Windows 8 + Core i9 7960X Intel Core i9-7960X testing with a MSI X299 SLI PLUS (MS-7A93) (1.A0 BIOS) and Microsoft Basic Display on Microsoft Windows 8.1 Pro Build 9600 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/1903133-SP-WINDOWS8C53&grs&rdt .
Windows 8 + Core i9 7960X Processor Motherboard Memory Disk Graphics Network OS Kernel Display Driver Compiler File-System Screen Resolution NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations Intel Core i9-7960X @ 2.80GHz (16 Cores / 32 Threads) MSI X299 SLI PLUS (MS-7A93) (1.A0 BIOS) 4 x 4096 MB 238GB NVMe INTEL SSDPEKKW25 Microsoft Basic Display Intel I211 Gigabit Connection + ASIX AX88772B USB2.0 to Fast + Microsoft ISATAP + LAN7500 USB 2.0 to 10/100/1000 Microsoft Windows 8.1 Pro Build 9600 6.3 (x86_64) 6.3.9600.16384 GCC 7.1.0 NTFS 1024x768 OpenBenchmarking.org Python Details - Python 2.7.15
Windows 8 + Core i9 7960X fio: Seq Write - Windows AIO - No - No - 8MB - Default Test Directory fio: Seq Write - Windows AIO - No - Yes - 8MB - Default Test Directory fio: Seq Write - Windows AIO - No - No - 4MB - Default Test Directory fio: Seq Write - Windows AIO - No - Yes - 4MB - Default Test Directory sqlite: Timed SQLite Insertions git: Time To Complete Common Git Commands fio: Rand Write - Windows AIO - No - No - 4MB - Default Test Directory fio: Seq Write - Windows AIO - No - Yes - 2MB - Default Test Directory osbench: Launch Programs apptimer: Blender 2.79 fio: Rand Write - Windows AIO - No - No - 8MB - Default Test Directory t-test1: 2 fio: Rand Write - Windows AIO - No - Yes - 2MB - Default Test Directory tesseract-ocr: Time To OCR 7 Images fio: Rand Read - Windows AIO - No - No - 2MB - Default Test Directory fio: Rand Read - Windows AIO - No - Yes - 2MB - Default Test Directory osbench: Create Threads apptimer: File Explorer osbench: Memory Allocations dacapobench: Tradesoap iozone: 1MB - 512MB - Read Performance dacapobench: Tradebeans perl-benchmark: Interpreter apptimer: LibreOffice darktable: Server Room - CPU-only redis: GET go-benchmark: http blogbench: Read gimp: resize fio: Seq Read - Windows AIO - Yes - No - 4MB - Default Test Directory fio: Seq Read - Windows AIO - Yes - No - 2MB - Default Test Directory fio: Seq Read - Windows AIO - Yes - Yes - 2MB - Default Test Directory fio: Seq Read - Windows AIO - Yes - No - 8MB - Default Test Directory apptimer: VLC Media Player gimp: rotate redis: SADD redis: LPOP darktable: Boat - CPU-only gimp: unsharp-mask redis: SET redis: LPUSH darktable: Masskrug - CPU-only fio: Rand Write - Windows AIO - No - Yes - 4MB - Default Test Directory fio: Seq Read - Windows AIO - Yes - Yes - 4MB - Default Test Directory gimp: auto-levels fio: Seq Read - Windows AIO - Yes - Yes - 8MB - Default Test Directory blogbench: Write osbench: Create Files john-the-ripper: Traditional DES fio: Rand Write - Windows AIO - Yes - No - 2MB - Default Test Directory t-test1: 1 fio: Rand Write - Windows AIO - Yes - Yes - 2MB - Default Test Directory fio: Rand Write - Windows AIO - Yes - Yes - 4MB - Default Test Directory fio: Seq Write - Windows AIO - Yes - Yes - 2MB - Default Test Directory x264: H.264 Video Encoding go-benchmark: build perl-benchmark: Pod2html iozone: 1MB - 512MB - Write Performance fio: Seq Write - Windows AIO - Yes - No - 2MB - Default Test Directory fio: Seq Write - Windows AIO - Yes - Yes - 4MB - Default Test Directory compress-zstd: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19 fio: Seq Write - Windows AIO - Yes - No - 4MB - Default Test Directory geekbench: Multi Core fio: Rand Write - Windows AIO - Yes - No - 4MB - Default Test Directory compress-7zip: Compress Speed Test stockfish: Total Time fio: Rand Read - Windows AIO - No - Yes - 8MB - Default Test Directory geekbench: Single Core fio: Seq Write - Windows AIO - Yes - No - 8MB - Default Test Directory dacapobench: H2 fio: Rand Read - Windows AIO - No - No - 8MB - Default Test Directory fio: Seq Read - Windows AIO - No - No - 8MB - Default Test Directory scimark2: Fast Fourier Transform fio: Rand Read - Windows AIO - No - Yes - 4MB - Default Test Directory fio: Rand Write - Windows AIO - Yes - Yes - 8MB - Default Test Directory unpack-linux: linux-4.15.tar.xz phpbench: PHP Benchmark Suite fio: Rand Read - Windows AIO - Yes - No - 2MB - Default Test Directory dacapobench: Jython euler3d: CFD Cycle Freq encode-flac: WAV To FLAC fio: Seq Write - Windows AIO - Yes - Yes - 8MB - Default Test Directory sunflow: Global Illumination + Image Synthesis fio: Rand Read - Windows AIO - No - No - 4MB - Default Test Directory fio: Rand Read - Windows AIO - Yes - Yes - 2MB - Default Test Directory pybench: Total For Average Test Times fio: Rand Write - Windows AIO - Yes - No - 8MB - Default Test Directory fio: Rand Read - Windows AIO - Yes - Yes - 4MB - Default Test Directory fio: Rand Write - Windows AIO - No - No - 2MB - Default Test Directory go-benchmark: garbage go-benchmark: json fio: Seq Read - Windows AIO - No - No - 2MB - Default Test Directory john-the-ripper: Blowfish openssl: RSA 4096-bit Performance cinebench: Single-Core Test cinebench: Multi-Core Test encode-mp3: WAV To MP3 fio: Seq Write - Windows AIO - No - No - 2MB - Default Test Directory fio: Rand Write - Windows AIO - No - Yes - 8MB - Default Test Directory fio: Rand Read - Windows AIO - Yes - No - 8MB - Default Test Directory fio: Rand Read - Windows AIO - Yes - No - 4MB - Default Test Directory fio: Rand Read - Windows AIO - Yes - Yes - 8MB - Default Test Directory fio: Seq Read - Windows AIO - No - No - 4MB - Default Test Directory blender: Barbershop - CPU-Only scimark2: Sparse Matrix Multiply c-ray: Total Time - 4K, 16 Rays Per Pixel john-the-ripper: MD5 fio: Seq Read - Windows AIO - No - Yes - 4MB - Default Test Directory fio: Seq Read - Windows AIO - No - Yes - 8MB - Default Test Directory darktable: Server Rack - CPU-only scimark2: Jacobi Successive Over-Relaxation scimark2: Dense LU Matrix Factorization scimark2: Monte Carlo scimark2: Composite fio: Seq Read - Windows AIO - No - Yes - 2MB - Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 286 879 285 559 43.24 19.03 263 284 1240 0.02 870 161 996 53.23 1826 2202 27.87 0.06 65.39 5837 4837 2930 0.00995273 0.40 0.51 1555518 6801 7646 16.61 4253 4266 4239 4271 0.13 24.31 1229409 1524747 0.42 56.68 1163167 965113 0.50 649 4213 37.43 4242 225 829 60588000 5866 39.58 5860 5778 3185 140 30551110050 0.15239782 965 3184 3151 10.47 3153 39303 5772 84261 43853306 2318 5164 3184 3305 2316 2408 298 2256 5761 237 361339 7450 3954 22.88 9.69 3171 1.02 2257 7448 1317 5760 7354 282 781498 3525723 2403 23676 181 194 3220 11.19 284 286 7351 7343 7347 2400 699 785 52.90 373270 2410 2411 0.34 1234 964 149 686 2411 1100 286 565 285 82.36 10.54 441 435 1875 0.03 605 222 749 65.85 2204 1833 32.64 0.07 75.56 6626 4270 3289 0.01097142 0.44 0.56 1423302 7429 7007 18.07 3921 3937 3925 3959 0.14 26.17 1144953 1420556 0.45 60.65 1092598 910014 0.53 687 3997 39.42 4039 215 864 58169500 5674 40.84 5683 5605 3090 136 31443839750 0.15682659 989 3109 3087 10.68 3095 38610 5671 82803 43157877 2354 5089 3138 3258 2349 2375 302 2286 5686 234 365923 7358 4001 23.14 9.79 3140 1.03 2279 7379 1306 5717 7301 284 786986 3546503 2389 23544 182 193 3204 11.23 285 285 7326 7319 7325 2407 701 783 52.81 372908 2409 2412 0.34 1234 964 149 686 2411 OpenBenchmarking.org
Flexible IO Tester Type: Sequential Write - IO Engine: Windows AIO - Buffered: No - Direct: No - Block Size: 8MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Sequential Write - IO Engine: Windows AIO - Buffered: No - Direct: No - Block Size: 8MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 200 400 600 800 1000 SE +/- 2.50, N = 2 286 1100
Flexible IO Tester Type: Sequential Write - IO Engine: Windows AIO - Buffered: No - Direct: Yes - Block Size: 8MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Sequential Write - IO Engine: Windows AIO - Buffered: No - Direct: Yes - Block Size: 8MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 200 400 600 800 1000 SE +/- 75.50, N = 2 879 286
Flexible IO Tester Type: Sequential Write - IO Engine: Windows AIO - Buffered: No - Direct: No - Block Size: 4MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Sequential Write - IO Engine: Windows AIO - Buffered: No - Direct: No - Block Size: 4MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 120 240 360 480 600 SE +/- 279.50, N = 2 285 565
Flexible IO Tester Type: Sequential Write - IO Engine: Windows AIO - Buffered: No - Direct: Yes - Block Size: 4MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Sequential Write - IO Engine: Windows AIO - Buffered: No - Direct: Yes - Block Size: 4MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 120 240 360 480 600 SE +/- 250.50, N = 2 559 285
SQLite Timed SQLite Insertions OpenBenchmarking.org Seconds, Fewer Is Better SQLite 3.22 Timed SQLite Insertions NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 20 40 60 80 100 SE +/- 2.28, N = 2 SE +/- 8.90, N = 2 43.24 82.36
Git Time To Complete Common Git Commands OpenBenchmarking.org Seconds, Fewer Is Better Git Time To Complete Common Git Commands NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 5 10 15 20 25 SE +/- 2.10, N = 2 SE +/- 0.07, N = 2 19.03 10.54 1. git version 2.21.0.windows.1
Flexible IO Tester Type: Random Write - IO Engine: Windows AIO - Buffered: No - Direct: No - Block Size: 4MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Random Write - IO Engine: Windows AIO - Buffered: No - Direct: No - Block Size: 4MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 100 200 300 400 500 SE +/- 19.00, N = 2 SE +/- 156.50, N = 2 263 441
Flexible IO Tester Type: Sequential Write - IO Engine: Windows AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Sequential Write - IO Engine: Windows AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 90 180 270 360 450 SE +/- 0.50, N = 2 SE +/- 152.50, N = 2 284 435
OSBench Test: Launch Programs OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Launch Programs NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 400 800 1200 1600 2000 SE +/- 786.06, N = 2 SE +/- 190.29, N = 2 1240 1875
AppTimer Time To Launch: Blender 2.79 OpenBenchmarking.org Seconds, Fewer Is Better AppTimer Time To Launch: Blender 2.79 NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 0.0068 0.0136 0.0204 0.0272 0.034 0.02 0.03
Flexible IO Tester Type: Random Write - IO Engine: Windows AIO - Buffered: No - Direct: No - Block Size: 8MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Random Write - IO Engine: Windows AIO - Buffered: No - Direct: No - Block Size: 8MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 200 400 600 800 1000 SE +/- 2.50, N = 2 SE +/- 131.00, N = 2 870 605
t-test1 Threads: 2 OpenBenchmarking.org Seconds, Fewer Is Better t-test1 2017-01-13 Threads: 2 NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 50 100 150 200 250 SE +/- 0.20, N = 2 SE +/- 0.04, N = 2 161 222
Flexible IO Tester Type: Random Write - IO Engine: Windows AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Random Write - IO Engine: Windows AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 200 400 600 800 1000 SE +/- 52.00, N = 2 SE +/- 360.00, N = 2 996 749
Tesseract OCR Time To OCR 7 Images OpenBenchmarking.org Seconds, Fewer Is Better Tesseract OCR v4.0.0.20181030 Time To OCR 7 Images NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 15 30 45 60 75 SE +/- 0.22, N = 2 SE +/- 0.05, N = 2 53.23 65.85
Flexible IO Tester Type: Random Read - IO Engine: Windows AIO - Buffered: No - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Random Read - IO Engine: Windows AIO - Buffered: No - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 500 1000 1500 2000 2500 SE +/- 373.50, N = 2 SE +/- 2.50, N = 2 1826 2204
Flexible IO Tester Type: Random Read - IO Engine: Windows AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Random Read - IO Engine: Windows AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 500 1000 1500 2000 2500 SE +/- 1.00, N = 2 SE +/- 381.00, N = 2 2202 1833
OSBench Test: Create Threads OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Threads NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 8 16 24 32 40 SE +/- 0.26, N = 2 SE +/- 0.34, N = 2 27.87 32.64
AppTimer Time To Launch: File Explorer OpenBenchmarking.org Seconds, Fewer Is Better AppTimer Time To Launch: File Explorer NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 0.0158 0.0316 0.0474 0.0632 0.079 0.06 0.07
OSBench Test: Memory Allocations OpenBenchmarking.org Ns Per Event, Fewer Is Better OSBench Test: Memory Allocations NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 20 40 60 80 100 SE +/- 1.81, N = 2 SE +/- 0.04, N = 2 65.39 75.56
DaCapo Benchmark Java Test: Tradesoap OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Tradesoap NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 1400 2800 4200 5600 7000 SE +/- 23.00, N = 2 5837 6626
IOzone Record Size: 1MB - File Size: 512MB - Disk Test: Read Performance OpenBenchmarking.org MB/s, More Is Better IOzone 3.465 Record Size: 1MB - File Size: 512MB - Disk Test: Read Performance NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 1000 2000 3000 4000 5000 SE +/- 116.97, N = 2 SE +/- 68.41, N = 2 4837 4270
DaCapo Benchmark Java Test: Tradebeans OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Tradebeans NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 700 1400 2100 2800 3500 SE +/- 23.00, N = 2 SE +/- 23.00, N = 2 2930 3289
Perl Benchmarks Test: Interpreter OpenBenchmarking.org Seconds, Fewer Is Better Perl Benchmarks Test: Interpreter NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 0.0025 0.005 0.0075 0.01 0.0125 SE +/- 0.00022783, N = 2 SE +/- 0.00019539, N = 2 0.00995273 0.01097142
AppTimer Time To Launch: LibreOffice OpenBenchmarking.org Seconds, Fewer Is Better AppTimer Time To Launch: LibreOffice NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 0.099 0.198 0.297 0.396 0.495 0.40 0.44
Darktable Test: Server Room - Acceleration: CPU-only OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.4.1 Test: Server Room - Acceleration: CPU-only NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 0.126 0.252 0.378 0.504 0.63 SE +/- 0.01, N = 2 SE +/- 0.01, N = 2 0.51 0.56
Redis Test: GET OpenBenchmarking.org Requests Per Second, More Is Better Redis 3.2.1 Test: GET NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 300K 600K 900K 1200K 1500K SE +/- 10162.06, N = 2 SE +/- 21367.19, N = 2 1555518 1423302
Go Benchmarks Test: http OpenBenchmarking.org Nanoseconds/Operation, Fewer Is Better Go Benchmarks Test: http NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 1600 3200 4800 6400 8000 SE +/- 88.50, N = 2 SE +/- 67.00, N = 2 6801 7429
BlogBench Test: Read OpenBenchmarking.org Final Score, More Is Better BlogBench 1.1 Test: Read NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 1600 3200 4800 6400 8000 SE +/- 150.50, N = 2 SE +/- 21.00, N = 2 7646 7007
GIMP Test: resize OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.0 Test: resize NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 4 8 12 16 20 SE +/- 1.60, N = 2 SE +/- 1.47, N = 2 16.61 18.07
Flexible IO Tester Type: Sequential Read - IO Engine: Windows AIO - Buffered: Yes - Direct: No - Block Size: 4MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Sequential Read - IO Engine: Windows AIO - Buffered: Yes - Direct: No - Block Size: 4MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 900 1800 2700 3600 4500 SE +/- 4.00, N = 2 SE +/- 5.50, N = 2 4253 3921
Flexible IO Tester Type: Sequential Read - IO Engine: Windows AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Sequential Read - IO Engine: Windows AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 900 1800 2700 3600 4500 SE +/- 10.00, N = 2 SE +/- 1.50, N = 2 4266 3937
Flexible IO Tester Type: Sequential Read - IO Engine: Windows AIO - Buffered: Yes - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Sequential Read - IO Engine: Windows AIO - Buffered: Yes - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 900 1800 2700 3600 4500 SE +/- 4.00, N = 2 SE +/- 23.00, N = 2 4239 3925
Flexible IO Tester Type: Sequential Read - IO Engine: Windows AIO - Buffered: Yes - Direct: No - Block Size: 8MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Sequential Read - IO Engine: Windows AIO - Buffered: Yes - Direct: No - Block Size: 8MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 900 1800 2700 3600 4500 SE +/- 1.00, N = 2 4271 3959
AppTimer Time To Launch: VLC Media Player OpenBenchmarking.org Seconds, Fewer Is Better AppTimer Time To Launch: VLC Media Player NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 0.0315 0.063 0.0945 0.126 0.1575 0.13 0.14
GIMP Test: rotate OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.0 Test: rotate NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 6 12 18 24 30 SE +/- 0.06, N = 2 SE +/- 0.03, N = 2 24.31 26.17
Redis Test: SADD OpenBenchmarking.org Requests Per Second, More Is Better Redis 3.2.1 Test: SADD NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 300K 600K 900K 1200K 1500K SE +/- 9748.25, N = 2 SE +/- 1442.00, N = 2 1229409 1144953
Redis Test: LPOP OpenBenchmarking.org Requests Per Second, More Is Better Redis 3.2.1 Test: LPOP NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 300K 600K 900K 1200K 1500K SE +/- 3603.50, N = 2 SE +/- 1109.94, N = 2 1524747 1420556
Darktable Test: Boat - Acceleration: CPU-only OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.4.1 Test: Boat - Acceleration: CPU-only NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 0.1013 0.2026 0.3039 0.4052 0.5065 SE +/- 0.00, N = 2 SE +/- 0.00, N = 2 0.42 0.45
GIMP Test: unsharp-mask OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.0 Test: unsharp-mask NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 14 28 42 56 70 SE +/- 0.09, N = 2 SE +/- 0.01, N = 2 56.68 60.65
Redis Test: SET OpenBenchmarking.org Requests Per Second, More Is Better Redis 3.2.1 Test: SET NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 200K 400K 600K 800K 1000K SE +/- 11093.25, N = 2 SE +/- 537.19, N = 2 1163167 1092598
Redis Test: LPUSH OpenBenchmarking.org Requests Per Second, More Is Better Redis 3.2.1 Test: LPUSH NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 200K 400K 600K 800K 1000K SE +/- 1164.28, N = 2 SE +/- 3395.28, N = 2 965113 910014
Darktable Test: Masskrug - Acceleration: CPU-only OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.4.1 Test: Masskrug - Acceleration: CPU-only NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 0.1193 0.2386 0.3579 0.4772 0.5965 SE +/- 0.02, N = 2 SE +/- 0.02, N = 2 0.50 0.53
Flexible IO Tester Type: Random Write - IO Engine: Windows AIO - Buffered: No - Direct: Yes - Block Size: 4MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Random Write - IO Engine: Windows AIO - Buffered: No - Direct: Yes - Block Size: 4MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 150 300 450 600 750 SE +/- 430.00, N = 2 SE +/- 403.00, N = 2 649 687
Flexible IO Tester Type: Sequential Read - IO Engine: Windows AIO - Buffered: Yes - Direct: Yes - Block Size: 4MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Sequential Read - IO Engine: Windows AIO - Buffered: Yes - Direct: Yes - Block Size: 4MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 900 1800 2700 3600 4500 SE +/- 4.50, N = 2 SE +/- 5.50, N = 2 4213 3997
GIMP Test: auto-levels OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.0 Test: auto-levels NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 9 18 27 36 45 SE +/- 0.07, N = 2 SE +/- 0.03, N = 2 37.43 39.42
Flexible IO Tester Type: Sequential Read - IO Engine: Windows AIO - Buffered: Yes - Direct: Yes - Block Size: 8MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Sequential Read - IO Engine: Windows AIO - Buffered: Yes - Direct: Yes - Block Size: 8MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 900 1800 2700 3600 4500 SE +/- 2.50, N = 2 SE +/- 3.50, N = 2 4242 4039
BlogBench Test: Write OpenBenchmarking.org Final Score, More Is Better BlogBench 1.1 Test: Write NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 50 100 150 200 250 SE +/- 8.00, N = 2 SE +/- 5.00, N = 2 225 215
OSBench Test: Create Files OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Files NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 200 400 600 800 1000 SE +/- 31.61, N = 2 SE +/- 28.45, N = 2 829 864
John The Ripper Test: Traditional DES OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.8.0-jumbo-1 Test: Traditional DES NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 13M 26M 39M 52M 65M SE +/- 107000.00, N = 2 SE +/- 553500.00, N = 2 60588000 58169500
Flexible IO Tester Type: Random Write - IO Engine: Windows AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Random Write - IO Engine: Windows AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 1300 2600 3900 5200 6500 SE +/- 22.00, N = 2 SE +/- 12.50, N = 2 5866 5674
t-test1 Threads: 1 OpenBenchmarking.org Seconds, Fewer Is Better t-test1 2017-01-13 Threads: 1 NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 9 18 27 36 45 SE +/- 0.71, N = 2 SE +/- 0.01, N = 2 39.58 40.84
Flexible IO Tester Type: Random Write - IO Engine: Windows AIO - Buffered: Yes - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Random Write - IO Engine: Windows AIO - Buffered: Yes - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 1300 2600 3900 5200 6500 SE +/- 16.50, N = 2 SE +/- 7.50, N = 2 5860 5683
Flexible IO Tester Type: Random Write - IO Engine: Windows AIO - Buffered: Yes - Direct: Yes - Block Size: 4MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Random Write - IO Engine: Windows AIO - Buffered: Yes - Direct: Yes - Block Size: 4MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 1200 2400 3600 4800 6000 SE +/- 43.50, N = 2 SE +/- 5.50, N = 2 5778 5605
Flexible IO Tester Type: Sequential Write - IO Engine: Windows AIO - Buffered: Yes - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Sequential Write - IO Engine: Windows AIO - Buffered: Yes - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 700 1400 2100 2800 3500 SE +/- 2.00, N = 2 SE +/- 1.50, N = 2 3185 3090
x264 H.264 Video Encoding OpenBenchmarking.org Frames Per Second, More Is Better x264 2018-09-25 H.264 Video Encoding NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 30 60 90 120 150 SE +/- 1.01, N = 2 SE +/- 0.96, N = 2 140 136
Go Benchmarks Test: build OpenBenchmarking.org Nanoseconds/Operation, Fewer Is Better Go Benchmarks Test: build NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 7000M 14000M 21000M 28000M 35000M SE +/- 4206425350.00, N = 2 SE +/- 4293071650.00, N = 2 30551110050 31443839750
Perl Benchmarks Test: Pod2html OpenBenchmarking.org Seconds, Fewer Is Better Perl Benchmarks Test: Pod2html NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 0.0353 0.0706 0.1059 0.1412 0.1765 SE +/- 0.00038525, N = 2 SE +/- 0.00060709, N = 2 0.15239782 0.15682659
IOzone Record Size: 1MB - File Size: 512MB - Disk Test: Write Performance OpenBenchmarking.org MB/s, More Is Better IOzone 3.465 Record Size: 1MB - File Size: 512MB - Disk Test: Write Performance NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 200 400 600 800 1000 SE +/- 23.03, N = 2 SE +/- 6.70, N = 2 965 989
Flexible IO Tester Type: Sequential Write - IO Engine: Windows AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Sequential Write - IO Engine: Windows AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 700 1400 2100 2800 3500 SE +/- 7.00, N = 2 SE +/- 3.50, N = 2 3184 3109
Flexible IO Tester Type: Sequential Write - IO Engine: Windows AIO - Buffered: Yes - Direct: Yes - Block Size: 4MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Sequential Write - IO Engine: Windows AIO - Buffered: Yes - Direct: Yes - Block Size: 4MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 700 1400 2100 2800 3500 SE +/- 10.00, N = 2 SE +/- 1.00, N = 2 3151 3087
Zstd Compression Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19 OpenBenchmarking.org Seconds, Fewer Is Better Zstd Compression 1.3.4 Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19 NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 3 6 9 12 15 SE +/- 0.01, N = 2 SE +/- 0.05, N = 2 10.47 10.68
Flexible IO Tester Type: Sequential Write - IO Engine: Windows AIO - Buffered: Yes - Direct: No - Block Size: 4MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Sequential Write - IO Engine: Windows AIO - Buffered: Yes - Direct: No - Block Size: 4MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 700 1400 2100 2800 3500 SE +/- 24.00, N = 2 SE +/- 7.50, N = 2 3153 3095
Geekbench Test: Multi Core OpenBenchmarking.org Score, More Is Better Geekbench 4.3.3 Test: Multi Core NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 8K 16K 24K 32K 40K SE +/- 33.50, N = 2 SE +/- 5.00, N = 2 39303 38610
Flexible IO Tester Type: Random Write - IO Engine: Windows AIO - Buffered: Yes - Direct: No - Block Size: 4MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Random Write - IO Engine: Windows AIO - Buffered: Yes - Direct: No - Block Size: 4MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 1200 2400 3600 4800 6000 SE +/- 29.00, N = 2 SE +/- 25.00, N = 2 5772 5671
7-Zip Compression Compress Speed Test OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 16.02 Compress Speed Test NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 20K 40K 60K 80K 100K SE +/- 707.50, N = 2 SE +/- 344.00, N = 2 84261 82803
Stockfish Total Time OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 9 Total Time NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 9M 18M 27M 36M 45M SE +/- 370611.00, N = 2 SE +/- 31953.00, N = 2 43853306 43157877
Flexible IO Tester Type: Random Read - IO Engine: Windows AIO - Buffered: No - Direct: Yes - Block Size: 8MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Random Read - IO Engine: Windows AIO - Buffered: No - Direct: Yes - Block Size: 8MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 500 1000 1500 2000 2500 SE +/- 0.50, N = 2 2318 2354
Geekbench Test: Single Core OpenBenchmarking.org Score, More Is Better Geekbench 4.3.3 Test: Single Core NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 1100 2200 3300 4400 5500 SE +/- 1.50, N = 2 SE +/- 2.50, N = 2 5164 5089
Flexible IO Tester Type: Sequential Write - IO Engine: Windows AIO - Buffered: Yes - Direct: No - Block Size: 8MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Sequential Write - IO Engine: Windows AIO - Buffered: Yes - Direct: No - Block Size: 8MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 700 1400 2100 2800 3500 SE +/- 8.00, N = 2 SE +/- 5.00, N = 2 3184 3138
DaCapo Benchmark Java Test: H2 OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: H2 NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 700 1400 2100 2800 3500 SE +/- 164.00, N = 2 SE +/- 39.00, N = 2 3305 3258
Flexible IO Tester Type: Random Read - IO Engine: Windows AIO - Buffered: No - Direct: No - Block Size: 8MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Random Read - IO Engine: Windows AIO - Buffered: No - Direct: No - Block Size: 8MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 500 1000 1500 2000 2500 SE +/- 2.00, N = 2 2316 2349
Flexible IO Tester Type: Sequential Read - IO Engine: Windows AIO - Buffered: No - Direct: No - Block Size: 8MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Sequential Read - IO Engine: Windows AIO - Buffered: No - Direct: No - Block Size: 8MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 500 1000 1500 2000 2500 SE +/- 1.50, N = 2 SE +/- 29.50, N = 2 2408 2375
SciMark Computational Test: Fast Fourier Transform OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Fast Fourier Transform NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 70 140 210 280 350 SE +/- 2.40, N = 2 SE +/- 0.85, N = 2 298 302
Flexible IO Tester Type: Random Read - IO Engine: Windows AIO - Buffered: No - Direct: Yes - Block Size: 4MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Random Read - IO Engine: Windows AIO - Buffered: No - Direct: Yes - Block Size: 4MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 500 1000 1500 2000 2500 SE +/- 3.50, N = 2 SE +/- 1.00, N = 2 2256 2286
Flexible IO Tester Type: Random Write - IO Engine: Windows AIO - Buffered: Yes - Direct: Yes - Block Size: 8MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Random Write - IO Engine: Windows AIO - Buffered: Yes - Direct: Yes - Block Size: 8MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 1200 2400 3600 4800 6000 SE +/- 10.50, N = 2 SE +/- 12.50, N = 2 5761 5686
Unpacking The Linux Kernel linux-4.15.tar.xz OpenBenchmarking.org Seconds, Fewer Is Better Unpacking The Linux Kernel linux-4.15.tar.xz NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 50 100 150 200 250 SE +/- 3.57, N = 2 SE +/- 2.01, N = 2 237 234
PHPBench PHP Benchmark Suite OpenBenchmarking.org Score, More Is Better PHPBench 0.8.1 PHP Benchmark Suite NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 80K 160K 240K 320K 400K SE +/- 49.50, N = 2 SE +/- 29.50, N = 2 361339 365923
Flexible IO Tester Type: Random Read - IO Engine: Windows AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Random Read - IO Engine: Windows AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 1600 3200 4800 6400 8000 SE +/- 4.00, N = 2 7450 7358
DaCapo Benchmark Java Test: Jython OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Jython NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 900 1800 2700 3600 4500 SE +/- 15.50, N = 2 SE +/- 31.50, N = 2 3954 4001
Euler3D CFD Cycle Frequency OpenBenchmarking.org Hz, More Is Better Euler3D CFD Cycle Frequency NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 6 12 18 24 30 SE +/- 3.03, N = 2 SE +/- 2.82, N = 2 22.88 23.14
FLAC Audio Encoding WAV To FLAC OpenBenchmarking.org Seconds, Fewer Is Better FLAC Audio Encoding 1.3.2 WAV To FLAC NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 3 6 9 12 15 SE +/- 0.00, N = 2 SE +/- 0.03, N = 2 9.69 9.79
Flexible IO Tester Type: Sequential Write - IO Engine: Windows AIO - Buffered: Yes - Direct: Yes - Block Size: 8MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Sequential Write - IO Engine: Windows AIO - Buffered: Yes - Direct: Yes - Block Size: 8MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 700 1400 2100 2800 3500 SE +/- 10.50, N = 2 SE +/- 1.50, N = 2 3171 3140
Sunflow Rendering System Global Illumination + Image Synthesis OpenBenchmarking.org Seconds, Fewer Is Better Sunflow Rendering System 0.07.2 Global Illumination + Image Synthesis NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 0.2318 0.4636 0.6954 0.9272 1.159 SE +/- 0.08, N = 2 SE +/- 0.07, N = 2 1.02 1.03
Flexible IO Tester Type: Random Read - IO Engine: Windows AIO - Buffered: No - Direct: No - Block Size: 4MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Random Read - IO Engine: Windows AIO - Buffered: No - Direct: No - Block Size: 4MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 500 1000 1500 2000 2500 SE +/- 1.00, N = 2 2257 2279
Flexible IO Tester Type: Random Read - IO Engine: Windows AIO - Buffered: Yes - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Random Read - IO Engine: Windows AIO - Buffered: Yes - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 1600 3200 4800 6400 8000 SE +/- 8.50, N = 2 SE +/- 6.50, N = 2 7448 7379
PyBench Total For Average Test Times OpenBenchmarking.org Milliseconds, Fewer Is Better PyBench 2018-02-16 Total For Average Test Times NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 300 600 900 1200 1500 SE +/- 5.50, N = 2 1317 1306
Flexible IO Tester Type: Random Write - IO Engine: Windows AIO - Buffered: Yes - Direct: No - Block Size: 8MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Random Write - IO Engine: Windows AIO - Buffered: Yes - Direct: No - Block Size: 8MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 1200 2400 3600 4800 6000 SE +/- 16.00, N = 2 SE +/- 5.50, N = 2 5760 5717
Flexible IO Tester Type: Random Read - IO Engine: Windows AIO - Buffered: Yes - Direct: Yes - Block Size: 4MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Random Read - IO Engine: Windows AIO - Buffered: Yes - Direct: Yes - Block Size: 4MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 1600 3200 4800 6400 8000 SE +/- 3.00, N = 2 SE +/- 4.00, N = 2 7354 7301
Flexible IO Tester Type: Random Write - IO Engine: Windows AIO - Buffered: No - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Random Write - IO Engine: Windows AIO - Buffered: No - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 60 120 180 240 300 SE +/- 0.50, N = 2 SE +/- 0.50, N = 2 282 284
Go Benchmarks Test: garbage OpenBenchmarking.org Nanoseconds/Operation, Fewer Is Better Go Benchmarks Test: garbage NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 200K 400K 600K 800K 1000K SE +/- 2014.00, N = 2 SE +/- 3647.00, N = 2 781498 786986
Go Benchmarks Test: json OpenBenchmarking.org Nanoseconds/Operation, Fewer Is Better Go Benchmarks Test: json NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 800K 1600K 2400K 3200K 4000K SE +/- 12220.00, N = 2 SE +/- 3534.00, N = 2 3525723 3546503
Flexible IO Tester Type: Sequential Read - IO Engine: Windows AIO - Buffered: No - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Sequential Read - IO Engine: Windows AIO - Buffered: No - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 500 1000 1500 2000 2500 SE +/- 3.00, N = 2 SE +/- 5.50, N = 2 2403 2389
John The Ripper Test: Blowfish OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.8.0-jumbo-1 Test: Blowfish NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 5K 10K 15K 20K 25K SE +/- 77.00, N = 2 23676 23544
OpenSSL RSA 4096-bit Performance OpenBenchmarking.org Signs Per Second, More Is Better OpenSSL 1.0.1g RSA 4096-bit Performance NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 40 80 120 160 200 SE +/- 0.50, N = 2 SE +/- 0.15, N = 2 181 182
Maxon Cinebench Test: Single-Core Test OpenBenchmarking.org pts, More Is Better Maxon Cinebench 15.038 Test: Single-Core Test NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 40 80 120 160 200 194 193
Maxon Cinebench Test: Multi-Core Test OpenBenchmarking.org pts, More Is Better Maxon Cinebench 15.038 Test: Multi-Core Test NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 700 1400 2100 2800 3500 3220 3204
LAME MP3 Encoding WAV To MP3 OpenBenchmarking.org Seconds, Fewer Is Better LAME MP3 Encoding 3.100 WAV To MP3 NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 3 6 9 12 15 SE +/- 0.02, N = 2 SE +/- 0.01, N = 2 11.19 11.23
Flexible IO Tester Type: Sequential Write - IO Engine: Windows AIO - Buffered: No - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Sequential Write - IO Engine: Windows AIO - Buffered: No - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 60 120 180 240 300 SE +/- 1.00, N = 2 SE +/- 0.50, N = 2 284 285
Flexible IO Tester Type: Random Write - IO Engine: Windows AIO - Buffered: No - Direct: Yes - Block Size: 8MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Random Write - IO Engine: Windows AIO - Buffered: No - Direct: Yes - Block Size: 8MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 60 120 180 240 300 SE +/- 0.50, N = 2 286 285
Flexible IO Tester Type: Random Read - IO Engine: Windows AIO - Buffered: Yes - Direct: No - Block Size: 8MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Random Read - IO Engine: Windows AIO - Buffered: Yes - Direct: No - Block Size: 8MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 1600 3200 4800 6400 8000 SE +/- 3.00, N = 2 SE +/- 8.00, N = 2 7351 7326
Flexible IO Tester Type: Random Read - IO Engine: Windows AIO - Buffered: Yes - Direct: No - Block Size: 4MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Random Read - IO Engine: Windows AIO - Buffered: Yes - Direct: No - Block Size: 4MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 1600 3200 4800 6400 8000 SE +/- 2.50, N = 2 7343 7319
Flexible IO Tester Type: Random Read - IO Engine: Windows AIO - Buffered: Yes - Direct: Yes - Block Size: 8MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Random Read - IO Engine: Windows AIO - Buffered: Yes - Direct: Yes - Block Size: 8MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 1600 3200 4800 6400 8000 SE +/- 1.00, N = 2 SE +/- 3.00, N = 2 7347 7325
Flexible IO Tester Type: Sequential Read - IO Engine: Windows AIO - Buffered: No - Direct: No - Block Size: 4MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Sequential Read - IO Engine: Windows AIO - Buffered: No - Direct: No - Block Size: 4MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 500 1000 1500 2000 2500 SE +/- 9.00, N = 2 SE +/- 1.00, N = 2 2400 2407
Blender Blend File: Barbershop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.79a Blend File: Barbershop - Compute: CPU-Only NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 150 300 450 600 750 699 701
SciMark Computational Test: Sparse Matrix Multiply OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Sparse Matrix Multiply NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 200 400 600 800 1000 SE +/- 0.16, N = 2 SE +/- 2.39, N = 2 785 783
C-Ray Total Time - 4K, 16 Rays Per Pixel OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 1.1 Total Time - 4K, 16 Rays Per Pixel NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 12 24 36 48 60 SE +/- 0.09, N = 2 SE +/- 0.01, N = 2 52.90 52.81
John The Ripper Test: MD5 OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.8.0-jumbo-1 Test: MD5 NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 80K 160K 240K 320K 400K SE +/- 2248.00, N = 2 SE +/- 171.00, N = 2 373270 372908
Flexible IO Tester Type: Sequential Read - IO Engine: Windows AIO - Buffered: No - Direct: Yes - Block Size: 4MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Sequential Read - IO Engine: Windows AIO - Buffered: No - Direct: Yes - Block Size: 4MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 500 1000 1500 2000 2500 SE +/- 0.50, N = 2 SE +/- 2.00, N = 2 2410 2409
Flexible IO Tester Type: Sequential Read - IO Engine: Windows AIO - Buffered: No - Direct: Yes - Block Size: 8MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Sequential Read - IO Engine: Windows AIO - Buffered: No - Direct: Yes - Block Size: 8MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 500 1000 1500 2000 2500 SE +/- 0.50, N = 2 SE +/- 1.00, N = 2 2411 2412
Darktable Test: Server Rack - Acceleration: CPU-only OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.4.1 Test: Server Rack - Acceleration: CPU-only NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 0.0765 0.153 0.2295 0.306 0.3825 SE +/- 0.01, N = 2 SE +/- 0.01, N = 2 0.34 0.34
SciMark Computational Test: Jacobi Successive Over-Relaxation OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Jacobi Successive Over-Relaxation NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 300 600 900 1200 1500 SE +/- 0.25, N = 2 SE +/- 0.00, N = 2 1234 1234
SciMark Computational Test: Dense LU Matrix Factorization OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Dense LU Matrix Factorization NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 200 400 600 800 1000 SE +/- 0.00, N = 2 SE +/- 0.18, N = 2 964 964
SciMark Computational Test: Monte Carlo OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Monte Carlo NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 30 60 90 120 150 SE +/- 0.02, N = 2 SE +/- 0.31, N = 2 149 149
SciMark Computational Test: Composite OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Composite NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 150 300 450 600 750 SE +/- 0.45, N = 2 SE +/- 0.28, N = 2 686 686
Flexible IO Tester Type: Sequential Read - IO Engine: Windows AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Sequential Read - IO Engine: Windows AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory NVMe INTEL SSDPEKKW25 Spectre + Meltdown Mitigations 500 1000 1500 2000 2500 SE +/- 0.50, N = 2 SE +/- 0.50, N = 2 2411 2411
Phoronix Test Suite v10.8.5