Intel Core i7-12700K testing with a MSI PRO Z690-A DDR4(MS-7D25) v1.0 (1.15 BIOS) and Gigabyte AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 6GB on Pop 21.04 via the Phoronix Test Suite.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2112125-TJ-12700KHPC62
12700k HPC+OpenCL AVX512 performance profiling,
"ACES DGEMM 1.0 - Sustained Floating-Point Rate",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",4.918968,4.807757,4.900068
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",4.988461,5.029801,5.03011
"Algebraic Multi-Grid Benchmark 1.2 - ",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",304067700,303968400,303889200
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",301796500,303123400,302933000
"ArrayFire 3.7 - Test: BLAS CPU",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",1204.32,1206.6,1204.34
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",1208.09,1206.85,1208.68
"ASKAP 1.0 - Test: tConvolve MT - Gridding",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",1244.55,1246.37,1246.01
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",1250.03,1249.66,1247.1
"ASKAP 1.0 - Test: tConvolve MT - Degridding",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",2051.08,2056.03,2057.02
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",2051.08,2057.02,2055.04
"ASKAP 1.0 - Test: tConvolve MPI - Degridding",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",4859.18,4859.18,4859.18
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",4859.18,4950.86,4859.18
"ASKAP 1.0 - Test: tConvolve MPI - Gridding",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",5046.07,5046.07,5046.07
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",5046.07,5046.07,5046.07
"ASKAP 1.0 - Test: tConvolve OpenMP - Gridding",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",1875.04,1861.93,1861.93
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",1901.83,1929.39,1888.34
"ASKAP 1.0 - Test: tConvolve OpenMP - Degridding",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",3598.05,3647.34,3598.05
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",3647.34,3647.34,3503.37
"ASKAP 1.0 - Test: Hogbom Clean OpenMP",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",266.667,269.542,265.957
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",269.542,270.27,268.097
"Caffe 2020-02-13 - Model: AlexNet - Acceleration: CPU - Iterations: 100",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",22527,23220,23619
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",23120,23785,24073
"Caffe 2020-02-13 - Model: AlexNet - Acceleration: CPU - Iterations: 200",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",47502,46284,46086
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",47436,47019,46679
"Caffe 2020-02-13 - Model: AlexNet - Acceleration: CPU - Iterations: 1000",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",229899,236471,248405,255712,248170,246877,254460,251418,257201
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",242032,235281,237992
"Caffe 2020-02-13 - Model: GoogleNet - Acceleration: CPU - Iterations: 100",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",75191,79748,84122,78505,81833,79878,79623,80632,76583,77419,81354,80181,76313,81243,82479
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",67709,67433,68414
"Caffe 2020-02-13 - Model: GoogleNet - Acceleration: CPU - Iterations: 200",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",158182,158884,154750
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",137740,135508,135313
"Caffe 2020-02-13 - Model: GoogleNet - Acceleration: CPU - Iterations: 1000",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",757080,772991,703086,701045,732236,761144,738745,686138,686407
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",685439,678548,676544
"cl-mem 2017-01-13 - Benchmark: Copy",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",198.2,198.6,198.3
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",195.4,195.1,195
"cl-mem 2017-01-13 - Benchmark: Read",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",263.7,263.6,263.5
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",261.1,261.1,261.3
"cl-mem 2017-01-13 - Benchmark: Write",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",255.3,255.6,255
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",248.6,248.4,248.1
"CP2K Molecular Dynamics 8.2 - Input: Fayalite-FIST",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",
"Darktable 3.4.1 - Test: Boat - Acceleration: OpenCL",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",4.05,3.88,3.984
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",4.238,4.109,4.107
"Darktable 3.4.1 - Test: Masskrug - Acceleration: OpenCL",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",3.851,3.817,3.814
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",3.826,3.805,3.823
"Darktable 3.4.1 - Test: Server Rack - Acceleration: OpenCL",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",0.132,0.133,0.135
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",0.131,0.131,0.132
"Darktable 3.4.1 - Test: Server Room - Acceleration: OpenCL",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",3.017,3.015,3.004
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",3.003,3.008,2.986
"Darmstadt Automotive Parallel Heterogeneous Suite - Backend: OpenMP - Kernel: NDT Mapping",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",1028.2723482142,1056.0498455527,1015.9968707296
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",1027.372631478,1027.0420162889,1046.7952363838
"Darmstadt Automotive Parallel Heterogeneous Suite - Backend: OpenMP - Kernel: Points2Image",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",34261.828896427,35551.342063163,35253.265333702
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",35867.576906063,36582.019937201,35894.82815351
"Darmstadt Automotive Parallel Heterogeneous Suite - Backend: OpenMP - Kernel: Euclidean Cluster",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",1670.8112066877,1670.7414193505,1672.9915039915
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",1682.1329445737,1636.991645886,1683.1758161299
"DeepSpeech 0.6 - Acceleration: CPU",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",49.53139,48.53947,48.48349
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",49.53467,48.60201,48.74488
"FFTW 3.3.6 - Build: Stock - Size: 1D FFT Size 32",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",22775,22773,22775
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",22769,22778,22784
"FFTW 3.3.6 - Build: Stock - Size: 2D FFT Size 32",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",22352,23236,23255
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",22829,23061,22591
"FFTW 3.3.6 - Build: Stock - Size: 1D FFT Size 4096",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",18679,18040,18160
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",18575,18193,18737
"FFTW 3.3.6 - Build: Stock - Size: 2D FFT Size 4096",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",13665,13762,13882
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",14081,13965,14013
"FFTW 3.3.6 - Build: Float + SSE - Size: 1D FFT Size 32",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",32199,32143,32197
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",31615,31867,31198
"FFTW 3.3.6 - Build: Float + SSE - Size: 2D FFT Size 32",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",80683,79960,80846
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",82322,81026,84198
"FFTW 3.3.6 - Build: Float + SSE - Size: 1D FFT Size 4096",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",104150,105630,102100
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",105970,105250,102030
"FFTW 3.3.6 - Build: Float + SSE - Size: 2D FFT Size 4096",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",44967,44904,42344,43604,43682
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",43080,42955,42769
"GNU Octave Benchmark 6.1.1~hg.2021.01.26 - ",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",5.095,5.013,5.112,5.105,5.074
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",5.098,5.091,5.012,5.127,4.99
"GROMACS 2021.2 - Implementation: MPI CPU - Input: water_GMX50_bare",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",1.182,1.178,1.179
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",1.176,1.194,1.189
"Himeno Benchmark 3.0 - Poisson Pressure Solver",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",9224.388663,9590.727411,9600.099033
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",9566.390641,9548.39142,9547.388341
"HPL Linpack 2.3 - ",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",97.4,97.837,97.425
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",98.518,102.06,101.2
"Intel MPI Benchmarks 2019.3 - Test: IMB-P2P PingPong",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",8668776,8631860,8586310
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",8310157,8629973,8600359
"Intel MPI Benchmarks 2019.3 - Test: IMB-MPI1 Exchange",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",14819.37,15754.07,15709.09,14464.63,15918.33,15826.15,15945.69,14323.83,15457.38,13494.78,15473.06,15547.01,15562.46,15007.59,14542.92
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",14261.61,15626.53,14436.2,14379.23,15106.9,15330.13,13863.49,15943.59,15841.24,16147.24,15872.71,14010.86,14062.94,14413.47,16063.6
"Intel MPI Benchmarks 2019.3 - Test: IMB-MPI1 Exchange",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",114.13,104.78,105.84,114,107.73,108.16,105.33,108.49,107.32,108.16,106.12,106.42,112.02,110.9,115.78
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",113.3,105.83,109.05,112.15,106.91,105.73,114.36,105.33,107.06,102.69,106.03,109.19,109.04,111.62,104.8
"Intel MPI Benchmarks 2019.3 - Test: IMB-MPI1 PingPong",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",10446.25,10331.22,8826.03,10532.28,9762.36,10131.87,10399.35,10359.27,8957.65,9411.32,10273.28,9792.97,10399.07,10252.28,10191.64
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",10557.94,10160.97,10163.84
"Intel MPI Benchmarks 2019.3 - Test: IMB-MPI1 Sendrecv",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",12061.34,12321.72,12437.56
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",12465.8,12334.66,12615.22
"Intel MPI Benchmarks 2019.3 - Test: IMB-MPI1 Sendrecv",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",52.8,53.87,53.84
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",53.2,52.26,52.53
"LeelaChessZero 0.28 - Backend: BLAS",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",862,898,915,874,850,930,915,964,946
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",986,931,969,949
"LULESH 2.0.3 - ",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",6627.8028,6982.109,6947.1413,6934.2657
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",6743.9785,6942.4885,6949.4017
"miniFE 2.2 - Problem Size: Small",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",6410.7,6411.8,6411.78
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",6407.6,6408.96,6404.8
"NAMD 2.14 - ATPase Simulation - 327,506 Atoms",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",1.16303,1.16362,1.16082
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",1.18229,1.18887,1.16496
"Numpy Benchmark - ",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",611.34,623.87,620.67
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",607.42,620.39,608.72
"oneDNN 2.1.2 - Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",2.57917,2.58099,2.59896
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",2.57502,2.57435,2.58717
"oneDNN 2.1.2 - Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",8.78193,8.80202,8.76408
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",10.6385,8.76123,8.75118,8.79185,8.74913,8.72886,8.72887,8.8521,8.74895,8.79559,8.72667,8.7328,8.76512,8.75217
"oneDNN 2.1.2 - Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",0.676695,0.698398,0.680304
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",0.687089,0.702719,0.68281
"oneDNN 2.1.2 - Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",1.93627,1.94369,1.92044
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",1.90892,1.93672,1.93054
"oneDNN 2.1.2 - Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",2.42265,2.41915,2.49456
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",2.4284,2.55405,2.41668,2.49217,2.43242
"oneDNN 2.1.2 - Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",3.57113,3.61702,3.51697
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",3.55045,3.70938,3.44303,3.39961,3.54171,3.4819,3.54237,3.49132,3.60205,3.51701
"oneDNN 2.1.2 - Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",13.4076,13.3887,13.3907
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",13.4089,13.4182,13.4073
"oneDNN 2.1.2 - Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",6.68514,7.2568,5.72044,6.17582,5.75298,6.28773,5.55598,6.08664,6.46631,6.32272,6.06648,5.8333,6.74909,6.46822,6.74035
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",6.96122,6.8002,7.21192,6.71434,6.05934,6.22446,5.96177,6.36705,6.13239,7.02752,7.27184,6.49731
"oneDNN 2.1.2 - Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",4.11876,4.12237,4.15393
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",4.098,5.07766,4.14215,4.18004,4.10354,4.09871,4.09775,4.08976,4.09259,4.13579,5.02107,4.12176,4.09873,4.10347,4.08919
"oneDNN 2.1.2 - Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",13.279,13.2947,13.277
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",13.3835,13.4015,13.439
"oneDNN 2.1.2 - Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",0.872428,0.875644,0.869976
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",0.875951,0.892634,0.867178
"oneDNN 2.1.2 - Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",1.11468,1.01985,1.11382,1.03305,1.11442,1.01744,1.11977,1.01588,1.12179,1.01362,1.12904,1.00852,1.01659,1.17287,1.0171
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",1.08072,1.02266,1.1035,1.02741,1.09996,1.01279,1.10821,1.01405,1.15668,1.01204,1.27251,1.01304
"oneDNN 2.1.2 - Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",2534.01,2537.61,2549.23
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",2547.2,2522.23,2527.93
"oneDNN 2.1.2 - Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",1334.06,1376.69,1422.24,1383.9,1447.49,1384.86,1379.9,1377.58
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",1336.87,1339.67,1348.3
"oneDNN 2.1.2 - Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",2590.58,2603.69,2594.69
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",2611.92,2522.42,2547.11
"oneDNN 2.1.2 - Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",6.81187,6.65511,6.85305
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",6.33735,6.35687,6.35309
"oneDNN 2.1.2 - Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",7.50572,7.43495,7.35545
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",6.69019,6.72594,6.75751
"oneDNN 2.1.2 - Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",4.8196,4.46537,4.87245,4.47687,4.89009,4.45869,4.89588,4.45024,4.52293,5.04513,4.46114,4.52154,5.43056,4.43197,4.42584
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",4.52682,4.39065,5.06682,4.35673,4.33465,5.18615,4.3388,5.20675,4.39421,5.24314,4.4328,4.64552,4.88604,4.78528,4.29958
"oneDNN 2.1.2 - Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",1337.95,1333.65,1331.33
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",1325.2,1327.53,1332.54
"oneDNN 2.1.2 - Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",2.3367,2.33064,2.34105
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",2.37147,2.33465,2.29005
"oneDNN 2.1.2 - Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",2634.76,2548.56,2572.14
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",2581.3,2612.41,2541.91
"oneDNN 2.1.2 - Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",1336.62,1341.62,1334.16
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",1336.19,1332.39,1350.92
"oneDNN 2.1.2 - Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",0.555609,0.566318,0.57517
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",0.53097,0.561993,0.566112,0.552369,0.540882,0.551199
"oneDNN 2.1.2 - Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",1.18438,1.20915,1.16395
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",1.17142,1.20964,1.1801
"OpenFOAM 8 - Input: Motorbike 30M",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",137.54,139.01,136.59
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",135.7,135.49,135.95
"OpenFOAM 8 - Input: Motorbike 60M",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",871.79,865.14,864.66
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",864,865.01,863
"Parboil 2.5 - Test: OpenMP LBM",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",114.026962,114.120605,114.058884
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",114.115662,114.109276,114.065048
"Parboil 2.5 - Test: OpenMP CUTCP",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",3.189566,3.173291,3.168566
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",3.201948,3.177063,3.170317
"Parboil 2.5 - Test: OpenMP Stencil",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",14.943817,14.935024,15.155529
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",15.015103,14.877428,15.048594
"Parboil 2.5 - Test: OpenMP MRI Gridding",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",52.274147,49.838287,47.228542,45.327122,51.588055,47.500378,44.021545,50.024574,46.887058,51.569199,50.061527,51.664539,52.126221,47.097412,50.052059
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",43.665462,47.088135,43.60471,52.011917,49.346924,51.493454,47.105167,51.97073,51.470989,52.013943,49.267544,43.766006
"Pennant 1.0.1 - Test: sedovbig",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",69.2366,70.03827,70.40815
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",67.82286,67.5204,67.97749
"Pennant 1.0.1 - Test: leblancbig",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",49.86824,49.89655,50.02584
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",47.32243,47.43787,47.40191
"QMCPACK 3.11 - Input: simple-H2O",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",17.603,17.943,20.669,17.746,17.809,17.619,17.943,17.525,17.77,17.475,17.8,17.758,17.747,17.887
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",18.239,18.216,17.924
"R Benchmark - ",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",0.10546816759131,0.10366365212225,0.10406073398534
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",0.10354105943162,0.10404106265493,0.11490873412055,0.10386767869527,0.10394927705176,0.1037850815097,0.10391353734614,0.10378198004697,0.10951248421094,0.10470322278798,0.10379708857363,0.10331917060661,0.1035691309403,0.10526757396856,0.10355822499747
"RELION 3.1.1 - Test: Basic - Device: CPU",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",1683.703,1691.973,1678.43
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",1656.555,1657.528,1656.056
"RNNoise 2020-06-28 - ",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",16.083,16.718,16.727
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",17.106,17.137,17.114
"SHOC Scalable HeterOgeneous Computing 2020-04-17 - Target: OpenCL - Benchmark: S3D",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",123.668,125.79,125.776
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",125.484,123.963,125.763
"SHOC Scalable HeterOgeneous Computing 2020-04-17 - Target: OpenCL - Benchmark: Triad",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",12.4573,12.8769,12.465
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",12.0831,12.2959,12.832,12.509,12.0424,12.1162
"SHOC Scalable HeterOgeneous Computing 2020-04-17 - Target: OpenCL - Benchmark: FFT SP",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",681.768,678.968,681.914
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",681.983,681.903,682.164
"SHOC Scalable HeterOgeneous Computing 2020-04-17 - Target: OpenCL - Benchmark: MD5 Hash",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",9.3029,9.3059,9.3035
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",9.318,9.3176,9.3181
"SHOC Scalable HeterOgeneous Computing 2020-04-17 - Target: OpenCL - Benchmark: Reduction",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",253.695,254.389,254.293
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",254.608,254.517,254.097
"SHOC Scalable HeterOgeneous Computing 2020-04-17 - Target: OpenCL - Benchmark: GEMM SGEMM_N",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",1836.54,1858.69,1830.03
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",1843.75,1894.1,1840.36
"SHOC Scalable HeterOgeneous Computing 2020-04-17 - Target: OpenCL - Benchmark: Max SP Flops",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",8417800,8463750,8248360
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",8207140,9258460,9272150,9190960,9166560,9283590,9330160,9207290,8368080
"SHOC Scalable HeterOgeneous Computing 2020-04-17 - Target: OpenCL - Benchmark: Bus Speed Download",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",20.4956,20.2588,19.6916
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",20.2315,19.9927,19.7104
"SHOC Scalable HeterOgeneous Computing 2020-04-17 - Target: OpenCL - Benchmark: Bus Speed Readback",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",20.3753,20.3841,20.4019
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",20.4896,20.5173,21.6791,20.5797,19.7535,21.326,21.6072,22.0827,20.6783,20.217,22.0498,20.4944,21.8326,20.1758,22.2807
"SHOC Scalable HeterOgeneous Computing 2020-04-17 - Target: OpenCL - Benchmark: Texture Read Bandwidth",
Higher Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",347.054,352.277,348.689
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",350.812,347.032,349.191
"TensorFlow Lite 2020-08-23 - Model: SqueezeNet",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",144633,146535,146321
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",144110,145962,145652
"TensorFlow Lite 2020-08-23 - Model: Inception V4",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",2078810,2082610,2078910
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",2074150,2083050,2091270
"TensorFlow Lite 2020-08-23 - Model: NASNet Mobile",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",123526,125387,125663
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",125378,123740,125705
"TensorFlow Lite 2020-08-23 - Model: Mobilenet Float",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",96995.3,97233.6,97532.7
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",97809.8,97332.7,97535.9
"TensorFlow Lite 2020-08-23 - Model: Mobilenet Quant",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",98277.4,98287.3,98471.1
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",98131.8,98273,98456.1
"TensorFlow Lite 2020-08-23 - Model: Inception ResNet V2",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",1870740,1881820,1883630
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",1879930,1878440,1886620
"Timed HMMer Search 3.3.2 - Pfam Database Search",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",82.674,82.491,82.281
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",82.426,83.083,82.321
"Timed MAFFT Alignment 7.471 - Multiple Sequence Alignment - LSU RNA",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",7.73,7.697,7.683
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",7.508,7.548,7.514
"Timed MrBayes Analysis 3.2.7 - Primate Phylogeny Analysis",
Lower Results Are Better
"12700k AVX512 march=sapphirerapids gcc 11.1 rx 5600xt",74.009,74.295,73.079
"12700k AVX512 march=native + AVX512 gcc 11.1 rx 5600xt",74.205,74.635,74.178