06 July 2017

AMD FX 8350 versus AMD Ryzen 7 1700 Scaling on Windows 7

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.
  • 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

Win7Idle_CPU-Z.png

  • Sandy Bridge has excellent single-threaded performance.

Passmark CPU Score

Win7Idle_Passmark_CPU.png

  • Passmark CPU is not a great benchmark.

Passmark Memory

Win7Idle_Passmark_Memory.png

  • So increasing clock speed helps memory performance marginally but changing GPUs does not. Interesting.

MaxMEM2

Win7Idle_MaxMEM2.png

  • My FX system has lousy memory writes.

7-Zip Benchmark

Win7Idle_7-Zip.png

CineBenchR15 CPU Multithreaded

Win7Idle_CineBenchR15_CPUMulti.png

  • Ryzen 1700 @ 3 Ghz with SMT=off is about 1k. SMT increases raw performance by about 40% in apps that care about both cores and threads.

x265 Encoding Time

Win7Idle_x265_minutes.png

  • Do not use dual-cores for encoding.

x265 Encoding FPS

Win7Idle_x265_fps.png

  • Ryzen 1700 @ stock has exactly twice the performance as FX 8350 @ 3.4Ghz.
  • Given some rough pixel calculations and that these are my typical clock speeds for both system, Ryzen does 1080p in the same time frame as an FX system at 720p. Hello 1080p HEVC.

Synthetic GPU Benchmarks

Passmark GPU

Win7Idle_Passmark_GPU.png

  • Intel HD3000 ftw. Take that ATI Radeon 3200!
  • Integrated aside, this is what proper scaling looks like.

CineBenchR15 OpenGL

Win7Idle_CineBenchR15_OpenGL.png

  • No. Just no. What is this synthetic benchmark even supposed to be measuring?

3DMark Firestrike Score

Win7Idle_3DMark_Firestrike.png

  • Firestrike is an excellent benchmark. It shows perfect scaling whenever increasing CPU frequency, architecture and/or changing GPU with very small error margins, regardless of idle or load conditions.
  • This benchmark is how games should perform if perfectly optimized.

3DMark TimeSpy Score

Win7Idle_3DMark_Timespy.png

  • Windows 7 does not support DX12.

Unigine-Heaven FPS

Win7Idle_Unigine-Heaven_FPS.png

  • So increasing CPU performance means getting better frame times/minimums.
  • The averages calculations for this benchmark do not take into account the minimums adequately.

Unigine-Heaven Score

Win7Idle_Unigine-Heaven_Score.png

  • The score completely ignores the minimums and related scaling.

Games

Tomb Raider

Win7Idle_TombRaider.png

  • Tomb Raider does not care about your CPU.
  • This is one of the few games that actually is playable at 1080p on Ultra with a $45 2008 dual-core.

Metro Last Light

Win7Idle_MetroLastLight.png

  • Regarding MetroLL and Ryzen's SMT.
  • This graph brings to attention so much wrongness in the world of PC gaming. Win 10 has significantly better minimums compared to 7. AMD's SMT on Ryzen does not play with MetroLL and MetroLL will not get updates to fix that. Disabling SMT causes other apps harm. Reenabling requires a cold boot. Charts with minimums do not adequtely describe frame times. The “Average FPS” calulations methods reported from games sometimes do not take into account minimums and stuttering.

Shadow of Mordor

Win7Idle_ShadowOfMordor.png

  • So increasing clock speed does nothing but going from FX to Ryzen (different architecure) means a 6 fps or, 16% increase, in minimums. Averages do not change.
  • Borderline almost playable with a 4850e and 1050 Ti at 720p. Nice.

Ashes of the Singularity Escalation

Win7Idle_Ashes.png

  • The scaling in Ashes is very similar to synthetic GPU benchmarks.
Posted by at
Labels: , , , , , , , ,

No comments:

Post a Comment

Subscribe to: Post Comments (Atom)