loongson1
ARMv8 rev 4 testing with a Qualcomm MSM8998 MSM 8998 v2.1 MTP and mdssfb_90000 on Debian GNU/Linux 10 via the Phoronix Test Suite.


Loongson-3B R2: 

	Processor: Loongson-3B R2 @ 1.20GHz (8 Cores), Motherboard: loongson generic, Chipset: AMD RS780 + SB7x0/SB8x0/SB9x0, Memory: 4096MB, Disk: 500GB Western Digital WD5000AAKS-0, Graphics: AMD OLAND 1GB, Audio: Conexant CX20631, Monitor: 2243W, Network: Intel 82574L

	OS: Fedora 28, Kernel: 4.14.77gs-tweak-1+ (mips64), Desktop: MATE 1.20.3, Display Server: X Server 1.19.6, Display Driver: modesetting 1.19.6, OpenGL: 4.5 Mesa 18.2.2 (LLVM 6.0.1), Compiler: Clang 6.0.1, File-System: ext4, Screen Resolution: 1920x1080

loongson3b1500e-vs-msm8998sdm835: 

	Processor: ARMv8 rev 4 @ 2.04GHz (8 Cores), Motherboard: Qualcomm MSM8998 MSM 8998 v2.1 MTP, Memory: 6144MB, Disk: 58GB KLUCG4J1ED-B0C1 + 4GB KLUCG4J1ED-B0C1 + 2GB KLUCG4J1ED-B0C1, Graphics: mdssfb_90000

	OS: Debian GNU/Linux 10, Kernel: 4.4.153-ElementalX-OP5-5.02 (armv8l), Display Server: X Server 1.20.3 + SurfaceFlinger, Display Driver: fbdev 0.5.0, Compiler: GCC 8.3.0 + Clang 7.0.1-8 + LLVM 7.0.1, File-System: ext4, Screen Resolution: 1080x3840


High Performance Conjugate Gradient 3.0

GFLOP/s > Higher Is Better
Loongson-3B R2 ................... 0.06 |====
loongson3b1500e-vs-msm8998sdm835 . 0.53 |======================================


GNU MPC 1.1.0
Multi-Precision Benchmark
Global Score > Higher Is Better
Loongson-3B R2 ................... 193  |===
loongson3b1500e-vs-msm8998sdm835 . 2790 |======================================


CacheBench
Test: Read
MB/s > Higher Is Better
Loongson-3B R2 ................... 1302 |==========
loongson3b1500e-vs-msm8998sdm835 . 4907 |======================================


CacheBench
Test: Write
MB/s > Higher Is Better
Loongson-3B R2 ................... 2985 |============
loongson3b1500e-vs-msm8998sdm835 . 9611 |======================================


CacheBench
Test: Read / Modify / Write
MB/s > Higher Is Better
Loongson-3B R2 ................... 760   |==
loongson3b1500e-vs-msm8998sdm835 . 15432 |=====================================


SciMark 2.0
Computational Test: Composite
Mflops > Higher Is Better
Loongson-3B R2 ................... 21.72  |===
loongson3b1500e-vs-msm8998sdm835 . 228.07 |====================================


SciMark 2.0
Computational Test: Monte Carlo
Mflops > Higher Is Better
Loongson-3B R2 ................... 11.39 |======
loongson3b1500e-vs-msm8998sdm835 . 72.34 |=====================================


SciMark 2.0
Computational Test: Fast Fourier Transform
Mflops > Higher Is Better
Loongson-3B R2 ................... 7.94  |======
loongson3b1500e-vs-msm8998sdm835 . 52.77 |=====================================


SciMark 2.0
Computational Test: Sparse Matrix Multiply
Mflops > Higher Is Better
Loongson-3B R2 ................... 13.53  |==
loongson3b1500e-vs-msm8998sdm835 . 218.83 |====================================


SciMark 2.0
Computational Test: Dense LU Matrix Factorization
Mflops > Higher Is Better
Loongson-3B R2 ................... 23.08  |===
loongson3b1500e-vs-msm8998sdm835 . 252.45 |====================================


SciMark 2.0
Computational Test: Jacobi Successive Over-Relaxation
Mflops > Higher Is Better
Loongson-3B R2 ................... 52.68  |===
loongson3b1500e-vs-msm8998sdm835 . 543.97 |====================================


FFTE 6.0
Test: N=256, 1D Complex FFT Routine
MFLOPS > Higher Is Better
Loongson-3B R2 . 1237.06 |=====================================================


Stockfish 9
Total Time
Nodes Per Second > Higher Is Better
Loongson-3B R2 ................... 1839463 |=============
Loongson-3B R2 ................... 1809735 |=============
loongson3b1500e-vs-msm8998sdm835 . 4942767 |===================================


TSCP 1.81
AI Chess Performance
Nodes Per Second > Higher Is Better
Loongson-3B R2 ................... 145262 |=========
loongson3b1500e-vs-msm8998sdm835 . 611575 |====================================


PolyBench-C 4.2
Test: Correlation Computation
Seconds < Lower Is Better
Loongson-3B R2 ................... 83.37 |=====================================
loongson3b1500e-vs-msm8998sdm835 . 13.10 |======


PolyBench-C 4.2
Test: 3 Matrix Multiplications
Seconds < Lower Is Better
Loongson-3B R2 ................... 179.39 |====================================
loongson3b1500e-vs-msm8998sdm835 . 20.67  |====


PolyBench-C 4.2
Test: Covariance Computation
Seconds < Lower Is Better
Loongson-3B R2 ................... 84.02 |=====================================
loongson3b1500e-vs-msm8998sdm835 . 13.07 |======


Sample Pi Program

Seconds < Lower Is Better
Loongson-3B R2 ................... 250.63 |====================================
loongson3b1500e-vs-msm8998sdm835 . 34.07  |=====


Timed MAFFT Alignment 7.392
Multiple Sequence Alignment
Seconds < Lower Is Better
Loongson-3B R2 ................... 63.95 |=====================================
Loongson-3B R2 ................... 63.94 |=====================================
loongson3b1500e-vs-msm8998sdm835 . 10.23 |======


C-Ray 1.1
Total Time - 4K, 16 Rays Per Pixel
Seconds < Lower Is Better
Loongson-3B R2 ................... 1600 |======================================
loongson3b1500e-vs-msm8998sdm835 . 356  |========


POV-Ray 3.7.0.7
Trace Time
Seconds < Lower Is Better
Loongson-3B R2 ................... 1374 |======================================
loongson3b1500e-vs-msm8998sdm835 . 282  |========