counted-float 1.0.0__tar.gz → 1.0.2__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-1.0.0 → counted_float-1.0.2}/PKG-INFO +117 -98
- {counted_float-1.0.0 → counted_float-1.0.2}/README.md +116 -97
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/counting/_builtin_data.py +7 -6
- {counted_float-1.0.0 → counted_float-1.0.2}/pyproject.toml +1 -1
- {counted_float-1.0.0 → counted_float-1.0.2}/.gitignore +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/LICENSE +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/__init__.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/__init__.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/_cli.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/benchmarking/__init__.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/benchmarking/counted_float/__init__.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/benchmarking/counted_float/_counted_float_benchmark.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/benchmarking/flops/__init__.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/benchmarking/flops/_array_generator.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/benchmarking/flops/_flops_benchmark_suite.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/benchmarking/flops/_flops_micro_benchmark.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/benchmarking/micro/__init__.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/benchmarking/micro/_micro_benchmark.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/compatibility/__init__.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/compatibility/_numba.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/counting/__init__.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/counting/_context_managers.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/counting/_counted_float.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/counting/_global_counter.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/counting/config/__init__.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/counting/config/_config.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/counting/config/_defaults.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/models/__init__.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/models/_base.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/models/_flop_counts.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/models/_flop_type.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/models/_flop_weights.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/models/_flops_benchmark_meta_data.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/models/_flops_benchmark_result.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/models/_flops_benchmark_type.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/models/_instruction_latencies.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/models/_micro_benchmark_result.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/utils/__init__.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/utils/_cpu_freq.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/utils/_formatting.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/utils/_geo_mean.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/utils/_latency.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/utils/_missing_data.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/utils/_rounding.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/utils/_timer.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/benchmarking/__init__.py +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/config/__init__.py +0 -0
- /counted_float-1.0.0/counted_float/data/arm/v8_x/benchmarks/gh_apple_m1.json → /counted_float-1.0.2/counted_float/data/arm/v8_x/benchmarks/apple_m1_github_actions.json +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/data/arm/v8_x/benchmarks/apple_m3_max_mbp16.json +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/data/arm/v8_x/benchmarks/apple_m3_mba15.json +0 -0
- /counted_float-1.0.0/counted_float/data/arm/v8_x/benchmarks/ec2_m6g_xlarge_graviton_2_neoverse_n1.json → /counted_float-1.0.2/counted_float/data/arm/v8_x/benchmarks/aws_graviton_2_neoverse_n1_ec2_m6g_xlarge.json +0 -0
- /counted_float-1.0.0/counted_float/data/arm/v8_x/benchmarks/ec2_m7g_xlarge_graviton_3_neoverse_v1.json → /counted_float-1.0.2/counted_float/data/arm/v8_x/benchmarks/aws_graviton_3_neoverse_v1_ec2_m7g_xlarge.json +0 -0
- /counted_float-1.0.0/counted_float/data/arm/v8_x/specs/arm_v8_cortex_a76.json → /counted_float-1.0.2/counted_float/data/arm/v8_x/specs/arm_cortex_a76.json +0 -0
- /counted_float-1.0.0/counted_float/data/arm/v8_x/specs/arm_v9_cortex_x1.json → /counted_float-1.0.2/counted_float/data/arm/v8_x/specs/arm_cortex_x1.json +0 -0
- /counted_float-1.0.0/counted_float/data/arm/v8_x/specs/arm_v9_neoverse_n1.json → /counted_float-1.0.2/counted_float/data/arm/v8_x/specs/arm_neoverse_n1.json +0 -0
- /counted_float-1.0.0/counted_float/data/arm/v8_x/specs/arm_v9_neoverse_v1.json → /counted_float-1.0.2/counted_float/data/arm/v8_x/specs/arm_neoverse_v1.json +0 -0
- /counted_float-1.0.0/counted_float/data/arm/v9_0/benchmarks/ec2_m8g_xlarge_graviton_4_neoverse_v2.json → /counted_float-1.0.2/counted_float/data/arm/v9_0/benchmarks/aws_graviton_4_neoverse_v2_ec2_m8g_xlarge.json +0 -0
- /counted_float-1.0.0/counted_float/data/arm/v9_0/benchmarks/gh_azure_cobalt_100_neoverse_n2.json → /counted_float-1.0.2/counted_float/data/arm/v9_0/benchmarks/azure_cobalt_100_neoverse_n2_github_actions.json +0 -0
- /counted_float-1.0.0/counted_float/data/arm/v9_0/specs/arm_v9_cortex_x2.json → /counted_float-1.0.2/counted_float/data/arm/v9_0/specs/arm_cortex_x2.json +0 -0
- /counted_float-1.0.0/counted_float/data/arm/v9_0/specs/arm_v9_cortex_x3.json → /counted_float-1.0.2/counted_float/data/arm/v9_0/specs/arm_cortex_x3.json +0 -0
- /counted_float-1.0.0/counted_float/data/arm/v9_0/specs/arm_v9_neoverse_n2.json → /counted_float-1.0.2/counted_float/data/arm/v9_0/specs/arm_neoverse_n2.json +0 -0
- /counted_float-1.0.0/counted_float/data/arm/v9_0/specs/arm_v9_neoverse_v2.json → /counted_float-1.0.2/counted_float/data/arm/v9_0/specs/arm_neoverse_v2.json +0 -0
- {counted_float-1.0.0 → counted_float-1.0.2}/counted_float/data/arm/v9_2/benchmarks/apple_m4_pro_mbp16.json +0 -0
- /counted_float-1.0.0/counted_float/data/arm/v9_2/specs/arm_v9_cortex_x4.json → /counted_float-1.0.2/counted_float/data/arm/v9_2/specs/arm_cortex_x4.json +0 -0
- /counted_float-1.0.0/counted_float/data/arm/v9_2/specs/arm_v9_cortex_x925.json → /counted_float-1.0.2/counted_float/data/arm/v9_2/specs/arm_cortex_x925.json +0 -0
- /counted_float-1.0.0/counted_float/data/arm/v9_2/specs/arm_v9_neoverse_v3.json → /counted_float-1.0.2/counted_float/data/arm/v9_2/specs/arm_neoverse_v3.json +0 -0
- /counted_float-1.0.0/counted_float/data/x86/amd/2017_zen1/benchmark_ryzen_1700x.json → /counted_float-1.0.2/counted_float/data/x86/amd/2017_zen1/benchmarks/amd_ryzen_1700x.json +0 -0
- {counted_float-1.0.0/counted_float/data/x86/amd/2017_zen1 → counted_float-1.0.2/counted_float/data/x86/amd/2017_zen1/other}/analysis_uops_info_zen1+.json +0 -0
- /counted_float-1.0.0/counted_float/data/x86/amd/2020_zen3/benchmark_gh_amd_epyc_7763_linux.json → /counted_float-1.0.2/counted_float/data/x86/amd/2020_zen3/benchmark/amd_epyc_7763_linux_github.json +0 -0
- /counted_float-1.0.0/counted_float/data/x86/amd/2020_zen3/benchmark_gh_amd_epyc_7763_windows.json → /counted_float-1.0.2/counted_float/data/x86/amd/2020_zen3/benchmark/amd_epyc_7763_windows_github.json +0 -0
- {counted_float-1.0.0/counted_float/data/x86/amd/2020_zen3 → counted_float-1.0.2/counted_float/data/x86/amd/2020_zen3/other}/analysis_agner_fog_r7_5800x.json +0 -0
- {counted_float-1.0.0/counted_float/data/x86/amd/2020_zen3 → counted_float-1.0.2/counted_float/data/x86/amd/2020_zen3/other}/analysis_uops_info_zen3.json +0 -0
- /counted_float-1.0.0/counted_float/data/x86/amd/2022_zen4/benchmark_ec2_m7a_xlarge_zen4.json → /counted_float-1.0.2/counted_float/data/x86/amd/2022_zen4/benchmark/amd_epyc_9r14_ec2_m7a_xlarge.json +0 -0
- {counted_float-1.0.0/counted_float/data/x86/amd/2022_zen4 → counted_float-1.0.2/counted_float/data/x86/amd/2022_zen4/other}/analysis_agner_fog_r9_7900x.json +0 -0
- {counted_float-1.0.0/counted_float/data/x86/amd/2022_zen4 → counted_float-1.0.2/counted_float/data/x86/amd/2022_zen4/other}/analysis_uops_info_zen4.json +0 -0
- {counted_float-1.0.0/counted_float/data/x86/amd/2022_zen4 → counted_float-1.0.2/counted_float/data/x86/amd/2022_zen4/other}/specs_amd.json +0 -0
- /counted_float-1.0.0/counted_float/data/x86/amd/2024_zen5/benchmark_ec2_m8a_xlarge_zen5.json → /counted_float-1.0.2/counted_float/data/x86/amd/2024_zen5/benchmark/amd_epyc_9r45_ec2_m8a_xlarge.json +0 -0
- {counted_float-1.0.0/counted_float/data/x86/amd/2024_zen5 → counted_float-1.0.2/counted_float/data/x86/amd/2024_zen5/other}/analysis_agner_fog_r7_9800x3d.json +0 -0
- {counted_float-1.0.0/counted_float/data/x86/amd/2024_zen5 → counted_float-1.0.2/counted_float/data/x86/amd/2024_zen5/other}/specs_amd.json +0 -0
- /counted_float-1.0.0/counted_float/data/x86/intel/2017_coffee_lake_gen_8/benchmark_intel_i7_8550U_windows.json → /counted_float-1.0.2/counted_float/data/x86/intel/2017_coffee_lake_gen_8/benchmarks/intel_i7_8550U_windows.json +0 -0
- /counted_float-1.0.0/counted_float/data/x86/intel/2017_coffee_lake_gen_8/benchmark_gh_intel_i7_8700B_macos.json → /counted_float-1.0.2/counted_float/data/x86/intel/2017_coffee_lake_gen_8/benchmarks/intel_i7_8700B_macos_github_actions.json +0 -0
- {counted_float-1.0.0/counted_float/data/x86/intel/2017_coffee_lake_gen_8 → counted_float-1.0.2/counted_float/data/x86/intel/2017_coffee_lake_gen_8/other}/analysis_agner_fog_coffee_lake.json +0 -0
- {counted_float-1.0.0/counted_float/data/x86/intel/2017_coffee_lake_gen_8 → counted_float-1.0.2/counted_float/data/x86/intel/2017_coffee_lake_gen_8/other}/analysis_uops_info_coffee_lake.json +0 -0
- /counted_float-1.0.0/counted_float/data/x86/intel/2019_sunny_cove_gen_10/benchmark_ec2_m6i_xlarge_ice_lake.json → /counted_float-1.0.2/counted_float/data/x86/intel/2019_sunny_cove_gen_10/benchmarks/intel_xeon_8375c_ice_lake_ec2_m6i_xlarge.json +0 -0
- {counted_float-1.0.0/counted_float/data/x86/intel/2019_sunny_cove_gen_10 → counted_float-1.0.2/counted_float/data/x86/intel/2019_sunny_cove_gen_10/other}/analysis_agner_fog_ice_lake.json +0 -0
- {counted_float-1.0.0/counted_float/data/x86/intel/2019_sunny_cove_gen_10 → counted_float-1.0.2/counted_float/data/x86/intel/2019_sunny_cove_gen_10/other}/analysis_uops_info_ice_lake.json +0 -0
- {counted_float-1.0.0/counted_float/data/x86/intel/2019_sunny_cove_gen_10 → counted_float-1.0.2/counted_float/data/x86/intel/2019_sunny_cove_gen_10/other}/analysis_uops_info_tiger_lake.json +0 -0
- /counted_float-1.0.0/counted_float/data/x86/intel/2021_golden_cove_gen_12/benchmark_ec2_m7i_xlarge_sapphire_rapids.json → /counted_float-1.0.2/counted_float/data/x86/intel/2021_golden_cove_gen_12/benchmarks/intel_xeon_8488c_sapphire_rapids_ec2_m7i_xlarge.json +0 -0
- {counted_float-1.0.0/counted_float/data/x86/intel/2021_golden_cove_gen_12 → counted_float-1.0.2/counted_float/data/x86/intel/2021_golden_cove_gen_12/other}/analysis_uops_info_alder_lake_p.json +0 -0
- {counted_float-1.0.0/counted_float/data/x86/intel/2021_golden_cove_gen_12 → counted_float-1.0.2/counted_float/data/x86/intel/2021_golden_cove_gen_12/other}/specs_intel.json +0 -0
- /counted_float-1.0.0/counted_float/data/x86/intel/2022_raptor_cove_gen_13_14/benchmark_ec2_i7i_xlarge_emerald_rapids.json → /counted_float-1.0.2/counted_float/data/x86/intel/2022_raptor_cove_gen_13_14/benchmarks/intel_xeon_8559c_emerald_rapids_ec2_i7i_xlarge.json +0 -0
- {counted_float-1.0.0/counted_float/data/x86/intel/2022_raptor_cove_gen_13_14 → counted_float-1.0.2/counted_float/data/x86/intel/2022_raptor_cove_gen_13_14/other}/specs_intel.json +0 -0
- /counted_float-1.0.0/counted_float/data/x86/intel/2023_redwood_cove_ultra_1/benchmark_ec2_m8i_xlarge_granite_rapids.json → /counted_float-1.0.2/counted_float/data/x86/intel/2023_redwood_cove_ultra_1/benchmarks/intel_xeon_6975p_granite_rapids_ec2_m8i_xlarge.json +0 -0
- {counted_float-1.0.0/counted_float/data/x86/intel/2023_redwood_cove_ultra_1 → counted_float-1.0.2/counted_float/data/x86/intel/2023_redwood_cove_ultra_1/other}/specs_intel.json +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: counted-float
|
|
3
|
-
Version: 1.0.
|
|
3
|
+
Version: 1.0.2
|
|
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
|
|
@@ -175,9 +175,9 @@ rationale behind choice of data sources and methodology.
|
|
|
175
175
|
FlopType.SQRT [sqrt(x)] : 7.50000
|
|
176
176
|
FlopType.EXP2 [2^x] : 16.00000
|
|
177
177
|
FlopType.EXP [e^x] : 18.00000
|
|
178
|
-
FlopType.LOG [log(x)] :
|
|
178
|
+
FlopType.LOG [log(x)] : 18.00000
|
|
179
|
+
FlopType.EXP10 [10^x] : 22.00000
|
|
179
180
|
FlopType.LOG2 [log2(x)] : 22.00000
|
|
180
|
-
FlopType.EXP10 [10^x] : 24.00000
|
|
181
181
|
FlopType.LOG10 [log10(x)] : 24.00000
|
|
182
182
|
FlopType.COS [cos(x)] : 30.00000
|
|
183
183
|
FlopType.SIN [sin(x)] : 30.00000
|
|
@@ -235,28 +235,28 @@ from counted_float.config import get_default_consensus_flop_weights
|
|
|
235
235
|
>>> get_default_consensus_flop_weights(rounding_mode=None).show()
|
|
236
236
|
|
|
237
237
|
{
|
|
238
|
-
FlopType.MINUS [-x] : 0.
|
|
239
|
-
FlopType.ABS [abs(x)] : 0.
|
|
240
|
-
FlopType.COMP [x<=y] : 0.
|
|
241
|
-
FlopType.SUB [x-y] : 0.
|
|
238
|
+
FlopType.MINUS [-x] : 0.43688
|
|
239
|
+
FlopType.ABS [abs(x)] : 0.71585
|
|
240
|
+
FlopType.COMP [x<=y] : 0.97866
|
|
241
|
+
FlopType.SUB [x-y] : 0.99565
|
|
242
242
|
FlopType.ADD [x+y] : 1.00000
|
|
243
|
-
FlopType.MUL [x*y] : 1.
|
|
244
|
-
FlopType.RND [round] : 1.
|
|
245
|
-
FlopType.F2I [float->int] : 1.
|
|
246
|
-
FlopType.I2F [int->float] : 1.
|
|
247
|
-
FlopType.DIV [x/y] : 5.
|
|
248
|
-
FlopType.SQRT [sqrt(x)] : 7.
|
|
249
|
-
FlopType.EXP2 [2^x] : 15.
|
|
250
|
-
FlopType.EXP [e^x] : 17.
|
|
251
|
-
FlopType.LOG [log(x)] :
|
|
252
|
-
FlopType.LOG2 [log2(x)] : 22.
|
|
253
|
-
FlopType.EXP10 [10^x] :
|
|
254
|
-
FlopType.LOG10 [log10(x)] : 24.
|
|
255
|
-
FlopType.SIN [sin(x)] : 30.
|
|
256
|
-
FlopType.COS [cos(x)] : 31.
|
|
257
|
-
FlopType.POW [x^y] : 41.
|
|
258
|
-
FlopType.TAN [tan(x)] :
|
|
259
|
-
FlopType.CBRT [cbrt(x)] : 44.
|
|
243
|
+
FlopType.MUL [x*y] : 1.39506
|
|
244
|
+
FlopType.RND [round] : 1.78130
|
|
245
|
+
FlopType.F2I [float->int] : 1.91125
|
|
246
|
+
FlopType.I2F [int->float] : 1.91839
|
|
247
|
+
FlopType.DIV [x/y] : 5.53385
|
|
248
|
+
FlopType.SQRT [sqrt(x)] : 7.37309
|
|
249
|
+
FlopType.EXP2 [2^x] : 15.79616
|
|
250
|
+
FlopType.EXP [e^x] : 17.45201
|
|
251
|
+
FlopType.LOG [log(x)] : 18.93143
|
|
252
|
+
FlopType.LOG2 [log2(x)] : 22.29433
|
|
253
|
+
FlopType.EXP10 [10^x] : 22.93876
|
|
254
|
+
FlopType.LOG10 [log10(x)] : 24.56277
|
|
255
|
+
FlopType.SIN [sin(x)] : 30.28970
|
|
256
|
+
FlopType.COS [cos(x)] : 31.27413
|
|
257
|
+
FlopType.POW [x^y] : 41.65022
|
|
258
|
+
FlopType.TAN [tan(x)] : 41.99495
|
|
259
|
+
FlopType.CBRT [cbrt(x)] : 44.15405
|
|
260
260
|
}
|
|
261
261
|
```
|
|
262
262
|
There are 3 rounding modes:
|
|
@@ -393,78 +393,97 @@ after which the results will be shown as .json.
|
|
|
393
393
|
|
|
394
394
|
```
|
|
395
395
|
[~] counted_float show-data
|
|
396
|
-
|
|
397
|
-
ALL
|
|
398
|
-
├─arm
|
|
399
|
-
│ ├─v8_x
|
|
400
|
-
│ │ ├─benchmarks
|
|
401
|
-
│ │ │ ├─
|
|
402
|
-
│ │ │ ├─
|
|
403
|
-
│ │ │ ├─
|
|
404
|
-
│ │ │ ├─
|
|
405
|
-
│ │ │ └─
|
|
406
|
-
│ │ └─specs
|
|
407
|
-
│ │ ├─
|
|
408
|
-
│ │ ├─
|
|
409
|
-
│ │ ├─
|
|
410
|
-
│ │ └─
|
|
411
|
-
│ ├─v9_0
|
|
412
|
-
│ │ ├─benchmarks
|
|
413
|
-
│ │ │ ├─
|
|
414
|
-
│ │ │ └─
|
|
415
|
-
│ │ └─specs
|
|
416
|
-
│ │ ├─
|
|
417
|
-
│ │ ├─
|
|
418
|
-
│ │ ├─
|
|
419
|
-
│ │ └─
|
|
420
|
-
│ └─v9_2
|
|
421
|
-
│ ├─benchmarks
|
|
422
|
-
│ │ └─apple_m4_pro_mbp16
|
|
423
|
-
│ └─specs
|
|
424
|
-
│ ├─
|
|
425
|
-
│ ├─
|
|
426
|
-
│ └─
|
|
427
|
-
└─x86
|
|
428
|
-
├─amd
|
|
429
|
-
│ ├─2017_zen1
|
|
430
|
-
│ │ ├─
|
|
431
|
-
│ │ └─
|
|
432
|
-
│
|
|
433
|
-
│ │
|
|
434
|
-
│
|
|
435
|
-
│ │ ├─
|
|
436
|
-
│ │
|
|
437
|
-
│
|
|
438
|
-
│ │
|
|
439
|
-
│ │
|
|
440
|
-
│ │
|
|
441
|
-
│
|
|
442
|
-
│
|
|
443
|
-
│
|
|
444
|
-
│
|
|
445
|
-
│
|
|
446
|
-
|
|
447
|
-
|
|
448
|
-
|
|
449
|
-
|
|
450
|
-
|
|
451
|
-
|
|
452
|
-
|
|
453
|
-
|
|
454
|
-
|
|
455
|
-
|
|
456
|
-
│
|
|
457
|
-
├─
|
|
458
|
-
│
|
|
459
|
-
│
|
|
460
|
-
│
|
|
461
|
-
|
|
462
|
-
|
|
463
|
-
│
|
|
464
|
-
└─
|
|
465
|
-
|
|
466
|
-
|
|
396
|
+
MINUS ABS COMP SUB ADD MUL RND F2I I2F DIV SQRT EXP2 EXP LOG LOG2 EXP10 LOG10 SIN COS POW TAN CBRT
|
|
397
|
+
ALL 0.44 0.72 0.98 1.00 1.00 1.40 1.78 1.91 1.92 5.53 7.37 15.80 17.45 18.93 22.29 22.94 24.56 30.29 31.27 41.65 41.99 44.15
|
|
398
|
+
├─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
|
|
399
|
+
│ ├─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
|
|
400
|
+
│ │ ├─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
|
|
401
|
+
│ │ │ ├─apple_m1_github_actions 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
|
|
402
|
+
│ │ │ ├─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
|
|
403
|
+
│ │ │ ├─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
|
|
404
|
+
│ │ │ ├─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
|
|
405
|
+
│ │ │ └─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
|
|
406
|
+
│ │ └─specs 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.73 2.12 7.50 8.25 / / / / / / / / / / /
|
|
407
|
+
│ │ ├─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 / / / / / / / / / / /
|
|
408
|
+
│ │ ├─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 / / / / / / / / / / /
|
|
409
|
+
│ │ ├─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 / / / / / / / / / / /
|
|
410
|
+
│ │ └─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 / / / / / / / / / / /
|
|
411
|
+
│ ├─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
|
|
412
|
+
│ │ ├─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
|
|
413
|
+
│ │ │ ├─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
|
|
414
|
+
│ │ │ └─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
|
|
415
|
+
│ │ └─specs 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
|
|
416
|
+
│ │ ├─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 / / / / / / / / / / /
|
|
417
|
+
│ │ ├─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 / / / / / / / / / / /
|
|
418
|
+
│ │ ├─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 / / / / / / / / / / /
|
|
419
|
+
│ │ └─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 / / / / / / / / / / /
|
|
420
|
+
│ └─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
|
|
421
|
+
│ ├─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
|
|
422
|
+
│ │ └─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
|
|
423
|
+
│ └─specs 1.00 1.00 1.00 1.00 1.00 1.50 1.31 1.50 1.50 6.33 6.33 / / / / / / / / / / /
|
|
424
|
+
│ ├─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 / / / / / / / / / / /
|
|
425
|
+
│ ├─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 / / / / / / / / / / /
|
|
426
|
+
│ └─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 / / / / / / / / / / /
|
|
427
|
+
└─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
|
|
428
|
+
├─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
|
|
429
|
+
│ ├─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
|
|
430
|
+
│ │ ├─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
|
|
431
|
+
│ │ │ └─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
|
|
432
|
+
│ │ └─other 0.33 0.33 2.33 1.00 1.00 1.33 1.33 3.33 3.33 4.33 6.67 / / / / / / / / / / /
|
|
433
|
+
│ │ └─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 / / / / / / / / / / /
|
|
434
|
+
│ ├─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
|
|
435
|
+
│ │ ├─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
|
|
436
|
+
│ │ │ ├─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
|
|
437
|
+
│ │ │ └─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
|
|
438
|
+
│ │ └─other 0.33 0.33 1.97 1.00 1.00 0.95 1.00 2.45 2.65 4.42 6.67 / / / / / / / / / / /
|
|
439
|
+
│ │ ├─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 / / / / / / / / / / /
|
|
440
|
+
│ │ └─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 / / / / / / / / / / /
|
|
441
|
+
│ ├─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
|
|
442
|
+
│ │ ├─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
|
|
443
|
+
│ │ │ └─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
|
|
444
|
+
│ │ └─other 0.33 0.33 1.28 1.00 1.00 1.01 1.00 2.00 1.92 4.33 6.89 / / / / / / / / / / /
|
|
445
|
+
│ │ ├─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 / / / / / / / / / / /
|
|
446
|
+
│ │ ├─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 / / / / / / / / / / /
|
|
447
|
+
│ │ └─specs_amd 0.33 0.33 0.67 1.00 1.00 1.00 1.00 1.33 1.33 4.33 6.67 / / / / / / / / / / /
|
|
448
|
+
│ └─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
|
|
449
|
+
│ ├─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
|
|
450
|
+
│ │ └─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
|
|
451
|
+
│ └─other 0.71 0.71 2.72 1.00 1.00 1.66 1.50 2.72 3.17 6.50 10.00 / / / / / / / / / / /
|
|
452
|
+
│ ├─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 / / / / / / / / / / /
|
|
453
|
+
│ └─specs_amd 0.50 0.50 / 1.00 1.00 1.50 1.50 / / 6.50 10.00 / / / / / / / / / / /
|
|
454
|
+
└─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
|
|
455
|
+
├─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
|
|
456
|
+
│ ├─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
|
|
457
|
+
│ │ ├─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
|
|
458
|
+
│ │ └─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
|
|
459
|
+
│ └─other 0.25 0.25 0.73 1.00 1.00 1.00 2.00 1.62 1.62 3.62 4.36 / / / / / / / / / / /
|
|
460
|
+
│ ├─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 / / / / / / / / / / /
|
|
461
|
+
│ └─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 / / / / / / / / / / /
|
|
462
|
+
├─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
|
|
463
|
+
│ ├─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
|
|
464
|
+
│ │ └─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
|
|
465
|
+
│ └─other 0.25 0.25 0.66 1.00 1.00 0.97 2.00 1.66 1.66 3.66 4.49 / / / / / / / / / / /
|
|
466
|
+
│ ├─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 / / / / / / / / / / /
|
|
467
|
+
│ ├─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 / / / / / / / / / / /
|
|
468
|
+
│ └─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 / / / / / / / / / / /
|
|
469
|
+
├─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
|
|
470
|
+
│ ├─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
|
|
471
|
+
│ │ └─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
|
|
472
|
+
│ └─other 0.41 0.41 1.22 1.00 1.00 1.63 3.27 2.86 2.42 5.92 7.55 / / / / / / / / / / /
|
|
473
|
+
│ ├─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 / / / / / / / / / / /
|
|
474
|
+
│ └─specs_intel 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
|
|
475
|
+
├─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
|
|
476
|
+
│ ├─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
|
|
477
|
+
│ │ └─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
|
|
478
|
+
│ └─other 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
|
|
479
|
+
│ └─specs_intel 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
|
|
480
|
+
└─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
|
|
481
|
+
├─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
|
|
482
|
+
│ └─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
|
|
483
|
+
└─other 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
|
|
484
|
+
└─specs_intel 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
|
|
467
485
|
|
|
486
|
+
|
|
468
487
|
```
|
|
469
488
|
|
|
470
489
|
## 4.2. Test performance of `CountedFloat` vs `float`
|
|
@@ -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
|
|
@@ -154,9 +154,9 @@ rationale behind choice of data sources and methodology.
|
|
|
154
154
|
FlopType.SQRT [sqrt(x)] : 7.50000
|
|
155
155
|
FlopType.EXP2 [2^x] : 16.00000
|
|
156
156
|
FlopType.EXP [e^x] : 18.00000
|
|
157
|
-
FlopType.LOG [log(x)] :
|
|
157
|
+
FlopType.LOG [log(x)] : 18.00000
|
|
158
|
+
FlopType.EXP10 [10^x] : 22.00000
|
|
158
159
|
FlopType.LOG2 [log2(x)] : 22.00000
|
|
159
|
-
FlopType.EXP10 [10^x] : 24.00000
|
|
160
160
|
FlopType.LOG10 [log10(x)] : 24.00000
|
|
161
161
|
FlopType.COS [cos(x)] : 30.00000
|
|
162
162
|
FlopType.SIN [sin(x)] : 30.00000
|
|
@@ -214,28 +214,28 @@ from counted_float.config import get_default_consensus_flop_weights
|
|
|
214
214
|
>>> get_default_consensus_flop_weights(rounding_mode=None).show()
|
|
215
215
|
|
|
216
216
|
{
|
|
217
|
-
FlopType.MINUS [-x] : 0.
|
|
218
|
-
FlopType.ABS [abs(x)] : 0.
|
|
219
|
-
FlopType.COMP [x<=y] : 0.
|
|
220
|
-
FlopType.SUB [x-y] : 0.
|
|
217
|
+
FlopType.MINUS [-x] : 0.43688
|
|
218
|
+
FlopType.ABS [abs(x)] : 0.71585
|
|
219
|
+
FlopType.COMP [x<=y] : 0.97866
|
|
220
|
+
FlopType.SUB [x-y] : 0.99565
|
|
221
221
|
FlopType.ADD [x+y] : 1.00000
|
|
222
|
-
FlopType.MUL [x*y] : 1.
|
|
223
|
-
FlopType.RND [round] : 1.
|
|
224
|
-
FlopType.F2I [float->int] : 1.
|
|
225
|
-
FlopType.I2F [int->float] : 1.
|
|
226
|
-
FlopType.DIV [x/y] : 5.
|
|
227
|
-
FlopType.SQRT [sqrt(x)] : 7.
|
|
228
|
-
FlopType.EXP2 [2^x] : 15.
|
|
229
|
-
FlopType.EXP [e^x] : 17.
|
|
230
|
-
FlopType.LOG [log(x)] :
|
|
231
|
-
FlopType.LOG2 [log2(x)] : 22.
|
|
232
|
-
FlopType.EXP10 [10^x] :
|
|
233
|
-
FlopType.LOG10 [log10(x)] : 24.
|
|
234
|
-
FlopType.SIN [sin(x)] : 30.
|
|
235
|
-
FlopType.COS [cos(x)] : 31.
|
|
236
|
-
FlopType.POW [x^y] : 41.
|
|
237
|
-
FlopType.TAN [tan(x)] :
|
|
238
|
-
FlopType.CBRT [cbrt(x)] : 44.
|
|
222
|
+
FlopType.MUL [x*y] : 1.39506
|
|
223
|
+
FlopType.RND [round] : 1.78130
|
|
224
|
+
FlopType.F2I [float->int] : 1.91125
|
|
225
|
+
FlopType.I2F [int->float] : 1.91839
|
|
226
|
+
FlopType.DIV [x/y] : 5.53385
|
|
227
|
+
FlopType.SQRT [sqrt(x)] : 7.37309
|
|
228
|
+
FlopType.EXP2 [2^x] : 15.79616
|
|
229
|
+
FlopType.EXP [e^x] : 17.45201
|
|
230
|
+
FlopType.LOG [log(x)] : 18.93143
|
|
231
|
+
FlopType.LOG2 [log2(x)] : 22.29433
|
|
232
|
+
FlopType.EXP10 [10^x] : 22.93876
|
|
233
|
+
FlopType.LOG10 [log10(x)] : 24.56277
|
|
234
|
+
FlopType.SIN [sin(x)] : 30.28970
|
|
235
|
+
FlopType.COS [cos(x)] : 31.27413
|
|
236
|
+
FlopType.POW [x^y] : 41.65022
|
|
237
|
+
FlopType.TAN [tan(x)] : 41.99495
|
|
238
|
+
FlopType.CBRT [cbrt(x)] : 44.15405
|
|
239
239
|
}
|
|
240
240
|
```
|
|
241
241
|
There are 3 rounding modes:
|
|
@@ -372,78 +372,97 @@ after which the results will be shown as .json.
|
|
|
372
372
|
|
|
373
373
|
```
|
|
374
374
|
[~] counted_float show-data
|
|
375
|
-
|
|
376
|
-
ALL
|
|
377
|
-
├─arm
|
|
378
|
-
│ ├─v8_x
|
|
379
|
-
│ │ ├─benchmarks
|
|
380
|
-
│ │ │ ├─
|
|
381
|
-
│ │ │ ├─
|
|
382
|
-
│ │ │ ├─
|
|
383
|
-
│ │ │ ├─
|
|
384
|
-
│ │ │ └─
|
|
385
|
-
│ │ └─specs
|
|
386
|
-
│ │ ├─
|
|
387
|
-
│ │ ├─
|
|
388
|
-
│ │ ├─
|
|
389
|
-
│ │ └─
|
|
390
|
-
│ ├─v9_0
|
|
391
|
-
│ │ ├─benchmarks
|
|
392
|
-
│ │ │ ├─
|
|
393
|
-
│ │ │ └─
|
|
394
|
-
│ │ └─specs
|
|
395
|
-
│ │ ├─
|
|
396
|
-
│ │ ├─
|
|
397
|
-
│ │ ├─
|
|
398
|
-
│ │ └─
|
|
399
|
-
│ └─v9_2
|
|
400
|
-
│ ├─benchmarks
|
|
401
|
-
│ │ └─apple_m4_pro_mbp16
|
|
402
|
-
│ └─specs
|
|
403
|
-
│ ├─
|
|
404
|
-
│ ├─
|
|
405
|
-
│ └─
|
|
406
|
-
└─x86
|
|
407
|
-
├─amd
|
|
408
|
-
│ ├─2017_zen1
|
|
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
|
-
│
|
|
439
|
-
│
|
|
440
|
-
|
|
441
|
-
|
|
442
|
-
│
|
|
443
|
-
└─
|
|
444
|
-
|
|
445
|
-
|
|
375
|
+
MINUS ABS COMP SUB ADD MUL RND F2I I2F DIV SQRT EXP2 EXP LOG LOG2 EXP10 LOG10 SIN COS POW TAN CBRT
|
|
376
|
+
ALL 0.44 0.72 0.98 1.00 1.00 1.40 1.78 1.91 1.92 5.53 7.37 15.80 17.45 18.93 22.29 22.94 24.56 30.29 31.27 41.65 41.99 44.15
|
|
377
|
+
├─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
|
|
378
|
+
│ ├─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
|
|
379
|
+
│ │ ├─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
|
|
380
|
+
│ │ │ ├─apple_m1_github_actions 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
|
|
381
|
+
│ │ │ ├─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
|
|
382
|
+
│ │ │ ├─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
|
|
383
|
+
│ │ │ ├─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
|
|
384
|
+
│ │ │ └─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
|
|
385
|
+
│ │ └─specs 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.73 2.12 7.50 8.25 / / / / / / / / / / /
|
|
386
|
+
│ │ ├─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 / / / / / / / / / / /
|
|
387
|
+
│ │ ├─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 / / / / / / / / / / /
|
|
388
|
+
│ │ ├─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 / / / / / / / / / / /
|
|
389
|
+
│ │ └─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 / / / / / / / / / / /
|
|
390
|
+
│ ├─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
|
|
391
|
+
│ │ ├─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
|
|
392
|
+
│ │ │ ├─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
|
|
393
|
+
│ │ │ └─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
|
|
394
|
+
│ │ └─specs 1.00 1.00 1.00 1.00 1.00 1.50 1.50 1.50 1.50 7.50 8.00 / / / / / / / / / / /
|
|
395
|
+
│ │ ├─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 / / / / / / / / / / /
|
|
396
|
+
│ │ ├─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 / / / / / / / / / / /
|
|
397
|
+
│ │ ├─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 / / / / / / / / / / /
|
|
398
|
+
│ │ └─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 / / / / / / / / / / /
|
|
399
|
+
│ └─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
|
|
400
|
+
│ ├─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
|
|
401
|
+
│ │ └─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
|
|
402
|
+
│ └─specs 1.00 1.00 1.00 1.00 1.00 1.50 1.31 1.50 1.50 6.33 6.33 / / / / / / / / / / /
|
|
403
|
+
│ ├─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 / / / / / / / / / / /
|
|
404
|
+
│ ├─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 / / / / / / / / / / /
|
|
405
|
+
│ └─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 / / / / / / / / / / /
|
|
406
|
+
└─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
|
|
407
|
+
├─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
|
|
408
|
+
│ ├─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
|
|
409
|
+
│ │ ├─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
|
|
410
|
+
│ │ │ └─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
|
|
411
|
+
│ │ └─other 0.33 0.33 2.33 1.00 1.00 1.33 1.33 3.33 3.33 4.33 6.67 / / / / / / / / / / /
|
|
412
|
+
│ │ └─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 / / / / / / / / / / /
|
|
413
|
+
│ ├─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
|
|
414
|
+
│ │ ├─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
|
|
415
|
+
│ │ │ ├─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
|
|
416
|
+
│ │ │ └─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
|
|
417
|
+
│ │ └─other 0.33 0.33 1.97 1.00 1.00 0.95 1.00 2.45 2.65 4.42 6.67 / / / / / / / / / / /
|
|
418
|
+
│ │ ├─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 / / / / / / / / / / /
|
|
419
|
+
│ │ └─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 / / / / / / / / / / /
|
|
420
|
+
│ ├─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
|
|
421
|
+
│ │ ├─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
|
|
422
|
+
│ │ │ └─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
|
|
423
|
+
│ │ └─other 0.33 0.33 1.28 1.00 1.00 1.01 1.00 2.00 1.92 4.33 6.89 / / / / / / / / / / /
|
|
424
|
+
│ │ ├─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 / / / / / / / / / / /
|
|
425
|
+
│ │ ├─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 / / / / / / / / / / /
|
|
426
|
+
│ │ └─specs_amd 0.33 0.33 0.67 1.00 1.00 1.00 1.00 1.33 1.33 4.33 6.67 / / / / / / / / / / /
|
|
427
|
+
│ └─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
|
|
428
|
+
│ ├─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
|
|
429
|
+
│ │ └─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
|
|
430
|
+
│ └─other 0.71 0.71 2.72 1.00 1.00 1.66 1.50 2.72 3.17 6.50 10.00 / / / / / / / / / / /
|
|
431
|
+
│ ├─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 / / / / / / / / / / /
|
|
432
|
+
│ └─specs_amd 0.50 0.50 / 1.00 1.00 1.50 1.50 / / 6.50 10.00 / / / / / / / / / / /
|
|
433
|
+
└─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
|
|
434
|
+
├─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
|
|
435
|
+
│ ├─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
|
|
436
|
+
│ │ ├─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
|
|
437
|
+
│ │ └─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
|
|
438
|
+
│ └─other 0.25 0.25 0.73 1.00 1.00 1.00 2.00 1.62 1.62 3.62 4.36 / / / / / / / / / / /
|
|
439
|
+
│ ├─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 / / / / / / / / / / /
|
|
440
|
+
│ └─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 / / / / / / / / / / /
|
|
441
|
+
├─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
|
|
442
|
+
│ ├─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
|
|
443
|
+
│ │ └─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
|
|
444
|
+
│ └─other 0.25 0.25 0.66 1.00 1.00 0.97 2.00 1.66 1.66 3.66 4.49 / / / / / / / / / / /
|
|
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
|
+
├─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
|
|
449
|
+
│ ├─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
|
|
450
|
+
│ │ └─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
|
|
451
|
+
│ └─other 0.41 0.41 1.22 1.00 1.00 1.63 3.27 2.86 2.42 5.92 7.55 / / / / / / / / / / /
|
|
452
|
+
│ ├─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 / / / / / / / / / / /
|
|
453
|
+
│ └─specs_intel 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
|
|
454
|
+
├─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
|
|
455
|
+
│ ├─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
|
|
456
|
+
│ │ └─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
|
|
457
|
+
│ └─other 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
|
|
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
|
+
└─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
|
|
460
|
+
├─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
|
|
461
|
+
│ └─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
|
|
462
|
+
└─other 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
|
|
463
|
+
└─specs_intel 0.50 0.50 1.50 1.00 1.00 2.00 4.00 3.50 2.50 7.00 9.00 / / / / / / / / / / /
|
|
446
464
|
|
|
465
|
+
|
|
447
466
|
```
|
|
448
467
|
|
|
449
468
|
## 4.2. Test performance of `CountedFloat` vs `float`
|
|
@@ -240,7 +240,7 @@ class FlopWeightsTreeView:
|
|
|
240
240
|
sorted_flop_types = self.lst_flop_weights[0].get_sorted_flop_types()
|
|
241
241
|
max_indent = max(self.lst_indent)
|
|
242
242
|
|
|
243
|
-
n_cols_per_block = int((console_width - tree_width) / col_width)
|
|
243
|
+
n_cols_per_block = max(1, int((console_width - tree_width) / col_width))
|
|
244
244
|
flop_types_per_block = [
|
|
245
245
|
sorted_flop_types[i_start : i_start + n_cols_per_block]
|
|
246
246
|
for i_start in range(0, len(sorted_flop_types), n_cols_per_block)
|
|
@@ -252,7 +252,7 @@ class FlopWeightsTreeView:
|
|
|
252
252
|
legend = " " * tree_width
|
|
253
253
|
for flop_type in flop_types:
|
|
254
254
|
legend += flop_type.name.rjust(col_width)
|
|
255
|
-
console.print(legend, style="bold
|
|
255
|
+
console.print(legend, style="bold")
|
|
256
256
|
|
|
257
257
|
# --- actual tree view ---
|
|
258
258
|
for indent, is_leaf, tree_str, flop_weights in zip(
|
|
@@ -278,10 +278,11 @@ class FlopWeightsTreeView:
|
|
|
278
278
|
# highlight as bold and with a colored background
|
|
279
279
|
style_tag = [
|
|
280
280
|
"[bold on #888888]", # indent 0
|
|
281
|
-
"[bold on #
|
|
282
|
-
"[bold on #
|
|
283
|
-
"[bold on #ee7777]", # indent 3
|
|
284
|
-
|
|
281
|
+
"[bold on #7777dd]", # indent 1
|
|
282
|
+
"[bold on #77dd77]", # indent 2
|
|
283
|
+
"[bold on #ee7777]", # indent 3
|
|
284
|
+
"[bold italic]", # indent 4+
|
|
285
|
+
][min(indent, 4)]
|
|
285
286
|
line = line[: 3 * indent] + style_tag + line[3 * indent :] + "[/]"
|
|
286
287
|
console.print(line, highlight=False)
|
|
287
288
|
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/benchmarking/flops/__init__.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/benchmarking/micro/__init__.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/counting/_context_managers.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/counting/config/_defaults.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/models/_flops_benchmark_meta_data.py
RENAMED
|
File without changes
|
{counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/models/_flops_benchmark_result.py
RENAMED
|
File without changes
|
{counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/models/_flops_benchmark_type.py
RENAMED
|
File without changes
|
{counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/models/_instruction_latencies.py
RENAMED
|
File without changes
|
{counted_float-1.0.0 → counted_float-1.0.2}/counted_float/_core/models/_micro_benchmark_result.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|