Flops

[sakul]

Flops zur Messung der Gleitkomma-Leistung einer CPU
Link:https://github.com/Mysticial/Flops
Achtung: Dieser Benchmark kann auf Ryzen Systemen ohne entsprechendes Biosupdate zu Abstürtzen führen also vorsicht ! ! !

Ich habe mal einen Test mit meinem kleinen VIA gemacht leider konnte ich dafür nur die veralteten Core2 Binarys verwenden alle anderen von INTEL und AMD führten zum Crash auf der VIA-CPU unter Windows 7 - x64.

Test System: VIA QuadCore E C4650 2.0GHz

[Darkman.X]

i7-5930K @ 4 GHz

x64-13-Haswell.exe:
Running Benchmarks for Intel Haswell...

Single-Precision - 128-bit SSE - Add/Sub:
Dependency Chains = 8
Result = 518.4
FP Ops = 1536000000000
seconds = 16.0353
GFlops = 95.7887

Single-Precision - 128-bit SSE - Multiply:
Dependency Chains = 12
Result = 892.8
FP Ops = 2304000000000
seconds = 12.3407
GFlops = 186.699

Single-Precision - 128-bit SSE - Multiply + Add:
Dependency Chains = 12
Result = 892.8
FP Ops = 2304000000000
seconds = 12.0597
GFlops = 191.049

Single-Precision - 128-bit FMA3 - Fused Multiply Add:
Dependency Chains = 12
Result = 892.8
FP Ops = 4608000000000
seconds = 12.0243
GFlops = 383.225

Double-Precision - 128-bit SSE2 - Add/Sub:
Dependency Chains = 8
Result = 259.2
FP Ops = 768000000000
seconds = 16.018
GFlops = 47.946

Double-Precision - 128-bit SSE2 - Multiply:
Dependency Chains = 12
Result = 446.4
FP Ops = 1152000000000
seconds = 12.3491
GFlops = 93.2859

Double-Precision - 128-bit SSE2 - Multiply + Add:
Dependency Chains = 12
Result = 446.4
FP Ops = 1152000000000
seconds = 12.0358
GFlops = 95.7144

Double-Precision - 128-bit FMA3 - Fused Multiply Add:
Dependency Chains = 12
Result = 446.4
FP Ops = 2304000000000
seconds = 12.0276
GFlops = 191.56

Single-Precision - 256-bit AVX - Add/Sub:
Dependency Chains = 8
Result = 1036.8
FP Ops = 3072000000000
seconds = 16.0335
GFlops = 191.598

Single-Precision - 256-bit AVX - Multiply:
Dependency Chains = 12
Result = 1785.6
FP Ops = 4608000000000
seconds = 12.5893
GFlops = 366.026

Single-Precision - 256-bit AVX - Multiply + Add:
Dependency Chains = 12
Result = 1785.6
FP Ops = 4608000000000
seconds = 12.2326
GFlops = 376.697

Single-Precision - 256-bit FMA3 - Fused Multiply Add:
Dependency Chains = 12
Result = 1785.6
FP Ops = 9216000000000
seconds = 12.0321
GFlops = 765.948

Double-Precision - 256-bit AVX - Add/Sub:
Dependency Chains = 8
Result = 518.4
FP Ops = 1536000000000
seconds = 16.0499
GFlops = 95.7018

Double-Precision - 256-bit AVX - Multiply:
Dependency Chains = 12
Result = 892.8
FP Ops = 2304000000000
seconds = 12.5929
GFlops = 182.96

Double-Precision - 256-bit AVX - Multiply + Add:
Dependency Chains = 12
Result = 892.8
FP Ops = 2304000000000
seconds = 12.2122
GFlops = 188.664

Double-Precision - 256-bit FMA3 - Fused Multiply Add:
Dependency Chains = 12
Result = 892.8
FP Ops = 4608000000000
seconds = 12.0437
GFlops = 382.608

Dr�cken Sie eine beliebige Taste . . .

[Rente]

i7-5820K@4.5 GHz

x64-13-Haswell.exe

Single-Precision - 128-bit SSE - Add/Sub:
Dependency Chains = 8
Result = 518.4
FP Ops = 1536000000000
seconds = 14.2828
GFlops = 107.542

Single-Precision - 128-bit SSE - Multiply:
Dependency Chains = 12
Result = 892.8
FP Ops = 2304000000000
seconds = 10.9619
GFlops = 210.183

Single-Precision - 128-bit SSE - Multiply + Add:
Dependency Chains = 12
Result = 892.8
FP Ops = 2304000000000
seconds = 10.7183
GFlops = 214.959

Single-Precision - 128-bit FMA3 - Fused Multiply Add:
Dependency Chains = 12
Result = 892.8
FP Ops = 4608000000000
seconds = 10.6908
GFlops = 431.025

Double-Precision - 128-bit SSE2 - Add/Sub:
Dependency Chains = 8
Result = 259.2
FP Ops = 768000000000
seconds = 14.24
GFlops = 53.9328

Double-Precision - 128-bit SSE2 - Multiply:
Dependency Chains = 12
Result = 446.4
FP Ops = 1152000000000
seconds = 10.9731
GFlops = 104.984

Double-Precision - 128-bit SSE2 - Multiply + Add:
Dependency Chains = 12
Result = 446.4
FP Ops = 1152000000000
seconds = 10.7168
GFlops = 107.495

Double-Precision - 128-bit FMA3 - Fused Multiply Add:
Dependency Chains = 12
Result = 446.4
FP Ops = 2304000000000
seconds = 10.7279
GFlops = 214.767

Single-Precision - 256-bit AVX - Add/Sub:
Dependency Chains = 8
Result = 1036.8
FP Ops = 3072000000000
seconds = 14.2347
GFlops = 215.81

Single-Precision - 256-bit AVX - Multiply:
Dependency Chains = 12
Result = 1785.6
FP Ops = 4608000000000
seconds = 11.1952
GFlops = 411.606

Single-Precision - 256-bit AVX - Multiply + Add:
Dependency Chains = 12
Result = 1785.6
FP Ops = 4608000000000
seconds = 10.8649
GFlops = 424.117

Single-Precision - 256-bit FMA3 - Fused Multiply Add:
Dependency Chains = 12
Result = 1785.6
FP Ops = 9216000000000
seconds = 10.6814
GFlops = 862.808

Double-Precision - 256-bit AVX - Add/Sub:
Dependency Chains = 8
Result = 518.4
FP Ops = 1536000000000
seconds = 14.2399
GFlops = 107.866

Double-Precision - 256-bit AVX - Multiply:
Dependency Chains = 12
Result = 892.8
FP Ops = 2304000000000
seconds = 11.1977
GFlops = 205.757

Double-Precision - 256-bit AVX - Multiply + Add:
Dependency Chains = 12
Result = 892.8
FP Ops = 2304000000000
seconds = 10.8553
GFlops = 212.247

Double-Precision - 256-bit FMA3 - Fused Multiply Add:
Dependency Chains = 12
Result = 892.8
FP Ops = 4608000000000
seconds = 10.6862
GFlops = 431.211

[atopisch]

Core i7-4790K@4.6

Running Benchmarks for Intel Haswell...

Single-Precision - 128-bit SSE - Add/Sub:
Dependency Chains = 8
Result = 345.6
FP Ops = 1024000000000
seconds = 14.4168
GFlops = 71.0281

Single-Precision - 128-bit SSE - Multiply:
Dependency Chains = 12
Result = 595.2
FP Ops = 1536000000000
seconds = 11.0224
GFlops = 139.352

Single-Precision - 128-bit SSE - Multiply + Add:
Dependency Chains = 12
Result = 595.2
FP Ops = 1536000000000
seconds = 10.72
GFlops = 143.283

Single-Precision - 128-bit FMA3 - Fused Multiply Add:
Dependency Chains = 12
Result = 595.2
FP Ops = 3072000000000
seconds = 10.5528
GFlops = 291.108

Double-Precision - 128-bit SSE2 - Add/Sub:
Dependency Chains = 8
Result = 172.8
FP Ops = 512000000000
seconds = 14.1406
GFlops = 36.2079

Double-Precision - 128-bit SSE2 - Multiply:
Dependency Chains = 12
Result = 297.6
FP Ops = 768000000000
seconds = 11.1845
GFlops = 68.6663

Double-Precision - 128-bit SSE2 - Multiply + Add:
Dependency Chains = 12
Result = 297.6
FP Ops = 768000000000
seconds = 10.7123
GFlops = 71.6936

Double-Precision - 128-bit FMA3 - Fused Multiply Add:
Dependency Chains = 12
Result = 297.6
FP Ops = 1536000000000
seconds = 10.5622
GFlops = 145.424

Single-Precision - 256-bit AVX - Add/Sub:
Dependency Chains = 8
Result = 691.2
FP Ops = 2048000000000
seconds = 13.9997
GFlops = 146.289

Single-Precision - 256-bit AVX - Multiply:
Dependency Chains = 12
Result = 1190.4
FP Ops = 3072000000000
seconds = 11.1388
GFlops = 275.792

Single-Precision - 256-bit AVX - Multiply + Add:
Dependency Chains = 12
Result = 1190.4
FP Ops = 3072000000000
seconds = 10.8708
GFlops = 282.593

Single-Precision - 256-bit FMA3 - Fused Multiply Add:
Dependency Chains = 12
Result = 1190.4
FP Ops = 6144000000000
seconds = 10.6624
GFlops = 576.231

Double-Precision - 256-bit AVX - Add/Sub:
Dependency Chains = 8
Result = 345.6
FP Ops = 1024000000000
seconds = 14.0073
GFlops = 73.1046

Double-Precision - 256-bit AVX - Multiply:
Dependency Chains = 12
Result = 595.2
FP Ops = 1536000000000
seconds = 11.1497
GFlops = 137.762

Double-Precision - 256-bit AVX - Multiply + Add:
Dependency Chains = 12
Result = 595.2
FP Ops = 1536000000000
seconds = 10.8612
GFlops = 141.421

Double-Precision - 256-bit FMA3 - Fused Multiply Add:
Dependency Chains = 12
Result = 595.2
FP Ops = 3072000000000
seconds = 10.5378
GFlops = 291.522