Cpu benchmark for gaming: CPU Benchmarks Hierarchy 2022: Processor Ranking Charts

Quad Core with Hyperthreading versus Quad CoreThe Importance of DataCPUs, GPUs, Motherboards, and MemoryTesting Methodology, Hardware ConfigurationsCPU BenchmarksGPU Benchmarks: Metro2033GPU Benchmarks: Dirt 3GPU Benchmarks: Civilization VGPU Benchmarks: Sleeping DogsFinal Results, Conclusions and Recommendations

Point Calculations — 3D Movement Algorithm Test

The algorithms in 3DPM employ both uniform random number generation or normal distribution random number generation, and vary in various amounts of trigonometric operations, conditional statements, generation and rejection, fused operations, etc.   The benchmark runs through six algorithms for a specified number of particles and steps, and calculates the speed of each algorithm, then sums them all for a final score.  This is an example of a real world situation that a computational scientist may find themselves in, rather than a pure synthetic benchmark.  The benchmark is also parallel between particles simulated, and we test the single thread performance as well as the multi-threaded performance.

For single thread performance, the higher MHz Haswell CPUs sit on top of the list — interestingly enough it is the Xeons.  Comparing these to the i7-4960X, which also sits at 4 GHz, shows the generational difference in this purely multithreaded test.  The 100 MHz difference between the i5-4670K and the i7-4770K shows up as two points in this test.  The s1366 CPUs are staggered between a score of 90.93 and 115.79, with the i7-920 falling short of the X6-1100T.  Due to the IPC difference the i7-990X is behind the i5-2500K and anything older at a similar MHz.

For the multithreaded test, cores and MHz with FP performance win out here, so the i5-4670K, even in a motherboard with Multi-Core Turbo, sits behind the eight threads of the FX-8350 and six threads of the X6-1100T.  The i7-4770K scores another 75%, along with the Xeons.  In terms of the Nehalem CPUs, the i7-990X performs an extra 200 points higher than the latest Haswell CPUs due to its six core / twelve thread design.  Unfortunately the i7-920/i7-950 are a little behind, with the i7-2600K offering a noticable boost.

Compression — WinRAR x64 3.93 + WinRAR 4.2

With 64-bit WinRAR, we compress the set of files used in the USB speed tests. WinRAR x64 3.93 attempts to use multithreading when possible, and provides as a good test for when a system has variable threaded load.  WinRAR 4.2 does this a lot better! If a system has multiple speeds to invoke at different loading, the switching between those speeds will determine how well the system will do.

The only downside with WinRAR is that when you’re dealing with slow CPUs, they are very slow!  The quad core Nehalem CPUs are kept on track by the FX-8350 using this older version of WinRAR, although it seems the higher IPC wins out here over cores with the 4.0 GHz Haswell Xeons scoring best.

The improvements in WinRAR 4.2 due to optimisations and multi-threading result in more cores giving better results.  The i7-990X does well here, although Sandy Bridge-E and Ivy Bridge-E take the top spots.  Due to the threading advantage WinRAR takes, the i7-4770K gets a 20 second advantage of its non-hyperthreaded cousin, the i5-4670K.

Image Manipulation — FastStone Image Viewer 4.2

FastStone Image Viewer is a free piece of software I have been using for quite a few years now.  It allows quick viewing of flat images, as well as resizing, changing color depth, adding simple text or simple filters.  It also has a bulk image conversion tool, which we use here.   The software currently operates only in single-thread mode, which should change in later versions of the software.  For this test, we convert a series of 170 files, of various resolutions, dimensions and types (of a total size of 163MB), all to the .gif format of 640×480 dimensions.

FastStone loves single threaded IPC and MHz, so it’s no surprise for the Haswell CPUs to be on top, with no discernable difference between the i5-4670K and the i7-4770K.  The old school Nehalems take a knock, with the i7-920 being almost a full 60% slower than the top scores.

Video Conversion — Xilisoft Video Converter 7

With XVC, users can convert any type of normal video to any compatible format for smartphones, tablets and other devices.  By default, it uses all available threads on the system, and in the presence of appropriate graphics cards, can utilize CUDA for NVIDIA GPUs as well as AMD WinAPP for AMD GPUs.  For this test, we use a set of 33 HD videos, each lasting 30 seconds, and convert them from 1080p to an iPod H. 264 video format using just the CPU.  The time taken to convert these videos gives us our result.

For fully multithreaded video conversion, a combination of cores, IPC and MHz take top spots, hence the i7-4960X is the consumer CPU to get.  The i7-990X has a smaller advantage over the quad core Haswells this time, and here is one benchmark where the i5-4670K falls behind the FX-8350s due to the integer nature of the workload.  Interestingly enough the i5-4430 slots in with an i5-2500K due to IPC increases despite lower power consumption and MHz.

Rendering – PovRay 3.7

The Persistence of Vision RayTracer, or PovRay, is a freeware package for as the name suggests, ray tracing.  It is a pure renderer, rather than modeling software, but the latest beta version contains a handy benchmark for stressing all processing threads on a platform. We have been using this test in motherboard reviews to test memory stability at various CPU speeds to good effect – if it passes the test, the IMC in the CPU is stable for a given CPU speed.   As a CPU test, it runs for approximately 2-3 minutes on high end platforms.

PovRay is another ‘multithreading takes all’, as shown by our 4P testing on E5-4650L CPUs.  The i7-990X still shows its worth, being as quick as the i7-4770K at least, although the i7-920 and i7-950 are further down the pecking order.

Video Conversion — x264 HD Benchmark

The x264 HD Benchmark uses a common HD encoding tool to process an HD MPEG2 source at 1280×720 at 3963 Kbps.  This test represents a standardized result which can be compared across other reviews, and is dependent on both CPU power and memory speed.  The benchmark performs a 2-pass encode, and the results shown are the average of each pass performed four times.

Grid Solvers — Explicit Finite Difference

For any grid of regular nodes, the simplest way to calculate the next time step is to use the values of those around it.  This makes for easy mathematics and parallel simulation, as each node calculated is only dependent on the previous time step, not the nodes around it on the current calculated time step.   By choosing a regular grid, we reduce the levels of memory access required for irregular grids.  We test both 2D and 3D explicit finite difference simulations with 2ⁿ nodes in each dimension, using OpenMP as the threading operator in single precision.  The grid is isotropic and the boundary conditions are sinks.  Values are floating point, with memory cache sizes and speeds playing a part in the overall score.

Grid solvers do love a fast processor and plenty of cache in order to store data.  When moving up to 3D, it is harder to keep that data within the CPU and spending extra time coding in batches can help throughput.  Our simulation takes a very naïve approach in code, using simple operations, but that doesn’t stop the single socket, highly threaded CPUs taking top spots.  The i5-4670K takes a surprising twist in 2D, outpacing the i7-4770K.

Grid Solvers — Implicit Finite Difference + Alternating Direction Implicit Method

The implicit method takes a different approach to the explicit method – instead of considering one unknown in the new time step to be calculated from known elements in the previous time step, we consider that an old point can influence several new points by way of simultaneous equations.   This adds to the complexity of the simulation – the grid of nodes is solved as a series of rows and columns rather than points, reducing the parallel nature of the simulation by a dimension and drastically increasing the memory requirements of each thread.  The upside, as noted above, is the less stringent stability rules related to time steps and grid spacing.  For this we simulate a 2D grid of 2ⁿ nodes in each dimension, using OpenMP in single precision.  Again our grid is isotropic with the boundaries acting as sinks. Values are floating point, with memory cache sizes and speeds playing a part in the overall score.

If anything, large caches matter more in implicit simulation, in line with both cores and threads.  The i5-4430 is on the lower rungs of the Intel bloc, but the 990X is at the top.

Point Calculations — n-Body Simulation

When a series of heavy mass elements are in space, they interact with each other through the force of gravity.   Thus when a star cluster forms, the interaction of every large mass with every other large mass defines the speed at which these elements approach each other.  When dealing with millions and billions of stars on such a large scale, the movement of each of these stars can be simulated through the physical theorems that describe the interactions. The benchmark detects whether the processor is SSE2 or SSE4 capable, and implements the relative code.  We run a simulation of 10240 particles of equal mass — the output for this code is in terms of GFLOPs, and the result recorded was the peak GFLOPs value.

Due to extension enhancements, we see that a quad core Haswell Xeon scores roughly the same as the hex-core Nehalem, with the i5-4430 not far behind. If anything, the i7-920 and i7-950 take a nose dive here, and it’s worth investing even in an i5-4430 for a 50% performance enhancement.

Testing Methodology, Hardware Configurations
GPU Benchmarks: Metro2033
Quad Core with Hyperthreading versus Quad CoreThe Importance of DataCPUs, GPUs, Motherboards, and MemoryTesting Methodology, Hardware ConfigurationsCPU BenchmarksGPU Benchmarks: Metro2033GPU Benchmarks: Dirt 3GPU Benchmarks: Civilization VGPU Benchmarks: Sleeping DogsFinal Results, Conclusions and Recommendations

Tweet

PRINT THIS ARTICLE

How to Benchmark Your Gaming PC

A PC benchmark is a free and easy way to test your system thoroughly. Whether its a new gaming PC or steady old rig, it is always beneficial to see the performance

Updated: Apr 21, 2022 11:28 am

Share this article…

What is a Computer Benchmark, exactly?

Gaming Benchmarks

Synthetic Benchmarks

What components should I benchmark?

Processor (CPU)

Graphics Card (GPU)

Full System

Before You Benchmark

Looking to stress-test your PC, check out our video below!

How to Benchmark my PCs CPU?

PassMark

Geekbench

CPU-Z

How to Benchmark my PCs GPU?

Unigine Heaven

Basemark

3DMark

How to Benchmark my PCs Entire System?

UserBenchmark

Novabench

PCMark 10

Conclusion

Today, we’re going to tell you all you need to know about benchmarking your gaming PC. This will include a brief explanation of what benchmarks even are, the difference between gaming and synthetic benchmarks, what components you should be benchmarking in your system, and our recommended tools for benchmarking said components.

Rest assured. If you’re here to learn how to benchmark your PC, you’re in the right place. You’ll know how to benchmark your system and then some by the time we’re done.

What is a Computer Benchmark, exactly?

If you aren’t sure what a benchmark is exactly, that’s okay, a lot of people don’t. In this context, benchmarks are used to assess and compare performance between your system and the millions of others out there. To get a benchmark, people usually run games (gaming benchmarks) or specialized applications (synthetic benchmarks) to extract performance numbers from, allowing individual components or full systems to be pitted against one another.

Gaming Benchmarks

Perhaps the most important benchmark you’ll ever get is a real-world gaming benchmark. After all, you can have the best synthetic benchmarks in the world, but if things don’t actually work when the game is running, then what’s the point.

This means running a game through a set scenario, usually more than once, to find an average level of performance in that game, on that hardware, with those particular settings.

Some modern games even have built-in benchmarks for players to run. While this isn’t a comprehensive list, you can find a lot of games with built-in benchmarks at XS Reviews.

You’ll see these frequently in CPU and GPU reviews, as well as gaming PC reviews and even individual game reviews. You may also be inclined to run these yourself, but these aren’t the type of benchmark we’re covering in this article. Instead, we’re talking primarily about…

Synthetic Benchmarks

Synthetic benchmarks are basically computer performance tests. Unlike gaming benchmarks, synthetic benchmarks are meant to serve as a standard point of reference, regardless of the hardware you’re running.

With gaming benchmarks, some games may run better on otherwise-equal Nvidia cards versus AMD cards, for instance. Synthetic benchmarks, however, won’t reflect these outlier scenarios and will focus instead on establishing the standard level of performance that you can expect from your system.

If you want to see how your PC will do for a specific game or application, we recommend checking out our How To Check If My PC Will Run This Game article. If you want to get an idea of how your PC and its components will do in general, though, keep reading.

What components should I benchmark?

Processor (CPU)

First and foremost, you should benchmark your CPU. It’s called the Central Processing Unit for a reason, after all.

While many games out there are primarily GPU-dependent, you still need to make sure that your CPU is up to par before buying the latest games. Additionally, CPU performance pertains to your entire system, not just games or video, as the GPU does. If your PC is a body, think of your CPU as its brain- integral, irreplaceable, and more important than any other part of the whole.

Graphics Card (GPU)

Next up is the GPU, which will have the most impact on your gaming performance… unless it’s being bottlenecked by other components or the game is CPU-bound instead of GPU-bound.

The GPU is going to be doing most of the work in your games and many of these benchmarking applications. If there are any instabilities or issues with your GPU, these benchmarks should expose them while also giving you an idea of your performance.

Full System

Last but not least, full system benchmarks! It usually isn’t worth running individual-component benchmarks for components that aren’t the CPU or GPU.

Anyway, with full system benchmarks, you can get easy, accurate numbers on your memory and storage drives as well. The only time you should need to run individual benchmarks on non-CPU/GPU components is if you’re a reviewer or journalist, but for consumers, this isn’t necessary.

Before You Benchmark

Now, actually running a benchmark application is pretty straightforward. You pretty much just install it, open it, and let it run. However, there are a few things you’re going to want to do before you start benchmarking your PC:

• Close everything else, including non-essential background applications. You want your results to be as accurate as possible, and keeping applications running will lower your scores, CPU scores especially.
• Set aside some time. While most benchmarks shouldn’t take any longer than a few minutes to run, this can be extended by anywhere from 10-30 minutes, depending on your system. Make sure that before you start recording benchmarks that there isn’t anything urgent for you to take care of and that you have something to occupy your time while they’re running.
• Be patient. Don’t expect instant gratification with any of the benchmark suites, and don’t interrupt them at all if you want good results. This may seem like a no-brainer, but patience is in short supply among more people than you’d think, so we’re still saying it here.

Lastly, it’s worth mentioning that all of these benchmarks are compatible with Windows, including Windows 10 (and some are even compatible with Android and iOS devices). Got all those bases covered? Great. Let’s get benchmarking!

Looking to stress-test your PC, check out our video below!

How to Benchmark my PCs CPU?

PassMark

Our first CPU benchmark tool is PassMark and it comes with a free 30-day trial (it costs $29 to use afterward). (So pretty much free if you only plan on running it once or twice!) It technically offers a full system benchmark, but I mostly recommend it for its CPU benchmarking suite, which is pretty thorough. This includes the ability to compare your performance to similar systems, “baselines”, and more.

If you want a sort-of-free and reliable CPU benchmark, PassMark is a pretty solid pick. It’s far from the only one, though…

Geekbench

Geekbench is another great CPU benchmarking tool. While its premium versions also offer CUDA and Metal Benchmarks, its tryout version offers a 64-bit benchmark right out of the box, which is exactly what you want from a CPU benchmarking tool.

Since Geekbench is also multi-platform, you can even compare your PC’s scores to, say, the latest iPhone’s scores! It won’t really change anything, but it’s pretty nifty!

CPU-Z

CPU-Z is primarily an application focused on getting exact specifications and performance information on your CPU. It isn’t exactly a “benchmarking application”, per se, but it can be used to determine if your CPU is performing as expected, and you can compare your results to those of others with the same CPU.

If you’re worried that there’s something wrong with your CPU, this can be a pretty good application to run to get to the bottom of the issue.

How to Benchmark my PCs GPU?

Unigine Heaven

While this may be an older benchmark, it’s still a favorite among enthusiasts for a few key reasons:

• It was actually pretty ahead of its time
• It looks fairly nice

Unigine Heaven released in 2009, but GPUs that could run it well at higher presets didn’t start coming out until 2012, with the release of the GTX 600 series. This is a great benchmarking application to run for older GPUs and modern GPUs alike, thanks to its great support for DirectX 11 features and age, making it easier to compare GPUs of different eras in actual performance numbers.

The best part? Most of it is completely free. While a few more advanced features (like per-frame analysis and automated benchmark looping) are locked to higher tiers, your basic benchmarking functions should be just fine with the free version of the benchmark.

Basemark

If you want another free benchmark test, but one that’s more… modern, we recommend Basemark. Basemark tests for Vulkan 1.0, Open GL 4.5, and OpenGL ES 3.1 support and features with more graphics APIs coming in the future. In addition to being available for desktop PCs, it’s also available for smartphones, smart TVs, and even cars. (Probably the self-driving variety.)

As far as benchmarks go, this is a much newer entrant to the scene, and it probably won’t be very useful for older GPUs. However, it does serve as a great way to see how your modern GPU handles heavy graphical effects like depth of field, advanced lighting, etc.

3DMark

Last, but certainly not least, is the premium industry standard: 3DMark. 3DMark is easily one of the most popular GPU benchmarking suites out there thanks to its wide variety of benchmarks released over the course of the past decade. When people want to show off their benchmark scores, 3DMark is one of the most frequently used applications, but there is a catch.

Namely, it isn’t free. If you want this– even for individual usage– you’re going to need to shell out $29.99 unless it’s on sale. That being said, 3DMark is certainly worth the price, though. For the money you’re paying, you’re getting years’ worth of great graphics benchmarks to run through your GPU, and a large community of other consumers to compare your results against.

How to Benchmark my PCs Entire System?

UserBenchmark

Thanks to its simplicity, low price of “free”, and massive community of testers, UserBenchmark is probably my favorite full system benchmark application out there. While it may not be as precise or strenuous as per-component GPU/CPU benchmarks, it’s very good at giving an approximate level of performance for your system and its components. Thanks to the large community of people also running UserBenchmark, you’ll be able to see how your PC is performing when compared to PCs of similar or identical specs.

In addition to the easy benchmarking, sharing, and comparison benefits, UserBenchmark can also be good for diagnosing your system. For instance, if one of your drives are starting to run more slowly than average drives of identical make and model, UserBenchmark will pick up on that and notify you if that component is performing below expectations.

Novabench

Next up is Novabench, another free full system benchmarking solution. It’s another favorite of mine– while it doesn’t have as large of a community as UserBenchmark or premium benchmarking suites, it still provides solid results and a very clean, easy-to-use UI.

Once you’ve run the benchmark, you get a results screen and the ability to compare your PC to multiple others, including “baseline” PCs for various price ranges and comparisons to other, similarly-specced PCs to your own.

PCMark 10

Lastly is PCMark 10, which is a premium product. Like 3DMark, PCMark usually retails for $30 unless it’s on sale, but it offers a thorough full-system benchmark for all of your components. However, it doesn’t really offer any features that the other listed products don’t, and a lot of its tests are centered around “productivity”, which is better tested by… well, just doing productivity work.

Honestly, PCMark is probably more for pro usage than consumer usage. It’s still good enough to earn its place on the list here, though.

Conclusion

And there you go! Now you know how to benchmark your PC and its most important components. All of these benchmarking applications are safe and straightforward to use, with the only extra step being a purchase in the cases where they aren’t provided for free.

That being said, what else do you need help with? Is there anything you think we missed! If you have any issues whatsoever benchmarking your PC, feel free to comment below and let us know!

WePC is reader-supported. When you buy through links on our site, we may earn an affiliate commission. Learn more

Destiny 2 Launch CPU Benchmark: Ryzen, Kaby Lake, & 8350K | GamersNexus

Our Destiny 2 GPU benchmark highlighted massive performance uplift vs. beta on some devices, upwards of 50% on Vega, but was conducted in largely GPU-constrained scenarios. For this content piece, we’ll be exploring the opposite: CPU-constrained scenarios to benchmark Destiny 2 performance on AMD Ryzen and Intel Kaby/Coffee Lake parts, including the R7 1700, R5 1600X, R3 1200, and i7-7700K, i5-7600K, i3-8350K, and G4560.

Most of our test notes have already been recapped in the GPU benchmark, and won’t be fully repeated. Again, we ran a wide spread of tests during the beta, which will be informing our analysis for the Destiny 2 launch benchmarks. Find the previous content below:

• Destiny 2 Beta GPU Benchmark (+ graphics optimization guide, PvP scalability)
• Destiny 2 Beta CPU Benchmark (soon replaced by our Destiny 2 launch CPU bench)
• Destiny 2 texture comparison

Starter CPUs

Our goal for this testing was to get a relatively wide sweep of CPUs tested so that we could find any potential shortcomings of the testing approach. For this reason, we have an eclectic mix of CPUs, but did put most of our emphasis on testing the R7 2700(X), i9-9900K, and R5/i7 CPUs, as we know these are the most interesting to our audience. Here’s the list of initial CPUs we tested, with more to be added as we go:

• AMD R5 2600
• AMD R5 2600X
• AMD R7 2700
• AMD R7 2700X
• AMD TR 2990WX (in most benchmarks)
• Intel i5-8600K
• Intel i7-8700K
• Intel i7-9700K
• Intel i9-9900K

Most of these CPUs were also overclocked for a second pass through the entire test suite. A full run on the test suite, including games (not featured today), takes approximately 8 hours per CPU, plus another ~8 hours for the overclocked variant. We try to keep them running relatively non-stop and around the clock when we’re working on CPU content.

We are still adding CPUs. This is a ‘pilot episode’ of our new workstation testing!

CPU Test Methodology

Our CPU testing methodology is split into two types of benchmarks: Games and workstation workloads, but every CPU which is sufficiently high-end will go through both sets of tests. We are beginning to spend more effort publicly documenting the exact versions of our tests, hoping that this is helpful to those reading our tests. We are also detailing more explicitly the unit of measurement in text, although our charts typically do this as well. Our workstation benchmarks include the following tests:

• 7-ZIP Compression benchmark (version 1806 x64). Unit of measurement: MIPS (millions of instructions per second; higher is better)
• 7-ZIP Decompression benchmark (version 1806 x64). 25 bytes, 4 passes and then averaged. Thread count equals the CPU thread count.
• Blender 2.79 GN Logo render (frame from GN intro animation, heavy on ray-tracing). Unit of measurement: Render time in minutes (lower is better)
• Blender 2.79 GN Monkey Heads render (CPU-targeted workload with mixed assets, transparencies, and effects). Unit of measurement: Render time in minutes (lower is better).
• GNU Compiler Collection (GCC) version 7.4.0, compiling 8.2.0 on Windows 10. Unit of measurement: Render time in minutes (lower is better). Run with Cygwin environment.
• Chaos Group V-Ray CPU Benchmark (1.0.8). Unit of measurement: Render time in minutes (lower is better)
• Cinebench R15 (used for internal validation). Unit of measurement: CB Marks (higher is better)
• TimeSpy Physics. Unit of measurement: 3DMark points & FPS (higher is better)
• Adobe Photoshop CC 2019 (Puget 18.10). Unit of measurement: Average score (higher is better)
• Adobe Premiere & AME CC 2019 (GN test suite: 1080p60 convention shot; H. 264, 35Mbps, 5.2, High profile, AAC+Version 2, Audio 256K). Unit of measurement: Render time in AME (lower is better). CUDA enabled.
• Adobe Premiere & AME CC 2019 (GN test suite: 4K60 aroll+broll; H.264, 35Mbps, 5.2, High profile, AAC+Version 2, Audio 256K). Unit of measurement: Render time in AME (lower is better). CUDA enabled.
• Adobe Premiere & AME CC 2019 (GN test suite: 4K60 charts; H.264, 35Mbps, 5.2, High profile, AAC+Version 2, Audio 256K). Unit of measurement: Render time in AME (lower is better). CUDA enabled.

All tests are conducted multiple times for parity and then averaged, with outliers closely and manually inspected. The number of times tested depends on the application and its completion time. We use an internal peer review process where one technician runs tests, then the other reviews the results (applying basic logic) to ensure everything looks accurate. Any stand-out results are reported back to the test technician and rerun after investigation. Error margins are also defined in our chart bars to help illustrate the limitations of statistical relevance when analyzing result differences. These are determined by taking thousands of test results per benchmark and determining standard deviation for each individual test and product. Any product that has significant excursions from the mean deviation will be highlighted in its respective review.

GN CPU Test Bench 2019

Motherboards used are varied based upon platform. Where compatible, we used the following:

• ASUS Maximus XI Hero Z390
• ASUS Crosshair VII Hero X470
• MSI MEG X399 Creation

Although we’d all love to run numerous test benches simultaneously, we have determined that GPU silicon variance can significantly alter results even within the same video card model. As such, we only one run bench at a time, and we always use the same GPU. Driver version 417.71 is used. Adaptive sync is not used in testing.

MCE is always disabled on test platforms, ensuring that turbo boost durations should be running within specifications set by the CPU manufacturer. We also try to keep an eye out for other motherboard trickery, like MSI’s oft-boosted BCLK, and then reset to stock settings when applicable. XMP is used on the Corsair memory in our test benches.

GNU Compiler Collection

We had a lot of requests to add compiler benchmarks to our test suite, so we finally did. For this, we’ve added the GCC Benchmark, which involves compiling the GNU Compiler Collection version 8. 2.0 with GCC version 7.4.0. We set a flag to allow it to spawn as many threads as possible, so the compilation process involves both some single-threaded and heavily multi-threaded parts. Interestingly, the results for this test are the inverse of many of the gaming tests that we’ll next publish, with all the AMD chips on top and all the Intel chips at the bottom. The 2990WX with Coreprio enabled logged the fastest time and an 11% time reduction versus the stock 2990WX. The AMD chips below this are ordered predictably: the 4.2GHz 16-thread 2700 is at the top, allowing the 2990WX a time reduction of about half, with the R5 2600 at 4.2GHz following the 2700. This shows that frequency still matters, as it outpaces the 2700X stock CPU marginally. The R7 2700X’s 8.7-minute compile time leads the 9900K stock CPU by 22%, a meaningful improvement. The 9900K leads the Intel CPUs, and again the order is predictable: other than the AMD/Intel divide, the CPUs are logically ordered by the highest frequency/core count parts, with the stock 8600K at the very bottom. Frequency and core count are important factors, but they aren’t everything, and this is one real-world workload that shows it.

Note that other compilers may behave differently, and also that linking is a factor worthy of consideration. If using linkers that are typically single-threaded, this can pose a bottleneck. We are also doing all of our testing on Windows, and so Linux workloads would further exhibit different behavior.

7-Zip Compression / Decompression CPU Workstation Benchmark

7-Zip includes a built-in benchmark that can generate scores for both compression and decompression measured in millions of instructions per second. Interestingly, decompression appears to be more thread-dependent than compression. The 9900K leads in compression by a good margin, with 21.4% more instructions per second than the 9700K when both are overclocked, so threads still do affect the score. The worst performer in this category is the stock i5-8600K with only 6 cores and 6 threads, but the 32 core/64 thread 2990WX only lands in the middle of the chart. We seem to be constrained to some extent by single-threaded performance.

In decompression, however, Threadripper tears ahead of anything else with 115% more instructions per second than the overclocked 9900K. The stock AMD R7 2700X and overclocked R7 2700 actually manage to beat-out the stock i9-9900K, although overclocking to 5.2GHz does allow it to regain the lead at the expense of power. The stock 2700 outperforms the overclocked 9700K at 5.1GHz, illustrating a limitation in the i7’s thread count as the R7 gains a 5% lead. Even the R5 2600 at 4.2GHz nearly keeps-up with the OC 9700K.

Adobe Photoshop CC 2019 CPU Benchmark

We’re now using Puget Systems’ Photoshop benchmark. It recommends 32GB of system memory, which is the main reason we now use four 8GB sticks of RAM for all of our tests rather than just for CPUs that can run memory in quad-channel. We run the extended version of the benchmark, which produces seven scores as well as an overall score to summarize them. Thread-count isn’t much help here, and the 5.2GHz 9900K tops the chart again. The chart is roughly ordered by CPU frequency, with the 2990WX scoring slightly worse than the stock R5 2600, even with game mode or Coreprio. The ordering by frequency is further illustrated by the 8600K at 5GHz outperforming a stock 8700K, or the 9700K at 5.1GHz outperforming the stock 9900K. Photoshop appears to be frequency-bound in these tests, which include the application of various filters, transforms, resizes, photomerges, and more.

Blender CPU Benchmarks

Blender benchmarking has also changed with this round. We’re keeping our in-house made benchmark scenes, using realistic workloads with ray tracing, movie-ready render settings, and realistic effects. We’ve eliminated the Blender 2.78 monkey head render testing and the temperamental 2.79 Splash render, leaving only the Blender 2.79 monkey head and GN logo renders. The monkey heads are a varied workload, while the logo hammers the CPU and is typically the test that causes unstable overclocks to reveal themselves. Blender is an important test to us because we actually use it, and it directly benefits us to know which CPUs handle it best.

Let’s start with the monkey head render. The 2990WX takes this test handily with its 64 threads, and the rest of the stack lines-up in a similar order to other thread-bound workloads, with the 9700K being the only CPU breaking the more cores/higher score pattern. The 2990WX finished testing in 10.9 minutes stock, roughly the same with Coreprio, and demonstrates clear value to professionals who work in tile-based rendering applications like Blender. The biggest value add is when high system memory requirements exist, as this can rapidly exit confines of GPU memory allotment, thus limiting usefulness of CUDA. We still need to retest our HEDT Intel CPUs, so Threadripper remains relatively isolated for now.

The 9900K at stock completes its render in 20.6 minutes, a time reduction of 11% from the stock R7 2700X’s 23-minute render time. The 2700X comes close, given the price difference, and that’s because Blender tends to favor thread count since it spawns one tile per thread.

For the GN Logo render, the TR 2990WX obviously still leads, and will until further updates to the chart. The 9900K stock CPU roughly equates an overclocked 2700 at 4.2GHz, although outperforms the stock 2700X with a 6% render time reduction. The stock 2700 and stock 9700K also end up roughly tied, with the 8700K approaching both of these CPUs.

Adobe Premiere CC 2019 CPU Benchmarks

Premiere is a test that we’ve done in the past, but haven’t kept up with faithfully due to the amount of manual setup required. Our last Adobe Premiere test was with our old test methodology, where we showed the Intel 28-core 3175X proving genuinely good when overclocked. It drew a hell of a lot of power, but it also managed the fastest render times, even outperforming the 9980XE. We haven’t retested that with our new test suite just yet, but we do have the more mainstream CPUs tested for today.

We’ve streamlined the process and we’re now rendering three videos: one at 1080p60, one at 4K60, and one 4K video consisting entirely of charts. H.264 is our codec for these for now, with a high profile and 35Mbps output. We have video clips of these in our video embedded above, in case you want to see what they’re rendering.

Starting with the 1080p60 a-roll and b-roll footage from a convention, where we used clips entirely off of our Panasonic UX180 and recorded through our Zoom audio devices, we get the chart on the screen now. We haven’t yet put the 9980XE or 3175X on here yet, but they’d probably outpace the 9900K’s 3.9-minute render. Render times reduced by nearly 8% with an overclock to 5.1GHz. The 9700K at 5.1GHz shows that, despite being frequency-locked with our chart-topping 9900K, the extra threads are beginning to help more as Adobe Premiere Pro CC 2019 updates. The 9900K at 5.1GHz holds a lead of 15% over the 9700K, advantaged by its double thread count. AMD’s R7 2700 at 4.2GHz and 2700X finish the render in about 4.4 to 4.55 minutes, landing roughly equal to the stock 9700K. Despite increasing thread utilization, Premiere still likes higher frequencies. This much is proven by comparing the 2700 stock result of 5.2 minutes to the OC result, where we see a reduction of 13% versus baseline.

The R5 2600 at 4.2GHz does exceptionally well when considering its more budget-oriented positioning, although professionals who use Premiere every single day may still want to consider the higher-end options at the top of the chart.

Our 4K60 aroll+broll render was more intensive, clearly, as it’s dealing with a higher quality output. The 9900K OC finishes this render in 10.8 minutes, which is a render time reduction of 10% from baseline. The stack is almost exactly the same for these tests, except the 2700 stock and 8700K reshuffle, but they’re within error margins of each other in both tests. The difference between a 2700X and a 9900K, both stock, is that the 9900K finishes its render in 13% less time.

Above: Invalid testing found as a result of shifting workload to other components.

The chart render in particular seems to be a lighter workload, and we will be scrapping it moving forward. This is an illustrating of a workload that isn’t as heavily reliant upon the CPU, and we see CUDA kicking-in to help more frequently with our chart renders. That’d be what you’re seeing on the screen now. Because of how scattered these results are, especially with how unreliable the differences are, we must scrap it in the future.

V-Ray

Chaos Group’s V-Ray benchmark includes a GPU and a CPU test, but we use the command line interface and only run the CPU one. It takes between 1 and 2 minutes to complete on most of our CPUs, and the results align closely with the Cinebench and Blender render benchmarks, with the higher thread-count CPUs like the 2990WX and 9900K heavily advantaged, leaving the stock 8600K in dead last. Until we retest our HEDT Intel CPUs, the 9900K at 5.2GHz is Intel’s highest result on our chart. This one completes the workload in 0.95 minutes, allowing the 2990WX a time reduction of about 52%. This demonstrates that V-Ray actually leverages the threads available to it and, although the 9900K does well to keep up with an HEDT part, extra threads do win-out in this test. The 2700 at 4.2GHz outperforms an overclocked 9700K, demonstrating again the thread advantage, but is barely beaten by the 9900K stock CPU. Price is a factor, granted, and the 2700 comes in about $265 cheaper. The R5 2600 at 4.2GHz lands at 1.53 minutes, putting it within range of the 8700K stock CPU.

Conclusion

As stated earlier, this is more meant to debut our new workstation test cases. We have a big list of additional testing ideas, but for now, we’ll start with this benchmark assortment. Gaming benchmarks are next due for publication, with our target being before end of April. We should easily hit that target.

These tests better show the differences between core count and frequency scaling than previously, as we only ever really used Blender for workstation-class testing in the past. With the new additions, we can see where some software, like Adobe’s, benefits more from a high-end mainstream desktop CPU than from an HEDT CPU, whereas Blender or 7-Zip decompression workloads benefit heavily from higher core counts. GCC tests also give some insight into what programmers deal with, albeit from our Windows test environment.

We still have more to do, but we’re happy with this list for now. Keep an eye out for our revamped CPU gaming benchmarks as we continue to work on them.

Editorial, Test Lead: Steve Burke
Testing: Patrick Lathan
Video: Josh Svoboda

How to evaluate a gaming PC — performance test

Today we will tell you everything you need to know about testing your PC. This will include a brief explanation of what benchmarks are, the difference between gaming and synthetic benchmarks, what components you should be testing on your system, and our recommended tools for testing said components.

If you are here to learn how to test your computer , you are in the right place. By the time we’re done, you’ll know how to test and compare your system with other builds.

What is Benchmark

If you don’t know what a benchmark is, it’s ok, many people are not familiar with it. In the current context, benchmarks are used to evaluate and compare performance between your system and millions of other users.

To get test results, games (gaming tests) or specialized applications (synthetic tests) are usually run to extract performance metrics from them that allow individual components or entire systems to be compared to each other.

Computer Gaming Benchmark

Perhaps the most important score you’ll ever get is real gaming benchmark . You may have the best synthetic benchmarks in the world, but if something doesn’t work when the game is running, then what’s the point?

The gaming benchmark involves running a game in a given scenario, usually more than once, to determine the average level of performance in that game, on that hardware, with those particular settings. Some modern games even have benchmarks built in.

You’ll often see them in CPU and GPU reviews, as well as gaming PC reviews and even individual game reviews. You can also run them yourself, but that’s not the type of test we’ll cover in this article. Instead, we’re talking primarily about…

Synthetic benchmarks

Synthetic benchmarks are basically computer performance tests. Unlike gaming benchmarks, synthetic benchmarks are meant to be used as a standard benchmark, regardless of the hardware being used.

Game tests — depending on the specific version — may show the best on Nvidia or AMD cards. Synthetic benchmarks don’t show that kind of hardware dependency, instead they aim to establish a standard performance level that you can expect from your system.

Which computer components to compare

Processor (CPU) benchmark

First of all, you should compare your processor . After all, he is not simply called CPU .

While many games rely on the GPU, you still need to make sure your CPU is performing at its best before purchasing the latest games. In addition, CPU performance applies to the entire system, not just games or videos like the GPU does.

If we imagine a computer as a body, then the processor will be its brain, indispensable and more important than any other part.

Video card benchmark (GPU)

Next comes the GPU, which has the most impact on gaming performance…unless it’s bottlenecked by other components or the game is CPU bound instead of GPU bound.

The GPU will do most of the work in your games and many of your testing applications. If there are any instabilities or issues with your GPU, these tests should show them as well as give you an idea of ​​your build’s performance.

Full system benchmark

Last but not least, full system benchmark! It usually doesn’t make sense to run tests on individual components other than the CPU and GPU, so a full system test is used.

In any case, with the help of complete system tests, you can easily and accurately obtain data about your memory and drives. The only time it makes sense to run tests on individual components is if you are a reviewer or journalist, but this is not necessary for consumers.

How to prepare your computer for testing

It’s actually quite easy to run the benchmark application. You just install it, open it and run it.

However, there are a few things to do before testing the PC:

• Quit everything else, including non-essential background applications . If you want your results to be as accurate as possible, keeping your applications running will lower your scores, especially CPU scores.
• Set aside some time . Although most tests may take no more than a few minutes to complete, this time may increase by 10-30 minutes, depending on your system. Before starting the test, make sure you don’t need a computer within the next hour.
• Be patient . Don’t expect instant results and don’t stop testing if you want to see an accurate result. This may seem like an easy thing to do, but most people lack patience, so we remind you of it here.

Finally, it’s worth noting that all of these tests are compatible with Windows, including Windows 10 (and some are even compatible with Android and iOS devices). Excellent. Let’s start testing!

How to Test Your Computer’s CPU

Easy PC Benchmarking

Our first Easy PC Benchmarking tool from PassMark. It comes in a free 30-day trial (later costs $29). So it’s almost free if you only plan to run it once or twice!

It technically offers a full system test, but I recommend using it for a CPU performance test, which it does quite thoroughly. It also includes the ability to compare your performance to similar systems, «baselines» and more.

If you’re looking for some sort of free and reliable CPU benchmark, PassMark’s Easy PC Benchmarking is a pretty good choice. But far from the only one…

Geekbench

Geekbench is another great CPU benchmarking tool. While its premium version also offers CUDA and Metal Benchmark, the trial version offers a 64-bit benchmark right out of the box, which is exactly what you want from a CPU benchmark tool.

Because Geekbench is also multi-platform, you can even compare your PC scores to, say, the latest iPhone scores! It won’t really change anything, but it’s pretty neat!

CPU-Z

CPU-Z is primarily an application focused on getting accurate specifications and performance information about your CPU. It’s not really a «benchmark» app at all, but it can be used to determine if your processor is performing as expected and you can compare your results with those of others with the same processor.

If you want another free benchmark, but more up-to-date… we recommend Basemark. Base tests with support for Vulkan 1.0, Open GL 4.5 and OpenGL ES 3.1 and features with more graphical APIs. In addition to being available for desktop PCs, it is also available for smartphones, smart TVs, and even cars.

Due to its simplicity, «free» price and massive tester community, UserBenchmark is perhaps my favorite option for full system testing. While it may not be as precise or as strenuous as the GPU/CPU benchmarks, it is very good for estimating the approximate performance level of your system and its components.

Thanks to the large community of people who also use UserBenchmark, you will be able to see how your PC performs in comparison to similar or identical computers.

In addition to the convenience of benchmarking, sharing, and comparison, UserBenchmark can also be useful for diagnosing your system. For example, if one of your drives starts to run slower than regular drives of the same brand and model, UserBenchmark will detect this and let you know.

Novabench

Next is Novabench, another free solution for testing the entire system. This is another one of my favorites — although it doesn’t have as large a community as UserBenchmark, it still produces solid results and a very clean, easy to use user interface.

When you run the test, you’ll get a results screen and the ability to compare your PC with several others, including «base» PCs across various price ranges.

PCMark 10

Finally, PCMark 10, which is a premium product. Like 3DMark, PCMark usually sells for $30, but it offers a full system test for all your components. However, it doesn’t offer any features that the other listed products don’t, and many of its tests center around «performance.»

Frankly speaking, PCMark is probably more suitable for professional use than for consumer use.

Conclusion

Now you know how to compare your computer and its most important components . All of these testing apps are safe and easy to use. The only additional step is to purchase in cases where they are not free.

Benchmark of the 386th processor and the dashing nineties / Sudo Null IT News The video is not playing. Music in MP3 cannot, or can, but with such quality that you will not like it. Crysis will not run. But after I put together and ran a vintage system from almost 30 year old parts, I wondered: how exactly is he not capable? In what units is it expressed? And how to measure it?

It’s not easy with measurements if you try to compare an ancient computer with a modern one: if you can run old benchmarks on new PCs, the results will be strange. More modern software will not take off on an old computer. Today there will be a more or less boring technical post in which I compare the processing power of the 386 processor with a Pentium III laptop and an Intel Xeon X5690 desktop. Spoiler: productivity in the nineties grew much faster than in the zero.

All related articles:

0. 1992 in the computer press
1. We consider the motherboard of the 386th computer
2. Benchmark of the 386th processor and dashing nineties < — you are here
3. Difficult choice of sound card for DOS games
4. Features of Sound Blaster Pro 2
5. Roland MT-32, alternative sound for DOS games

I keep a diary of a collector of old pieces of iron in Telegram.

Actors

So, our main test subject is a computer based on the 80386DX processor with a frequency of 40 megahertz, 32 megabytes of RAM, an 80387 coprocessor and a flash drive instead of a hard drive. So far, this is not a computer, but a collection of boards installed on a box from under an old video card. We can conditionally attribute such a system to 1991-1992: in those days there were computers and more powerful ones, but such a 386th was quite a reasonable choice.

Let’s add a ThinkPad T22 laptop based on an Intel Pentium III processor with a frequency of 900 megahertz, 256 megabytes of memory and a hard drive of 80 gigabytes. Read more about this laptop here. It was released in 2001, about ten years after the 386th.

If so, it would be logical to rewind time another ten years ahead. For this, a moderately vintage desktop based on the Intel X58 chipset, assembled at the beginning of this year, with a Xeon X5690 processor (3.3 GHz nominal frequency, operating frequency 3.9) and 32 gigabytes of memory. Despite the impressive characteristics, this is a representative of the «still that» school of computer construction. You can natively connect a disk drive to it and boot into MS-DOS without dancing with a tambourine. The motherboard of this computer was released in 2009, but the processor went on sale in 2011.

DOS benchmarks

Benchmarks in their modern form, as separate programs for the comprehensive measurement of computer performance, did not appear immediately. For most of the 1980s, PC Magazine measured the most basic performance parameters: instruction execution, memory processing speed, and the like. Most often, the time of operations was measured, which presents a problem: on a modern PC, what used to take minutes is now completed in fractions of seconds.

One of the early universal benchmarks is the LandMark test, developed since 1981. Since the performance of the system already then depended not only on the frequency of the processor, but also, for example, on the presence of a coprocessor and the presence of a cache memory, the manufacturers advertised the results in LandMark. The calculation method was strange: the performance was compared with the IBM PC/AT reference system based on the 286th processor with a frequency of 6 megahertz. The result of the test for your computer is a certain theoretical value of the frequency of the 286th processor, at which it would be equal to the system under study. For example, my 386th processor works the same as the 286th would work at a frequency of 69.45 megahertz. A laptop on the Pentium III is like the 286th running at a frequency of 8695 megahertz. We run the test on Xeon and get a result counter overflow:

Such situations in the early era of personal computers development happened often: developers could not imagine that the processor frequency, computing power or memory size would reach such gigantic values. Or they just didn’t think: the Y2K problem has similar roots. By the way, the 386th motherboard is partially affected by it — after December 31, 19The year 99 comes on January 1, 1900. If you directly set the year, then everything works fine. And this is how the DOS version of SimCity 2000 responds to 32 megabytes of RAM:

In general, LandMark is suitable for comparing computers before 1993 with each other. It also performs calculations continuously, and thanks to it you can check if the processor frequency is lowered due to the Turbo button: in some systems, the corresponding contact on the motherboard must be closed, on others it must be open. But I had to look for something else. The Speedsys benchmark already mentioned in the previous article comes to the rescue:

It was developed before the mid-2000s, it recognizes processors of that era without any problems, and, most importantly, it works fine even on Xeon. The result for 386 (we are interested in the graph at the bottom left) is 7.07 points.

The result on a laptop with PIII-900 is 1039.51 points.

This benchmark can only be run natively on Xeon. In DosBox, and in a virtual machine with FreeDos, it did not work for me. A bootable flash drive with DOS helped. The result is 7540.05 points. In other words, from 1991 to 2001 productivity increased by 147 times, from 2001 to 2011 by 7. 2 times. Yes, but this test does not take into account that the Xeon has six processor cores. By the way, if you decide to repeat this strange experiment, I recommend disabling all power saving systems in the BIOS, otherwise you will get a scatter in the results.

I’d like to try some real applications, and games are the best. The first Doom was released in late 1993, and on 386 computers it had about the same effect as 2007 Crysis. I mean, you just had a decent, if not the newest, PC. But Doom comes out and you can’t play it. More precisely, you can, but the image will be the size of a postage stamp. Here it is important to accurately reproduce the testing parameters: graphics settings, image size, and the version of Doom itself.

At one time, the host of the YouTube channel Phil’s Computer Lab compiled a package of ancient benchmarks for DOS with a handy batch file. I ran Doom and other tests from its assembly. The package has two versions of the Doom benchmark — with minimum and maximum settings. The last option was almost never used in a real game, as it hides the game menu. But it’s good for tests. The benchmark writes the result in its own units, which must be converted to frames per second. The 386 showed 28.7 fps «at minimum» and 7.12 fps with maximum quality. Comparable to more modern PCs: 461 and 123 fps on the Pentium III, and completely frivolous 426 and 93 fps on Xeon X5690. «Dum» clearly does not like something in my most powerful system and it shows results lower than on the Pentium III.

A similar situation occurs in the Norton System Information 8.0 utility. The integrated processor benchmark shows 43.2 points on 386, 344.7 points on PIII and 960 points on Xeon. Processor development has slowed down over the past 15 years, but not by that much.

Windows 95 and SuperPi

Okay, running MS-DOS on a six-core machine is a perversion. What about programs written for 32-bit Windows? Theoretically, they can be run on all three systems. In practice, you need to carefully select software versions and benchmarks: developers have begun to abandon support for Win9x is already in the middle of the 2000s. Some software works fine on Windows 98, but I have a computer from 1991-1992, and Windows 95 is too much for it. We’ll put it on.

Windows 95, OSR2 edition, was released in 1996. On 386, it works not only slowly, but not fast either. It saves a huge (by the standards of those years) amount of RAM, but the retrocomputer draws even the standard Control Panel slowly. However, it has one advantage: unlike modern systems, Windows 95 slows down predictably . In any case, PCMark or any other complex benchmark will not run on this system. We need something very simple, dependent only on computing power. For example SuperPi.

On the Vogons forum, I found a version of the SuperPi benchmark that runs on both Windows 95, Windows 98, and Windows 10. Results for calculating one million decimal places of Pi:

• Xeon X5690: 10.531 seconds
• Pentium III 900: 3 minutes 3.786 seconds
• 80386 DX40: 16 hours 58 minutes 31.445 seconds

Hmm. This processor does not slow down, it maintains a balance of work and personal life. It turns out that the processor of 2001 calculates the number Pi 332 times faster than the 386th. The Xeon is 17.5 times faster than the Pentium III and 5800 times faster than the 386th processor. Good progress, you see.

WinRar and multithreading

The results in SuperPi give a similar performance boost compared to Speedsys. But they are not able to accurately evaluate all the capabilities of the six-core Intel Xeon, as they are strictly single-threaded. What benchmark can be run both on the old hardware and on the new one in several threads at the same time? Suggest options in the comments, but I found one — this is the WinRAR archiver. On Windows 95 and later PCs ran version 3.80 2008 without problems. Here are the results for Xeon in single threaded and multithreaded modes:

This is the result for Pentium III:

With the 386th processor it is more difficult. The built-in WinRar benchmark works like this: it continuously archives data, and after receiving a sufficient amount of statistics, it shows the result — the archiving speed in kilobytes per second. On a modern computer, the result is shown after processing approximately 25-30 megabytes of data. It took more than a day to reach this figure on the 386th processor!

At the end of the second day of the test, I gave up: WinRAR stubbornly did not show the result, but the screenshot above helps to accurately estimate the performance — about 214 bytes per second. This is 1210 times slower than the Pentium III. Xeon in single-threaded mode is about 4 times faster than the third Pentium. In multi-threaded mode, it is 15 times faster, although the difference between one thread and several threads slightly does not correspond to the number of cores — perhaps this is a limitation of the WinRAR code.

Pins

First, let’s go through the benchmark results. By definition, my measurements are inaccurate: I have a feeling that in the same WinRAR 386 system simply could not digest a large (for it) amount of data, and the processor was idle more often than it thought. However, three different benchmarks (Speedsys, SuperPi and WinRAR) have shown hundreds of times better performance between a 1991 and 2001 computer! The next ten years increased productivity by a maximum of tens of times. Again, this is not a fair comparison: old benchmarks may not use new instructions from fresh hardware.

Let’s look at an independent source. Here are the results of the universal Linpack computing power benchmark for systems starting from the 386th and up to the third generation Core i7 (moreover, with optimization for the architecture, using SSE and AVX instructions where possible). The difference between 386-40 (0.53 Mflops), Pentium III-1000 (316.67) and Core i7-3930K (3112.94) shows a similar alignment. An increase of almost 600 times in the nineties and only 10 times in the zero.

At the end of the last millennium, we saw an explosion in the performance of personal computers. In the new century, there was also growth, and significant, but there was no such crazy progress anymore. Moreover, in the eighties, from the very beginning of the era of PC-compatible PCs, development was also not so rapid — 8086 differs from 80386 (according to the results of the same Landmark test) by about 50 times, and not 500. This makes the nineties a unique phenomenon in the history of computers : We started with the Lexicon text editor and Norton Commander, and ended up with streaming audio over the network, 3D games and studio-quality video.

Despite the performance difference between a six-core Xeon and a 386 processor by a factor of a thousand, half of this article was typed without problems on the old system in Microsoft Word 6. 0. Some tasks do not require powerful modern systems at all, their performance is eaten up rather by “conveniences” (like synchronization with the cloud) and the approach to writing code. Two days of stress testing in WinRAR showed that my 386th system may not be the fastest, but stable and reliable. So, we will continue our research.

In the next article, I plan to explore 386 ancient sound cards. In the meantime, here’s another spoiler for another topic that will take me much longer to explore.

best mid-range desktop processor for gaming? —

AMD has released a new line of desktop processors based on the new Zen 3 architecture. One of the highlights of this series is AMD Ryzen 5 Processor ^{(AMD Ryzen 5)} 5600X, processor ^(CPU) , which promises top-notch performance for all workloads, especially gaming, all at a reasonable price. The new processor wants to deliver more performance per watt than ever, lower power consumption, and a feature set that cannot be beaten with similar Intel options. Read this review to see if the AMD Ryzen 5 5600X is a mid-range processor to buy:

AMD Ryzen 5 5600X: who is it for?

AMD Ryzen 5 5600X is the desktop processor you should buy next if you:

• Want to play any game, no matter how demanding
• Looking for a ^(Are) processor that can handle any workload at a reasonable price
• You need access to PCI-Express 4 and other new technologies

Pros and Cons of

Here are the best features of AMD Ryzen 5 5600X:

See price on:

buy now

• Its single-core performance is excellent, making it a great choice for gaming.

The

• ‘s multi-threaded performance is also outstanding, making it one of the best choices for productivity.
• The price that the AMD asks for is justified by the performance Ryzen 5 5600X.
• Acceleration frequency excellent
• This is an unlocked processor, so you can try to overclock it if you want.
• Supports PCI Express 4 and fast DDR4 memory.
• Its power consumption is low
• AMD is bundled with the Wraith Stealth cooler.
• The Intel ^(Intel) does not have a processor that can beat it at a similar price.

We don’t have any downsides to the AMD Ryzen 5 5600X to mention, except perhaps for a higher starting price compared to its predecessor in the Zen 2 family.

Verdict

The AMD Ryzen 5 5600X is one of the most balanced desktop processors we’ve tested. We’re blown away by what the AMD has been able to achieve and how significant the performance gains are from generation to generation. 9The 0008 ^(AMD) Ryzen 5 5600X is ahead of its big brother, the Ryzen 5 3600X, and its direct competitor from the Intel ( Core i5-10600K). The Ryzen 5 5600X is the best mid-range processor of 2020 and possibly 2021 in our opinion. It gets our highest rating and a warm buy recommendation for all gamers.

AMD Ryzen 5 5600X comes in a fairly large cardboard box. Its front side shows the company logo, brand Ryzen , and it is also indicated that in front of you is a ^{(Series Processor)} 5000 series processor.

AMD Ryzen 5 5600X: box

On one side of the box, you can see the processor through a cutout, and on the back you will find some information about it.