AMD Bulldozer Compiler Tests AMD FX-4100 Bulldozer Quad-core compiler benchmarking under Ubuntu Linux with GCC 4.5 and GCC 4.6. Testing for a future article on Phoronix.com by Michael Larabel. Thanks to Daniel Newkirk for the SSH access to this AMD Bulldozer system due to lack of AMD FX CPUs at Phoronix.
HTML result view exported from: https://openbenchmarking.org/result/1110161-LI-1110159AR87&grs&sro .
AMD Bulldozer Compiler Tests Processor Motherboard Chipset Memory Disk Graphics Audio Network OS Kernel Display Driver Compiler File-System Desktop Display Server OpenGL Screen Resolution Bulldozer GCC 4.5.2 Bulldozer GCC 4.6.1 phii840 AMD FX-4100 @ 3.60GHz (4 Cores) ASUS M5A97 EVO ATI RD890 PCI to PCI bridge 16384MB 60GB SSD G2 64 + 2000GB SAMSUNG HD204UI + 1000GB Western Digital WD1001FALS-0 NVIDIA GeForce 8400 GS Realtek ALC892 Realtek RTL8111/8168B Ubuntu 11.04 2.6.38-11-generic (x86_64) NVIDIA 1.0.0 GCC 4.5.2 xfs GCC 4.6.1 AMD Phenom II X4 840 @ 3.21GHz (4 Cores) Gigabyte GA-MA790GP-DS4H AMD RS780 + SB700/SB800 4096MB 1000GB SAMSUNG HD103SJ + 500GB Western Digital WDC WD5000AAKS-0 + 1000GB SAMSUNG HD103UJ NVIDIA Quadro FX 570 256MB (460/400MHz) Realtek ALC889A Fedora 14 2.6.35.10-74.fc14.x86_64 (x86_64) GNOME 2.32.0 X Server 1.9.5 NVIDIA 270.41.06 3.3.0 NVIDIA 270.41.06 ext4 1920x1080 OpenBenchmarking.org System Details - phii840: Compiz was running on this system. SELinux: Enabled.
AMD Bulldozer Compiler Tests npb: CG.B scimark2: Dense LU Matrix Factorization npb: LU.A npb: SP.A scimark2: Sparse Matrix Multiply scimark2: Composite gcrypt: CAMELLIA256-ECB Cipher graphics-magick: Blur npb: FT.B n-queens: Elapsed Time npb: MG.B john-the-ripper: Traditional DES npb: IS.C npb: UA.A clomp: Static OMP Speedup povray: Total Time npb: EP.B graphics-magick: Resizing mafft: Multiple Sequence Alignment smallpt: Global Illumination Renderer; 100 Samples scimark2: Fast Fourier Transform graphics-magick: HWB Color Space tscp: AI Chess Performance npb: BT.A john-the-ripper: MD5 fhourstones: Complex Connect-4 Solving john-the-ripper: Blowfish openssl: RSA 4096-bit Performance x264: H.264 Video Encoding graphics-magick: Local Adaptive Thresholding encode-mp3: WAV To MP3 scimark2: Monte Carlo encode-flac: WAV To FLAC scimark2: Jacobi Successive Over-Relaxation c-ray: Total Time compress-7zip: Compress Speed Test ffmpeg: AVI To NTSC VCD graphics-magick: Sharpen Bulldozer GCC 4.5.2 Bulldozer GCC 4.6.1 phii840 1788.94 1616.56 6058.10 3735.79 968.47 738.80 3777 87 3785.19 281.74 3645.03 3523667 99.91 21.48 2.31 913 78.97 92 28.86 211 72.89 123 293780 5982.31 14082 9425.30 866 63.65 50.19 44 28.69 345.55 8.75 690.52 106.75 8877 16.50 44 1639.84 940.56 735.23 2503 90 322.56 3321333 99.50 2.31 916 96 28.83 215 69.17 134 286148 13598 9221.03 895 63.83 50.89 43 29.76 336.07 8.66 690.51 105.49 8783 17.06 55 532.17 698.09 2601.13 2171.99 571.28 475.59 63 2754.65 241.08 2794.51 2787000 79.57 17.61 2.78 1071 88.81 103 32.02 194 66.13 122 270068 6488.78 14677 8830.77 910 60.85 52.57 45 29.85 337.66 8.51 704.81 107.42 8885 13.64 50 OpenBenchmarking.org
NAS Parallel Benchmarks Test / Class: CG.B OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: CG.B Bulldozer GCC 4.5.2 phii840 400 800 1200 1600 2000 SE +/- 0.92, N = 3 SE +/- 4.70, N = 3 1788.94 532.17
SciMark Computational Test: Dense LU Matrix Factorization OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Dense LU Matrix Factorization Bulldozer GCC 4.5.2 Bulldozer GCC 4.6.1 phii840 400 800 1200 1600 2000 SE +/- 14.44, N = 4 SE +/- 6.26, N = 4 SE +/- 1.29, N = 4 1616.56 1639.84 698.09
NAS Parallel Benchmarks Test / Class: LU.A OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: LU.A Bulldozer GCC 4.5.2 phii840 1300 2600 3900 5200 6500 SE +/- 82.99, N = 3 SE +/- 1.62, N = 3 6058.10 2601.13
NAS Parallel Benchmarks Test / Class: SP.A OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: SP.A Bulldozer GCC 4.5.2 phii840 800 1600 2400 3200 4000 SE +/- 13.66, N = 3 SE +/- 4.54, N = 3 3735.79 2171.99
SciMark Computational Test: Sparse Matrix Multiply OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Sparse Matrix Multiply Bulldozer GCC 4.5.2 Bulldozer GCC 4.6.1 phii840 200 400 600 800 1000 SE +/- 6.77, N = 4 SE +/- 3.24, N = 4 SE +/- 1.03, N = 4 968.47 940.56 571.28
SciMark Computational Test: Composite OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Composite Bulldozer GCC 4.5.2 Bulldozer GCC 4.6.1 phii840 160 320 480 640 800 SE +/- 4.39, N = 4 SE +/- 1.65, N = 4 SE +/- 0.84, N = 4 738.80 735.23 475.59
Gcrypt Library CAMELLIA256-ECB Cipher OpenBenchmarking.org Microseconds, Fewer Is Better Gcrypt Library 1.4.4 CAMELLIA256-ECB Cipher Bulldozer GCC 4.5.2 Bulldozer GCC 4.6.1 800 1600 2400 3200 4000 SE +/- 3.33, N = 3 SE +/- 8.82, N = 3 3777 2503
GraphicsMagick Operation: Blur OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.12 Operation: Blur Bulldozer GCC 4.5.2 Bulldozer GCC 4.6.1 phii840 20 40 60 80 100 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 87 90 63
NAS Parallel Benchmarks Test / Class: FT.B OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: FT.B Bulldozer GCC 4.5.2 phii840 800 1600 2400 3200 4000 SE +/- 15.77, N = 3 SE +/- 7.81, N = 3 3785.19 2754.65
N-Queens Elapsed Time OpenBenchmarking.org Seconds, Fewer Is Better N-Queens 1.0 Elapsed Time Bulldozer GCC 4.5.2 Bulldozer GCC 4.6.1 phii840 70 140 210 280 350 SE +/- 0.01, N = 2 SE +/- 0.02, N = 2 SE +/- 0.33, N = 2 281.74 322.56 241.08
NAS Parallel Benchmarks Test / Class: MG.B OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: MG.B Bulldozer GCC 4.5.2 phii840 800 1600 2400 3200 4000 SE +/- 1.71, N = 3 SE +/- 2.71, N = 3 3645.03 2794.51
John The Ripper Test: Traditional DES OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.7.8 Test: Traditional DES Bulldozer GCC 4.5.2 Bulldozer GCC 4.6.1 phii840 800K 1600K 2400K 3200K 4000K SE +/- 5897.27, N = 3 SE +/- 15452.44, N = 3 SE +/- 4509.25, N = 3 3523667 3321333 2787000
NAS Parallel Benchmarks Test / Class: IS.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: IS.C Bulldozer GCC 4.5.2 Bulldozer GCC 4.6.1 phii840 20 40 60 80 100 SE +/- 0.09, N = 3 SE +/- 0.02, N = 3 SE +/- 0.12, N = 3 99.91 99.50 79.57
NAS Parallel Benchmarks Test / Class: UA.A OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: UA.A Bulldozer GCC 4.5.2 phii840 5 10 15 20 25 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 21.48 17.61
CLOMP Static OMP Speedup OpenBenchmarking.org Speedup, More Is Better CLOMP 3.3 Static OMP Speedup Bulldozer GCC 4.5.2 Bulldozer GCC 4.6.1 phii840 0.6255 1.251 1.8765 2.502 3.1275 SE +/- 0.01, N = 5 SE +/- 0.02, N = 5 SE +/- 0.02, N = 5 2.31 2.31 2.78
POV-Ray Total Time OpenBenchmarking.org Seconds, Fewer Is Better POV-Ray 3.6.1 Total Time Bulldozer GCC 4.5.2 Bulldozer GCC 4.6.1 phii840 200 400 600 800 1000 913 916 1071
NAS Parallel Benchmarks Test / Class: EP.B OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: EP.B Bulldozer GCC 4.5.2 phii840 20 40 60 80 100 SE +/- 0.14, N = 3 SE +/- 0.06, N = 3 78.97 88.81
GraphicsMagick Operation: Resizing OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.12 Operation: Resizing Bulldozer GCC 4.5.2 Bulldozer GCC 4.6.1 phii840 20 40 60 80 100 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 92 96 103
Timed MAFFT Alignment Multiple Sequence Alignment OpenBenchmarking.org Seconds, Fewer Is Better Timed MAFFT Alignment 6.706 Multiple Sequence Alignment Bulldozer GCC 4.5.2 Bulldozer GCC 4.6.1 phii840 7 14 21 28 35 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 28.86 28.83 32.02
Smallpt Global Illumination Renderer; 100 Samples OpenBenchmarking.org Seconds, Fewer Is Better Smallpt 1.0 Global Illumination Renderer; 100 Samples Bulldozer GCC 4.5.2 Bulldozer GCC 4.6.1 phii840 50 100 150 200 250 SE +/- 1.00, N = 3 SE +/- 1.20, N = 3 SE +/- 0.33, N = 3 211 215 194
SciMark Computational Test: Fast Fourier Transform OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Fast Fourier Transform Bulldozer GCC 4.5.2 Bulldozer GCC 4.6.1 phii840 16 32 48 64 80 SE +/- 1.30, N = 4 SE +/- 0.11, N = 4 SE +/- 0.13, N = 4 72.89 69.17 66.13
GraphicsMagick Operation: HWB Color Space OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.12 Operation: HWB Color Space Bulldozer GCC 4.5.2 Bulldozer GCC 4.6.1 phii840 30 60 90 120 150 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 123 134 122
TSCP AI Chess Performance OpenBenchmarking.org Nodes Per Second, More Is Better TSCP 1.81 AI Chess Performance Bulldozer GCC 4.5.2 Bulldozer GCC 4.6.1 phii840 60K 120K 180K 240K 300K SE +/- 250.13, N = 5 SE +/- 184.65, N = 5 SE +/- 189.99, N = 5 293780 286148 270068
NAS Parallel Benchmarks Test / Class: BT.A OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: BT.A Bulldozer GCC 4.5.2 phii840 1400 2800 4200 5600 7000 SE +/- 12.46, N = 3 SE +/- 11.21, N = 3 5982.31 6488.78
John The Ripper Test: MD5 OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.7.8 Test: MD5 Bulldozer GCC 4.5.2 Bulldozer GCC 4.6.1 phii840 3K 6K 9K 12K 15K SE +/- 4.70, N = 3 SE +/- 342.56, N = 3 SE +/- 15.17, N = 3 14082 13598 14677
Fhourstones Complex Connect-4 Solving OpenBenchmarking.org Kpos / sec, More Is Better Fhourstones 3.1 Complex Connect-4 Solving Bulldozer GCC 4.5.2 Bulldozer GCC 4.6.1 phii840 2K 4K 6K 8K 10K SE +/- 8.51, N = 3 SE +/- 12.73, N = 3 SE +/- 6.81, N = 3 9425.30 9221.03 8830.77
John The Ripper Test: Blowfish OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.7.8 Test: Blowfish Bulldozer GCC 4.5.2 Bulldozer GCC 4.6.1 phii840 200 400 600 800 1000 SE +/- 0.00, N = 3 SE +/- 11.67, N = 3 SE +/- 1.00, N = 3 866 895 910
OpenSSL RSA 4096-bit Performance OpenBenchmarking.org Signs Per Second, More Is Better OpenSSL 1.0.0a RSA 4096-bit Performance Bulldozer GCC 4.5.2 Bulldozer GCC 4.6.1 phii840 14 28 42 56 70 SE +/- 0.25, N = 4 SE +/- 0.31, N = 4 SE +/- 0.05, N = 4 63.65 63.83 60.85
x264 H.264 Video Encoding OpenBenchmarking.org Frames Per Second, More Is Better x264 2010-11-22 H.264 Video Encoding Bulldozer GCC 4.5.2 Bulldozer GCC 4.6.1 phii840 12 24 36 48 60 SE +/- 0.06, N = 3 SE +/- 0.13, N = 3 SE +/- 0.11, N = 3 50.19 50.89 52.57
GraphicsMagick Operation: Local Adaptive Thresholding OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.12 Operation: Local Adaptive Thresholding Bulldozer GCC 4.5.2 Bulldozer GCC 4.6.1 phii840 10 20 30 40 50 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 44 43 45
LAME MP3 Encoding WAV To MP3 OpenBenchmarking.org Seconds, Fewer Is Better LAME MP3 Encoding 3.98.2 WAV To MP3 Bulldozer GCC 4.5.2 Bulldozer GCC 4.6.1 phii840 7 14 21 28 35 SE +/- 0.01, N = 5 SE +/- 0.04, N = 5 SE +/- 0.01, N = 5 28.69 29.76 29.85
SciMark Computational Test: Monte Carlo OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Monte Carlo Bulldozer GCC 4.5.2 Bulldozer GCC 4.6.1 phii840 80 160 240 320 400 SE +/- 1.31, N = 4 SE +/- 0.31, N = 4 SE +/- 0.43, N = 4 345.55 336.07 337.66
FLAC Audio Encoding WAV To FLAC OpenBenchmarking.org Seconds, Fewer Is Better FLAC Audio Encoding 1.2.1 WAV To FLAC Bulldozer GCC 4.5.2 Bulldozer GCC 4.6.1 phii840 2 4 6 8 10 SE +/- 0.01, N = 5 SE +/- 0.01, N = 5 SE +/- 0.00, N = 5 8.75 8.66 8.51
SciMark Computational Test: Jacobi Successive Over-Relaxation OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Jacobi Successive Over-Relaxation Bulldozer GCC 4.5.2 Bulldozer GCC 4.6.1 phii840 150 300 450 600 750 SE +/- 1.27, N = 4 SE +/- 0.00, N = 4 SE +/- 1.61, N = 4 690.52 690.51 704.81
C-Ray Total Time OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 1.1 Total Time Bulldozer GCC 4.5.2 Bulldozer GCC 4.6.1 phii840 20 40 60 80 100 SE +/- 1.95, N = 3 SE +/- 0.70, N = 3 SE +/- 0.21, N = 3 106.75 105.49 107.42
7-Zip Compression Compress Speed Test OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 9.13 Compress Speed Test Bulldozer GCC 4.5.2 Bulldozer GCC 4.6.1 phii840 2K 4K 6K 8K 10K SE +/- 4.06, N = 3 SE +/- 55.43, N = 3 SE +/- 74.42, N = 3 8877 8783 8885
FFmpeg AVI To NTSC VCD OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 0.8.2 AVI To NTSC VCD Bulldozer GCC 4.5.2 Bulldozer GCC 4.6.1 phii840 4 8 12 16 20 SE +/- 0.84, N = 6 SE +/- 0.11, N = 3 SE +/- 0.07, N = 3 16.50 17.06 13.64
GraphicsMagick Operation: Sharpen OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.12 Operation: Sharpen Bulldozer GCC 4.5.2 Bulldozer GCC 4.6.1 phii840 12 24 36 48 60 SE +/- 1.00, N = 6 SE +/- 2.17, N = 6 SE +/- 0.00, N = 3 44 55 50
Phoronix Test Suite v10.8.4