06 July 2017

Windows 7 versus Windows 10 1703 Benchmarks

This posting is part of a series of posts meant to explore the following topics:

  • Testing designed to compare FX and Ryzen scaling with various workloads.
  • Testing designed to compare GTX 660 and GTX 1050 Ti scaling with various CPUs.
  • Testing designed to compare Windows 7 and Windows 10 under real-world idle conditions.
  • Testing designed to compare gaming/encoding performance while encoding (under CPU load) in the background.

Topic Index:

Disclaimers

The following benchmarks were performed with the following hardware configurations:

BenchmarksHWConfig2017.png

  • Windows 7 Sp1 Updated, Windows 10 1703 Updated
  • GeForce GTX 660 and 1050Ti both at stock frequences.
  • Tests focus on real-world configurations and actual usage variations, not solely hardware component isolation. For that, check out gamersnexus.
  • 1% lows, 0.1% lows and standard deviation calculations (for accurate error bars) not performed due to data analysis and time limitations.
  • For full disclaimers, detailed configuration information, and results data please see the raw results Google doc. Tabs exist.
  • Regarding MetroLL and Ryzen’s SMT.

Synthetic CPU/Memory Benchmarks

CPU-Z Single and Multithreaded

Win7vs10Idle_CPU-Z.png


Passmark CPU Score

Win7vs10Idle_Passmark_CPU.png

  • Passmark CPU is not a great benchmark.

Passmark Memory

Win7vs10Idle_Passmark_Memory.png


MaxMEM2

Win7vs10Idle_MaxMEM2.png

  • My FX system has lousy memory writes.

7-Zip Benchmark

Win7vs10Idle_7-Zip.png


CineBenchR15 CPU Multithreaded

Win7vs10Idle_CineBenchR15_CPUMulti.png


x265 Encoding Time

Win7vs10Idle_x265_minutes1.png

Win7vs10Idle_x265_minutes2.png

  • Do not use dual-cores for encoding.

x265 Encoding FPS

Win7vs10Idle_x265_fps.png


Synthetic GPU Benchmarks

Passmark GPU

Win7vs10Idle_Passmark_GPU.png


CineBenchR15 OpenGL

Win7vs10Idle_CineBenchR15_OpenGL.png

  • Error bars overly large. Conclusions uncertain.

3DMark Firestrike Score

Win7vs10Idle_3DMark_Firestrike.png

  • The 4850e does surprisingly well. Ryzen shows about 5-10% scaling over FX regardless of OS.

3DMark TimeSpy Score

Win7vs10Idle_3DMark_Timespy.png

  • Windows 7 does not have DX12.

Unigine-Heaven FPS

Win7vs10Idle_Unigine-Heaven_FPS.png

  • Those minimums scale really well, but with hardware, not operating systems.

Unigine-Heaven Score

Win7vs10Idle_Unigine-Heaven_Score.png

  • And Unigine, once again, does not understand the importance of those minimums.

Games

Tomb Raider

Win7vs10Idle_TombRaider.png

  • Windows 10 shows very small improvements in minimums, reflected in the averages.

Metro Last Light

Win7vs10Idle_MetroLastLight.png

  • Windows 10 shows amazing frame rate improvements, expecially to the minimums.
  • A 4850e cannot keep up, despite any GPU or OS changes.

Shadow of Mordor

Win7vs10Idle_ShadowOfMordor.png

  • With a very nice video card, like a 1050 Ti, there is no improvement in Win10 over Win7.
  • WIth anything less, like a GTX 660, Win 10 has substantially better minimums. Essentially, this means the GTX 660 struggles with this game substantially and Win10 is a band-aid.
  • This game is unplayable with a 4850e and 660 on Win7. But upgrade the video card -120- and downgrade the OS to Win10 -0- and amazing things happen.

Ashes of the Singularity Escalation

Win7vs10Idle_Ashes.png

  • That really is an 8x improvement in performance when switching to Win10. *Improvement only applies to dual-cores.

Conclusion

  • Unsurprisingly, synthetic/CPU bound workloads are unaffected by OS.
  • In games, Win 10 seems to deal with low-end hardware better than Win 7. Once the hardware improves, the OS is no longer a concern.
  • Have some cheapo hardware? Want to game? Is unplugging the ethernet cord a viable option? If so, then Win10 will provide a better experience.

No comments:

Post a Comment