The top 50+ fastest computers in the Weaver Research Group

See also my Green List which has power and GFLOPS/W results for all of these machines.

The raw data for these rankings is available here: http://github.com/deater/performance_results.git

# Name FLOPS arch vendor type Cores/Threads RAM Other Linpack Settings
1 haswell-ep 436 GFLOPS x86_64 Intel 6/63/2 hsw e5-2640v3 16 (32) 80GB (N=100000, 16 threads, OpenBLAS)
2 power8 195 GFLOPS ppc64el IBM power8 8348-21c 8 (64) 32GB (N=40000, 8 threads, OpenBLAS)
3 broadwell-ep 184 GFLOPS x86_64 Intel 6/79/1 bdw e5-2620v4 8 (16) 32GB (N=50000, 8 threads, OpenBLAS)
4 haswell/quadro (CPU only) 180 GFLOPS x86_64 Intel 6/60/3 hsw i7-4790 4 (8) 16GB Quadro K2200 (N=40000, 4 threads, OpenBLAS)
! haswell/quadro (GPU only) 38.4 GFLOPS (Double) NVIDIA Quadro K2200 4GB (N=40000, hpl-cuda)
5 m1 (CPU only) 154 GFLOPS ARM Apple m1 Macbook Air 4 (8) 16GB (N=12000, 4 threads, OpenBLAS)
6 skylake desktop 161 GFLOPS x86_64 Intel 6/94/3 skl i7-6700 4 (8) 8GB (N=30000, 4 threads, OpenBLAS)
7 haswell desktop 145 GFLOPS x86_64 Intel 6/60/3 hsw i7-4770 4 (8) 4GB (N=20000, 4 threads, OpenBLAS)
8 fam17h-epyc 131 GFLOPS x86_64 AMD 23/1/2 EPYC 7251 8 (16) 16GB (N=42000, 8 threads, OpenBLAS)
9 fam15h-piledriver 117 GFLOPS x86_64 AMD 21/2/0 Opteron 6376 16 (32) 16GB (N=40000, 16 threads, OpenBLAS)
10 haswell desktop (instrumented) 115 GFLOPS x86_64 Intel 6/60/3 hsw i5-4570S 4 (4) 4GB (N=20000, 4 threads, OpenBLAS)
11 sandybridge-ep 85 GFLOPS x86_64 Intel 6/45/? snb 12 (24) 16GB (N=40000 12 threads, ATLAS)
12 elitebook 77 GFLOPS x86_64 AMD 23/24/1 Ryzen 7-3700U 4 (8) 16GB Zen+ elitebook laptop (N=20000, 4 threads, OpenBLAS)
13 broadwell NUC 66 GFLOPS x86_64 Intel 6/61/4 Broadwell i7-5557U 2 (4) 8GB Intel NUC (N=20000, 2 threads, OpenBLAS)
14 fam15h-a10 54 GFLOPS x86_64 AMD 21/19/1 A10-6800B 4 8GB (N=30000, 4 threads, OpenBLAS)
15 broadwell MacBookAir 51 GFLOPS x86_64 Intel 6/61/4 Broadwell i5-5250U 2 (4) 4GB macbook-air (N=20000, 2 threads, OpenBLAS)
16 pi4 Cluster 50.7 GFLOPS arm64 pi4 Cortex A72 20 24GB pi-cluster2 (N=40000, 20 threads, OpenBLAS)
17 fam10h-phenom 41 GFLOPS x86_64 AMD 16/4/3 Phenom II X4 955 4 2GB (N=15000, 4 threads, OpenBLAS)
18 ivb-mac-mini 40 GFLOPS x86_64 Intel 6/58/9 ivb i5-3210M 2 (4) 4GB (N=20000, 2 threads, OpenBLAS)
19 ivb-macbook-air 36 GFLOPS x86_64 Intel 6/58/9 ivb i5-3427U 2 (4) 4GB (N=10000, 2 threads, OpenBLAS)
20 core2 18.4 GFLOPS x86_64 Intel 6/23/10 Core2 P8700 2 4GB (N=20000, 2 threads, OpenBLAS)
21 jetson-tx1 16.0 GFLOPS ARM ARMv8 CortexA57 4 4GB NVIDIA (N=20000, 4 thread, OpenBLAS)
22 pi-cluster 15.4 GFLOPS arm Cortex A7 Raspberry Pi 2 96 24GB (N=48000, OpenBLAS)
23 fam16h-a8-jaguar 14.0 GFLOPS x86_64 AMD 22/48/1 A8-6410 4 4GB (N=10000, 4 threads, OpenBLAS)
24 Raspberry Pi-400 (4GB) 13.8 GFLOPS ARM ARMv8 Cortex A72 4 4GB (N=12000, 4 threads, OpenBLAS)
25 Raspberry Pi-4B (4GB) (64-bit user/kernel) 13.5 GFLOPS ARM64 / aarch64 ARMv8 Cortex A72 4 4GB (N=20000, 4 threads, OpenBLAS)
26 Pentium D 11.8 GFLOPS x86_64 Intel 15/6/5 Pentium 4/D 1 (2) 1GB (N=10000, 2 threads, OpenBLAS)
27 Raspberry Pi-4B (1GB) 10.3 GFLOPS ARM ARMv7/v8 Cortex A72 4 1GB (N=9000, 4 threads, OpenBLAS)
28 Raspberry Pi-4B (4GB) 9.9 GFLOPS ARM ARMv7/v8 Cortex A72 4 4GB (N=19000, 4 threads, OpenBLAS)
29 odroid-xu 8.3 GFLOPS ARM ARMv7 Cortex A7/A15 4 Big 4 Little 2GB Exynos 5 Octa (N=12000, 4 threads, OpenBLAS)
30 Raspberry pi-3B+ 5.47 GFLOPS ARM ARMv7/8 Cortex A53 4 1GB 3 Model B+ (N=6000, 4 threads, OpenBLAS)
31 chromebook 5.44 GFLOPS ARM ARMv7 Cortex A15 2 2GB Exynos 5 Dual (N=10000, 2 threads, OpenBLAS)
32 beaglev 5.27 GFLOPS RISCV RISCV64 TH1520 4 4GB BeagleV-Ahead (N=8000, 4 threads, OpenBLAS)
33 Raspberry Pi Zero 2 W 5.10 GFLOPS ARM ARMv7/8 Cortex A53 4 512MB (N=6000, 4 threads, OpenBLAS)
34 Raspberry Pi-3A+ 4.93 GFLOPS ARM ARMv7/8 Cortex A53 4 512MB (N=5000, 4 threads, OpenBLAS)
35 Raspberry pi-2b-v1.2 4.39 GFLOPS ARM ARMv7/8 Cortex A53 4 1GB 2 Model B v1.2 (N=8000, 4 threads, OpenBLAS)
36 Raspberry pi-3b 3.62 GFLOPS ARM ARMv7/8 Cortex A53 4 1GB 3 Model B (N=8000*, 4 threads, OpenBLAS)
37 atom-cedarview server 3.35 GFLOPS x86_64 Intel 6/54/9 Atom S1260 2 (4) 4GB (N=20000, 2 threads, OpenBLAS)
38 atom-cedarview desktop 2.97 GFLOPS x86_64 Intel 6/54/1 Atom D2550 2 (4) 4GB (N=20000, 4 threads, OpenBLAS)
39 fam14h-bobcat 2.76 GFLOPS x86_64 AMD 20/2/0 Bobcat 2 2GB G-T56N (N=8000, 2 threads, OpenBLAS)
40 dragonboard 2.22 GFLOPS ARM ARMv8 Cortex-A53 4 1GB Snapdragon 410c (N=8000, 4 threads, OpenBLAS)
41 Raspberry pi-2b 1.47 GFLOPS ARM ARMv7 Cortex A7 4 1GB Model 2 (N=10000, 4 threads, OpenBLAS)
42 atom-eeepc 1.36 GFLOPS x86 Intel 6/28/2 Atom N270 1 (2) 2GB eeepc 901 (N=10000, 2 threads, OpenBLAS)
43 pandaboard-es 0.915 GFLOPS ARM ARMv7 Cortex A9 2 1GB ES, OMAP4 (N=5000 *, 2 threads, OpenBLAS)
44 cubieboard2 0.859 GFLOPS ARM ARMv7 Cortex A7 2 1GB Allwinner A20 (N=8000, 2 threads, OpenBLAS)
45 sparc 0.423 GFLOPS SUN SPARC Ultra 1 512MB TI Ultrasparc II (N=5000, 1 thread, OpenBLAS)
46 Raspberry pi-zero 0.319 GFLOPS ARM ARMv6 BCM2835 1 512MB Model Zero (N=5000, 1 thread, OpenBLAS)
47 Raspberry pi-zero-w 0.247 GFLOPS ARM ARMv6 BCM2835 1 512MB Model Zero W (N=4000, 1 thread, OpenBLAS)
48 Pentium II 0.241 GFLOPS x86 Intel 6/5/2 Pentium II 1 256MB (N=4000, 1 thread, OpenBLAS)
49 Raspberry pi-aplus 0.223 GFLOPS ARM ARMv6 BCM2835 1 256MB Model A+ (N=4000, 1 thread, OpenBLAS)
50 Raspberry pi compute-module 0.217 GFLOPS ARM ARMv6 BCM2835 1 512MB Pi Compute Module (N=5000, 1 thread, OpenBLAS)
51 Raspberry pi-b 0.213 GFLOPS ARM ARMv6 BCM2835 1 512MB Model B (N=5000, 1 thread, OpenBLAS)
52 Raspberry pi-bplus 0.213 GFLOPS ARM ARMv6 BCM2835 1 512MB Model B+ (N=5000, 1 thread, OpenBLAS)
53 beaglebone-black 0.068 GFLOPS ARM ARMv7 Cortex A8 1 512MB TI AM3 (N=5000, 1 thread, OpenBLAS)
54 beagleboard-xm 0.054 GFLOPS ARM ARMv7 Cortex A8 1 512MB TI DM3730 (N=5000, 1 thread, OpenBLAS)
55 gumstix-overo 0.041 GFLOPS ARM ARMv7 Cortex A8 1 256MB TI OMAP3 (N=4000, 1 thread, OpenBLAS)
56 appleII 133 FLOPS MOS 65C02 Apple IIe 1 128k platinum (N=10, 1 thread, BASIC)
? ELF Membership Card ??? GFLOPS ELF RCA1802 1 32kB ??? (??, 1 thread)
? trimslice ??? GFLOPS ARM ARMv7 Cortex A9 2 1GB Tegra2 ???
? octane ??? GFLOPS MIPS SGI MIPS R12k 1 ??? ??? (??, 1 thread)
? avr32 ??? GFLOPS AVR32 AVR AP7000 1 ??? ??? (??, 1 thread)
? gumstix-netstix ??? GFLOPS ARM ARMv5 Intel PXA255 1 64MB ??? (??, 1 thread)
? k6-2+ ??? GFLOPS x86 AMD K6-2+ 1 ?? ??? (??, 1 thread)
? 486 ??? GFLOPS x86 Cyrix 486 1 20MB ??? (??, 1 thread)
? g3-iBook ??? GFLOPS PPC Apple G3 1 640MB ??? (??, 1 thread)
? g4-powerBook ??? GFLOPS PPC Apple G4 1 2 GB ??? (??, 1 thread)
? p4 ??? GFLOPS x86 Intel Pentium 4 1 768MB ??? (??, 1 thread)
? core duo ??? GFLOPS x86 Intel Core Duo 2 2 GB ??? (??, 1 thread)
* -- the pandaboard crashes due to overheating (even with heatsinks) if N=10000 is used

* -- the pi3 FAILS or crashes (due to overheating?) on many of the N=8000/N=6000 runs. Reportedly with a full heatsink and active cooling it can achieve 6.4GFLOPS with N=8000.

Red indicates machine currently is not in working order

Back to VMW Research Group page