counted and analyzed in the `counted-float` package. All `math.*` entries below assume an active `FlopCountingContext` (outside one, the `math` module is not instrumented). For each flop type, you will find:
@@ -719,4 +719,4 @@ This appendix provides detailed information about how each floating-point operat
719
719
  - **ARM:** (software)
720
720
  - **x86:** (software)
721
721
  - **Counted Python operations:** `math.tan(x)` for `CountedFloat`
722
- - **Not counted:** `tan` on non-CountedFloat, `numpy.tan
722
+ - **Not counted:** `tan` on non-CountedFloat, `numpy.tan
{counted_float-1.1.0 → counted_float-1.1.1}/README.md RENAMED
@@ -1,7 +1,7 @@
1
1
  ![shields.io-python-versions](https://img.shields.io/badge/python-3.11%20%7C%203.12%20%7C%203.13-blue)
2
- ![genbadge-test-count](https://bertpl.github.io/counted-float/version_artifacts/develop/v1.1.0/badge-test-count.svg)
3
- ![genbadge-test-coverage](https://bertpl.github.io/counted-float/version_artifacts/develop/v1.1.0/badge-coverage.svg)
4
- ![counted_float logo](https://bertpl.github.io/counted-float/version_artifacts/develop/v1.1.0/splash.webp)
2
+ ![genbadge-test-count](https://bertpl.github.io/counted-float/version_artifacts/release/v1.1.1/badge-test-count.svg)
3
+ ![genbadge-test-coverage](https://bertpl.github.io/counted-float/version_artifacts/release/v1.1.1/badge-coverage.svg)
4
+ ![counted_float logo](https://bertpl.github.io/counted-float/version_artifacts/release/v1.1.1/splash.webp)
5
5
 
6
6
  # counted-float
7
7
 
@@ -9,8 +9,8 @@ This Python package provides functionality for...
9
9
  - **counting floating point operations** (FLOPs) of numerical algorithms implemented in plain Python, optionally weighted by their relative cost of execution
10
10
  - **running benchmarks** to estimate the relative cost of executing various floating-point operations (requires `numba` optional dependency for achieving accurate results)
11
11
 
12
- The target application area is evaluation of research prototypes of numerical algorithms where (weighted) flop counting can be
13
- useful for estimating total computational cost, in cases where benchmarking a compiled version (C, Rust, ...) is not
12
+ The target application area is evaluation of research prototypes of numerical algorithms where (weighted) flop counting can be
13
+ useful for estimating total computational cost, in cases where benchmarking a compiled version (C, Rust, ...) is not
14
14
  feasible or desirable.
15
15
 
16
16
  Flop weights are computed using a highly curated dataset spanning a wide range of modern CPUs:
@@ -169,7 +169,7 @@ counts.total_count() # 2
169
169
  ## 2.3. Weighted FLOP counting
170
170
 
171
171
  The `counted_float` package contains a set of default, built-in FLOP weights, based on both empirical measurements
172
- and theoretical estimates of the relative cost of different floating point operations.
172
+ and theoretical estimates of the relative cost of different floating point operations.
173
173
 
174
174
  See [fpu_data_sources.md](https://github.com/bertpl/counted-float/tree/develop/docs/analysis_methodology.md) for
175
175
  rationale behind choice of data sources and methodology.
@@ -220,7 +220,7 @@ with FlopCountingContext() as ctx:
220
220
  _ = cf1 + cf2
221
221
  _ = cf1 ** cf2
222
222
  _ = math.log2(cf2)
223
-
223
+
224
224
  flop_counts = ctx.flop_counts()
225
225
  total_cost = flop_counts.total_weighted_cost() # 1 + 40 + 22 = 63
226
226
  ```
@@ -322,7 +322,7 @@ from counted_float.config import get_builtin_flop_weights
322
322
 
323
323
  # 3. Benchmarking
324
324
 
325
- If the package is installed with the optional `numba` dependency, it provides the ability to micro-benchmark
325
+ If the package is installed with the optional `numba` dependency, it provides the ability to micro-benchmark
326
326
  floating point operations as follows:
327
327
 
328
328
  ```
@@ -360,7 +360,7 @@ div : wwwwwwwwwwwwwww.........................
360
360
  div_div : wwwwwwwwwwwwwww......................... [ 5.00 µs ± 0.2% | 20.3K cpu cycles ± 0.2% ] / 1000 iterations
361
361
  lte_addsub : wwwwwwwwwwwwwww......................... [ 1.71 µs ± 0.2% | 6.94K cpu cycles ± 0.2% ] / 1000 iterations
362
362
 
363
- >>> results.flop_weights().show()
363
+ >>> results.flop_weights().show()
364
364
 
365
365
  {
366
366
  FlopType.ABS [abs(x)] : 0.89904
@@ -420,86 +420,86 @@ ALL 0.44
420
420
  │ │ │ ├─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
421
421
  │ │ │ ├─aws_graviton_2_neoverse_n1_ec2_m6g_xlarge 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
422
422
  │ │ │ └─aws_graviton_3_neoverse_v1_ec2_m7g_xlarge 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
423
- │ │ └─specs 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.73 2.12 7.50 8.25 / / / / / / / / / / /
424
- │ │ ├─arm_cortex_a76 1.00 1.00 1.00 1.00 1.00 1.50 1.50 2.00 3.00 7.50 8.50 / / / / / / / / / / /
425
- │ │ ├─arm_cortex_x1 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
426
- │ │ ├─arm_neoverse_n1 1.00 1.00 1.00 1.00 1.00 1.50 1.50 2.00 3.00 7.50 8.50 / / / / / / / / / / /
427
- │ │ └─arm_neoverse_v1 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
423
+ │ │ └─specs 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.73 2.12 7.50 8.25 / / / / / / / / / / /
424
+ │ │ ├─arm_cortex_a76 1.00 1.00 1.00 1.00 1.00 1.50 1.50 2.00 3.00 7.50 8.50 / / / / / / / / / / /
425
+ │ │ ├─arm_cortex_x1 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
426
+ │ │ ├─arm_neoverse_n1 1.00 1.00 1.00 1.00 1.00 1.50 1.50 2.00 3.00 7.50 8.50 / / / / / / / / / / /
427
+ │ │ └─arm_neoverse_v1 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
428
428
  │ ├─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
429
429
  │ │ ├─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
430
430
  │ │ │ ├─aws_graviton_4_neoverse_v2_ec2_m8g_xlarge 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
431
431
  │ │ │ └─azure_cobalt_100_neoverse_n2_github_actions 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
432
- │ │ └─specs 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
433
- │ │ ├─arm_cortex_x2 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
434
- │ │ ├─arm_cortex_x3 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
435
- │ │ ├─arm_neoverse_n2 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
436
- │ │ └─arm_neoverse_v2 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
432
+ │ │ └─specs 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
433
+ │ │ ├─arm_cortex_x2 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
434
+ │ │ ├─arm_cortex_x3 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
435
+ │ │ ├─arm_neoverse_n2 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
436
+ │ │ └─arm_neoverse_v2 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
437
437
  │ └─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
438
438
  │ ├─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
439
439
  │ │ └─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
440
- │ └─specs 1.00 1.00 1.00 1.00 1.00 1.50 1.31 1.50 1.50 6.33 6.33 / / / / / / / / / / /
441
- │ ├─arm_cortex_x4 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 6.50 6.50 / / / / / / / / / / /
442
- │ ├─arm_cortex_x925 1.00 1.00 1.00 1.00 1.00 1.50 1.00 1.50 1.50 6.00 6.00 / / / / / / / / / / /
443
- │ └─arm_neoverse_v3 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 6.50 6.50 / / / / / / / / / / /
440
+ │ └─specs 1.00 1.00 1.00 1.00 1.00 1.50 1.31 1.50 1.50 6.33 6.33 / / / / / / / / / / /
441
+ │ ├─arm_cortex_x4 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 6.50 6.50 / / / / / / / / / / /
442
+ │ ├─arm_cortex_x925 1.00 1.00 1.00 1.00 1.00 1.50 1.00 1.50 1.50 6.00 6.00 / / / / / / / / / / /
443
+ │ └─arm_neoverse_v3 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 6.50 6.50 / / / / / / / / / / /
444
444
  └─x86 0.21 0.49 1.50 0.98 1.00 1.30 1.97 2.46 2.31 4.98 7.15 15.62 16.40 18.29 23.83 22.58 24.87 28.39 28.70 41.03 41.15 43.35
445
445
  ├─amd 0.25 0.45 1.52 0.99 1.00 1.17 1.22 2.39 2.51 4.74 7.38 18.22 16.50 17.98 24.59 23.73 24.13 28.04 28.30 42.41 40.31 45.11
446
446
  │ ├─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
447
447
  │ │ ├─benchmarks 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
448
448
  │ │ │ └─amd_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
449
- │ │ └─other 0.33 0.33 2.33 1.00 1.00 1.33 1.33 3.33 3.33 4.33 6.67 / / / / / / / / / / /
450
- │ │ └─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 / / / / / / / / / / /
449
+ │ │ └─other 0.33 0.33 2.33 1.00 1.00 1.33 1.33 3.33 3.33 4.33 6.67 / / / / / / / / / / /
450
+ │ │ └─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 / / / / / / / / / / /
451
451
  │ ├─2020_zen3 0.18 0.34 1.16 1.00 1.00 0.98 1.00 2.17 2.34 4.36 6.76 11.69 15.85 16.99 22.46 19.32 21.13 24.05 24.07 38.13 38.04 39.06
452
452
  │ │ ├─benchmark 0.10 0.34 0.68 1.00 1.00 1.00 1.00 / / 4.30 6.86 10.33 14.01 15.02 19.86 17.08 18.69 21.26 21.28 33.72 33.63 34.54
453
453
  │ │ │ ├─amd_epyc_7763_linux_github 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
454
454
  │ │ │ └─amd_epyc_7763_windows_github 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
455
- │ │ └─other 0.33 0.33 1.97 1.00 1.00 0.95 1.00 2.45 2.65 4.42 6.67 / / / / / / / / / / /
456
- │ │ ├─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 / / / / / / / / / / /
457
- │ │ └─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 / / / / / / / / / / /
455
+ │ │ └─other 0.33 0.33 1.97 1.00 1.00 0.95 1.00 2.45 2.65 4.42 6.67 / / / / / / / / / / /
456
+ │ │ ├─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 / / / / / / / / / / /
457
+ │ │ └─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 / / / / / / / / / / /
458
458
  │ ├─2022_zen4 0.15 0.33 1.41 0.99 1.00 0.99 1.00 1.85 1.78 4.41 6.92 10.77 12.47 17.12 20.49 15.83 25.03 24.11 24.56 32.21 35.99 33.32
459
459
  │ │ ├─benchmark 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
460
460
  │ │ │ └─amd_epyc_9r14_ec2_m7a_xlarge 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
461
- │ │ └─other 0.33 0.33 1.28 1.00 1.00 1.01 1.00 2.00 1.92 4.33 6.89 / / / / / / / / / / /
462
- │ │ ├─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 / / / / / / / / / / /
463
- │ │ ├─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 / / / / / / / / / / /
464
- │ │ └─specs_amd 0.33 0.33 0.67 1.00 1.00 1.00 1.00 1.33 1.33 4.33 6.67 / / / / / / / / / / /
461
+ │ │ └─other 0.33 0.33 1.28 1.00 1.00 1.01 1.00 2.00 1.92 4.33 6.89 / / / / / / / / / / /
462
+ │ │ ├─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 / / / / / / / / / / /
463
+ │ │ ├─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 / / / / / / / / / / /
464
+ │ │ └─specs_amd 0.33 0.33 0.67 1.00 1.00 1.00 1.00 1.33 1.33 4.33 6.67 / / / / / / / / / / /
465
465
  │ └─2024_zen5 0.39 1.04 2.83 0.95 1.00 1.50 1.68 2.64 3.08 6.31 9.84 13.71 19.04 21.09 24.62 23.64 34.12 34.84 35.83 45.40 49.16 47.78
466
466
  │ ├─benchmark 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
467
467
  │ │ └─amd_epyc_9r45_ec2_m8a_xlarge 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
468
- │ └─other 0.71 0.71 2.72 1.00 1.00 1.66 1.50 2.72 3.17 6.50 10.00 / / / / / / / / / / /
469
- │ ├─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 / / / / / / / / / / /
470
- │ └─specs_amd 0.50 0.50 / 1.00 1.00 1.50 1.50 / / 6.50 10.00 / / / / / / / / / / /
468
+ │ └─other 0.71 0.71 2.72 1.00 1.00 1.66 1.50 2.72 3.17 6.50 10.00 / / / / / / / / / / /
469
+ │ ├─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 / / / / / / / / / / /
470
+ │ └─specs_amd 0.50 0.50 / 1.00 1.00 1.50 1.50 / / 6.50 10.00 / / / / / / / / / / /
471
471
  └─intel 0.18 0.53 1.47 0.98 1.00 1.45 3.17 2.53 2.14 5.23 6.93 13.38 16.30 18.60 23.09 21.50 25.64 28.75 29.11 39.70 42.01 41.67
472
472
  ├─2017_coffee_lake_gen_8 0.14 0.40 1.12 0.98 1.00 1.03 1.99 1.69 1.69 3.54 4.56 10.27 16.31 12.42 19.10 21.50 12.84 20.48 20.47 32.65 28.21 35.74
473
473
  │ ├─benchmarks 0.08 0.63 1.73 0.96 1.00 1.05 1.99 / / 3.45 4.78 10.69 16.98 12.92 19.88 22.38 13.37 21.31 21.31 33.99 29.36 37.20
474
474
  │ │ ├─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
475
475
  │ │ └─intel_i7_8700B_macos_github_actions 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
476
- │ └─other 0.25 0.25 0.73 1.00 1.00 1.00 2.00 1.62 1.62 3.62 4.36 / / / / / / / / / / /
477
- │ ├─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 / / / / / / / / / / /
478
- │ └─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 / / / / / / / / / / /
476
+ │ └─other 0.25 0.25 0.73 1.00 1.00 1.00 2.00 1.62 1.62 3.62 4.36 / / / / / / / / / / /
477
+ │ ├─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 / / / / / / / / / / /
478
+ │ └─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 / / / / / / / / / / /
479
479
  ├─2019_sunny_cove_gen_10 0.10 0.33 0.92 0.95 1.00 0.98 1.94 1.60 1.60 3.58 4.54 12.27 9.43 14.01 17.18 13.39 20.23 19.23 19.83 28.71 29.72 28.95
480
480
  │ ├─benchmarks 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
481
481
  │ │ └─intel_xeon_8375c_ice_lake_ec2_m6i_xlarge 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
482
- │ └─other 0.25 0.25 0.66 1.00 1.00 0.97 2.00 1.66 1.66 3.66 4.49 / / / / / / / / / / /
483
- │ ├─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 / / / / / / / / / / /
484
- │ ├─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 / / / / / / / / / / /
485
- │ └─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 / / / / / / / / / / /
482
+ │ └─other 0.25 0.25 0.66 1.00 1.00 0.97 2.00 1.66 1.66 3.66 4.49 / / / / / / / / / / /
483
+ │ ├─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 / / / / / / / / / / /
484
+ │ ├─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 / / / / / / / / / / /
485
+ │ └─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 / / / / / / / / / / /
486
486
  ├─2021_golden_cove_gen_12 0.23 0.64 1.76 0.99 1.00 1.80 4.05 3.11 2.63 6.34 8.58 14.98 18.37 21.93 25.63 24.02 32.77 34.73 35.06 44.04 50.72 46.59
487
487
  │ ├─benchmarks 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
488
488
  │ │ └─intel_xeon_8488c_sapphire_rapids_ec2_m7i_xlarge 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
489
- │ └─other 0.41 0.41 1.22 1.00 1.00 1.63 3.27 2.86 2.42 5.92 7.55 / / / / / / / / / / /
490
- │ ├─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 / / / / / / / / / / /
491
- │ └─specs_intel 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
489
+ │ └─other 0.41 0.41 1.22 1.00 1.00 1.63 3.27 2.86 2.42 5.92 7.55 / / / / / / / / / / /
490
+ │ ├─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 / / / / / / / / / / /
491
+ │ └─specs_intel 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
492
492
  ├─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
493
493
  │ ├─benchmarks 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
494
494
  │ │ └─intel_xeon_8559c_emerald_rapids_ec2_i7i_xlarge 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
495
- │ └─other 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
496
- │ └─specs_intel 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
495
+ │ └─other 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
496
+ │ └─specs_intel 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
497
497
  └─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
498
498
  ├─benchmarks 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
499
499
  │ └─intel_xeon_6975p_granite_rapids_ec2_m8i_xlarge 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
500
- └─other 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
501
- └─specs_intel 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
502
-
500
+ └─other 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
501
+ └─specs_intel 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
502
+
503
503
 
504
504
  ```
505
505
 
@@ -536,7 +536,7 @@ CountedFloat is 37.3x slower than float
536
536
  - currently any non-Python-built-in math operations are not counted (e.g. `numpy`)
537
537
  - not all Python built-in math operations are counted (e.g. hyperbolic functions)
538
538
  - flop weights should be taken with a grain of salt and should only provide relative ballpark estimates w.r.t computational complexity. Production implementations in a compiled language could have vastly differing performance depending on cpu cache sizes, branch prediction misses, compiler optimizations using vector operations (AVX etc...), etc...
539
-
539
+
540
540
  # Appendix A - Flop counting / analysis details
541
541
 
542
542
  This appendix provides detailed information about how each floating-point operation (FLOP) type is counted and analyzed in the `counted-float` package. All `math.*` entries below assume an active `FlopCountingContext` (outside one, the `math` module is not instrumented). For each flop type, you will find:
@@ -698,4 +698,4 @@ This appendix provides detailed information about how each floating-point operat
698
698
  - **ARM:** (software)
699
699
  - **x86:** (software)
700
700
  - **Counted Python operations:** `math.tan(x)` for `CountedFloat`
701
- - **Not counted:** `tan` on non-CountedFloat, `numpy.tan
701
+ - **Not counted:** `tan` on non-CountedFloat, `numpy.tan
{counted_float-1.1.0 → counted_float-1.1.1}/counted_float/__init__.py RENAMED
@@ -1,3 +1,5 @@
1
+ """Top-level public API for flop counting: CountedFloat, FlopCountingContext, and related models."""
2
+
1
3
  import counted_float.benchmarking as benchmarking
2
4
  import counted_float.config as config
3
5
 
@@ -5,8 +7,6 @@ from ._core.counting import BuiltInData, CountedFloat, FlopCountingContext, Paus
5
7
  from ._core.models import FlopCounts, FlopType, FlopWeights, Quantiles, SystemInfo
6
8
 
7
9
  __all__ = [
8
- "benchmarking",
9
- "config",
10
10
  "CountedFloat",
11
11
  "FlopCountingContext",
12
12
  "FlopCounts",
@@ -15,4 +15,6 @@ __all__ = [
15
15
  "PauseFlopCounting",
16
16
  "Quantiles",
17
17
  "SystemInfo",
18
+ "benchmarking",
19
+ "config",
18
20
  ]
{counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/_cli.py RENAMED
@@ -8,23 +8,23 @@ from counted_float._core.benchmarking import run_counted_float_benchmark, run_fl
8
8
  # Commands
9
9
  # -------------------------------------------------------------------------
10
10
  @click.group()
11
- def cli():
11
+ def cli() -> None:
12
12
  pass
13
13
 
14
14
 
15
15
  @cli.command(short_help="run flop benchmarks")
16
- def benchmark():
16
+ def benchmark() -> None:
17
17
  result = run_flops_benchmark()
18
18
  result.show()
19
19
 
20
20
 
21
21
  @cli.command(short_help="show all built-in data")
22
22
  @click.option("--key_filter", default="", help="Optional key filter for built-in data")
23
- def show_data(key_filter: str):
23
+ def show_data(key_filter: str) -> None:
24
24
  BuiltInData.show(key_filter=key_filter)
25
25
 
26
26
 
27
27
  @cli.command(short_help="run benchmark of float vs CountedFloat performance")
28
- def benchmark_counted_float():
28
+ def benchmark_counted_float() -> None:
29
29
  result = run_counted_float_benchmark()
30
30
  result.show()
{counted_float-1.1.0 → counted_float-1.1.1}/counted_float/_core/benchmarking/__init__.py RENAMED
@@ -4,7 +4,6 @@ from .flops import FlopsBenchmarkResults, FlopsBenchmarkSuite
4
4
 
5
5
  def run_flops_benchmark(n_seconds_per_run_target: float = 0.1) -> FlopsBenchmarkResults:
6
6
  """Run the flops benchmark suite with default settings returns a FlopsBenchmarkResults object."""
7
-
8
7
  benchmark_results = FlopsBenchmarkSuite().run(n_seconds_per_run_target=n_seconds_per_run_target)
9
8
 
10
9
  print()