• Welcome to TechPowerUp Forums, Guest! Please check out our forum guidelines for info related to our community.

AMD's Ryzen 7 1700X Glorious Benchmarks Leak; IHS, Pin Layout Photographed

I don't know how you some of you guys can claim "low IPC" by looking at this info.
IPC proxies which you can calculate from here are based on assumptions, not actual data.

Let me explain: Nobody knows at what "actual" clocks the Ryzen chip was running during the single-thread Cinebench run. Same goes for the Intel chips, among which it seems 6900K is the fitting contender for 1700X (8-core to 8-core).
Further, 1700X score of 154 was with a 2133MHz memory speed, while 6900K score of 153 was with 2400MHz (incidentally at same timings). Nobody knows if/how 1700X score would be impacted if it was run with a 2400Mhz memory.

Still, for the fun of it, let's do some calculations:

Anandtech disabled Turbo 3.0, so it is I suppose safe to assume that 6900K was running at its normal normal Turbo speed of 3.7GHz. So, per GHz, Broadwell did 153/3.7 = 41.3514

Even though we do not know, let's assume 1700X was working at its normal Turbo speed of 3.8GHz. So, per GHz, Ryzen did 154/3.8 = 40.5263

This means, relative to Broadwell, coupled with a slower memory, Ryzen single-thread CB15 performance at same clocks (again, not sure) is 98%.

Furthermore, do I have to remind everyone that this is a single-chip to single-chip comparison and with such small samples, 2% deviation could happen even if you used the same friggin chip on two different days???

From this limited data, anyone with a little sense would not find any reason to deny that Ryzen is equivalent to Broadwell in IPC performance.

Even when you compare the 1700X with the top 4-core Kaby Lake part (7700K, with 42.8889 per GHz score), you get 94.45% performance.

So you basically have an architecture that provides performance within 5% of the current top dog, hitting incredible price/performance and watt/performance levels, and you're not happy?
 
You should read everything on the source link. Maybe you could avoid being silly.

You should really use your brain & think about what AMD's trying to do. They created Mantle which then evolved into Vulkan & DX12 API's too better utilize CPU cores & their GPU's via Async Compute. Look at the rumored prices of Ryzen CPU's, they clearly want the 8 core 16 thread CPU's to become the standard over time just like Intel quad cores have for the past 6 years & IMO 6 years way too long. The single thread performance is clearly up to par with Intel's offerings, not the highest but still very competitive as well as the multi thread performance assuming these leaks are accurate.
 
if numbers are true the new&future amd cpu's will be quite good and will help also intel fanboys to buy their stuff at lower prices

the best thing is that we'll have again competition and reasonable prices; what do we need more?

personally i won't upgrade cpu as i still can use it for a while...maybe will buy a used one sometime..when prices will be half of today's one... 1st in my mind is the wallet not the e-peen
 
All the graphs show Intel only CPUs, dafak? :) BTW: best single-core raper (& notoious one at that) is Prime95. Atleast for me. Not that I won't DL Cinebench, I'd actually would. Cheers.
 
I almost got the i7-6700/7700 in early January, but then all these rumors came out suggesting that Ryzen will offer the same for half the price. I'd have to choose so many parts once again...
I feel very relieved ( :P ) seeing that the top of the range 7 1700X is somehow behind consumer Skylake CPUs, because actually I was thinking about the slower 65W models (1700 or 1500).

That said, it's impressive that they've packed 8 HT cores in such a small and cheap CPU. It obviously gives impressive multi-core results and while most users will never utilize this potential, the numbers are very nice. :)
 
Last edited:
Hype train just got faster:

4y301f8q0ehy.jpg
 
You should really use your brain & think about what AMD's trying to do. They created Mantle which then evolved into Vulkan & DX12 API's too better utilize CPU cores & their GPU's via Async Compute. Look at the rumored prices of Ryzen CPU's, they clearly want the 8 core 16 thread CPU's to become the standard over time just like Intel quad cores have for the past 6 years & IMO 6 years way too long. The single thread performance is clearly up to par with Intel's offerings, not the highest but still very competitive as well as the multi thread performance assuming these leaks are accurate.

You should use yours instead and understand that I don´t care about multi thread performance or about the best price vs performance ratio cpu. I want the absolute best performance per clock CPU. 7700k clocks at 4,8ghz easily (won´t even mention the number of samples at 5ghz wich are a lot anyway) with 4000mhz DDR4 ram. Can Ryzen surprass this kind of performance? Most likely it can´t, so I don´t care if it has 16 threads. I only play games and 4 cores + 4 logical wich stunning clock performance are good to me.

The fact here is that for GAMING:

Ryzen will be worse than Intel comparing both at stock clocks.
Ryzen will be worse than Intel comparing both at max CPU + RAM overclock.

If your concern is price vs performance ratio or Multi-Threaded operations on your computer, be happy, but don´t try to convince others that they need it too. We´re all different.
 
So many people here somehow think that ryzen will be worse for gaming. :D Sure if we talk about CSGO FPS in 2017 at +1300 FPS ye you'll get some principal win having better singlethreaded performance. But the thing is; new games are not made for the CPUs but the GFXes; im pretty sure ryzen vs. 6700K will be 1:1 when it comes to FPS in games UNLESS the game either is HEAVILY coded for single-core(6700K wins or multicores(Ryzen wins). So in other words; If you are buying a computer to play older games and NOT newer titles; go with singlethreaded performance; if you are planning on playing new games the comming years (2017-2019) Go with a multithreaded performer because if you think that technology will not find its way you are a dinosaur in the field.
 
I only play games and 4 cores + 4 logical wich stunning clock performance are good to me.

Games are already using more than 4 cores: Overwatch, Battlefield 1, Assasin's Creed, Cities: Skyline, Ashes of Singularity, Star Ruler 2.

But Intel approves your approach.
 
Did AMD make a mistake going with PGA? Some CPU enthusiast believe AMD should have opted for LGA

Is it true? Or is it just preference?
 
Did AMD make a mistake going with PGA? Some CPU enthusiast believe AMD should have opted for LGA

Is it true? Or is it just preference?

I think it was a cost cutting measure. I recall reading somewhere that using LGA will increase the cost of a motherboard by at least $20 for the end user across the board. I don't recall the source so take that with a cup of salt.
 
I think it was a cost cutting measure. I recall reading somewhere that using LGA will increase the cost of a motherboard by at least $20 for the end user across the board. I don't recall the source so take that with a cup of salt.

I'm not sure of cost increase, but that's what I read, too. Intel decides to save some money and stick on the consumer even more.
 
Games are already using more than 4 cores: Overwatch, Battlefield 1, Assasin's Creed, Cities: Skyline, Ashes of Singularity, Star Ruler 2.

But Intel approves your approach.

Sure. That´s why 7700k at 4,8ghz stinks on 6800k on all those games.

btw, Ryzen can reach 5ghz....... with LN2:

Maxium air overclock between the 2 chips will dictate the winner for gaming. Not threads, and so far all we know is that Ryzen can´t reach kabylake clocks on air, only LN2.

Suddenly everyone needs threads when before "i5 was enough for everyone" :D Oh I love the fanboys that need to justify their phurcases or favourite brands :D
 
No, i´m debunking everything and making claims backed up by facts: Ryzen ships with lower clock than Intel, Ryzen only reaches Intel clocks with LN2, games prefer higher/faster clock 4+4 instead of lower/slower clock 8+8.

Wait some days for some real game benchmarks and we will see if "I´m justifying" anything or just quoting facts.
 
No, i´m debunking everything and making claims backed up by facts: Ryzen ships with lower clock than Intel, Ryzen only reaches Intel clocks with LN2, games prefer higher/faster clock 4+4 instead of lower/slower clock 8+8.

Wait some days for some real game benchmarks and we will see if "I´m justifying" anything or just quoting facts.
You're not quoting facts, alternate facts o_O
ZW5KNUdR.jpeg
 
DIrect comparison (mips * clock frequency) is not a true measure.

For example, multiply/divide of two integers may take 20+ clock ticks with Intel, and because of design improvements, the same operation on the Ryzen may only require 16+ clock ticks.

How to explain the difference? Consider parallel operations within the chip. But to achieve more parallelism, you need to allocate more logic to the multiplier/divider circuitry. And that is probably what has happened. (Smaller circuit sizes allows more logic space available within the CPU die)

Go through all the instructions that can be optimized by smarter circuitry, and you have the explanation why the AMD chips are more performing.

I am willing to bet that chip for chip, the AMD has many more transistors and gates for logic to support parallel sub-instruction processing. More parallelism used to support fewer clock-ticks.

Instructions within a CPU are also within a pipeline queue. I do not know the chip internals, but there may be up to 10+ instructions in the input queue that are at various stages of being decoded. The queue is flushed if an interrupt instruction is received.

Taken all together, fewer clock ticks to decode an instruction, perhaps saving some of the queue contents during an interrupt may be the major reason the AMD chips are faster, even with slower clock frequencies.
 
Last edited:
I am pretty impressed with the scores they showed at the AMD even. 1612 in cinebench with the stock 1800X, even with a toasty overclock that is a good jump ahead of my 6850K. These numbers keep looking good. Albeit all of the test systems AMD showed seemed to be really pushing the more cores is better mentality and look at this multithreading so color me nervously optimistic.

cinebench-4544-6850k-1398.jpg
 
I get 3347 in Cinebench on my work system. (2133 mem). That 1500 looks pretty good.

View attachment 84359

My work system with dual ES E5 V4 scores 3482 and runs around 3.6x as fast as my 6700k entertainment system in some of my programming loads. With each at the price of a Ryzen 5, the ES Xeons look not too bad in value. :)

On the other hand, my 6700k does seem obsolete now. Maybe time to get the system RYZEN.
 
You're not quoting facts, alternate facts o_O
ZW5KNUdR.jpeg

I´m quoting facts, you´re quoting an overclock on LN2 wich is what I mentioned in the first place. That Ryzen can only achieve 7700k clocks with those super high voltages.
 
I´m quoting facts, you´re quoting an overclock on LN2 wich is what I mentioned in the first place. That Ryzen can only achieve 7700k clocks with those super high voltages.
You're not quoting any facts, unless you're claiming 7700K can do ~5.2 GHz easily. Then there's the 4 vs 8 core thing you must've overlooked, or that the octa core R7 are listed at 95W TDP?
 
Well its settled now. Intel is shuddering in fear, and their fanboys are rolling in denial.

AMD has pulled an athlon off once again.

I dont really care if AMD isnt significantly faster than intels offering.
AMD is beating intel, at a much lower price. and they are on par in single threaded. So its all good.
 
Back
Top