Processor comparison performance: AMD Ryzen 5 5500U vs Intel Core i5-1135G7 @ 2.40GHz [cpubenchmark.net] by PassMark Software

Qualcomm vs. Intel CPU comparison

Loading…

November 08, 2017 8:03PM

Vlad Krasnov

One of the nicer perks I have here at Cloudflare is access to the latest hardware, long before it even reaches the market.

Until recently I mostly played with Intel hardware. For example Intel supplied us with an engineering sample of their Skylake based Purley platform back in August 2016, to give us time to evaluate it and optimize our software. As a former Intel Architect, who did a lot of work on Skylake (as well as Sandy Bridge, Ivy Bridge and Icelake), I really enjoy that.

Our previous generation of servers was based on the Intel Broadwell micro-architecture. Our configuration includes dual-socket Xeons E5-2630 v4, with 10 cores each, running at 2.2GHz, with a 3.1GHz turbo boost and hyper-threading enabled, for a total of 40 threads per server.

Since Intel was, and still is, the undisputed leader of the server CPU market with greater than 98% market share, our upgrade process until now was pretty straightforward: every year Intel releases a new generation of CPUs, and every year we buy them. In the process we usually get two extra cores per socket, and all the extra architectural features such upgrade brings: hardware AES and CLMUL in Westmere, AVX in Sandy Bridge, AVX2 in Haswell, etc.

In the current upgrade cycle, our next server processor ought to be the Xeon Silver 4116, also in a dual-socket configuration. In fact, we have already purchased a significant number of them. Each CPU has 12 cores, but it runs at a lower frequency of 2.1GHz, with 3.0GHz turbo boost. It also has smaller last level cache: 1.375MiB/core, compared to 2.5MiB the Broadwell processors had. In addition, the Skylake based platform supports 6 memory channels and the AVX-512 instruction set.

As we head into 2018, however, change is in the air. For the first time in a while, Intel has serious competition in the server market: Qualcomm and Cavium both have new server platforms based on the ARMv8 64-bit architecture (aka aarch64 or arm64). Qualcomm has the Centriq platform (codename Amberwing), based on the Falkor core, and Cavium has the ThunderX2 platform, based on the, ahm … ThunderX2 core?

The majestic Amberwing powered by the Falkor CPU CC BY-SA 2.0 image by DrPhotoMoto

Recently, both Qualcomm and Cavium provided us with engineering samples of their ARM based platforms, and in this blog post I would like to share my findings about Centriq, the Qualcomm platform.

The actual Amberwing in question

Overview

I tested the Qualcomm Centriq server, and compared it with our newest Intel Skylake based server and previous Broadwell based server.

Platform	Grantley (Intel)	Purley (Intel)	Centriq (Qualcomm)
Core	Broadwell	Skylake	Falkor
Process	14nm	14nm	10nm
Issue	8 µops/cycle	8 µops/cycle	8 instructions/cycle
Dispatch	4 µops/cycle	5 µops/cycle	4 instructions/cycle
# Cores	10 x 2S + HT (40 threads)	12 x 2S + HT (48 threads)	46
Frequency	2. 2GHz (3.1GHz turbo)	2.1GHz (3.0GHz turbo)	2.5 GHz
LLC	2.5 MB/core	1.35 MB/core	1.25 MB/core
Memory Channels	4	6	6
TDP	170W (85W x 2S)	170W (85W x 2S)	120W
Other features	AES CLMUL AVX2	AES CLMUL AVX512	AES CLMUL NEON Trustzone CRC32

Overall on paper Falkor looks very competitive. In theory a Falkor core can process 8 instructions/cycle, same as Skylake or Broadwell, and it has higher base frequency at a lower TDP rating.

Ecosystem readiness

Up until now, a major obstacle to the deployment of ARM servers was lack, or weak, support by the majority of the software vendors. In the past two years, ARM’s enablement efforts have paid off, as most Linux distros, as well as most popular libraries support the 64-bit ARM architecture. Driver availability, however, is unclear at that point.

At Cloudflare we run a complex software stack that consists of many integrated services, and running each of them efficiently is top priority.

On the edge we have the NGINX server software, that does support ARMv8. NGINX is written in C, and it also uses several libraries written in C, such as zlib and BoringSSL, therefore solid C compiler support is very important.

In addition our flavor of NGINX is highly integrated with the lua-nginx-module, and we rely a lot on LuaJIT.

Finally a lot of our services, such as our DNS server, RRDNS, are written in Go.

The good news is that both gcc and clang not only support ARMv8 in general, but have optimization profiles for the Falkor core.

Go has official support for ARMv8 as well, and they improve the arm64 backend constantly.

As for LuaJIT, the stable version, 2.0.5 does not support ARMv8, but the beta version, 2.1.0 does. Let’s hope it gets out of beta soon.

Benchmarks

OpenSSL

The first benchmark I wanted to perform, was OpenSSL version 1. 1.1 (development version), using the bundled openssl speed tool. Although we recently switched to BoringSSL, I still prefer OpenSSL for benchmarking, because it has almost equally well optimized assembly code paths for both ARMv8 and the latest Intel processors.

In my opinion handcrafted assembly is the best measure of a CPU’s potential, as it bypasses the compiler bias.

Public key cryptography

Public key cryptography is all about raw ALU performance. It is interesting, but not surprising to see that in the single core benchmark, the Broadwell core is faster than Skylake, and both in turn are faster than Falkor. This is because Broadwell runs at a higher frequency, while architecturally it is not much inferior to Skylake.

Falkor is at a disadvantage here. First, in a single core benchmark, the turbo is engaged, meaning the Intel processors run at a higher frequency. Second, in Broadwell, Intel introduced two special instructions to accelerate big number multiplication: ADCX and ADOX. These perform two independent add-with-carry operations per cycle, whereas ARM can only do one. Similarly the ARMv8 instruction set does not have a single instruction to perform 64-bit multiplication, instead it uses a pair of MUL and UMULH instructions.

Nevertheless, at the SoC level, Falkor wins big time. It is only marginally slower than Skylake at an RSA2048 signature, and only because RSA2048 does not have an optimized implementation for ARM. The ECDSA performance is ridiculously fast. A single Centriq chip can satisfy the ECDSA needs of almost any company in the world.

It is also very interesting to see Skylake outperform Broadwell by a 30% margin, despite losing the single core benchmark, and only having 20% more cores. This can be explained by more efficient all-core turbo, and improved hyper-threading.

Symmetric key cryptography

Symmetric key performance of the Intel cores is outstanding.

AES-GCM uses a combination of special hardware instructions to accelerate AES and CLMUL (carryless multiplication). Intel first introduced those instructions back in 2010, with their Westmere CPU, and every generation since they have improved their performance. ARM introduced a set of similar instructions just recently, with their 64-bit instruction set, and as an optional extension. Fortunately every hardware vendor I know of implemented those. It is very likely that Qualcomm will improve the performance of the cryptographic instructions in future generations.

ChaCha20-Poly1305 is a more generic algorithm, designed in such a way as to better utilize wide SIMD units. The Qualcomm CPU only has the 128-bit wide NEON SIMD, while Broadwell has 256-bit wide AVX2, and Skylake has 512-bit wide AVX-512. This explains the huge lead Skylake has over both in single core performance. In the all-cores benchmark the Skylake lead lessens, because it has to lower the clock speed when executing AVX-512 workloads. When executing AVX-512 on all cores, the base frequency goes down to just 1.4GHz—keep that in mind if you are mixing AVX-512 and other code.

The bottom line for symmetric crypto is that although Skylake has the lead, Broadwell and Falkor both have good enough performance for any real life scenario, especially considering the fact that on our edge, RSA consumes more CPU time than all of the other crypto algorithms combined.

Compression

The next benchmark I wanted to see was compression. This is for two reasons. First, it is a very important workload on the edge, as having better compression saves bandwidth, and helps deliver content faster to the client. Second, it is a very demanding workload, with a high rate of branch mispredictions.

Obviously the first benchmark would be the popular zlib library. At Cloudflare we use an improved version of the library, optimized for 64-bit Intel processors, and although it is written mostly in C, it does use some Intel specific intrinsics. Comparing this optimized version to the generic zlib library wouldn’t be fair. Not to worry, with little effort I adapted the library to work very well on the ARMv8 architecture, with the use of NEON and CRC32 intrinsics. In the process it is twice as fast as the generic library for some files.

The second benchmark is the emerging brotli library, it is written in C, and allows for a level playing field for all platforms.

All the benchmarks are performed on the HTML of blog.cloudflare.com, in memory, similar to the way NGINX performs streaming compression. The size of the specific version of the HTML file is 29,329 bytes, making it a good representative of the type of files we usually compress. The parallel benchmark compresses multiple files in parallel, as opposed to compressing a single file on many threads, also similar to the way NGINX works.

gzip

When using gzip, at the single core level Skylake is the clear winner. Despite having lower frequency than Broadwell, it seems that having lower penalty for branch misprediction helps it pull ahead. The Falkor core is not far behind, especially with lower quality settings. At the system level Falkor performs significantly better, thanks to the higher core count. Note how well gzip scales on multiple cores.

brotli

With brotli on single core the situation is similar. Skylake is the fastest, but Falkor is not very much behind, and with quality setting 9, Falkor is actually faster. Brotli with quality level 4 performs very similarly to gzip at level 5, while actually compressing slightly better (8,010B vs 8,187B).

When performing many-core compression, the situation becomes a bit messy. For levels 4, 5 and 6 brotli scales very well. At level 7 and 8 we start seeing lower performance per core, bottoming with level 9, where we get less than 3x the performance of single core, running on all cores.

My understanding is that at those quality levels Brotli consumes significantly more memory, and starts thrashing the cache. The scaling improves again at levels 10 and 11.

Bottom line for brotli, Falkor wins, since we would not consider going above quality 7 for dynamic compression.

Golang

Golang is another very important language for Cloudflare. It is also one of the first languages to offer ARMv8 support, so one would expect good performance. I used some of the built-in benchmarks, but modified them to run on multiple goroutines.

Go crypto

I would like to start the benchmarks with crypto performance. Thanks to OpenSSL we have good reference numbers, and it is interesting to see just how good the Go library is.

As far as Go crypto is concerned ARM and Intel are not even on the same playground. Go has very optimized assembly code for ECDSA, AES-GCM and Chacha20-Poly1305 on Intel. It also has Intel optimized math functions, used in RSA computations. All those are missing for ARMv8, putting it at a big disadvantage.

Nevertheless, the gap can be bridged with a relatively small effort, and we know that with the right optimizations, performance can be on par with OpenSSL. Even a very minor change, such as implementing the function addMulVVW in assembly, lead to an over tenfold improvement in RSA performance, putting Falkor ahead of both Broadwell and Skylake, with 8,009 signatures/second.

Another interesting thing to note is that on Skylake, the Go Chacha20-Poly1305 code, that uses AVX2 performs almost identically to the OpenSSL AVX512 code, this is again due to AVX2 running at higher clock speeds.

Go gzip

Next in Go performance is gzip. Here again we have a reference point to pretty well optimized code, and we can compare it to Go. In the case of the gzip library, there are no Intel specific optimizations in place.

Gzip performance is pretty good. The single core Falkor performance is way below both Intel processors, but at the system level it manages to outperform Broadwell, and lags behind Skylake. Since we already know that Falkor outperforms both when C is used, it can only mean that Go’s backend for ARMv8 is still pretty immature compared to gcc.

Go regexp

Regexp is widely used in a variety of tasks, so its performance is quite important too. I ran the builtin benchmarks on 32KB strings.

Go regexp performance is not very good on Falkor. In the medium and hard tests it takes second place, thanks to the higher core count, but Skylake is significantly faster still.

Doing some profiling shows that a lot of the time is spent in the function bytes.IndexByte. This function has an assembly implementation for amd64 (runtime.indexbytebody), but generic implementation for Go. The easy regexp tests spend most of time in this function, which explains the even wider gap.

Go strings

Another important library for a webserver is the Go strings library. I only tested the basic Replacer class here.

In this test again, Falkor lags behind, and loses even to Broadwell. Profiling shows significant time is spent in the function runtime.memmove. Guess what? It has a highly optimized assembly code for amd64, that uses AVX2, but only very simple ARM assembly, that copies 8 bytes at a time. By changing three lines in that code, and using the LDP/STP instructions (load pair/store pair) to copy 16 bytes at a time, I improved the performance of memmove by 30%, which resulted in 20% faster EscapeString and UnescapeString performance. And that is just scratching the surface.

Go conclusion

Go support for aarch64 is quite disappointing. I am very happy to say that everything compiles and works flawlessly, but on the performance side, things should get better. Is seems like the enablement effort so far was concentrated on the compiler back end, and the library was left largely untouched. There are a lot of low hanging optimization fruits out there, like my 20 minute fix for addMulVVW clearly shows. Qualcomm and other ARMv8 vendors intends to put significant engineering resources to amend this situation, but really any one can contribute to Go. So if you want to leave your mark, now is the time.

LuaJIT

Lua is the glue that holds Cloudflare together.

With the exception of the binary_trees benchmark, the performance of LuaJIT on ARM is very competitive. It wins two benchmarks, and is in almost a tie in a third one.

That being said, binary_trees is a very important benchmark, because it triggers many memory allocations and garbage collection cycles. It will require deeper investigation in the future.

NGINX

For the NGINX workload, I decided to generate a load that would resemble an actual server.

I set up a server that serves the HTML file used in the gzip benchmark, over https, with the ECDHE-ECDSA-AES128-GCM-SHA256 cipher suite.

It also uses LuaJIT to redirect the incoming request, remove all line breaks and extra spaces from the HTML file, while adding a timestamp. The HTML is then compressed using brotli with quality 5.

Each server was configured to work with as many workers as it has virtual CPUs. 40 for Broadwell, 48 for Skylake and 46 for Falkor.

As the client for this test, I used the hey program, running from 3 Broadwell servers.

Concurrently with the test, we took power readings from the respective BMC units of each server.

With the NGINX workload Falkor handled almost the same amount of requests as the Skylake server, and both significantly outperform Broadwell. The power readings, taken from the BMC show that it did so while consuming less than half the power of other processors. That means Falkor managed to get 214 requests/watt vs the Skylake’s 99 requests/watt and Broadwell’s 77.

I was a bit surprised to see Skylake and Broadwell consume about the same amount of power, given both are manufactured with the same process, and Skylake has more cores.

The low power consumption of Falkor is not surprising, Qualcomm processors are known for their great power efficiency, which has allowed them to be a dominant player in the mobile phone CPU market.

The engineering sample of Falkor we got certainly impressed me a lot. This is a huge step up from any previous attempt at ARM based servers. Certainly core for core, the Intel Skylake is far superior, but when you look at the system level the performance becomes very attractive.

The production version of the Centriq SoC will feature up to 48 Falkor cores, running at a frequency of up to 2.6GHz, for a potential additional 8% better performance.

Obviously the Skylake server we tested is not the flagship Platinum unit that has 28 cores, but those 28 cores come both with a big price and over 200W TDP, whereas we are interested in improving our bang for buck metric, and performance per watt.

Currently my main concern is weak Go language performance, but that is bound to improve quickly once ARM based servers start gaining some market share.

Both C and LuaJIT performance is very competitive, and in many cases outperforms the Skylake contender. In almost every benchmark Falkor shows itself as a worthy upgrade from Broadwell.

The largest win by far for Falkor is the low power consumption. Although it has a TDP of 120W, during my tests it never went above 89W (for the go benchmark). In comparison Skylake and Broadwell both went over 160W, while the TDP of the two CPUs is 170W.

If you enjoy testing and selecting hardware on behalf of millions of Internet properties, come [join us](https://www.cloudflare.com/careers/).

We protect
entire corporate networks,
help customers build
Internet-scale applications efficiently,
accelerate any
website
or Internet application,
ward off DDoS
attacks, keep
hackers at
bay,
and can help you on
your journey to Zero Trust.

Visit 1.1.1.1 from any device to get started with
our free app that makes your Internet faster and safer.

To learn more about our mission to help build a better Internet, start here. If you’re looking for a
new career direction, check out our open
positions.

SSL
OpenSSL
Compression
Speed & Reliability
LUA

Every Apple chip compared in the ultimate speed test!

Home / Accessories / Feature

Feature

Let’s take a look at the current processors in the iPhone, iPad, and Mac lineup to see how each performs.

By Roman Loyola

Senior Editor, Macworld JAN 28, 2023 7:15 am PST

Image: Foundry

At the heart of every Apple device is an Apple processor. Apple has been using its own chips in its iPhones and iPads for some time, while the Mac lineup has nearly completed its transition away from Intel chips. Apple has far more devices with its own silicon than Intel’s now—all that remains is the Mac Pro—and before the end of 2023, every product Apple makes will likely be powered by a home-grown chip.

What’s remarkable about Apple silicon is its performance and power efficiency. But all chips aren’t created equally. Understanding the performance differences between each chip will help with your buying decisions, especially when you’re deciding between iPhone 14 or MacBook models. Knowing how each chip performs gives you a better idea of what products to buy and whether or not it’s worth your money to step up to a higher model.

Let’s take a look at how the new processors compare with the rest of the processors in the iPhone, iPad, and Mac lineup and see how each performs and what that means to you. For the sake of consistency, we’ve used Geekbench 5 benchmarks. Here’s every chip and how the benchmarks compare with each other.

Every processor compared

Before we get into the individual processors, let’s let the chips fall where they may. We’ve only included chips in Apple devices that are still for sale and it’s a somewhat predictable chart, with the fastest Mac chips at the top, followed by a mix of iPads and iPhones. But there are still some fascinating results: Owners of the iPad Pro can say their tablet is about as fast as a MacBook Air and that wouldn’t be an exaggeration. And the difference between the $399 iPhone SE and the $899 iPhone 14 isn’t as huge as their price difference indicates.

Read about how Apple’s M1 and M2 processors compare to Intel in our Mac processor guide.

iPhone processors

Let’s take a look at the specifications so we can understand the differences between them.

Processor	Performance cores	Efficiency cores	Graphics cores	Neural Engine	Memory	Transistors	Thermal Design Power	Devices
A16 Bionic	2 at 3.46GHz	4 at 2.02GHz	5	16-core	8GB	16 billion	6W	iPhone 14 Pro
A15 Bionic	2 at 3. 22GHz	4 at 1.82GHz	5	16-core	8GB	15 billion	6W	iPhone 14
A15 Bionic	2 at 3.22GHz	4 at 1.82GHz	4	16-core	8GB	15 billion	6W	iPhone 13, iPhone SE
A14 Bionic	2 at 3.1 GHz	4 at 1.8GHz	4	16-core	6GB	11.8 billion	6W	iPhone 12

Now let’s look at how each processor performs. Not surprisingly, the A16 Bionic in the iPhone 14 Pro is the fastest. The iPhone 14 and iPhone 13 both have an A15 Bionic processor, but the iPhone 13 has one fewer GPU core than the iPhone 13 Pro, which gives it better graphics performance.

iPhone 14 Pro

Apple still sells the iPhone 12, which has an A14 Bionic. It’s actually not much slower than the iPhone 13’s A15 Bionic–the specs between the two processors are practically the same, with the A15 Bionic’s performance cores having a slightly faster clock speed and more RAM. If price is the main priority over the camera and other features, consider the iPhone 12 instead of the iPhone 13.

The speed difference is more obvious between the iPhone 12’s A14 Bionic and the chips in the iPhone 14 models. This could be the last hurrah for the A14 Bionic since the iPhone 12 will be replaced by the 13 as the low-cost option with Apple’s next major iPhone rollout next fall, though it’s possible it makes its way into the next Apple TV revision.

iPad processors

The staggered release of Apple’s iPad lineup creates an odd-looking performance order of CPU and its device.

Processor	Performance cores	Efficiency cores	Graphics cores	Neural Engine	Memory	Transistors	Thermal Design Power	Devices
M2	4 at 3.49GHz	4 at 2.06GHz	10	16-core	8GB	20 billion	15W	12.9″ & 11″ iPad Pro
M1	4 at 3. 2GHz	4 at 2.06GHz	8	16-core	8GB	16 billion	14W	iPad Air
A15 Bionic	2 at 2.93GHz	4 at 1.82GHz	5	16-core	4GB	15 billion	6W	iPad mini
A14 Bionic	2 at 3.1GHz	4 at 1.8GHz	4	16-core	6GB	11.8 billion	6W	iPad

The M2-equipped iPad Pros are the fastest models, and the gap between them and the iPad and iPad mini is significant. Furthermore, the M2 is 15 percent faster than the M1 that it replaced in the previous iPad Pros and is in the current iPad Air.

The new 10th-gen iPad that was released in the fall of 2022 has an A14 Bionic, an upgrade from the A13 Bionic in the previous model. Apple says the new 10th-gen iPad offers a 20 percent CPU boost and a 10 percent graphics increase.

iPad mini (6th generation)

Mac processors

With Apple’s M-series of chips for the Mac, the company’s release schedule involves the base version in the MacBook Air, 13-inch MacBook Pro, and other Macs. Apple then modifies it to create higher-end versions. Read about how the M2 compared to the M1 Pro and M1 Max.

The latest M-Series chip is the M2, which was released with the new 13-inch MacBook Pro and the MacBook Air in the summer of 2022, right after WWDC. The M2 replaces the M1 in those Macs, but Apple may keep around M1 models to offer as low-cost options, such as the $999 M1 MacBook Air. In January 2023, Apple released the M2 Pro in the 14- and 16-inch MacBook Pro and Mac mini, and M2 Max in the 14- and 16-inch MacBook Pro along with an M2 Mac mini.

Processor	Performance cores	Efficiency cores	Graphics cores	Neural Engine	Base memory	Transistors	Thermal Design Power	Device
M2 Max	8 at 3.49GHz	4 at 2.4GHz	38	16-core	32GB	67 billion	30W	14″ & 16″ MacBook Pro
M2 Max	8 at 3. 49GHz	4 at 2.4GHz	30	16-core	32GB	67 billion	30W	14″ & 16″ MacBook Pro
M2 Pro	8 at 3.49GHz	4 at 2.4GHz	19	16-core	16GB	40 billion	30W	14″ & 16″ MacBook Pro
M2 Pro	6 at 3.49GHz	4 at 2.4GHz	16	16-core	16GB	40 billion	30W	14″ MacBook Pro
M2	4 at 3.49GHz	4 at 2.4GHz	10	16-core	8GB	20 billion	15W	13″ MacBook Pro, MacBook Air
M2	4 at 3.49GHz	4 at 2.4GHz	8	16-core	8GB	20 billion	15W	MacBook Air
M1 Ultra	16 at 3.2GHz	4 at 2.06GHz	64	32-core	64GB	114 billion	60W	Mac Studio
M1 Ultra	16 at 3.2GHz	4 at 2. 06GHz	48	32-core	64GB	114 billion	60W	Mac Studio
M1 Max	8 at 3.2GHz	2 at 2.06GHz	32	16-core	32GB	57 billion	30W	Mac Studio
M1 Max	8 at 3.2GHz	2 at 2.06GHz	24	16-core	32GB	57 billion	30W	Mac Studio
M1	4 at 3.2GHz	4 at 2.06GHz	8	16-core	8GB	16 billion	14W	MacBook Air, 24″ iMac
M1	4 at 3.2GHz	4 at 2.06GHz	7	16-core	8GB	16 billion	14W	MacBook Air, 24″ iMac

With the M2, Apple claims an 18 percent improvement in general CPU performance over the M1. In the multi-core CPU test, we are able to confirm Apple’s claim. The single-core CPU test showed a lower 13 percent increase for the M2. With the M2 Pro and M2 Max, Apple claims a 20 percent boost over the M1 Pro (which is no longer in any current Mac) and the M2 Max.

The M1 Ultra is a beast of a chip, doubling the CPU multi-core performance of the M1 Max, which has half as many CPU cores. It blazes in GPU performance, too. There’s no word on when Apple will release an M2 Ultra, but it will most likely debut in the upcoming Mac Pro.

MacBook Air M2 (2022)

Apple’s Max chips have the same CPU configuration as the Plus versions; the key difference is the GPU. The Max can have double the GPU cores as the Plus, so its graphics performance is much improved.

The chip that started it all, the good ol’ M1, may seem slow compared to Apple’s more current chips—but that’s not to undermine Apple’s original Mac processor. Remember, the M1 blows past the Intel processors it replaced, resulting in a significant price/performance value.

Author: Roman Loyola, Senior Editor

Roman has covered technology since the early 1990s. His career started at MacUser, and he’s worked for MacAddict, Mac|Life, and TechTV.

Notebook processor performance comparison

Author Novikov Vladimir To read 10 min Views 4. 6k.
Updated 06.06.2022

Content

Best Intel processors of past
5. Intel Pentium N5000
4. Intel Core M3 8100Y
3. Intel Core i3 8130u

9000 9000 2. Intel Core I7555555555555555555555555555555555555555555510 9000 9000 9000 9000 2 1. Intel Core i7 8809G

The best processors of past years from AMD
5. AMD A12 9720p
4. AMD Athlon 300u
3. AMD Ryzen 3 2200u
2. AMD Ryzen 7 2700u
1. AMD Ryzen 5 2500u

9000 9000 9000 9000 9000. Intel

5. Intel Core i9 8950HK
4. Intel Core i7 9750h
3. Intel Core i7 9850h
2. Intel Core i9 9880h

9000

9980HK

0 9000 AMD AMD AMD AMD AMD AMD AMD AMD AMD Ryzen 7 2800H

4. AMD RYZEN 3 3300U
3. AMD RYZEN 5 3500U
2. AMD RYZEN 7 3700U
1. AMD RYZEN 7 3750H
Recommendations for choice

Information processing in a computer — this is a lot performed by the CPU. The capabilities of the PC, its speed, suitability for various types of human activity depend on the characteristics of this device. The cost of a computer directly depends on the parameters of its main component, which is usually compared with the brain.

Processors that are used in portable electronics are often soldered to the motherboard, so that replacement of such an element is possible only in a workshop with special and expensive equipment. Therefore, laptop owners instead of upgrading are forced to look for new, more powerful and expensive equipment. It follows from this that the choice of processor for a laptop should be balanced and take into account the needs, tasks and well-being of the user. To navigate the abundance of models, it is worth studying the parameters of devices that are considered the best.

The best Intel processors of yesteryear

The list includes 2017 and 2018 models. This is due to the fact that not all buyers need new items, because many people buy a laptop for office work and study. The latest processors will be of interest to gamers, lovers of high-quality video content in high resolution and 3D format, as well as professionals in IT and related fields. First, old, but still relevant models will be considered.

5. Intel Pentium N5000

The quad-core model, which entered the market in 2017, opens the rating of laptop processors. The nominal clock frequency, which indicates the number of operations per second, is 1.1 GHz, the maximum achievable as a result of overclocking is 2.7 GHz. The N5000 has 4 MB of cache memory, it performs calculations in 4 parallel threads, which increases the speed of data processing (compared to previous generation processors, where hyper-threading technology is not implemented). The amount of RAM used is 8 GB. The device is equipped with an integrated graphics card UHD Graphics 605, which is capable of operating at a frequency of 200-750 MHz. The video adapter supports DirectX 12 technology and 4K video playback.

A model with the listed characteristics is great for working with office programs, surfing the net, watching videos, but not for running games. Laptops with such a CPU can be bought for small amounts, in comparison with analogues.

4. Intel Core M3 8100Y

Quad-thread yet dual-core processor with 4 MB L3 cache, 1.1 GHz base frequency and 3.4 GHz maximum, UHD 615 integrated graphics (300 to 900 MHz). The supported amount of RAM is up to 16 GB. Released in 2018. The model is not for games, although it copes well with high-definition video. Saves battery power thanks to improved energy efficiency.

3. Intel Core i3 8130U

Gen 8 device with 2 cores, 4 threads capability and 4 MB cache. Its frequency is 2.2 GHz, in Turbo Boost mode it rises to 3.4 GHz. Equipped with an integrated video adapter with a frequency of 300 MHz — 1000 MHz and native support for H. 265 and VP9 codecs. The maximum amount of system memory that can be used is 32 GB. A great option for a not too demanding user who does not want to overpay for unnecessary cores.

2. Intel Core i7 8750H

Last year’s 6-core model with 12 threads, an impressive 9MB cache and 64GB RAM capability. The frequency is 2.2-4.1 GHz, for the integrated UHD 630 video card of the same manufacturer — 350-1100 MHz. Powerful laptop processor with a number of threads and cores that will satisfy the most demanding users. However, for games you will have to use a discrete adapter.

1. Intel Core i7 8809G

The leader of the previous year’s Intel mobile processor rating. The quad-core model has 8 computing threads, the clock frequency ranges from 3.1-4.2 GHz, the cache is 8 MB in size. This is an APU that is unique among others as it comes with two graphics cards: an integrated Intel HD Graphics 630 at 350-1100 MHz and a discrete Radeon RX Vega M GH at 1190 MHz. The latter can work with 6 displays. The processor excels at running games and graphics applications.

The best processors of yesteryear from AMD

You can choose a processor for a laptop from among the options from the second most important manufacturer — AMD. The list includes 5 options that were released in the past years, but still remain in demand.

5. AMD A12 9720P

The device went on sale in 2016. Model with 4 cores and the same number of threads, 2 MB cache in the second level, a base frequency of 2.7 GHz and a maximum of 3.6 GHz (when operating in Turbo Core mode). Integrated Graphics — Radeon R7 @ 900 MHz. The device is very popular due to acceptable performance, which is more than enough for everyday tasks.

4. AMD Athlon 300U

Dual-core processor with 4 threads, 4 MB cache, frequency 2.4-3. 3 GHz, integrated video adapter Radeon RX Vega 3 with three cores and 1000 MHz frequency. Can work with 64 GB of system memory. This is a new generation model that entered the market at the very beginning of 2019.of the year. Recommended for running office programs.

3. AMD Ryzen 3 2200U

A more affordable analogue of the Core i3 from Intel, released in 2018. A model with two cores and twice as many threads, a frequency of 2.5-3.4 GHz, a cache of 4 MB. The integrated video adapter is a tri-core Radeon Vega 3 Graphics, whose frequency is 1100 MHz. The amount of system memory that the model can use is 32 GB. The non-gaming processor has gained popularity by achieving the perfect balance between price and performance.

2. AMD Ryzen 7 2700U

2017 model, quad-core, double threads, frequency spread from 2.2 to 3.8 GHz, and 4 MB cache. Graphics card — integrated, Radeon RX Vega 10 Graphics with 10 cores and a frequency of up to 1300 MHz. The maximum RAM is 32 GB. Suitable for thin and light laptops. Performance leader among models based on Zen architecture, comparable to similar Core i7 processors from the Intel range.

1. AMD Ryzen 5 2500U

Rounding out the list of the best AMD processors to see the light of day in the past few years is the 2018 quad-core model with 8 threads. Frequency — 2 GHz (nominal), during overclocking it increases to 3.6 GHz. Level 3 cache size is 4 MB. Equipped with integrated graphics Radeon RX Vega 8 (the figure indicates the number of cores), the operating frequency of which can reach 1100 MHz. In terms of performance, the processor is comparable to similar options from Intel (Core i5 and i7). The most profitable model among those close in parameters.

Top New Intel

Processors

8th and 9th generation processors have increased the number of cores and threads. Although the average performance has increased, the company still produces models that differ in power and cost. This allows buyers to choose the appropriate option without overpaying for unnecessary indicators.

5. Intel Core i9 8950HK

8th Gen 6-core processor with 12 threads. In normal mode, the frequency of the model is 2.9 GHz, in Turbo mode it can reach 4.8 GHz, the cache is 12 MB, the maximum RAM size is 64 GB. The built-in video card, UHD 630, operates at speeds from 350 to 1200 MHz. The model needs effective cooling, as it heats up during overclocking. Suitable for home use, internet surfing, music, video, games (except the latest versions).

4. Intel Core i7 9750H

Representative of the 9th generation with 6 cores and twice as many threads. The frequency fluctuates between 2.6-4.5 GHz. The cache capacity is impressive: 12 MB. Usable system memory — up to 128 GB. The video adapter is the same as in the previous case: UHD 630 with a maximum frequency of 1.15 GHz. Excellent processor for a pre-top gaming model (requires a powerful cooler for cooling during overclocking).

3. Intel Core i7 9850H

The characteristics are almost identical to the previous model, only the maximum clock frequency in Turbo mode is different — 4.6 GHz. This can be a decisive argument, other things being equal, one of which is the price.

2. Intel Core i9 9880H

Octa-core processor with 16 processing threads, 16 MB cache, base and maximum frequencies of 2.3 GHz and 4.8 GHz, respectively. The amount of RAM with which the model is able to work is 128 GB. The version of the integrated graphics adapter is Intel UHD 630, frequency from 350 MHz to 1.2 GHz. Processor comparison tables and customer surveys indicate that this model is the first in performance for top-level work laptops.

1. Intel Core i9 9980HK

The

model rightfully tops the rating of Intel mobile processors in terms of performance: with 8 cores, 16 threads, 16 MB cache and a nominal frequency of 2.4 GHz, it can accelerate to 5 GHz in turbo mode. The integrated UHD 630 graphics differ from those used in the four models listed above with a higher frequency (1. 25 GHz). A multi-purpose processor that is suitable for the most demanding users.

Top New AMD

Processors

The company does not lag behind its main competitor and produces high-performance components that are sold at more affordable prices.

5. AMD Ryzen 7 2800H

Quad-core model capable of computing in 8 threads. 4 MB cache (level 3), frequency spread — 3.3 to 3.8 GHz. Complemented by a powerful built-in eleven-core video adapter Radeon RX Vega 11 Graphics, operating at speeds up to 1300 MHz. Supported RAM up to 32 GB.

4. AMD Ryzen 3 3300U

This model has 4 threads and cores. With 4 MB of cache, 64 GB of RAM, a frequency of 2.1 to 3.5 GHz, a six-core video adapter Radeon Vega 6 Graphics (1.2 GHz), the processor has a low price for a new generation model. Budget option for office work, study and home leisure.

3.

AMD Ryzen 5 3500U

Quad-core model, performs operations in 8 threads. Frequencies range from 2.1 to 3.7 GHz, cache size is 4 MB, RAM is 64 GB. The integrated graphics card Radeon Vega 8 Graphics has 8 cores and decent video processing speed: 1.2 GHz. Popular due to the optimal combination of performance and cost, it is energy efficient, but does not meet the requirements of avid gamers.

2. AMD Ryzen 7 3700U

Processor with improved architecture. With the same power consumption as its predecessors, it performs more operations per unit of time, and also has an increased core bandwidth, for which it is called a «smart» processor. Quad-core, 8 threads, 4 MB cache, rated at 2.3 GHz and maximum achievable at 4 GHz. The ten-core integrated graphics card Radeon RX Vega 10 Graphics operates at a speed of 1.4 GHz.

1. AMD Ryzen 7 3750H

The parameters are similar to the previous model, but the performance of the new version is higher. It differs from analogues from the Core i7 line in terms of price and heat dissipation, which will not only save money, but also do without improving the cooling system. It is used in gaming laptops, as it provides the necessary performance. The power of the built-in video card is enough to render graphics at lower settings, which allows you to do without a discrete adapter. Best laptop processor in 2019year in the line from AMD.

Selection guide

Some models are excellent for some specific applications:

Users looking for value for money and performance should take a closer look at the AMD Ryzen 2500U and 1500U processors.
For those who work with video (cameramen, editors, streamers), you will need a laptop with a Ryzen 3700U or 3750H model.
Fans of Intel video processing will be pleased if they purchase a laptop equipped with Core i7 8750H.
For gamers with high performance requirements, the Core i9 9980HK from Intel will do.

The selection should begin with a clarification of the needs and aspirations of future users. A top-end laptop at an appropriate price is a must for IT workers, designers, and those whose activities are related to video and audio processing. Running heavy applications for solving engineering problems is possible on laptops with powerful processors. Office applications, standard programs for study, entertainment, communication require fewer resources, technical and financial, although a business may need a model with enhanced performance.

You need to pay attention to power consumption if the laptop is to work offline without recharging for a long time. The level of heat generation must be taken into account: overheating causes components to fail before their expected service life.

When choosing, it is useful to take into account the results of performance tests conducted by experts. Pivot tables, graphs, and charts help sort out inappropriate models. Another source of information is the opinions of customers who have already purchased a laptop and tested it in practice. Reviews are published on forums, websites of online stores, portals dedicated to computer technology.

Comparison of modern Intel and Amd processors

The processor is undoubtedly the most important component of any personal computer. Processor performance determines the overall performance of the entire system. So if you decide to buy a computer, the first thing you need to decide is the processor. And it doesn’t matter if you buy a ready-made computer, or prefer to build a computer to order, first of all you need to choose a processor.

Below is the processor performance rating — a comparison table that will help you understand what place a particular processor occupies among its competitors, how and how much the performance of different processors differs.

To rank the processors, the performance of each of them was measured when performing typical tasks. First, a general performance test, the result of which demonstrates the processor’s ability to perform mathematical calculations. The results of the general processor performance test are shown in the column

«General». This column should be taken into account if you plan to use the computer mainly for work, for example, with mathematical software packages such as MathCad, etc.

Secondly, performance was measured when working with programs for creating 3D graphics (3D Studio Max, 3D Mark) and in particular rendering. If you have to work a lot with 3D graphics, then you need to focus on the «3D graphics» column.

Thirdly, CPU performance test in modern games: Crysis, Call of Duty 4, Quake 4, Unreal Tournament 3. The results of these tests in the performance table are given in the «Games» column. These results can be a guide for most people who buy a gaming home computer. A home computer is generally not expected to perform time-consuming scientific calculations, and the applications that require the most performance are video games.

Fourth, we measured the performance of processors when encoding video. If you spend most of the time spent at the computer processing and editing videos, then the column «Coding» will be of most interest to you in the comparison table.

Finally, the column «Archiving» shows the results of measuring the performance of processors when archiving large amounts of data. WinRAR was used in this processor test.

The average processor performance («Average» column) is the arithmetic average of the performances obtained in all tests.

This table shows the numerical ratings for each processor in individual benchmarks and the average rating. The larger the number (i.e., the higher the rating), the better the performance.

This rating uses the Intel Core 2 Duo E7200 as the benchmark for performance. The performance of all other processors is shown in comparison with the performance of the E7200. What the numbers in the performance comparison table mean is best explained by an example: the performance of the Core 2 Duo E7200 processor in archiving is 100 points, and the Core 2 Duo E8500 is 131, so the E8500 will perform the same task 31% faster than the E7200 ( that is, where the E7200 takes a minute to archive, the E8500 can do it in 41 seconds). Similarly, you can compare the performance of any two processors from the table, both by the results of a separate test, and by the average performance.

After a careful study of the rating of processors and a comparison of performance, conclusions suggest themselves. Firstly, it is clear that AMD processors are significantly inferior to Intel processors: the most productive quad-core Phenom processors stand next to the dual-core Intel E8000 series processors and lose to the new quad-core Intel processors in all tests.

Among all performance tests, the game test stands apart. Quad-core processors, while showing high performance in other tests, in games are not so far ahead (and some even lag behind) of dual-core processors. The fact is that games are less optimized for multi-core processors and support multi-threading to a lesser extent, so a dual-core processor with a higher frequency is preferable to a 4-core processor with a lower frequency. This circumstance suggests that for gaming computers, most often, it will be preferable to have two — and not a four-core processor.

Before going to a computer store, you need to think about the price of the processor, or, in other words, the efficiency of the processor, expressed in rubles per unit of performance. Below is a table comparing processors by this indicator: the smaller the ratio, the better. The prices for processors for this rating are average prices from Yandex. Market.

As you can see from the table, the higher the performance, the worse the price-performance ratio.