April 12, 2026: AMA Livestream to Celebrate SkatterBencher #100 (Learn More)

SkatterBencher AI Benchmark Leaderboard

The SkatterBencher AI Benchmark leaderboard consists of all benchmark results from SkatterBencher CPU and GPU overclocking guides. You can find more information about how the benchmark is configured below the AI Benchmark leaderboard.

AI Benchmark Leaderboard

SKUTypeOC StrategyBenchmark Score
NVIDIA RTX A5000 LaptopGPUWSL_CUDNN26830
NVIDIA RTX A5000 LaptopGPUWSL_TENSORRT26767
NVIDIA RTX A5000 LaptopGPUWN_DIRECTML26318
NVIDIA RTX A5000 LaptopGPUWSL_DIRECTML23287
Intel Arc A770GPUSB64_OCS416935
Intel Arc A770GPUSB64_OCS316561
NVIDIA GeForce RTX 3050GPUSB62_OCS216418
Intel Arc A770GPUSB64_OCS215972
NVIDIA GeForce RTX 3050GPUSB62_OCS115847
Intel Arc A770GPUSB64_OCS115669
NVIDIA GeForce RTX 3050GPUSB62_OCS315167
NVIDIA GeForce RTX 3050GPUSB62_EVGA14556
Intel Arc A770GPUSB64_Stock14325
NVIDIA GeForce RTX 3050GPUSB62_Stock14209
AMD Ryzen Threadripper Pro 9975WXCPUSB88_OCS314137
AMD Ryzen Threadripper Pro 9975WXCPUSB88_OCS413592
AMD Ryzen Threadripper Pro 9975WXCPUSB88_OCS213447
AMD Ryzen Threadripper Pro 9975WXCPUSB88_OCS112985
AMD Radeon 780MGPUSB70_OCS512738
Intel Xeon 678XCPUSB99_OCS512117
Intel Xeon w7-3465XCPUSB63_OCS412100
Intel Xeon 678XCPUSB99_OCS412054
AMD Ryzen Threadripper Pro 9975WXCPUSB88_Stock11769
AMD Radeon 780MGPUSB70_OCS411705
AMD Radeon 780MGPUSB70_OCS311650
Intel Xeon 678XCPUSB99_OCS311503
Intel Xeon w7-3465XCPUSB63_OCS311431
Intel Xeon 658XCPUSB102_OCS511345
Intel Xeon 658XCPUSB102_OCS411321
Intel Xeon 678XCPUSB99_OCS211272
AMD Radeon 780MGPUSB70_OCS210688
Intel Xeon 658XCPUSB102_OCS310543
AMD Radeon 760GPUSB73_OCS510509
AMD Radeon 780MGPUSB70_OCS110353
Intel Xeon 658XCPUSB102_OCS210069
Intel Xeon 678XCPUSB99_OCS110043
AMD Radeon 780MGPUSB70_Stock9986
AMD Ryzen 9 9950X3DCPUSB85_OCS49819
AMD Radeon 760GPUSB73_OCS49751
AMD Radeon 760GPUSB73_OCS39742
AMD Ryzen 9 9950X3DCPUSB85_OCS39737
AMD Ryzen Threadripper 7960XCPUSB71_OCS49605
Intel Xeon w5-3435XCPUSB61_OCS49591
AMD Ryzen Threadripper 7980XCPUSB66_OCS29567
Intel Xeon w7-2495XCPUSB59_OCS49492
AMD Ryzen Threadripper 7980XCPUSB66_OCS29485
AMD Ryzen Threadripper 7980XCPUSB66_OCS19477
AMD Ryzen Threadripper 7980XCPUSB66_OCS19438
AMD Ryzen Threadripper 7980XCPUSB66_OCS39426
Intel Xeon w7-2495XCPUSB59_OCS29354
AMD Ryzen Threadripper 7960XCPUSB71_OCS39350
AMD Ryzen Threadripper 7980XCPUSB66_Stock9327
Intel Xeon 678XCPUSB99_Stock9308
Intel Xeon w5-3435XCPUSB61_OCS39283
AMD Ryzen Threadripper 7980XCPUSB66_OCS49270
AMD Ryzen 9 9950X3DCPUSB85_OCS29112
Intel Xeon 658XCPUSB102_OCS19044
Intel Xeon w7-2495XCPUSB59_OCS39033
AMD Ryzen Threadripper 7980XCPUSB66_Stock9023
AMD Ryzen 9 9950X3DCPUSB85_OCS59018
Intel Xeon w7-3465XCPUSB63_OCS18988
AMD Ryzen 9 9950X3DCPUSB85_OCS18987
AMD Ryzen 9 9950XCPUSB81_OCS48973
AMD Ryzen 9900XCPUSB92_OCS38875
AMD Ryzen 9 9950XCPUSB81_OCS38867
AMD Ryzen Threadripper 7960XCPUSB71_OCS28840
AMD Ryzen Threadripper 7960XCPUSB71_OCS18798
AMD Radeon 760GPUSB73_OCS28786
AMD Ryzen 9 9900XCPUSB95_OCS58646
Intel Xeon w7-3465XCPUSB63_Stock8599
AMD Ryzen 9 9900XCPUSB95_OCS48571
AMD Ryzen 7 9800X3DCPUSB82_OCS38561
Intel Xeon w5-3435XCPUSB61_OCS28541
AMD Ryzen 7 9800X3DCPUSB82_OCS48522
AMD Ryzen Threadripper 7960XCPUSB71_Stock8501
Intel Xeon 658XCPUSB102_Stock8467
AMD Ryzen 9900XCPUSB92_OCS28419
AMD Ryzen 9 9900XCPUSB96_OCS48411
AMD Ryzen 7 9850X3DCPUSB97_OCS5B8405
AMD Ryzen 9 9900XCPUSB95_OCS38389
AMD Ryzen 9 9950XCPUSB81_OCS28361
AMD Ryzen 7 9700XCPUSB78X_OCS28343
AMD Ryzen 7 9700XCPUSB80_OCS28343
AMD Ryzen 7 9850X3DCPUSB97_OCS48343
AMD Ryzen 9900XCPUSB92_OCS18296
AMD Ryzen 9 9900XCPUSB96_OCS38265
AMD Ryzen 9 9950XCPUSB81_OCS18200
AMD Ryzen 7 9800X3DCPUSB82_OCS28161
AMD Ryzen 7 9850X3DCPUSB97_OCS38151
AMD Ryzen 7 9850X3DCPUSB97_OCS5A8147
AMD Ryzen 9900XCPUSB92_OCS48127
AMD Ryzen 7 9700XCPUSB78X_OCS18119
AMD Ryzen 7 9700XCPUSB80_OCS18119
AMD Ryzen 9 9900XCPUSB95_OCS28104
AMD Radeon 760GPUSB73_OCS18091
AMD Ryzen 7 9700FCPUSB91_OCS48075
AMD Ryzen 7 9700FCPUSB91_OCS38016
Intel Xeon w7-2495XCPUSB59_OCS17988
AMD Ryzen 7 9800X3DCPUSB82_OCS17899
AMD Ryzen 7 9700XCPUSB78_OCS57882
AMD Ryzen 7 9700XCPUSB78_OCS47876
AMD Ryzen 9 9950X3DCPUSB85_Stock7868
AMD Ryzen 7 9850X3DCPUSB97_OCS27856
AMD Ryzen 9 9900XCPUSB95_OCS17832
Intel Core Ultra 7 270K PlusCPUSB101_OCS47601
Intel Xeon w7-2495XCPUSB59_Stock7593
AMD Ryzen 9 9900XCPUSB96_OCS27589
AMD Ryzen 7 9850X3DCPUSB97_OCS17583
Intel Core Ultra 9 285KCPUSB84_OCS67569
AMD Ryzen 9 7950XCPUSB45_OCS57497
AMD Ryzen 9 7950XCPUSB45_OCS37484
AMD Ryzen 7 9700FCPUSB91_OCS27480
Intel Core Ultra 9 285KCPUSB84_OCS57474
AMD Ryzen 9 7950XCPUSB45_OCS47441
AMD Ryzen 7 9700XCPUSB78_OCS37438
Intel Core Ultra 9 285KCPUSB84_OCS47416
AMD Ryzen 9 9900XCPUSB96_OCS17397
AMD Ryzen 9 7950XCPUSB45_OCS27363
AMD Radeon 760GPUSB73_Stock7347
Intel Core Ultra 9 285KCPUSB84_OCS37284
AMD Ryzen 7 9700FCPUSB91_OCS17250
AMD Ryzen 7 9700FCPUSB91_OCS57250
AMD Ryzen 9 9950XCPUSB81_Stock7242
Intel Core Ultra 7 270K PlusCPUSB101_OCS37238
Intel Core Ultra 7 270K PlusCPUSB101_OCS27235
AMD Ryzen 7 9700XCPUSB78_OCS27221
Intel Core Ultra 9 285KCPUSB84_OCS27215
AMD Ryzen 7 9700XCPUSB78_OCS17212
AMD Ryzen 9 7950X3DCPUSB56_OCS27080
AMD Ryzen 7 9800X3DCPUSB82_Stock7069
AMD Ryzen 9 9900XCPUSB95_Stock7062
AMD Ryzen 7 9850X3DCPUSB97_Stock7030
AMD Ryzen 9 7950XCPUSB45_OCS16990
Intel Xeon w5-3435XCPUSB61_OCS16981
Intel Core i9-13900KCPUSB49_OCS36980
Intel Core Ultra 7 270K PlusCPUSB101_OCS16978
AMD Ryzen 9900XCPUSB92_Stock6959
AMD Ryzen 9 7950X3DCPUSB56_OCS36956
Intel Core i9-13900KCPUSB49_OCS26954
Intel Core Ultra 9 285KCPUSB84_OCS16954
Intel Core i9-14900KCPUSB67_OCS36949
Intel Core i9-14900KCPUSB67_OCS46943
Intel Core i9-13900KCPUSB49_OCS46935
AMD Ryzen 9 7950X3DCPUSB56_OCS16928
Intel Xeon w5-3435XCPUSB61_Stock6800
AMD Ryzen 5 9600XCPUSB79_OCS46780
Intel Core i9-14900KCPUSB67_OCS26780
AMD Ryzen 5 9600XCPUSB79_OCS36772
Intel Core i9-13900KCPUSB49_OCS16754
AMD Ryzen 9 7900CPUSB54_OCS56687
AMD Ryzen 9 7900CPUSB54_OCS36657
AMD Ryzen 9 7900CPUSB54_OCS46587
Intel Arc A380GPUSB44_OCS46582
AMD Ryzen 9 7950XCPUSB45_Stock6580
AMD Ryzen 5 9500FCPUSB98_OCS46578
AMD Ryzen 5 9500FCPUSB98_OCS5B6562
Intel Core i9-14900KCPUSB67_OCS16552
AMD Ryzen 9 9900XCPUSB96_Stock6529
Intel Core i9-13900KSCPUSB53_OCS46526
AMD Ryzen 9 7900CPUSB54_OCS26489
Intel Core i9-13900KSCPUSB53_OCS36476
AMD Ryzen 9 7900XCPUSB46_OCS46466
AMD Ryzen 9 7900XCPUSB46_OCS36457
AMD Ryzen Threadripper 5990XCPUSB43_OCS56426
AMD Ryzen 5 9500FCPUSB98_OCS36414
AMD Ryzen 9 7900XCPUSB46_OCS56407
AMD Ryzen 9 7950X3DCPUSB56_Stock6405
AMD Ryzen 5 9600XCPUSB79_OCS26386
Intel Arc A380GPUSB44_OCS36382
AMD Ryzen 5 9500FCPUSB98_OCS5A6380
AMD Ryzen 9 7900XCPUSB46_OCS26359
Intel Arc A380GPUSB44_OCS26331
Intel Core i7-14700KCPUSB68_OCS56331
AMD Ryzen 9 7900CPUSB54_OCS16328
Intel Core i7-14700KCPUSB68_OCS46321
AMD Ryzen Threadripper 5990XCPUSB43_OCS46315
AMD Ryzen 9 7900XCPUSB46_OCS16311
AMD Ryzen Threadripper 5990XCPUSB43_OCS3_NoSMT6252
Intel Core i9-13900KSCPUSB53_OCS26219
Intel Core i7-14700KCPUSB68_OCS36212
Intel Core i7-14700KCPUSB68_OCS26211
AMD Ryzen 9 7900X3DCPUSB58_OCS36195
Intel Core i9-13900KCPUSB49_Stock6192
AMD Ryzen 5 9600XCPUSB79_OCS16191
Intel Graphics (Arrow Lake)GPUCTEX256139
AMD Ryzen 7 9700FCPUSB91_Stock6138
Intel Core Ultra 7 270K PlusCPUSB101_Stock6137
AMD Ryzen 9 7900X3DCPUSB58_OCS26125
AMD Ryzen 7 9700XCPUSB78_Stock6108
AMD Ryzen 9 7900X3DCPUSB58_OCS16098
Intel Arc A380GPUSB44_OCS16098
Intel Core i9-13900KSCPUSB53_OCS16073
AMD Ryzen 5 9500FCPUSB98_OCS26055
Intel Core i7-14700KCPUSB68_OCS16006
AMD Ryzen Threadripper 5990XCPUSB43_OCS2_NoSMT5952
AMD Ryzen 9 7900XCPUSB46_Stock5951
AMD Ryzen Threadripper 5990XCPUSB43_OCS1_NoSMT5950
AMD Radeon 740MGPUSB75_OCS55920
AMD Ryzen 5 9500FCPUSB98_OCS15882
Intel Arc A380GPUSB44_Stock5799
Intel Core Ultra 9 285KCPUSB84_Stock5798
Intel Core i9-13900K P-CoreCPUSB52_OCS55773
Intel Core i7-13700KCPUSB50_OCS45764
Intel Core i9-13900K P-CoreCPUSB52_OCS45755
AMD Ryzen 9 7900X3DCPUSB58_Stock5710
AMD Radeon 740MGPUSB75_OCS45671
Intel Core i9-13900K P-CoreCPUSB52_OCS35670
Intel Core i9-14900KCPUSB67_Stock5663
AMD Ryzen 7 7800X3DCPUSB60_OCS45655
Intel Core i7-13700KCPUSB50_OCS35629
AMD Ryzen 7 7700XCPUSB47_OCS35587
AMD Ryzen 7 7700XCPUSB47_OCS45576
AMD Ryzen 7 7700XCPUSB47_OCS25548
AMD Ryzen 5 9600XCPUSB79_Stock5543
AMD Ryzen 7 7700XCPUSB47_OCS55541
Intel Core i9-13900K P-CoreCPUSB52_OCS25539
AMD Ryzen 7 7700XCPUSB47_OCS65528
AMD Ryzen 7 7800X3DCPUSB60_OCS55527
AMD Radeon 740MGPUSB75_OCS35515
Intel Core Ultra 5 245KCPUSB83_OCS65494
AMD Ryzen 7 7800X3DCPUSB60_OCS25473
Intel Core i9-13900K P-CoreCPUSB52_OCS15471
AMD Ryzen 7 7700XCPUSB47_OCS15469
AMD Ryzen 7 7800X3DCPUSB60_OCS35468
Intel Core i9-13900KSCPUSB53_Stock5448
Intel Core Ultra 5 245KCPUSB83_OCS55433
AMD Ryzen Threadripper 5990XCPUSB43_OCS35401
Intel Core i7-14700KCPUSB68_Stock5370
Intel Core Ultra 7 265KCPUSB87_OCS55370
AMD Ryzen 9 7900CPUSB54_Stock5368
AMD Ryzen 7 7800X3DCPUSB60_OCS15363
AMD Ryzen Threadripper 3990XCPUSB36_OCS55344
AMD Ryzen Threadripper 3990XCPUSB36_OCS2_NoSMT5325
Intel Core Ultra 5 245KCPUSB83_OCS45296
AMD Ryzen 5 9500FCPUSB98_Stock5240
AMD Ryzen Threadripper 5990XCPUSB43_OCS25227
AMD Ryzen Threadripper 3990XCPUSB36_OCS1_NoSMT5212
Intel Core Ultra 5 245KCPUSB83_OCS35189
AMD Ryzen 7 7700XCPUSB47_Stock5172
Intel Graphics (Arrow Lake)GPUSB86_OCS45171
Intel Graphics (Arrow Lake)GPUSB86_OCS55164
AMD Ryzen Threadripper 5990XCPUSB43_OCS15158
Intel Core i9-12900KFCPUSB34_OCS45153
AMD Ryzen 7 7800X3DCPUSB60_Stock5144
Intel Core i9-12900KCPUSB30_OCS55115
Intel Core Ultra 7 265KCPUSB87_OCS45101
Intel Core i7-13700KCPUSB50_OCS25100
Intel Core Ultra 5 245KCPUSB83_OCS25064
Intel Core i7-13700KCPUSB50_OCS15062
Intel Core i9-12900KCPUSB30_OCS25044
Intel Core i9-12900KFCPUSB34_OCS34989
Intel Core i9-13900K P-CoreCPUSB52_Stock4961
Intel Core Ultra 7 265KCPUSB87_OCS34922
Intel Core Ultra 7 265KCPUSB87_OCS24883
AMD Radeon 740MGPUSB75_OCS24864
Intel Graphics (Arrow Lake)GPUSB86_OCS34843
Intel Core Ultra 7 265KCPUSB87_OCS14840
Intel Core Ultra 5 245KCPUSB83_OCS14823
Intel Core i9-12900KFCPUSB34_OCS24821
AMD Ryzen Threadripper 3990XCPUSB36_OCS24820
Intel Core i9-12900KCPUSB30_OCS44754
Intel Core i7-13700KCPUSB50_Stock4727
AMD Ryzen Threadripper 3990XCPUSB36_OCS44687
AMD Ryzen 7 8700GCPUSB69_OCS24680
Intel Graphics (Arrow Lake)GPUSB86_OCS24665
Intel Core i9-12900KCPUSB30_OCS14650
AMD Ryzen Threadripper 3990XCPUSB36_OCS14632
AMD Ryzen Threadripper 5990XCPUSB43_Stock_NoSMT4594
AMD Radeon 740MGPUSB75_OCS14580
AMD Ryzen 5 7600XCPUSB48_OCS44575
AMD Ryzen 5 7600XCPUSB48_OCS54573
AMD Ryzen 5 7600XCPUSB48_OCS64570
AMD Ryzen 5 7600XCPUSB48_OCS34562
Intel Core i9-12900KFCPUSB34_OCS14550
AMD Ryzen 7 8700GCPUSB69_OCS14544
AMD Ryzen 7 8700GCPUSB69_OCS44544
AMD Radeon 740MGPUSB75_Stock4530
AMD Ryzen 5 7600XCPUSB48_OCS24529
Intel Core i9-12900KCPUSB30_OCS34498
Intel Core i7-12700KCPUSB31_OCS44494
AMD Ryzen 5 7600XCPUSB48_OCS14491
AMD Ryzen 7 8700FCPUSB76_OCS24465
Intel Core i7-12700KCPUSB31_OCS34454
AMD Ryzen Threadripper 3990XCPUSB36_OCS34418
AMD Ryzen 7 8700GCPUSB69_OCS34407
Intel Core i5-13600KCPUSB51_OCS34337
AMD Ryzen 7 8700FCPUSB76_OCS34328
Intel Core i9-12900KCPUSB30_Stock4324
AMD Ryzen 7 8700FCPUSB76_OCS14304
Intel Core Ultra 5 245KCPUSB83_Stock4304
Intel Core i5-13600KCPUSB51_OCS44301
Intel Core i7-12700KCPUSB31_OCS24285
AMD Ryzen Threadripper 5990XCPUSB43_Stock4277
Intel Core i9-12900KFCPUSB34_Stock4269
Intel Core Ultra 7 265KCPUSB87_Stock4230
AMD Ryzen 5 7600XCPUSB48_Stock4205
AMD Ryzen 3 5300GE (IGP)CPUSB35_OCS34202
AMD Ryzen 3 5300GE (IGP)CPUSB35_OCS44200
AMD Ryzen 7 8700FCPUSB76_Stock4140
Intel Core i7-12700KCPUSB31_OCS14115
AMD Ryzen 5 8600GCPUSB72_OCS34084
AMD Ryzen 5 8600GCPUSB72_OCS24037
AMD Ryzen Threadripper 3990XCPUSB36_Stock_NoSMT4023
Intel Core i7-12700KCPUSB31_Stock3939
AMD Ryzen 5 8600GCPUSB72_OCS13837
Intel Core i5-13600KCPUSB51_OCS23813
Intel Core i5-13600KCPUSB51_OCS13748
AMD Ryzen 7 8700GCPUSB69_Stock3746
Intel Core i5-12400CPUSB37_OCS33680
Intel Graphics (Arrow Lake)GPUSB86_OCS13656
Intel Core i5-12400CPUSB37_OCS43648
AMD Ryzen Threadripper 3990XCPUSB36_Stock3626
AMD Ryzen 7 5800X3DCPUSB39_OCS33609
AMD Ryzen 3 5300GE (IGP)CPUSB35_OCS23596
AMD Ryzen 5 8600GCPUSB72_Stock3591
Intel Core i5-13600KCPUSB51_Stock3563
AMD Ryzen 7 5800X3DCPUSB39_OCS13480
AMD Ryzen 7 5800X3DCPUSB39_OCS23473
AMD Ryzen 3 5300GE (IGP)CPUSB35_OCS13470
AMD Ryzen 5 8500GECPUSB74_OCS33435
AMD Ryzen 5 8500GECPUSB74_OCS23395
Intel Graphics (Arrow Lake)GPUSB86_Stock3311
Intel Core i5-12600KFCPUSB32_OCS33257
AMD Ryzen 5 8500GECPUSB74_OCS13206
AMD Ryzen 7 5800X3DCPUSB39_Stock3196
Intel Core i5-12600KFCPUSB32_OCS23196
Intel Core i5-12400CPUSB37_OCS23195
Intel Core i5-12600KFCPUSB32_OCS13130
AMD Ryzen 5 8500GECPUSB74_Stock3110
Intel Core i9-11980HKCPUSB65_OCS33088
Intel Core i5-12400CPUSB37_OCS13083
Intel Core i9-11980HKCPUSB65_OCS23079
AMD Ryzen 3 5300GE (IGP)CPUSB35_Stock2775
Intel Core i9-11980HKCPUSB65_OCS12771
AMD Radeon Graphics (Ryzen 9000)GPUSB94_XOC12750
Intel Core i9-11900HCPUWSL_DIRECTML_ONEDNN2735
Intel Core i9-11900HCPUWN_DIRECTML_ONEDNN2713
Intel Core i5-12600KFCPUSB32_Stock2681
AMD Radeon Graphics (Ryzen 7000)GPUSB55_OCS32645
AMD Radeon Graphics (Ryzen 9000)GPUSB93_OCS42623
AMD Radeon Graphics (Ryzen 7000)GPUSB55_OCS22622
Intel Core i9-11980HKCPUSB65_Stock2575
Intel Core i5-12400CPUSB37_Stock2551
AMD Radeon Graphics (Ryzen 9000)GPUSB93_OCS32546
AMD Radeon Graphics (Ryzen 9000)GPUSB93_OCS22463
Intel Core i9-11900HCPUWSL_DIRECTML2240
Intel UHD Graphics 770 (13th Gen)GPUSB57_OCS42072
AMD Radeon Graphics (Ryzen 7000)GPUSB55_OCS12057
Intel UHD Graphics 770 (13th Gen)GPUSB57_OCS32055
Intel UHD Graphics 770 (12th Gen)GPUSB33_OCS42046
AMD Radeon Graphics (Ryzen 7000)GPUSB55_Stock2037
AMD Radeon Graphics (Ryzen 9000)GPUSB93_OCS12012
AMD Radeon Graphics (Ryzen 9000)GPUSB93_Stock2008
Intel UHD Graphics 770 (12th Gen)GPUSB33_OCS31949
Intel UHD Graphics 770 (12th Gen)GPUSB33_OCS21825
Intel UHD Graphics 770 (13th Gen)GPUSB57_OCS21739
AMD Ryzen 3 5300GECPUSB35_OCS31504
AMD Ryzen 3 5300GECPUSB35_OCS41469
AMD Ryzen 3 5300GECPUSB35_OCS21448
Intel UHD Graphics 750 (11th Gen)GPUSB28_OCS61446
AMD Ryzen 3 5300GECPUSB35_OCS11419
Intel UHD Graphics for 11th GenGPUWN_DIRECTML1417
Intel UHD Graphics for 11th GenGPUWSL_DIRECTML1396
Intel UHD Graphics 730 (12th Gen)GPUSB38_OCS41388
Intel UHD Graphics 770 (13th Gen)GPUSB57_OCS11387
Intel UHD Graphics 770 (13th Gen)GPUSB57_Stock1379
Intel UHD Graphics 770 (12th Gen)GPUSB33_OCS11361
Intel UHD Graphics 770 (12th Gen)GPUSB33_Stock1352
Intel UHD Graphics 750 (11th Gen)GPUSB28_OCS51264
Intel UHD Graphics 730 (12th Gen)GPUSB38_OCS31223
AMD Ryzen 3 5300GECPUSB35_Stock1179
Intel UHD Graphics 730 (12th Gen)GPUSB38_OCS21116
Intel UHD Graphics 750 (11th Gen)GPUSB28_OCS41107
Intel UHD Graphics 750 (11th Gen)GPUSB28_OCS31098
Intel UHD Graphics 730 (12th Gen)GPUSB38_OCS11080
Intel UHD Graphics 730 (12th Gen)GPUSB38_Stock1072
Intel UHD Graphics 750 (11th Gen)GPUSB28_OCS21066
Intel UHD Graphics 750 (11th Gen)GPUSB28_OCS11064
Intel UHD Graphics 750 (11th Gen)GPUSB28_Stock1064
Intel Core i9-11900HCPUWN_DIRECTML892
Orange Pi 5 Max 16GBSBCSB91_OCS2708
Orange Pi 5 Max 16GBSBCSB89_OCS3677
Orange Pi 5 Max 16GBSBCSB91_OCS1667
Orange Pi 5 Max 16GBSBCSB89_OCS4652
Orange Pi 5 Max 16GBSBCSB89_OCS2604
Orange Pi 5 Max 16GBSBCSB89_OCS1567
Orange Pi 5 Max 16GBSBCSB89_Stock510
Raspberry Pi 5SBCSB77_OCS2296
Raspberry Pi 5SBCSB77_OCS1293
Raspberry Pi 5SBCSB77_Stock272

Leaderboard Notes:

  1. OC Strategy is coded as SkatterBencher # + OC Strategy #
  2. The Core i9-13900KS benchmark scores seem off. I noticed a particular issue with the OS for that system where the score would be significantly slower than expected unless the process affinity was manually set.
  3. TensorFlow-DirectML was used for: Intel UHD Graphics 750 (11th Gen), Intel UHD Graphics 730 (12th Gen), Intel UHD Graphics 770 (12th Gen), Intel UHD Graphics 770 (13th Gen), AMD Radeon Graphics (Ryzen 7000), AMD Ryzen 3 5300GE (IGP), and Intel Arc A380.

AI Benchmark

ai benchmark installation guide

AI Benchmark Alpha is an open-source python library for evaluating AI performance of various hardware platforms, including CPUs, GPUs and TPUs. The benchmark is relying on the TensorFlow machine learning library, and is providing a lightweight solution for assessing inference and training speed for key Deep Learning models. The benchmark itself takes about 20 minutes to run and outputs three scores: inference score, training score, and AI-Score. It’s the latter we use as performance measurement.

While there are many ways to run AI Benchmark on your machine, I use an Anaconda Python environment with the latest Tensorflow optimizations.

In this blog post I describe my AI Benchmark process in detail: AI Benchmark to Measure Machine Learning Performance. Below you can find a quick summary

Installing AI Benchmark on Windows Native

  1. First, download and install Anaconda for Windows.
  2. After completing the installation, run the Anaconda Prompt.
  3. Create a new Python environment for the benchmark. Make sure to specify Python version 3.10 as the tensorflow-directml-plugin supports only versions 3.7, 3.8, 3.9, and 3.10
    • conda create -n aibench python=3.10
  4. Activate your newly created environment
    • conda activate aibench
  5. Download and install the base TensorFlow-CPU
    • pip install tensorflow-cpu
  6. Download and install the tensorflow-directml package
    • pip install tensorflow-directml-plugin
  7. Download and install the numpy 1.23 package
    • pip install numpy==1.23
  8. Download and install the ai_benchmark package
    • pip install ai_benchmark

Installing AI Benchmark on Windows Subsystem for Linux

  1. First, make sure WSL is correctly installed on your Windows PC.
    • Open PowerShell and type wsl –install
    • Follow the installation instructions
  2. If that’s the case, then open the WSL prompt.
  3. Now download the Anaconda for Linux 64-Bit (x86) installer.
  4. Next, install Anaconda
    • bash ~/Downloads/Anaconda3-2020.05-Linux-x86_64.sh
  5. Then, close and reopen Windows Subsystem for Linux
  6. Create a new Python environment for the benchmark. Make sure to specify Python version 3.10 as the tensorflow-directml-plugin supports only versions 3.7, 3.8, 3.9, and 3.10
    • conda create -n aibench python=3.10
  7. Activate your newly created environment
    • conda activate aibench
  8. Download and install the base TensorFlow-CPU
    • pip install tensorflow-cpu
  9. Download and install the tensorflow-directml package
    • pip install tensorflow-directml-plugin
  10. Download and install the numpy 1.23 package
    • pip install numpy==1.23
  11. Download and install the ai_benchmark package
    • pip install ai_benchmark

Running the AI Benchmark

Starting the AI Benchmark is the same on Windows Native and Windows Subsystem for Linux.

  • Open the Anaconda prompt
  • Activate the conda environment with AI Benchmark
    • conda activate aibench
  • Start Python
    • python
  • Import the AI Benchmark package
    • from ai_benchmark import AIBenchmark
  • Specify the benchmark parameters
    • benchmark = AIBenchmark(use_CPU=None, verbose_level=3)
      • Use_CPU=True runs the benchmark on the CPU
      • Use_CPU=None runs the benchmark on the GPU
      • Verbose_level=0 runs the test silently
      • Verbose_level=1 runs the test with short summary
      • Verbose_level=2 provides information about each run
      • Verbose_level=3 provides the tensorflow logs during the run
  • Then, lastly, start the benchmark
    • benchmark.run()

AI Benchmark Optimizations and Tricks

Since deep neural network and machine learning performance is a big selling point, companies work hard to release performance-optimizing software packages for their hardware. I tend to use these packages in my SkatterBencher guides.

OneDNN for Intel CPU Architectures

Intel oneDNN is an open-source, high-performance library designed to accelerate deep learning applications on Intel architecture CPUs. It provides optimized primitives for various deep learning operations, such as convolutions, inner products, and other key operations used in neural networks.

The oneAPI Deep Neural Network Library (oneDNN) optimizations are available in the official x86-64 TensorFlow after v2.5. The feature is off by default before v2.9, but users can enable those CPU optimizations by configuring the environment variable TF_ENABLE_ONEDNN_OPTS.

  • Windows Native: set TF_ENABLE_ONEDNN_OPTS=1
  • Windows Subsystem for Linux: export TF_ENABLE_ONEDNN_OPTS=1

Since TensorFlow v2.9, the oneAPI Deep Neural Network Library (oneDNN) optimizations are enabled by default.

ZenDNN for AMD CPU Architectures

I also came across an AMD equivalent library called ZenDNN. However, I’ve yet to try this on an AMD system, so I’ll leave you a link for now.

CuDNN or TensorRT for NVIDIA GPU Architectures

You can also rely on the NVIDIA CUDA Deep Neural Network library (cuDNN) for NVIDIA GPUs. CuDNN is a GPU-accelerated library of primitives for deep neural networks. The installation requires a different version of TensorFlow – not TensorFlow-DirectML – since TensorFlow 2.10 is no longer available on Windows Native.

The installation is pretty straightforward. After installing Anaconda for Linux on WSL, do the following

  • First, create and activate a new Anaconda environment
    • conda create -n aibenchNV
    • conda activate aibenchNV
  • Then, install the appropriate Cuda Toolkit. You can find a support matrix on NVIDIA’s website
    • conda install -c conda-forge cudatoolkit=11.8
  • Next, install the CuDNN package
    • pip install nvidia-cudnn-cu11==8.9.4.25
  • Then, install TensorFlow
    • pip install tensorflow
  • Then, install numpy 1.23
    • pip install numpy==1.23
  • Lastly, install AI Benchmark
    • pip install ai_benchmark

Instead of CuDNN, you can also consider installing the TensorRT Python library. Similarly, TensorRT is a deep-learning library powered by CUDA. TensorRT provides APIs and parsers to import trained models from all major deep learning frameworks. It then generates optimized runtime engines deployable in the data center, automotive, and embedded environments.

RocM for AMD GPU Architectures

Lastly, I also want to mention AMD’s ROCm software package. ROCm is an open-source software stack for GPU computation featuring a collection of drivers, development tools, and APIs enabling GPU programming from the low-level kernel to end-user applications.

While ROCm is fully integrated into ML frameworks such as PyTorch and TensorFlow, it’s currently unavailable on Windows Native, so I’ve yet to use ROCm optimizations for AMD graphics cards. So, just like with ZenDNN, I’ll leave you with a link to the documentation.

Multiple GPUs

These days it’s common to have multiple graphics devices in a single system. Usually, that’s the integrated graphics of the CPU and a high-performance discrete graphics card. If you want to switch between the graphics device, you can set an environment variable before starting Python.

  • Windows Native: set DML_VISIBLE_DEVICES=0,1
  • Windows Subsystem for Linux: export DML_VISIBLE_DEVICES=0,1

here the number indicates the specific device. Device 0 is the NVIDIA dGPU on the EK Flat PC, and device 1 is the Intel iGPU. By default, AI Benchmark will run the first available device. So, if I want to run on the iGPU, I’d have to set DML_VISIBLE_DEVICES=1.

DXGI_ERROR_DEVICE_REMOVED

The AI Benchmark is a pretty tough benchmark that can take a long time. Sometimes, you may run into an error called DXGI_ERROR_DEVICE_REMOVED while running the benchmark. That happens when there’s a timeout when the device takes too long to complete a workload.

You can increase the timeout with the registry entry “TdrDelay” to solve the issue. This registry entry will extend the time a software application waits for the IGP. https://docs.microsoft.com/en-us/windows-hardware/drivers/display/tdr-registry-keys

  • KeyPath: HKEY_LOCAL_MACHINE\System\CurrentControlSet\Control\GraphicsDrivers
  • KeyValue: TdrDelay
  • ValueType: REG_DWORD
  • ValueData: Number of seconds to delay. The default value is 2 seconds.

Subscribe To Newsletter

Archives