AMD Ryzen (Summit Ridge) Benchmarks Thread (use new thread)

Page 81 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.
Status
Not open for further replies.

Glo.

Diamond Member
Apr 25, 2015
5,765
4,668
136
Those are not SINGLE THREAD PERFORMANCE , those are 4 Threads CMT/SMT or 4 Cores
throughput.
If I understand excerpt from Anandtech review:
Many emulators are often bound by single thread CPU performance, and general reports tended to suggest that Haswell provided a significant boost to emulator performance. This benchmark runs a Wii program that raytraces a complex 3D scene inside the Dolphin Wii emulator. Performance on this benchmark is a good proxy of the speed of Dolphin CPU emulation, which is an intensive single core task using most aspects of a CPU.

Dolphin IS single threaded benchmark.

Otherwise it would be ridiculous that quad core Haswell is only few minutes faster than dual core Sandy Bridge(Pentium G3258) chip.
 

TheELF

Diamond Member
Dec 22, 2012
3,993
744
126
You can't be serious. Intel was caught red handed and had to pay $1.3B in settlement fees..
Exactly settlement fees,they settled things between them,for all we know intel gave amd the 1,25B to keep them afloat.
It's not like intel couldn't have dragged procedures out until amd would have ran out of money(intel had $1,3B just laying around) I mean if intel would have managed to keep AMD from selling anything that came out of gf it wouldn't even have taken that long, amd had nothing to keep intel from making money and even if they had...
 
Reactions: Arachnotronic

sirmo

Golden Member
Oct 10, 2011
1,014
391
136
Exactly settlement fees,they settled things between them,for all we know intel gave amd the 1,25B to keep them afloat.
It's not like intel couldn't have dragged procedures out until amd would have ran out of money(intel had $1,3B just laying around) I mean if intel would have managed to keep AMD from selling anything that came out of gf it wouldn't even have taken that long, amd had nothing to keep intel from making money and even if they had...
It took them 5 years to settle, you gotta settle sometime or face the music/courts decision. Although to be fair AMD didn't do themselves any favors either. Intel saw what kind of mess they were in and realized they no longer posed a threat.
 

Sven_eng

Member
Nov 1, 2016
110
57
61
Exactly settlement fees,they settled things between them,for all we know intel gave amd the 1,25B to keep them afloat.
It's not like intel couldn't have dragged procedures out until amd would have ran out of money(intel had $1,3B just laying around) I mean if intel would have managed to keep AMD from selling anything that came out of gf it wouldn't even have taken that long, amd had nothing to keep intel from making money and even if they had...

Yeah, do yourself a favour and read this - https://en.wikipedia.org/wiki/Intel#Controversies

Intel is one of the dirtiest companies in the world and was forced to settle before becoming overwhelmed by litigation in every jurisdiction.
 
Reactions: FIVR

CHADBOGA

Platinum Member
Mar 31, 2009
2,135
832
136

sirmo

Golden Member
Oct 10, 2011
1,014
391
136
Last edited:
Reactions: FIVR

cdimauro

Member
Sep 14, 2016
163
14
61
Yeah that would be way too clear for a legal document.
I see. But at the beginning of the document there's a list of lawsuits between AMD and Intel, and it isn't reported the specific one regarding the compiler "issue".
Yeah, do yourself a favour and read this - https://en.wikipedia.org/wiki/Intel#Controversies

Intel is one of the dirtiest companies in the world and was forced to settle before becoming overwhelmed by litigation in every jurisdiction.
It WAS, not it is. And from long time, if you take a look at end dates of the listed episodes.

Intel changed A LOT.
 

cdimauro

Member
Sep 14, 2016
163
14
61
If I understand excerpt from Anandtech review:
Many emulators are often bound by single thread CPU performance, and general reports tended to suggest that Haswell provided a significant boost to emulator performance. This benchmark runs a Wii program that raytraces a complex 3D scene inside the Dolphin Wii emulator. Performance on this benchmark is a good proxy of the speed of Dolphin CPU emulation, which is an intensive single core task using most aspects of a CPU.

Dolphin IS single threaded benchmark.

Otherwise it would be ridiculous that quad core Haswell is only few minutes faster than dual core Sandy Bridge(Pentium G3258) chip.
Exactly. Emulators usually are strictly single-threaded applications.

When/IF they use more core/threads is because the main thread (the one which emulates the CPU) offloads some o.s.-interface tasks to another thread (usually the "GUI" one), like displaying the elaborated framebuffer, updating the audio buffer, getting the keyboard/mouse events, reading/writing disk data.

But such tasks are very light. It's the CPU emulation one which strongly dominates.

Dolphin is a clear example. Another one is (Win|FS)UAE (the most famous Amiga emulator). And of course there's the evergreen MAME (arcade emulator), which strictly uses a single core/thread even when emulating games which have multiple processors, "slicing" emulation cycles for each one of them.

A (very rare) example of MT emulator is PCSX2 (the most famous and used PS2 emulator), which TRIES to offload operations for the second vector unit to another core/thread. I said "tries" because, of course, it works only if a PS2 game uses it (which is not common, since many games use just one vector unit, because it was way complicated, at the time, to write code to make use of both. And the PS2 architecture is very well known to be complicated), but due to this approach there might be synchronization issues (and that's the reason why MAME gives some small emulation cycles to each "processor": to try to eliminate such synchronization issues).
Here you can find some PCSX2 benchmarks, reporting a list of tested CPUs.
 

AtenRa

Lifer
Feb 2, 2009
14,003
3,361
136
If I understand excerpt from Anandtech review:
Many emulators are often bound by single thread CPU performance, and general reports tended to suggest that Haswell provided a significant boost to emulator performance. This benchmark runs a Wii program that raytraces a complex 3D scene inside the Dolphin Wii emulator. Performance on this benchmark is a good proxy of the speed of Dolphin CPU emulation, which is an intensive single core task using most aspects of a CPU.

Dolphin IS single threaded benchmark.

Otherwise it would be ridiculous that quad core Haswell is only few minutes faster than dual core Sandy Bridge(Pentium G3258) chip.

Ok I could take Dolphin as a single thread performance but Winrar is clearly not.
 

Masochrist_

Junior Member
Apr 8, 2016
5
2
36
Actually, Dolphin uses two threads: one for the interpreter and another for the GPU. Having more than two cores helps a little bit because it means anything outside the emulator can be set to those extra cores, freeing a bit of performance.

But yeah, emulation is probably one of the few real world tasks for the common mortal where single thread performance is of the utmost importance.
 

TheELF

Diamond Member
Dec 22, 2012
3,993
744
126
I see. But at the beginning of the document there's a list of lawsuits between AMD and Intel, and it isn't reported the specific one regarding the compiler "issue".
Because for AMD it wasn't a big issue,they always kept using the intel compiler because it provides the best performance for them,it would have come up under "other practices" (RECITALS B) but seriously how do you convince a judge that a performance loss is due to ill intend and not just a bug/lack of judgement?
Imagine intel suing "the consoles" (devs/sony/who ever) because of artificially gimping dualcores ,even to the point where games don't even start up,hurting intel's name and business,how much chance do you think that would have?And there is ample proof that it's all artificial gimping.

Only ones ever to bring the compiler issue up are die hard FX fanboys that need to have an excuse for them cinebench(and any other bench/prog) numbers.
 

bjt2

Senior member
Sep 11, 2016
784
180
86
Python is glue. Even when you use Python most heavy lifting is done by low level C/C++ libraries and the OS components themselves, in majority of apps where Python is applied. People who do heavy computational tasks with python leverage libraries like numpy, scipy or similar. For instance if you parse large blobs of text in python you might use the re (regular expressions) module which is written in C. You compile the regular expression once, and you pass it the blob to parse.. that work isn't done in python.

In a typical web app scenario which results in say a database query.. most of that heavy lifting is done by the database server, whether it be an RDBMS or some key value store.

The point I am making is right tool for the job is important. And Python is a very powerful tool. It is a rapid development scripting language with some of the best readability around, which makes it a great language for collaboration and quick development. That combined with a mature ecosystem makes it a right choice for a whole host of applications.

There are cases where it doesn't make sense like implementation of new performance sensitive algorithms, but most people don't come up with new algorithms all the time. Chances are a library for what you're trying to accomplish already exists.

I am a researcher and use Matlab... It integrates nicely with java (it includes the oracle JVM and you can use all java classes in Matlab scripts and functions)... It's very productive...
 

bjt2

Senior member
Sep 11, 2016
784
180
86
There's also one free "int" port, which can also handle branches.

Yes, because the free ports are two, both can do int and vecint, if i remember well... You may have a slowdown only on code with many FP vecint and int instructions that conflicts... If they are 256 bit, obviously on Zen can't be sustained in one cycle, while on intel yes. But i can't imagine an actual software with FP and vecint instruction intermixed...
 

Atari2600

Golden Member
Nov 22, 2016
1,409
1,655
136
Mate, even the 15.6" screens paired up with them were horrible. The saturation and contrast, or huge lack of, was visible in basic reviews.

To clarify, I'm talking about A12 Kaveri with a 17+" screen!
 

Atari2600

Golden Member
Nov 22, 2016
1,409
1,655
136
I am a researcher and use Matlab... It integrates nicely with java (it includes the oracle JVM and you can use all java classes in Matlab scripts and functions)... It's very productive...

For large arrays and datasets, I found python (through its extensions) orders of magnitude quicker than matlab.

At the time, I had a lot of experience in matlab and not much in python - it was a surprising difference.
 

Atari2600

Golden Member
Nov 22, 2016
1,409
1,655
136

cytg111

Lifer
Mar 17, 2008
23,551
13,116
136
For large arrays and datasets, I found python (through its extensions) orders of magnitude quicker than matlab.

At the time, I had a lot of experience in matlab and not much in python - it was a surprising difference.

These dynamic kids these days

http://benchmarksgame.alioth.debian.org/u64q/compare.php?lang=python3&lang2=gpp

all because they're just too cool to write "int i;"
python uses ~2000 cycles to add two numbers while a modern architecture like skylake can issue 4 adds per cycle(Think Zen can too). Think of the remaining 7999 trees dammit. . J/K. - (Or am I?)
 

bjt2

Senior member
Sep 11, 2016
784
180
86
For large arrays and datasets, I found python (through its extensions) orders of magnitude quicker than matlab.

At the time, I had a lot of experience in matlab and not much in python - it was a surprising difference.

For image processing, it's very fast. And now i learned how to integrate CUDA... We have a blade with 2 GTX 690... Way faster than the CPU...
 

Atari2600

Golden Member
Nov 22, 2016
1,409
1,655
136
These dynamic kids these days

http://benchmarksgame.alioth.debian.org/u64q/compare.php?lang=python3&lang2=gpp

all because they're just too cool to write "int i;"
python uses ~2000 cycles to add two numbers while a modern architecture like skylake can issue 4 adds per cycle(Think Zen can too). Think of the remaining 7999 trees dammit. . J/K. - (Or am I?)

True, C is always going to be quicker.

But I didn't have the experience in C or time to learn how to build something from scratch. So python was the answer that provided me the quickest result (including programming time).
 

nismotigerwvu

Golden Member
May 13, 2004
1,568
33
91
Actually, Dolphin uses two threads: one for the interpreter and another for the GPU. Having more than two cores helps a little bit because it means anything outside the emulator can be set to those extra cores, freeing a bit of performance.

But yeah, emulation is probably one of the few real world tasks for the common mortal where single thread performance is of the utmost importance.
Yeah I was going to mention the same thing. There's an option to run as a single thread (or at least there was at some point) but performance does take a significant hit.
 

Glo.

Diamond Member
Apr 25, 2015
5,765
4,668
136
Ok I could take Dolphin as a single thread performance but Winrar is clearly not.
How about this then:

67-40% = 40.2

Similarly to WinRAR, the FastStone test us updated to the latest version. FastStone is the program I use to perform quick or bulk actions on images, such as resizing, adjusting for color and cropping. In our test we take a series of 170 images in various sizes and formats and convert them all into 640x480 .gif files, maintaining the aspect ratio. FastStone does not use multithreading for this test, and thus single threaded performance is often the winner.
 
Status
Not open for further replies.
sale-70-410-exam    | Exam-200-125-pdf    | we-sale-70-410-exam    | hot-sale-70-410-exam    | Latest-exam-700-603-Dumps    | Dumps-98-363-exams-date    | Certs-200-125-date    | Dumps-300-075-exams-date    | hot-sale-book-C8010-726-book    | Hot-Sale-200-310-Exam    | Exam-Description-200-310-dumps?    | hot-sale-book-200-125-book    | Latest-Updated-300-209-Exam    | Dumps-210-260-exams-date    | Download-200-125-Exam-PDF    | Exam-Description-300-101-dumps    | Certs-300-101-date    | Hot-Sale-300-075-Exam    | Latest-exam-200-125-Dumps    | Exam-Description-200-125-dumps    | Latest-Updated-300-075-Exam    | hot-sale-book-210-260-book    | Dumps-200-901-exams-date    | Certs-200-901-date    | Latest-exam-1Z0-062-Dumps    | Hot-Sale-1Z0-062-Exam    | Certs-CSSLP-date    | 100%-Pass-70-383-Exams    | Latest-JN0-360-real-exam-questions    | 100%-Pass-4A0-100-Real-Exam-Questions    | Dumps-300-135-exams-date    | Passed-200-105-Tech-Exams    | Latest-Updated-200-310-Exam    | Download-300-070-Exam-PDF    | Hot-Sale-JN0-360-Exam    | 100%-Pass-JN0-360-Exams    | 100%-Pass-JN0-360-Real-Exam-Questions    | Dumps-JN0-360-exams-date    | Exam-Description-1Z0-876-dumps    | Latest-exam-1Z0-876-Dumps    | Dumps-HPE0-Y53-exams-date    | 2017-Latest-HPE0-Y53-Exam    | 100%-Pass-HPE0-Y53-Real-Exam-Questions    | Pass-4A0-100-Exam    | Latest-4A0-100-Questions    | Dumps-98-365-exams-date    | 2017-Latest-98-365-Exam    | 100%-Pass-VCS-254-Exams    | 2017-Latest-VCS-273-Exam    | Dumps-200-355-exams-date    | 2017-Latest-300-320-Exam    | Pass-300-101-Exam    | 100%-Pass-300-115-Exams    |
http://www.portvapes.co.uk/    | http://www.portvapes.co.uk/    |