AMD's Ryzen 9 3950X lands today, bringing the ultimate threaded performance to the mainstream desktop with an industry-leading and unprecedented 16 cores and 32 threads, paired with the bandwidth-doubling PCIe 4.0 interface for $749. The CPU upsets Intel's positioning in mainstream desktops and disrupts it's vaunted high-end desktop (HEDT) lineup in the process.
Aside from the deep dive on the CPU that we're tackling here, we've also tested and reviewed they Ryzen 9 3950X in Alienware's redesigned Aurora R10 gaming desktop. That system trounced competing high-end gaming rigs in many productivity tests. But Dell did a questionable job on the cooling front, including a single intake fan and a small radiator with the AIO liquid cooler.
AMD's Ryzen family has completely redefined our expectations for desktop processors, and Intel has struggled to respond. The company has slowly dialed up the frequency of its aging 14nm process and added more cores, but those tweaks can't offset the reality that AMD has moved onto a denser and more efficient 7nm process that enables higher core counts. Of course, process technology doesn't solve all the challenges of fielding a competitive chip, but that advantage is hard to beat when paired with a solid microarchitecture like AMD's Zen 2.
A few months ago, AMD moved the industry again with the 12-core Ryzen 9 3900X but left us with the promise of something even more powerful: The Ryzen 9 3950X that completely upsets the paradigm with 16 cores and 32 threads, encroaching on both Intel's Skylake-X Refresh HEDT lineup and AMD's own Threadripper platform. To say this chip blurs the lines between the mainstream desktop and HEDT is an understatement: In reality, it brings HEDT-class performance to the friendlier pricing of mainstream motherboards, placing it in a class of its own.
Both companies will update their HEDT lineups later this month, with AMD plowing ahead to 32-core Threadripper 3000 chips (possibly 64 cores in the future), while Intel releases yet another iteration of its Skylake-derived 14nm silicon with its Cascade Lake-X lineup. But Intel's chips will still top out at 18 cores, only two more than AMD's 3950X, and require a pricey X299 platform that comes equipped with the PCIe 3.0 interface. Meanwhile, AMD leads the industry with PCIe 4.0.
From early indications, Intel's mainstream Comet Lake processors will arrive next year with a maximum of 10 cores, leaving AMD with the uncontested core count lead for quite some time.
Perhaps Intel tipped its hat on its perception of the 3950X and Threadripper 3000 chips when it slashed its Cascade Lake-X pricing in half before either of AMD's competing chips even came to market.
But while we await the Threadripper 3000 goodness, we have the beefiest chip to ever drop into a mainstream motherboard: The Ryzen 9 3950X that features nearly as many cores as Intel's HEDT flagship. Let's see how it stacks up.
Ryzen 9 3950X Specifications and Pricing
Ryzen's 7nm process offers density advantages that manifest as higher performance, better power efficiency, more cores, and more cache packed into a smaller area than the first-gen Ryzen models. Like the Ryzen 9 3900X, the 3950X comes packing AMD's Zen 2 microarchitecture spread across two small 7nm eight-core compute chiplets tied together with the Infinity Fabric interconnect via a larger 12nm I/O die (IOD).
Each small compute chiplet, referred to as a CCD (Core Chiplet Die), comes with eight physical cores. All told, the chip sports ~9.89 billion transistors, and they are all active: Unlike the 12-core 3900X, all 16 of the 3950X's hyper-threaded cores are enabled, forging a 16-core 32-thread beast that fits inside the confines of a chip that drops into the AM4 socket on mainstream motherboards.
The Ryzen 9 3950X comes with AMD's highest-binned silicon to enable a 4.7 GHz boost clock, but like other Ryzen 3000 processors, it comes with a mix of faster and slower cores.
AMD weathered plenty of criticism in the immediate aftermath of its Ryzen 3000 launch because not all of its chips could hit the rated boost clocks, but a series of BIOS fixes have mostly addressed those shortcomings. The Ryzen 9 3900X seems to suffer the most from the issues, leaving some users unable to hit its 4.6 GHz boost clock. The 3950X features a 100 MHz higher boost clock than the 3900X, so naturally there has been some speculation that it, too, will not satisfy its boost specfication. We put that to the test, which we'll cover on the next page. Spoiler alert: We had no issues reaching the rated 4.7 GHz (and slightly beyond), though it isn't a sustained boost like we see with Intel's chips.
Cooling comes into play, though. The 3950X comes with an AMD-defined 105W TDP just like the 3900X, but the four extra active cores require a more robust cooling solution. As a result, the 3950X doesn't come with a bundled cooler, a first for AMD's mainstream Ryzen chips in this generation. AMD recommends a beefy 280mm AIO cooler as the entry-level solution, but as you'll see, better cooling yields better performance.
As expected with a core-heavy chip, AMD pared back the base clock to 3.5 GHz, but the chip retains the same 64MB of L3 cache as the 3900X along with access to 24 lanes of the PCIe 4.0 interface. The PCIe 4.0 interface provides twice the potential throughput from speedy SSDs and networking additives than Intel's chips, which remain mired on PCIe 3.0. The faster interface doesn't improve gaming performance, so it isn't as important for mainstream chips as it is with the Ryzen 9 3950X. Plenty of semi-professionals and creators will adopt this platform due to its HEDT-like slant, and those users will appreciate the higher throughput for productivity applications.
Like AMD's other mainstream processors, the 3950X supports dual-channel DDR4-3200 memory, but there are caveats based upon DIMM type and population.
The 3950X's $749 price point places it in a tier above Intel's current mainstream halo part, the $488 Core i9-9900K. Intel also has its Special Edition -9900KS on offer, but that chip is only available for a limited time so it doesn't fit into the long-term view.
Instead, the Ryzen 9 3950X lines up against Intel's HEDT Core i9 models. However, the current-gen Skylake-X refresh products, like the Core i9-9920X and -9960X, aren't competitive at current pricing (though it does appear we will see price cuts on those models soon).
That means we have to turn to Intel's Cascade Lake-X processors, which land later this month, for relevant comparisons. Oddly, Intel has left open a core-count gap in its HEDT lineup, so it doesn't have a 16C/32T chip to compete directly with the 3950X. At least not yet.
Ryzen 9 3950X Motherboards
The 3950X drops into the standard AM4 socket on X570, X470, and B450 motherboards, though you should select one with robust power delivery accommodations to feed the 3950X. AMD has only validated the Ryzen 9 3950X with its new 1.0.0.4B AGESA code, which motherboard vendors are rolling out for existing motherboards (via a firmware update) over the course of this month. AMD strongly recommends that all Ryzen users to migrate to the new motherboard firmwares.
The new firmwares include many of the fixes we've seen for AMD's boost clock algorithms, along with even more refinements that include faster boot times. This new BIOS also unifies all the Ryzen models under the same codebase, so there won't be any more split support for some older models.
Contrary to rampant speculation and some claims from motherboard vendors, the 1.0.0.4B firmware doesn't appear to impart any magical performance gains on the existing line of Ryzen processors. We retested the Ryzen 9 3900X and 3700X with the new firmware at both stock and auto-overclocked settings, and all of the results you'll see today reflect those results. We did find some performance improvements with AMD's auto-overclocking Precision Boost Overdrive (PBO), but most of the benchmarks fell within range of previous BIOS revisions. We did notice the faster boot times, which are appreciated, but stock performance is roughly equivalent.
Ryzen 9 3950X Boost Frequency
In light of the controversy surrounding Ryzen 3000's ability to reach its rated boost clocks, we turned the same amount of attention to the Ryzen 9 3950X as we have in our series of other Ryzen 3000 boost clock tests.
AMD recommends a 280mm AIO watercooler as the minimum bar for entry for the Ryzen 9 3950X, and advises that beefier coolers can unlock more performance. For stock testing, we used the same Corsair H115i 280mm watercoolers that we use in the lab for testing chips that don't come with a bundled cooler. We also used a beefy custom watercooling loop with two 360mm radiators for overclocking testing.
You'll need to install the 1.0.0.4B BIOS (or newer) in tandem with AMD's chipset drivers to enable the UEFI CPPC2 interface, which allows the operating system to prioritize scheduling threads into the fastest cores of the processor first. The chipset drivers also automatically install the required AMD-designed power plans (we recommend AMD's Ryzen High Performance Power Profile for enthusiasts). You'll also need the Windows May 2019 Update (or later) to enable the topology-aware scheduling implementation. Also, be aware that silicon quality, your motherboard, and firmware all play a role in the efficacy of AMD's unique boosting implementation, so your results may vary.
With those prerequisites in place, we turned to our now-standard test for measuring boost clocks. We begin by recording the frequencies of each core during a series of commonly-used tests that should expose the peak frequencies. The first two tests are LAME and Cinebench in single-core test mode. These programs only execute on one core of the processor, which typically allows the chip to reach its peak boost frequency within its power, current, and thermal envelope. We also used tests with intermittent "bursty" workloads: PCMark 10, Geekbench, and VRMark run in rapid succession after the first two tests.
With 16 cores hammering away, the per-core frequency recordings create almost-unintelligible charts, so the album above only includes the maximum and minimum frequencies recorded during each 1-second measurement interval (100ms sampling). That means these measurements could come from any one core, but it makes the charts easier to digest. We've also plotted chip temperature on the right axis (the dark red line).
We reached 4.7 GHz frequently during our tests, though you'll notice these boost frequencies are exceedingly short in duration, while Intel's processors tend to reach their boost clock and stay there for longer periods of time (contingent upon BIOS settings).
We frequently reached 4.7 GHz with the Corsair H115i cooler, and even recorded a few bursts of 4.75 GHz. Better cooling yields much better results: At stock settings, we reached 4.75GHz much more frequently when we topped the chip with an EKWB waterblock connected to our custom loop, and overall boost activity was much more frequent. Finally, we enabled AMD's auto-overclocking PBO feature to measure peak clocks, and again reached 4.75 GHz regularly with the custom loop.
We also examined the output from our logging software and noticed that the boost activity occurred much more frequently in active cores. That's an improvement over what we've seen with past firmwares that incorrectly boosted inactive cores. This indicates that the UEFI CPP2 interface is working correctly to enable Windows 10's Ryzen topology-aware thread scheduling.
Temperatures peaked at 75C with the Corsair H115i's fans cranking away at full speed, but these workloads primarily consist of lightly-threaded activity with short bursts of multi-threaded activity.
Ryzen 9 3950X Overclocking
AMD's Ryzen 3000 processors have drastically improved single-threaded performance, but you'll lose that benefit if you manually overclock. That's simply because the chips can't be manually overclocked on all cores to reach the same frequency as the single-core boost frequency. In fact, we often find the all-core overclock ceiling to be 200 to 300 MHz lower than the rated boost speeds, which is likely due to AMD’s new binning strategy that finds the Ryzen 3000 chips with a mix of both faster and slower cores.
As we've seen with other Ryzen processors, we couldn't maintain an all-core overclock beyond 4.3 GHz, which is well short of the 3950X's 4.7 GHz boost clock. As such, an all-core overclock has the predictable result of boosting performance in some heavily-threaded workloads, but the reduction in performance in lightly-threaded applications isn't worth the trade-off.
We had relatively little time during the NDA window to manually overclock the 3950X, so it's possible further tuning could expose larger gains. The overclocked 3950X's thermal output easily overwhelmed our 280mm AIO, so plan for a beefy watercooling solution if you plan on overclocking.
We turned to AMD's auto-overclocking Precision Boost Overdrive feature for our battery of tests. This auto-overclocking algorithm preserves the benefits of the single core boost, as seen in our boost testing above, while speeding up threaded workloads. We did pair our PBO-enabled configuration with our custom watercooling loop, enabling the utmost performance possible with our available cooling solutions. However, PBO performance will vary based upon your cooling solution, motherboard, and firmware.
Ryzen 9 3950X Power Consumption
It's important to remember that TDP isn't a one-to-one measure of power consumption. In the simplest terms, this rating quantifies the required performance of the CPU cooler based upon the chips' thermal dissipation – not power consumption. That means we won't see the Ryzen 9 3950X operate at 105W of power consumption.
Power consumption measurements are always a bit tricky. But as long as your 12V supply (EPS) readings, motherboard power supply sensor values, and voltage transformer losses plausibly coincide, everything is fine. Therefore, we're using pure package power to avoid possible influences from our motherboard. Results from the PWM controller are very reliable if you take them as averages over a few minutes
We measured great power consumption from the Ryzen 9 3950X during our synthetic AIDA64 stress tests with non-AVX and AVX workloads, however, the synthetic power tests could be a bit misleading. Here we see that the stock 3950X consumes the same amount of power as the Ryzen 9 3900X, which has four fewer active cores, in both tests. The overclocked 3950X also consumes less power than the overclocked 3900X, which doesn't make sense given its higher allotment of cores. While comparing notes with Ian Cutress at AnandTech, he noted that the 3950X draws less power when more cores are active than it does when lightly loaded. For instance, he measured peak power with 10 cores loaded, but a significant drop in overall power consumption as more cores came under load.
This is obviously a clever implementation by AMD to mitigate the thermal and power density issues associated with cramming 16 cores into such a small package, but it does mean that we'll have to chart out per-core power draw for a better view of synthetic power load. We'll update the article as necessary.
This type of power distribution is best measured by using a sustained workload with quantifiable performance metrics, such as our standard y-cruncher and Handbrake x264 and x265 tests, the latter of which has a heavier distribution of densely-packed AVX instructions. The y-cruncher tests show that while the 3900X draws more power during the test, it actually provides slightly better performance.
AVX instructions need copious data throughput, and the extra cores on the 3950X might incur a slight penalty from contention on the Infinity Fabric. The 3950X's 16 cores also have access to roughly the same aggregate memory bandwidth as the 12-core Ryzen 9 3900X, which means it has reduced memory throughput per core. That can manifest as reduced scaling in some workloads. You'll notice the overclocked Threadripper 2950X isn't present in the y-cruncher chart, but that's because the system repeatedly crashed during this single benchmark, indicating that either the motherboard firmware or AMD's PBO algorithms could use some additional work.
We see much the same trends emerge with our Handbrake tests, with the Ryzen 9 3900X consuming a similar amount, or slightly more, power than the Ryzen 9 3950X. However, these workloads tend to spread across the cores but not fully saturate them, which likely allows the 3950X to benefit from operating lower on the voltage/frequency curve, much like we observed with the Ryzen 9 3900, but still benefit from the parallelism of having more active cores. That equates to lower power consumption than the 3900X during the task even though the 3950X handily wins both benchmarks. Overall, the 3950X is incredibly power efficient.
Test Notes
All Ryzen entries with "PBO" indicate an auto-overclocked configuration with memory configured to DDR4-3600. Intel's overclocked configurations also use DDR4-3600. Except where noted, we tested the Ryzen Threadripper 2990WX and 2950X in game mode for all gaming tests, and in Creator mode for application tests.
VRMark and 3DMark
The 3DMark DX12 and DX11 tests measure the amount of raw horsepower exposed by the processor to game engines, but most game engines don't scale as linearly with additional compute resources.
As expected, the Ryzen 9 3950X is exceedingly powerful when the game engine can take advantage of its 16 cores and 32 threads, and paired with its solid per-core performance, it even outperforms the stock Core i9-9980XE, although that processor flips the tables after overclocking. The Core i9-9900K can't compete here due to its eight cores. We ran the Threadripper processors in Creator Mode for these tests, but the extra cores don't equate to extra performance due to the memory architecture.
VRMark responds well to high clock rates, giving the Intel processors a big advantage in this test.
Civilization VI AI and Stockfish
The Civilization VI AI test measures AI performance in a turn-based strategy game and is heavily influenced by high clock rates and instruction per cycle (IPC) throughput.
The top of these charts used to be Intel-only territory, but AMD has made amazing gains in per-core performance (a mixture of IPC and frequency) with the Zen 2 microarchitecture. The stock Ryzen 9 3950X beats the other Ryzen models while trailing the Intel Core i9-9900K, but overclocking propels it near the top of the chart. The result reflects that the Ryzen 9 3950X is boosting well and that the game engines' execution threads are correctly steered to the faster cores. Meanwhile, the stock -9980XE trails, but tuning pushes it up the chart.
The open-source Stockfish chess engine is the polar opposite of the Civilization VI engine. This engine is designed specifically for many-core chips and scales well up to 512 cores. The Ryzen 9 3950X shows its agility and matches the stock -9980XE step for step, but Intel's overclocking advantage hands the -9980XE the lead. As expected, the 32-core 64-thread Threadripper 2990WX takes the top of the chart, but you'll notice the Threadripper 2950X in Creator Mode falls far behind the 3950X.
Ashes of the Singularity: Escalation
Ashes of the Singularity: Escalation responds well to extra cores and threads, which benefits the Ryzen lineup. The Ryzen 9 3950X leads the AMD pack, but the Ryzen 7 3700X is plenty impressive after overclocking. The -9980XE is impressive in stock and overclocked trim. As you can see at the bottom of the chart, the second-gen Threadripper chips aren't the best solution for gaming due to the eccentricities of their multi-die design. We expect that to change radically with the arrival of the Threadripper 3000 chips and their EPYC Rome-based architecture.
Civilization VI Graphics Test
The Civilization VI graphics test finds the stock Ryzen 9 3950X delivering excellent performance. In fact, it actually outpaces the auto-overclocked 3950X configuration. We've become accustomed to these inversions with AMD's PBO feature, but they usually occur in our application testing. We ran this test several times to confirm the result.
In either case, the Ryzen 9 3950X beats the stock Intel processors handily in this benchmark, which is quite the feat.
Dawn of War III
The Core i9-9900K and -9700K take their traditional spots at the top of the Dawn of War III pecking order, a byproduct of their clock speed advantage. The Ryzen 9 3950X and Core i9-9980XE land within range of each other on the lower portion of the chart, but that still represents a big improvement over the Threadripper models.
Ryzen 7 3700X is very competitive with the much higher-priced models, reminding us that the majority of gamers are well-served by more modest accommodations.
Far Cry 5
Intel's mainstream chips convincingly lead the pack. The divide between the Core i9-9980XE at stock and overclocked settings is massive, highlighting the advantage of dialing up its clock speed. Intel plans to bring overclocked-like performance at stock settings with its Cascade Lake-X chips, which will certainly make the competition with the Ryzen 9 3950X more interesting.
Final Fantasy XV
We run this test with the standard quality preset to sidestep the impact of a bug that causes the game engine to render off-screen objects with the higher-resolution setting.
The Ryzen 9 3950X is competitive with Intel's stock Core i9-9900K and i7-9700K, but the -9980XE separates itself from the rest of the test pool.
Grand Theft Auto V
Grand Theft Auto V continues to be popular six long years after its release. This title favors Intel architectures and, more generally, multi-core designs with high clock rates. Intel's overclocked Core i9-9900K and Core i7-9700K push us to a graphics bottleneck in this test, but the middle of the test pool is very competitive with slight deltas separating the various models.
Hitman 2
The 3950X matches the stock Core i9-9900K and -9980XE step for step in this benchmark, but overclocking Intel's processors bottlenecks the graphics card.
Project Cars 2
Project Cars 2 is optimized for threading, but high clock rates pay off. That naturally results in a win for the Intel -9900K and -9700K processors.
The Core i9-9980XE shines in some benchmarks, but like the Threadripper chips, it has a unique architecture that can result in reduced performance with some existing software. Intel's mesh architecture is designed to increase scalability, much like AMD's Infinity Fabric, thus yielding higher core-count chips. But here we see the impact of the design.
World of Tanks enCore
World of Tanks finds another odd inversion with the auto-overclocked 3950X lagging behind the stock configuration. The delta between the two configurations weighs in at 2.4 fps, but it's repeatable.
Rendering
If ever there were a perfect use case for a copious number of cores and threads, rendering is it. The Ryzen 9 3950X is a great fit for applications hungry for parallelism. It takes a lot of firepower to outperform the Ryzen 9 3950X in the multi-threaded Cinebench test: only the 32-core Threadripper 2990WX and the heavily-overclocked Core i9-9980XE can pull off the feat. Surprisingly, the Ryzen 9 3950X also takes the crown in the single-threaded Cinebench test.
LuxMark, POV-Ray, and Blender exhibit much the same trend: Only the heftiest chips can challenge the 3950X, and the Intel Core i9-9980XE needs a significant boost via overclocking to join the 3950X at the top of the chart. Conversly, Corona and v-ray are a bright spot for the stock -9980XE as it wrests the lead from the 3950X.
In case you've forgotten, the Core i9-9980XE currently retails for ~$2,000, while the Ryzen 9 3950X weighs in at only $749. That's quite the value considering its solid performance.
The 3950X is also impressive in the highly-threaded NAMD benchmark, but the Threadripper 2990WX faced issues running the Windows version of the benchmark. We're troubleshooting that issue, but considering the results we've seen with Linux NAMD testing, the 2990WX should lead this chart easily.
Taken in context, it's incredibly impressive to see the 16-core 3950X outweighing the 32-core 2990WX in many of these rendering tests. Those wins really highlight the massive gains that AMD has made with the new architecture, which assures equal memory access to all cores. That corrects the problem faced by the current Threadripper lineup, which consists of two die (of four) that don't have direct access to memory controllers. Threadripper 3000, which debuts later this month, features the same Zen 2 architecture (albeit with modifications), which bodes well for the type of performance we can expect.
Encoding
The 3950X is also competitive in the lightly-threaded FLAC audio encoding test but trails the Intel -9900K and -9700K in the single-threaded LAME benchmark.
The Ryzen 9 3950X is much more impressive in the HandBrake x264 test, where it outperforms the rest of the test pool, and in the AVX-heavy x265 version of that same benchmark, where it only trails the overclocked 18-core -9980XE. Yet again, the Threadripper 2990WX shows its bipolar nature as it lags in this test due to its reduced memory throughput, but the Threadripper 2950X is more competitive. However, it isn't as fast as the 3950X.
Compression, Decompression, Encryption, AVX
The 7zip and Zlib compression/decompression benchmarks rely heavily upon threading and work directly from system memory, thus avoiding the traditional storage bottleneck in these types of tasks. Ryzen dominates these tests without storage throughput restrictions, but you also have access to the PCIe 4.0 interface with AMD's X570 platform. That extra throughput means these tremendous gains will largely transfer over to real-world application performance when you pair the Ryzen chips with a speedy PCIe 4.0 SSD.
It's impossible to beat the Threadripper 2900WX in decompression performance with today's desktop processors, but the Ryzen 9 3950X comes close with surprisingly strong performance. However, as impressive as the 2990WX is, it inexplicably suffers in some workloads, like compression. Meanwhile, the Ryzen 9 3950X offers a more balanced profile that is competitive in both types of workloads.
The heavily-threaded y-cruncher benchmark, which computes pi using the demanding AVX instruction set, finds the Ryzen 9 3950X in the middle of the pack as it falls behind the other Threadripper models and the Core i9-9980XE in the threaded tests. The 3950X trails even its 12-core sibling, the Ryzen 9 3900X, in the single-threaded y-cruncher benchmark. This is likely due to less available memory throughput on a per-core basis.
Office and Productivity
Microsoft's office suite runs via PCMark 10's new application test. This benchmark tests with real Microsoft Office applications. The 3950X takes third in the overall score, but much of that comes on the strength of its performance in Excel. The 3950X is competitive in the remainder of the Office suite, but the Intel chips are more agile at these types of applications.
The application start-up metric measures load time snappiness in word processors, GIMP, and Web browsers. Other platform-level considerations affect this test as well, including the storage subsystem. The Ryzen 9 3950X is very competitive in this benchmark, rivaling the -9900K in a test that it traditionally dominates. Adding a PCIe 4.0 SSD to our Ryzen test system would swing this benchmark in favor of the Ryzen 3000-series processors.
The 3950X is in rarefied air in the LLVM compilation benchmark as it trades blows with the Threadripper 2990WX and Core i9-9980XE. We see muted gains from overclocking in the heavily-threaded LLVM compile benchmark.
Web Browser
Browsers tend to be impacted more by the recent security mitigations than other types of applications, so Intel has generally taken a haircut in these benchmarks of fully-patched systems, though that handicap doesn't stop the company from sweeping the AMD competition. These tests are extremely sensitive to clock rates due to their lightly-threaded nature, and the 3950X falls behind itself after overclocking. That indicates that PBO can have an impact on lightly-threaded work.
A New Class of Performance
High end desktop processors have long offered the ultimate in performance, as long as you were willing to pay the price. Aside from high MSRPs, the chips also require expensive accommodations, like beefy motherboards and the added cost of fully populating quad-channel memory controllers. Add in the inevitable trade-offs, like reduced performance in lightly-threaded applications and games, and most regular users who could use the threaded horsepower of a HEDT chip just settle for mainstream offerings.
Now AMD's Ryzen 9 3950X brings HEDT-class performance to mainstream motherboards, lowering the bar for entry. The 3950X carries a $749 price tag, but that is downright affordable compared to competing HEDT processors.
Intel's current lineup of Skylake-X Refresh chips are hideously overpriced by comparison, but AMD's pressure has brought about some change: Intel's forthcoming Cascade Lake-X chips cost roughly half the price of the previous-gen models, yet the 18C/36T Core i9-10980XE still slots in at nearly $200 more than the 3950X. You'll also need to spring for an X299 motherboard, while the 3950X drops into X570, X470, and B450 motherboards, though the latter might not be a good choice to feed enough current to this beast.
As a general rule, we don't recommend HEDT processors for enthusiasts that are only interested in gaming, they're best served by mainstream processors that are often faster in games, and the Ryzen 9 3950X also falls into the same category. However, if you're after a platform that can do serious work, but still be nimble enough for some entertainment afterward, the Ryzen 9 3950X fits the bill.
Below we plot the geometric mean of our gaming test suite in both average fps and 99th percentile values, the latter of which is a good indicator of the overall smoothness of your gaming experience.
The Ryzen 9 3950X provides more than acceptable performance for 1080p gaming, as a whole, and it is very competitive with Intel's chips. These deltas will shrink tremendously when paired with high-resolution gaming. Given the target audience, that class of gaming is almost a given.
We see the same performance trend throughout our suite of application tests: Unlike some Threadripper processors, there were no significant performance outliers in lightly-threaded apps that were worthy of alarm. Turn to heavily-threaded applications, like rendering and professional applications, and the Ryzen 9 3950X often outstripped those same Threadripper processors, not to mention Intel's flagship Core i9-9980XE.
AMD says that it fully expects the Ryzen 9 3950X to be competitive with Intel's new -10980XE, but Intel also has its 14C/28T -10940X at $784, which aligns neatly with the 3950X's pricing. We're sure that you'll see reviews of both of those competing products shortly.
But we don't think those chips will change the landscape much, the Ryzen 9 3950X just has too much to offer at a much lower overall cost. A capable X570 motherboard doesn't come cheap, but you gain access to the PCIe 4.0 interface as a nice bonus. Budget in a beefy cooler to assure enthusiast-class performance from your chip, and AMD's Ryzen 9 3950X is truly in a class of its own.
Aside from the deep dive on the CPU that we're tackling here, we've also tested and reviewed they Ryzen 9 3950X in Alienware's redesigned Aurora R10 gaming desktop. That system trounced competing high-end gaming rigs in many productivity tests. But Dell did a questionable job on the cooling front, including a single intake fan and a small radiator with the AIO liquid cooler.
AMD's Ryzen family has completely redefined our expectations for desktop processors, and Intel has struggled to respond. The company has slowly dialed up the frequency of its aging 14nm process and added more cores, but those tweaks can't offset the reality that AMD has moved onto a denser and more efficient 7nm process that enables higher core counts. Of course, process technology doesn't solve all the challenges of fielding a competitive chip, but that advantage is hard to beat when paired with a solid microarchitecture like AMD's Zen 2.
A few months ago, AMD moved the industry again with the 12-core Ryzen 9 3900X but left us with the promise of something even more powerful: The Ryzen 9 3950X that completely upsets the paradigm with 16 cores and 32 threads, encroaching on both Intel's Skylake-X Refresh HEDT lineup and AMD's own Threadripper platform. To say this chip blurs the lines between the mainstream desktop and HEDT is an understatement: In reality, it brings HEDT-class performance to the friendlier pricing of mainstream motherboards, placing it in a class of its own.
Both companies will update their HEDT lineups later this month, with AMD plowing ahead to 32-core Threadripper 3000 chips (possibly 64 cores in the future), while Intel releases yet another iteration of its Skylake-derived 14nm silicon with its Cascade Lake-X lineup. But Intel's chips will still top out at 18 cores, only two more than AMD's 3950X, and require a pricey X299 platform that comes equipped with the PCIe 3.0 interface. Meanwhile, AMD leads the industry with PCIe 4.0.
From early indications, Intel's mainstream Comet Lake processors will arrive next year with a maximum of 10 cores, leaving AMD with the uncontested core count lead for quite some time.
Perhaps Intel tipped its hat on its perception of the 3950X and Threadripper 3000 chips when it slashed its Cascade Lake-X pricing in half before either of AMD's competing chips even came to market.
But while we await the Threadripper 3000 goodness, we have the beefiest chip to ever drop into a mainstream motherboard: The Ryzen 9 3950X that features nearly as many cores as Intel's HEDT flagship. Let's see how it stacks up.
Ryzen 9 3950X Specifications and Pricing
Ryzen's 7nm process offers density advantages that manifest as higher performance, better power efficiency, more cores, and more cache packed into a smaller area than the first-gen Ryzen models. Like the Ryzen 9 3900X, the 3950X comes packing AMD's Zen 2 microarchitecture spread across two small 7nm eight-core compute chiplets tied together with the Infinity Fabric interconnect via a larger 12nm I/O die (IOD).
Each small compute chiplet, referred to as a CCD (Core Chiplet Die), comes with eight physical cores. All told, the chip sports ~9.89 billion transistors, and they are all active: Unlike the 12-core 3900X, all 16 of the 3950X's hyper-threaded cores are enabled, forging a 16-core 32-thread beast that fits inside the confines of a chip that drops into the AM4 socket on mainstream motherboards.
The Ryzen 9 3950X comes with AMD's highest-binned silicon to enable a 4.7 GHz boost clock, but like other Ryzen 3000 processors, it comes with a mix of faster and slower cores.
AMD weathered plenty of criticism in the immediate aftermath of its Ryzen 3000 launch because not all of its chips could hit the rated boost clocks, but a series of BIOS fixes have mostly addressed those shortcomings. The Ryzen 9 3900X seems to suffer the most from the issues, leaving some users unable to hit its 4.6 GHz boost clock. The 3950X features a 100 MHz higher boost clock than the 3900X, so naturally there has been some speculation that it, too, will not satisfy its boost specfication. We put that to the test, which we'll cover on the next page. Spoiler alert: We had no issues reaching the rated 4.7 GHz (and slightly beyond), though it isn't a sustained boost like we see with Intel's chips.
Cooling comes into play, though. The 3950X comes with an AMD-defined 105W TDP just like the 3900X, but the four extra active cores require a more robust cooling solution. As a result, the 3950X doesn't come with a bundled cooler, a first for AMD's mainstream Ryzen chips in this generation. AMD recommends a beefy 280mm AIO cooler as the entry-level solution, but as you'll see, better cooling yields better performance.
As expected with a core-heavy chip, AMD pared back the base clock to 3.5 GHz, but the chip retains the same 64MB of L3 cache as the 3900X along with access to 24 lanes of the PCIe 4.0 interface. The PCIe 4.0 interface provides twice the potential throughput from speedy SSDs and networking additives than Intel's chips, which remain mired on PCIe 3.0. The faster interface doesn't improve gaming performance, so it isn't as important for mainstream chips as it is with the Ryzen 9 3950X. Plenty of semi-professionals and creators will adopt this platform due to its HEDT-like slant, and those users will appreciate the higher throughput for productivity applications.
Like AMD's other mainstream processors, the 3950X supports dual-channel DDR4-3200 memory, but there are caveats based upon DIMM type and population.
The 3950X's $749 price point places it in a tier above Intel's current mainstream halo part, the $488 Core i9-9900K. Intel also has its Special Edition -9900KS on offer, but that chip is only available for a limited time so it doesn't fit into the long-term view.
Instead, the Ryzen 9 3950X lines up against Intel's HEDT Core i9 models. However, the current-gen Skylake-X refresh products, like the Core i9-9920X and -9960X, aren't competitive at current pricing (though it does appear we will see price cuts on those models soon).
That means we have to turn to Intel's Cascade Lake-X processors, which land later this month, for relevant comparisons. Oddly, Intel has left open a core-count gap in its HEDT lineup, so it doesn't have a 16C/32T chip to compete directly with the 3950X. At least not yet.
Ryzen 9 3950X Motherboards
The 3950X drops into the standard AM4 socket on X570, X470, and B450 motherboards, though you should select one with robust power delivery accommodations to feed the 3950X. AMD has only validated the Ryzen 9 3950X with its new 1.0.0.4B AGESA code, which motherboard vendors are rolling out for existing motherboards (via a firmware update) over the course of this month. AMD strongly recommends that all Ryzen users to migrate to the new motherboard firmwares.
The new firmwares include many of the fixes we've seen for AMD's boost clock algorithms, along with even more refinements that include faster boot times. This new BIOS also unifies all the Ryzen models under the same codebase, so there won't be any more split support for some older models.
Contrary to rampant speculation and some claims from motherboard vendors, the 1.0.0.4B firmware doesn't appear to impart any magical performance gains on the existing line of Ryzen processors. We retested the Ryzen 9 3900X and 3700X with the new firmware at both stock and auto-overclocked settings, and all of the results you'll see today reflect those results. We did find some performance improvements with AMD's auto-overclocking Precision Boost Overdrive (PBO), but most of the benchmarks fell within range of previous BIOS revisions. We did notice the faster boot times, which are appreciated, but stock performance is roughly equivalent.
Ryzen 9 3950X Boost Frequency
In light of the controversy surrounding Ryzen 3000's ability to reach its rated boost clocks, we turned the same amount of attention to the Ryzen 9 3950X as we have in our series of other Ryzen 3000 boost clock tests.
AMD recommends a 280mm AIO watercooler as the minimum bar for entry for the Ryzen 9 3950X, and advises that beefier coolers can unlock more performance. For stock testing, we used the same Corsair H115i 280mm watercoolers that we use in the lab for testing chips that don't come with a bundled cooler. We also used a beefy custom watercooling loop with two 360mm radiators for overclocking testing.
You'll need to install the 1.0.0.4B BIOS (or newer) in tandem with AMD's chipset drivers to enable the UEFI CPPC2 interface, which allows the operating system to prioritize scheduling threads into the fastest cores of the processor first. The chipset drivers also automatically install the required AMD-designed power plans (we recommend AMD's Ryzen High Performance Power Profile for enthusiasts). You'll also need the Windows May 2019 Update (or later) to enable the topology-aware scheduling implementation. Also, be aware that silicon quality, your motherboard, and firmware all play a role in the efficacy of AMD's unique boosting implementation, so your results may vary.
With those prerequisites in place, we turned to our now-standard test for measuring boost clocks. We begin by recording the frequencies of each core during a series of commonly-used tests that should expose the peak frequencies. The first two tests are LAME and Cinebench in single-core test mode. These programs only execute on one core of the processor, which typically allows the chip to reach its peak boost frequency within its power, current, and thermal envelope. We also used tests with intermittent "bursty" workloads: PCMark 10, Geekbench, and VRMark run in rapid succession after the first two tests.
With 16 cores hammering away, the per-core frequency recordings create almost-unintelligible charts, so the album above only includes the maximum and minimum frequencies recorded during each 1-second measurement interval (100ms sampling). That means these measurements could come from any one core, but it makes the charts easier to digest. We've also plotted chip temperature on the right axis (the dark red line).
We reached 4.7 GHz frequently during our tests, though you'll notice these boost frequencies are exceedingly short in duration, while Intel's processors tend to reach their boost clock and stay there for longer periods of time (contingent upon BIOS settings).
We frequently reached 4.7 GHz with the Corsair H115i cooler, and even recorded a few bursts of 4.75 GHz. Better cooling yields much better results: At stock settings, we reached 4.75GHz much more frequently when we topped the chip with an EKWB waterblock connected to our custom loop, and overall boost activity was much more frequent. Finally, we enabled AMD's auto-overclocking PBO feature to measure peak clocks, and again reached 4.75 GHz regularly with the custom loop.
We also examined the output from our logging software and noticed that the boost activity occurred much more frequently in active cores. That's an improvement over what we've seen with past firmwares that incorrectly boosted inactive cores. This indicates that the UEFI CPP2 interface is working correctly to enable Windows 10's Ryzen topology-aware thread scheduling.
Temperatures peaked at 75C with the Corsair H115i's fans cranking away at full speed, but these workloads primarily consist of lightly-threaded activity with short bursts of multi-threaded activity.
Ryzen 9 3950X Overclocking
AMD's Ryzen 3000 processors have drastically improved single-threaded performance, but you'll lose that benefit if you manually overclock. That's simply because the chips can't be manually overclocked on all cores to reach the same frequency as the single-core boost frequency. In fact, we often find the all-core overclock ceiling to be 200 to 300 MHz lower than the rated boost speeds, which is likely due to AMD’s new binning strategy that finds the Ryzen 3000 chips with a mix of both faster and slower cores.
As we've seen with other Ryzen processors, we couldn't maintain an all-core overclock beyond 4.3 GHz, which is well short of the 3950X's 4.7 GHz boost clock. As such, an all-core overclock has the predictable result of boosting performance in some heavily-threaded workloads, but the reduction in performance in lightly-threaded applications isn't worth the trade-off.
We had relatively little time during the NDA window to manually overclock the 3950X, so it's possible further tuning could expose larger gains. The overclocked 3950X's thermal output easily overwhelmed our 280mm AIO, so plan for a beefy watercooling solution if you plan on overclocking.
We turned to AMD's auto-overclocking Precision Boost Overdrive feature for our battery of tests. This auto-overclocking algorithm preserves the benefits of the single core boost, as seen in our boost testing above, while speeding up threaded workloads. We did pair our PBO-enabled configuration with our custom watercooling loop, enabling the utmost performance possible with our available cooling solutions. However, PBO performance will vary based upon your cooling solution, motherboard, and firmware.
Ryzen 9 3950X Power Consumption
It's important to remember that TDP isn't a one-to-one measure of power consumption. In the simplest terms, this rating quantifies the required performance of the CPU cooler based upon the chips' thermal dissipation – not power consumption. That means we won't see the Ryzen 9 3950X operate at 105W of power consumption.
Power consumption measurements are always a bit tricky. But as long as your 12V supply (EPS) readings, motherboard power supply sensor values, and voltage transformer losses plausibly coincide, everything is fine. Therefore, we're using pure package power to avoid possible influences from our motherboard. Results from the PWM controller are very reliable if you take them as averages over a few minutes
We measured great power consumption from the Ryzen 9 3950X during our synthetic AIDA64 stress tests with non-AVX and AVX workloads, however, the synthetic power tests could be a bit misleading. Here we see that the stock 3950X consumes the same amount of power as the Ryzen 9 3900X, which has four fewer active cores, in both tests. The overclocked 3950X also consumes less power than the overclocked 3900X, which doesn't make sense given its higher allotment of cores. While comparing notes with Ian Cutress at AnandTech, he noted that the 3950X draws less power when more cores are active than it does when lightly loaded. For instance, he measured peak power with 10 cores loaded, but a significant drop in overall power consumption as more cores came under load.
This is obviously a clever implementation by AMD to mitigate the thermal and power density issues associated with cramming 16 cores into such a small package, but it does mean that we'll have to chart out per-core power draw for a better view of synthetic power load. We'll update the article as necessary.
This type of power distribution is best measured by using a sustained workload with quantifiable performance metrics, such as our standard y-cruncher and Handbrake x264 and x265 tests, the latter of which has a heavier distribution of densely-packed AVX instructions. The y-cruncher tests show that while the 3900X draws more power during the test, it actually provides slightly better performance.
AVX instructions need copious data throughput, and the extra cores on the 3950X might incur a slight penalty from contention on the Infinity Fabric. The 3950X's 16 cores also have access to roughly the same aggregate memory bandwidth as the 12-core Ryzen 9 3900X, which means it has reduced memory throughput per core. That can manifest as reduced scaling in some workloads. You'll notice the overclocked Threadripper 2950X isn't present in the y-cruncher chart, but that's because the system repeatedly crashed during this single benchmark, indicating that either the motherboard firmware or AMD's PBO algorithms could use some additional work.
We see much the same trends emerge with our Handbrake tests, with the Ryzen 9 3900X consuming a similar amount, or slightly more, power than the Ryzen 9 3950X. However, these workloads tend to spread across the cores but not fully saturate them, which likely allows the 3950X to benefit from operating lower on the voltage/frequency curve, much like we observed with the Ryzen 9 3900, but still benefit from the parallelism of having more active cores. That equates to lower power consumption than the 3900X during the task even though the 3950X handily wins both benchmarks. Overall, the 3950X is incredibly power efficient.
Test Notes
All Ryzen entries with "PBO" indicate an auto-overclocked configuration with memory configured to DDR4-3600. Intel's overclocked configurations also use DDR4-3600. Except where noted, we tested the Ryzen Threadripper 2990WX and 2950X in game mode for all gaming tests, and in Creator mode for application tests.
VRMark and 3DMark
The 3DMark DX12 and DX11 tests measure the amount of raw horsepower exposed by the processor to game engines, but most game engines don't scale as linearly with additional compute resources.
As expected, the Ryzen 9 3950X is exceedingly powerful when the game engine can take advantage of its 16 cores and 32 threads, and paired with its solid per-core performance, it even outperforms the stock Core i9-9980XE, although that processor flips the tables after overclocking. The Core i9-9900K can't compete here due to its eight cores. We ran the Threadripper processors in Creator Mode for these tests, but the extra cores don't equate to extra performance due to the memory architecture.
VRMark responds well to high clock rates, giving the Intel processors a big advantage in this test.
Civilization VI AI and Stockfish
The Civilization VI AI test measures AI performance in a turn-based strategy game and is heavily influenced by high clock rates and instruction per cycle (IPC) throughput.
The top of these charts used to be Intel-only territory, but AMD has made amazing gains in per-core performance (a mixture of IPC and frequency) with the Zen 2 microarchitecture. The stock Ryzen 9 3950X beats the other Ryzen models while trailing the Intel Core i9-9900K, but overclocking propels it near the top of the chart. The result reflects that the Ryzen 9 3950X is boosting well and that the game engines' execution threads are correctly steered to the faster cores. Meanwhile, the stock -9980XE trails, but tuning pushes it up the chart.
The open-source Stockfish chess engine is the polar opposite of the Civilization VI engine. This engine is designed specifically for many-core chips and scales well up to 512 cores. The Ryzen 9 3950X shows its agility and matches the stock -9980XE step for step, but Intel's overclocking advantage hands the -9980XE the lead. As expected, the 32-core 64-thread Threadripper 2990WX takes the top of the chart, but you'll notice the Threadripper 2950X in Creator Mode falls far behind the 3950X.
Ashes of the Singularity: Escalation
Ashes of the Singularity: Escalation responds well to extra cores and threads, which benefits the Ryzen lineup. The Ryzen 9 3950X leads the AMD pack, but the Ryzen 7 3700X is plenty impressive after overclocking. The -9980XE is impressive in stock and overclocked trim. As you can see at the bottom of the chart, the second-gen Threadripper chips aren't the best solution for gaming due to the eccentricities of their multi-die design. We expect that to change radically with the arrival of the Threadripper 3000 chips and their EPYC Rome-based architecture.
Civilization VI Graphics Test
The Civilization VI graphics test finds the stock Ryzen 9 3950X delivering excellent performance. In fact, it actually outpaces the auto-overclocked 3950X configuration. We've become accustomed to these inversions with AMD's PBO feature, but they usually occur in our application testing. We ran this test several times to confirm the result.
In either case, the Ryzen 9 3950X beats the stock Intel processors handily in this benchmark, which is quite the feat.
Dawn of War III
The Core i9-9900K and -9700K take their traditional spots at the top of the Dawn of War III pecking order, a byproduct of their clock speed advantage. The Ryzen 9 3950X and Core i9-9980XE land within range of each other on the lower portion of the chart, but that still represents a big improvement over the Threadripper models.
Ryzen 7 3700X is very competitive with the much higher-priced models, reminding us that the majority of gamers are well-served by more modest accommodations.
Far Cry 5
Intel's mainstream chips convincingly lead the pack. The divide between the Core i9-9980XE at stock and overclocked settings is massive, highlighting the advantage of dialing up its clock speed. Intel plans to bring overclocked-like performance at stock settings with its Cascade Lake-X chips, which will certainly make the competition with the Ryzen 9 3950X more interesting.
Final Fantasy XV
We run this test with the standard quality preset to sidestep the impact of a bug that causes the game engine to render off-screen objects with the higher-resolution setting.
The Ryzen 9 3950X is competitive with Intel's stock Core i9-9900K and i7-9700K, but the -9980XE separates itself from the rest of the test pool.
Grand Theft Auto V
Grand Theft Auto V continues to be popular six long years after its release. This title favors Intel architectures and, more generally, multi-core designs with high clock rates. Intel's overclocked Core i9-9900K and Core i7-9700K push us to a graphics bottleneck in this test, but the middle of the test pool is very competitive with slight deltas separating the various models.
Hitman 2
The 3950X matches the stock Core i9-9900K and -9980XE step for step in this benchmark, but overclocking Intel's processors bottlenecks the graphics card.
Project Cars 2
Project Cars 2 is optimized for threading, but high clock rates pay off. That naturally results in a win for the Intel -9900K and -9700K processors.
The Core i9-9980XE shines in some benchmarks, but like the Threadripper chips, it has a unique architecture that can result in reduced performance with some existing software. Intel's mesh architecture is designed to increase scalability, much like AMD's Infinity Fabric, thus yielding higher core-count chips. But here we see the impact of the design.
World of Tanks enCore
World of Tanks finds another odd inversion with the auto-overclocked 3950X lagging behind the stock configuration. The delta between the two configurations weighs in at 2.4 fps, but it's repeatable.
Rendering
If ever there were a perfect use case for a copious number of cores and threads, rendering is it. The Ryzen 9 3950X is a great fit for applications hungry for parallelism. It takes a lot of firepower to outperform the Ryzen 9 3950X in the multi-threaded Cinebench test: only the 32-core Threadripper 2990WX and the heavily-overclocked Core i9-9980XE can pull off the feat. Surprisingly, the Ryzen 9 3950X also takes the crown in the single-threaded Cinebench test.
LuxMark, POV-Ray, and Blender exhibit much the same trend: Only the heftiest chips can challenge the 3950X, and the Intel Core i9-9980XE needs a significant boost via overclocking to join the 3950X at the top of the chart. Conversly, Corona and v-ray are a bright spot for the stock -9980XE as it wrests the lead from the 3950X.
In case you've forgotten, the Core i9-9980XE currently retails for ~$2,000, while the Ryzen 9 3950X weighs in at only $749. That's quite the value considering its solid performance.
The 3950X is also impressive in the highly-threaded NAMD benchmark, but the Threadripper 2990WX faced issues running the Windows version of the benchmark. We're troubleshooting that issue, but considering the results we've seen with Linux NAMD testing, the 2990WX should lead this chart easily.
Taken in context, it's incredibly impressive to see the 16-core 3950X outweighing the 32-core 2990WX in many of these rendering tests. Those wins really highlight the massive gains that AMD has made with the new architecture, which assures equal memory access to all cores. That corrects the problem faced by the current Threadripper lineup, which consists of two die (of four) that don't have direct access to memory controllers. Threadripper 3000, which debuts later this month, features the same Zen 2 architecture (albeit with modifications), which bodes well for the type of performance we can expect.
Encoding
The 3950X is also competitive in the lightly-threaded FLAC audio encoding test but trails the Intel -9900K and -9700K in the single-threaded LAME benchmark.
The Ryzen 9 3950X is much more impressive in the HandBrake x264 test, where it outperforms the rest of the test pool, and in the AVX-heavy x265 version of that same benchmark, where it only trails the overclocked 18-core -9980XE. Yet again, the Threadripper 2990WX shows its bipolar nature as it lags in this test due to its reduced memory throughput, but the Threadripper 2950X is more competitive. However, it isn't as fast as the 3950X.
Compression, Decompression, Encryption, AVX
The 7zip and Zlib compression/decompression benchmarks rely heavily upon threading and work directly from system memory, thus avoiding the traditional storage bottleneck in these types of tasks. Ryzen dominates these tests without storage throughput restrictions, but you also have access to the PCIe 4.0 interface with AMD's X570 platform. That extra throughput means these tremendous gains will largely transfer over to real-world application performance when you pair the Ryzen chips with a speedy PCIe 4.0 SSD.
It's impossible to beat the Threadripper 2900WX in decompression performance with today's desktop processors, but the Ryzen 9 3950X comes close with surprisingly strong performance. However, as impressive as the 2990WX is, it inexplicably suffers in some workloads, like compression. Meanwhile, the Ryzen 9 3950X offers a more balanced profile that is competitive in both types of workloads.
The heavily-threaded y-cruncher benchmark, which computes pi using the demanding AVX instruction set, finds the Ryzen 9 3950X in the middle of the pack as it falls behind the other Threadripper models and the Core i9-9980XE in the threaded tests. The 3950X trails even its 12-core sibling, the Ryzen 9 3900X, in the single-threaded y-cruncher benchmark. This is likely due to less available memory throughput on a per-core basis.
Office and Productivity
Microsoft's office suite runs via PCMark 10's new application test. This benchmark tests with real Microsoft Office applications. The 3950X takes third in the overall score, but much of that comes on the strength of its performance in Excel. The 3950X is competitive in the remainder of the Office suite, but the Intel chips are more agile at these types of applications.
The application start-up metric measures load time snappiness in word processors, GIMP, and Web browsers. Other platform-level considerations affect this test as well, including the storage subsystem. The Ryzen 9 3950X is very competitive in this benchmark, rivaling the -9900K in a test that it traditionally dominates. Adding a PCIe 4.0 SSD to our Ryzen test system would swing this benchmark in favor of the Ryzen 3000-series processors.
The 3950X is in rarefied air in the LLVM compilation benchmark as it trades blows with the Threadripper 2990WX and Core i9-9980XE. We see muted gains from overclocking in the heavily-threaded LLVM compile benchmark.
Web Browser
Browsers tend to be impacted more by the recent security mitigations than other types of applications, so Intel has generally taken a haircut in these benchmarks of fully-patched systems, though that handicap doesn't stop the company from sweeping the AMD competition. These tests are extremely sensitive to clock rates due to their lightly-threaded nature, and the 3950X falls behind itself after overclocking. That indicates that PBO can have an impact on lightly-threaded work.
A New Class of Performance
High end desktop processors have long offered the ultimate in performance, as long as you were willing to pay the price. Aside from high MSRPs, the chips also require expensive accommodations, like beefy motherboards and the added cost of fully populating quad-channel memory controllers. Add in the inevitable trade-offs, like reduced performance in lightly-threaded applications and games, and most regular users who could use the threaded horsepower of a HEDT chip just settle for mainstream offerings.
Now AMD's Ryzen 9 3950X brings HEDT-class performance to mainstream motherboards, lowering the bar for entry. The 3950X carries a $749 price tag, but that is downright affordable compared to competing HEDT processors.
Intel's current lineup of Skylake-X Refresh chips are hideously overpriced by comparison, but AMD's pressure has brought about some change: Intel's forthcoming Cascade Lake-X chips cost roughly half the price of the previous-gen models, yet the 18C/36T Core i9-10980XE still slots in at nearly $200 more than the 3950X. You'll also need to spring for an X299 motherboard, while the 3950X drops into X570, X470, and B450 motherboards, though the latter might not be a good choice to feed enough current to this beast.
As a general rule, we don't recommend HEDT processors for enthusiasts that are only interested in gaming, they're best served by mainstream processors that are often faster in games, and the Ryzen 9 3950X also falls into the same category. However, if you're after a platform that can do serious work, but still be nimble enough for some entertainment afterward, the Ryzen 9 3950X fits the bill.
Below we plot the geometric mean of our gaming test suite in both average fps and 99th percentile values, the latter of which is a good indicator of the overall smoothness of your gaming experience.
The Ryzen 9 3950X provides more than acceptable performance for 1080p gaming, as a whole, and it is very competitive with Intel's chips. These deltas will shrink tremendously when paired with high-resolution gaming. Given the target audience, that class of gaming is almost a given.
We see the same performance trend throughout our suite of application tests: Unlike some Threadripper processors, there were no significant performance outliers in lightly-threaded apps that were worthy of alarm. Turn to heavily-threaded applications, like rendering and professional applications, and the Ryzen 9 3950X often outstripped those same Threadripper processors, not to mention Intel's flagship Core i9-9980XE.
AMD says that it fully expects the Ryzen 9 3950X to be competitive with Intel's new -10980XE, but Intel also has its 14C/28T -10940X at $784, which aligns neatly with the 3950X's pricing. We're sure that you'll see reviews of both of those competing products shortly.
But we don't think those chips will change the landscape much, the Ryzen 9 3950X just has too much to offer at a much lower overall cost. A capable X570 motherboard doesn't come cheap, but you gain access to the PCIe 4.0 interface as a nice bonus. Budget in a beefy cooler to assure enthusiast-class performance from your chip, and AMD's Ryzen 9 3950X is truly in a class of its own.
0 comments:
Post a Comment