CPU Results (wolf’s) Using (MB L3 cache/ 2) for threads
4x Intel Xeon E7-8870 V3 = 2600H/s (NB drops to 2000 over time)
2x Intel Xeon E5-2699 V4 = 1723H/s
1x Intel Xeon Phi 7210 = 602H/s (case to use nproc-1)
2x Intel Xeon E5-2698 V4 = 1572H/s
2x Intel Xeon E5-2698 V3 = 1463H/s
2x Intel Xeon E5-2690 V4 = 1312H/s
2x Intel Xeon E5-2690 V3 = 1100H/s
2x Intel Xeon E5-2667 V3 = 1090H/s
2x Intel Xeon E5-2658 V3 = 1050H/s
2x Intel Xeon E5-2650 V4 = 1047H/s
2x Intel Xeon E5-2650L V4 = 1031H/s
2x Intel Xeon E5-2683 V3 = 1014H/s
2x Intel Xeon E5-2680 V3 = 969H/s
2x Intel Xeon E5-2670 V3 = 969H/s
2x Intel Xeon E5-2628L V4 = 897H/s
2x Intel Xeon E5-2650L V3 = 874H/s
2x Intel Xeon E5-2630 V4 = 866H/s
2x Intel Xeon E5-2670 V1 = 829H/s
2x Intel Xeon E5-2650 V1 = 750H/s
1x Intel Xeon E5-2667 V4 = 538H/s
1x AMD Ryzen 7 1800X = 537H/s
1x AMD Ryzen 7 1700X = 516H/s
1x AMD Ryzen 7 1700 = 481H/s
2x Intel Xeon E5-2620 V1 = 480H/s
1x AMD Ryzen 5 1600X = 451H/s
1x Intel Xeon D-1587 = 388H/s
1x AMD Ryzen 5 1600 =363H/s
1x AMD Ryzen 5 1500X = 361H/s (note have to work on the zen image cache calculation)
1x Intel Xeon E5-2630L V3 = 354H/s

2x Intel Xeon X5675 = 340H/s (don’t laugh too hard, lack of AES-NI hurts the new crypto projects)
1x Intel Core i7-7700K = 322H/s
1x Intel Xeon E3-1280 V6 = 281H/s
1x Intel Xeon E3-1270 V6 = 273H/s
1x Intel Xeon E3-1275 V6 = 272H/s
1x Intel Xeon E3-1240 V6 = 265H/s
1x Intel Xeon E3-1245 V6 = 263H/s
1x Intel Core i7-7700 = 258H/s
1x Intel Xeon E3-1230 V6 = 250H/s
1x Intel Xeon E3-1230 V5 = 249H/s
1x Intel Xeon D-1541 = 242H/s
1x Intel Xeon E3-1515M V5 = 240H/s
1x Intel Xeon E3-1225 V6 = 236H/s
1x AMD Ryzen 5 1400 = 234H/s
1x Intel Xeon D-1540 = 218H/s
1x Intel Xeon E3-1220 V6 = 214H/s
1x Intel Xeon E3-1220 V3 = 186H/s
1x Intel Core i5-7400 = 165H/s
1x Intel Xeon E3-1245 V5 = 161H/s
1x Intel Xeon E5-2603 V3 = 156H/s (case to use nproc)
1x Special CPU = 153H/s (case to use nproc)
1x Intel Atom C3338 = 77H/s (case to use nproc)
1x Intel Pentium D1508 = 47H/s (case to use nproc-1)
1x Intel Atom C2358 = 18H/s (use nproc)

ARM CPU Results (thanks Fractal)
ARM Cortex A7 (Odroid-C1) 5.9H/s (no AES)
ARM Cortex A53 (Odroid-C2) 7.2 H/s (no AES)
ARM Cortex A53 (Pine64) 12.5 H/s @ 4.1W (using AES instructions, thermal limited) 3H/W

GPU Results (ccminer NVIDIA, Wolfs AMD)
1x GRID M40 GPU = 880H/s
1/4x GRID M40 GPU = 220H/s
1x AMD RX 480 8GB Gigabyte = 620H/s
1x AMD RX 470 4GB ASUS = 535H/s
1x NVIDIA GTX 1080 (EVGA Reference) = 475H/s
1x NVIDIA GTX 1070 (ASUS STRIX) = 475H/s
1x NVIDIA GTX 1060 6GB (ASUS dual fan) = 431H/s
1x NVIDIA GTX 1060 6GB (EVGA ACX single fan) = 432H/s
1x NVIDIA GTX 1050 Ti 4GB (PNY) = 297H/s
1x NVIDIA GTX 970 (ASUS STRIX) = 375H/s
1x NVIDIA GTX 750 Ti = 205 H/s (Fractal)
1x NVIDIA GRID K520 (AWS g2.2xlarge) = 164H/s
1x NVIDIA K80 (one of two GPUs AWS p2.xlarge) = 209H/s

GPU Results (ccminer)
1x NVIDIA GTX 560 Ti 2GB = 170 H/s
1x NVIDIA GTX 650 Ti 1GB = 92 H/s
1x NVIDIA GTX 750 Ti = 205 H/s
1x NVIDIA GTX 960 4GB (GIGA G1) = 250 H/s
2x NVIDIA GTX 970 = 890 H/s

AWS Instance CPU Mining (Wolf’s)
c4.8xlarge = 979H/s (25 threads)
r4.4xlarge = 560H/s (16 threads)
r4.2xlarge = 300H/s (9 threads)

AWS CPU Results (wolf’s) Using (nproc-1) for threads
g2.2xlarge = 321H/s
p2.xlarge = 114H/s

CPU/ GPU Build Results
g2.2xlarge = 485H/s
p2.xlarge = 323H/s
DeepLearning01 = 649H/s
DeepLearning02 = 347H/s

It seems like a dual E5-2620 V4 system with two GRID M40 cards outpaces a quad E7-8890 V4 system.

Depreciated CPU Results (wolf’s) Using (nproc – 1) for threads
4x Intel Xeon E7-8890 V4 = 2280H/s
4x Intel Xeon E7-8870 V4 = 1585H/s
2x Intel Xeon X5675 = 340H/s (Fractal)
1x Intel Xeon D-1541 = 178H/s
1x Intel Xeon D-1540 = 157H/s
2x Intel Xeon E5620 = 150H/s (cafcwest)