AMD Ryzen 9 7900X And 7950X CPU Review: Fantastic Zen 4 Performance Gains
When the Windows installation was complete, we installed all of the drivers necessary for our components, disabled Auto-Updating and Windows Defender, and installed all of our benchmarking software. When that process was done, we performed a disk clean-up, cleared any temp and prefetch data, processed idle tasks, and optimized all of the SSDs using Windows' built-in utility. Finally, we enabled Windows Focus Assist to minimize any potential interruptions and let the systems reach an idle state before invoking any tests.
HotHardware's Test Systems: Revamped For Windows 11
SiSoft SANDRA 2021 Benchmarks
We began our testing with the latest version of SiSoftware's SANDRA 2021, the System ANalyzer, Diagnostic and Reporting Assistant. We ran four of the built-in sub-system tests that partially comprise the suite with the new Ryzen 7000 series processors (CPU Arithmetic, Multimedia, Memory Bandwidth, and Cache and Memory Latency). All of the scores reported below were taken with the CPUs running at their default settings, with 32GB of DDR5 RAM running at an effective 5,200MHz, in dual-channel mode, on the Asus ROG Crosshair X670E Hero motherboard (with BIOS 604).
| AMD Ryzen 9 7950X Processor Arithmetic |
AMD Ryzen 9 7950X Multi-Media |
| AMD Ryzen 9 7950X Memory Bandwidth |
AMD Ryzen 9 7950X Cache & Memory |
| AMD Ryzen 9 7900X Processor Arithmetic |
AMD Ryzen 9 7900X Multi-Media |
| AMD Ryzen 9 7900X Memory Bandwidth |
AMD Ryzen 9 7900X Cache & Memory |
SANDRA's CPU Arithmetic test puts the Ryzen 9 7900X just north of 530GOp/s with the flagship 7950X topping 694GOp/s. The Multimedia test has the Ryzen 9 7900X and Ryzen 9 7950X finishing at 2.87Gpix/s and 3.65Gpix/s, respectively, with the higher-end 16-core chip pulling ahead. Aggregate memory bandwidth with the two processors hovers between 50GB/s - 54GB/s and memory latency, with the particular G.SKILL kit we used, is proximately 61ns.
AIDA64 Memory Bandwidth, Memory Latency & Cache Latency
AIDA64's CPU Cache and Memory benchmarks measure memory bandwidth during read, write and copy operations, in addition to memory latency, and cache bandwidth and latency.
In terms of memory bandwidth, the new Ryzen 7000 series processors, despite offering higher "official", non-overclocked DDR5-5200 memory support, put up somewhat lower bandwidth than Intel's 12th Gen Core processors, which fall within the 66GB/s - 75GB/s range, when paired to DDR5-4800 CL38 memory in dual channel mode (bandwidth with all platforms will be higher with faster memory). That puts memory bandwidth way above the previous-gen Ryzen 5000 mainstream platform, but behind the HEDT platforms that leverage quad channel memory configurations.
In contrast to the increased bandwidth afforded by DDR5's higher clocks, the higher CAS latency of current DDR5 memory kits results in significantly increased memory latency versus Ryzen 5000 processors, which use very mature DDR4 memory. Their higher memory frequency does, however, allow the Ryzen 7000 series to put up better memory latency results than Intel's 12th gen processors.
Cache latencies with the Ryzen 7000 series are a mixed bag. L1 and L3 cache latency is significantly improved over the 5000 series, but the L2 cache is slightly slower. Remember, the caches on the Ryzen 7000 series are bigger than their predecessors, which means more cache hits, so somewhat higher L2 latency may not hinder performance in the vast majority of circumstances.
In contrast to the increased bandwidth afforded by DDR5's higher clocks, the higher CAS latency of current DDR5 memory kits results in significantly increased memory latency versus Ryzen 5000 processors, which use very mature DDR4 memory. Their higher memory frequency does, however, allow the Ryzen 7000 series to put up better memory latency results than Intel's 12th gen processors.
Geekbench v5.4.1 CPU Compute Benchmark With Ryzen 7000
In the GeekBench tests, we're stressing only the CPU cores in a system (not the graphics card and GPU), with both single and multi-threaded workloads. The tests are comprised of encryption processing, image compression, HTML5 parsing, physics calculations and other general purpose compute processing workloads.
With our first compute benchmark, which is also impacted by Zen 4's support for AVX-512, the new Ryzen 7000 series comes out on top, besting every other platform we tested. The 16-core Ryzen 9 7950X and 12-core Ryzen 9- 7900X offer the best single-threaded and multi-threaded performance in the Geekbench tests, with both outpacing the 24-core Intel 12th Gen Core i9-12900K.
UL PCMark 10 Benchmarks
Next, up we have some full-system testing with PCMark. We're reporting all test results from the PCMark 10 benchmark suite, including the Essentials, Productivity, Digital Content Creation and and total PCMark score. The Essentials test covers workloads like web browsing, video conferencing and app start-up times, while Productivity tests everyday office apps from spreadsheets to word processing. Finally, the Digital Content Creation test evaluates performance of a machine with respect to photo and video editing, as well as rendering and visualization.
With the varied workloads that comprise the PCMark 10 suite, the new Ryzen 9 7950X and Ryzen 9- 7900X continue to top the charts. AMD's latest chips take the first and second positions, besting the Core i9-12900K across the board.
Bapco Crossmark Testing
Crossmark is a new cross-platform benchmark from Bapco that's available for Windows, Android, iOS and MacOS. Like PCMark, Crossmark measures overall system performance and using real-world applications. It characterizes system responsiveness as well, based on the results of its Creativity and Productivity benchmarks.
The Core i9-12900K takes the overall lead according to Crossmark, but the Ryzen 7000 is right there in the mix. In fact, the new Ryzen 9 7950X and Ryzen 9- 7900X offered the best Creativity scores of the bunch and it was really only the Responsiveness test where the Alder Lake-based 12th Gen processor had a clear advantage.
Browser & Web App Benchmarks: Jetstream 2 And Speedometer 2
Next up, we have some numbers from the Speedometer 2.0 and Jetstream 2 tests available at browserbench.org. The Speedometer Benchmark Suite uses a wide array of latency and throughput benchmarks to evaluate web application performance and Jetstream evaluates Javascript and WebAssembly performance; both tests take all of their individual results and tabulate them into a final score.
These benchmarks measures performance of an array of browser-based technologies used on modern, rich web applications. Scores in these benchmark are an indicator of the performance users would see when browsing the web and running advanced web apps. All of the systems were tested using the latest version of Microsoft's Edge browser, with default browser settings, on a clean, fully-updated install of Windows 11.
The browser-based Jetstream and Speedometer tests were hotly contested, with the new Ryzen 7000 series chips and Intel's top-end Core i9-12900K duking it out at the top of the charts. The fact is, all of these processors are plenty fast for web applications, but the fastest, latest-gen chips stand alone at the top.
These benchmarks measures performance of an array of browser-based technologies used on modern, rich web applications. Scores in these benchmark are an indicator of the performance users would see when browsing the web and running advanced web apps. All of the systems were tested using the latest version of Microsoft's Edge browser, with default browser settings, on a clean, fully-updated install of Windows 11.
7-Zip Data Decompression Tests
The 7-Zip benchmark measures compression and decompression performance using the LZMA method, which leverages the Lempel–Ziv–Markov chain algorithm to perform lossless data compression. The benchmark produces a final rating in GIPS (giga instructions per second).
AMD's 16-core Ryzen 9 7950X takes the pole position in 7-Zip's multi-threaded compression benchmark, besting the 16-core Ryzen 9 5950X by about 20%. Despite a 4-core deficit, the 12-core Ryzen 9- 7900X nearly catches the 5950X in the multi-threaded test, but its newer architecture and higher clocks just weren't enough. In the single-threaded tests, however, the new Ryzen 7000 series once again takes the lead, outgunning all of the other processors we tested.
AMD's 16-core Ryzen 9 7950X takes the pole position in 7-Zip's multi-threaded compression benchmark, besting the 16-core Ryzen 9 5950X by about 20%. Despite a 4-core deficit, the 12-core Ryzen 9- 7900X nearly catches the 5950X in the multi-threaded test, but its newer architecture and higher clocks just weren't enough. In the single-threaded tests, however, the new Ryzen 7000 series once again takes the lead, outgunning all of the other processors we tested.
