After a stunning pre-announcement tease and the official reveal occasion on November third, AMD’s long-awaited RDNA 3, Radeon RX 7900 sequence GPUs are right here… beginning tomorrow. When you may not be capable to press a purchase button immediately, we’ve our full evaluation able to share with you, together with our outcomes for thermal efficiency, energy draw, and benchmarks.
The Radeon RX 7900 XT and 7900 XTX each have a tall job forward of them–particularly in gentle of the uncooked energy we noticed from NVIDIA’s monoli-thicc RTX 4090. AMD, nonetheless, doesn’t appear to be phased by this. The corporate’s targets with the RX 7900 Sequence are clear: to supply “incredible efficiency, however at an inexpensive energy,” all whereas conserving prices below $1000 USD.
Did AMD achieve attaining these targets? In that case, which GPU is best for you – the RX 7900 XT or XTX?
Let’s discover out.
Below the RDNA 3 Hood: A Ryzen-Like GPU
When it got here to designing RDNA 3, AMD leveraged what it realized from its Ryzen and EPYC CPUs through the years, then utilized that data to Radeon graphics. Utilizing a chiplet-style design like we noticed with Ryzen, AMD has separated the primary Graphics Compute Die (GCD) and Reminiscence Cache Die (MCD).
G/O Media could get a fee
Addiction counseling
Safe Haven Health
Accessible for all
Safe Haven prioritizes your needs with flexible and individuated substance abuse treatment, specifically opioid & alcohol addiction.
This separation allowed AMD to do a few things differently, including multi-level processing. The GCD utilizes a 5nm process technology, while the smaller MCD dies utilize a tried-and-true 6nm for handling the GDDR6 memory interfaces. According to AMD, this allows the GPU to optimize where it routes power to, enabling both high performance and an uplift in performance-per-watt.
But that isn’t the only benefit to this redesign. Enter AMD’s 2nd Generation Infinity Cache. This technology serves as a “fast lane” for memory bandwidth, expanding data access to the GPU by providing an additional level of cache. This enables quicker access to assets, which translates to an increase in frames-per-second. With 2nd Generation Infinity Cache, AMD has fine-tuned the L0, L1, and L2 caches as well as expanded the bus bandwidth, allowing RDNA 3 to do more with less.
For context, the Radeon RX 6950 XT has 128MB of 1st Generation Infinity Cache on a 256-bit memory bus with 18Gbps GDDR6 memory. This setup provides a memory bandwidth up to 1793.g GB/s. Not too shabby, but it gets better with the RX 7900 Series.
The 7900 XT has 80MB of 2nd Generation Infinity Cache, but bumps up the memory bus to 320-bit and ever-so-slightly faster (20Gbps) GDD6, giving it a memory bandwidth of 2912 GB/s. That’s over 1 GB/s faster, but it gets even better.
The 7900 XTX stacks on 16MB of 2nd Generation Infinity Cache for a total of 96MB, cranks the memory bus up to 384-bit with GDDR6 comparable to the 7900 XT, and gets speeds of up to 3494.4 GB/s of bandwidth.
When we put all of this together, the “real world” effect of a faster Infinity Cache is that the GPUs are better able to efficiently store and recall recently processed data, rather than having to go back and reprocess it every time they need it. It’s much like being able to keep browser tabs open for quick access to, say, a game guide – the information is there, ready when you need it. This quicker access allows the GPU to move on to other tasks.
But wait, there’s more.
AMD has been watching the ways that users have been leveraging their technologies in multitasking situations, such as gaming and streaming from the same device. So, with RDNA 3, the company built in a new dual media engine to handle simultaneous operations without bogging down the user. This will allow for hardware-accelerated encoding and decoding for AVC and HEVC streaming loads, as well as additional support for AV1 encoding up to 8K60 – fantastic news for streamers!
Additionally, RDNA 3 introduces AMD’s Radiance Display Engine, which adds support for DisplayPort 2.1. With this new technology, the RX 7900 Series has hardware for displays up to 8K with refresh rates of 165 Hz. While this technology is not widely available just yet and the reach toward 8K gaming is ambitious, it is clear that AMD’s goal to provide “fantastic performance” reaches far beyond framerates.
Radeon RX 7900 XT and Radeon RX 7900 XTX Specs:
Now that we have a clear picture of what’s new with RDNA 3, it’s time to take a peek under the hoods of the RX 7900 XT and RX 7900 XTX.
Those are some handsome numbers, but what does this all mean when you put them all together?
To put it simply, compute units are like CPU cores, handling operations sent to the GPU while stream processors handle the more complex math. As for Clock speeds and Boost Clock, they determine how fast the data can be processed. Memory serves as a resource to the GPU, while the memory bandwidth determines the speeds of access to those resources. When you put all of these together, every piece of the system impacts your overall experience, which results most notably in pixels and pixel quality.
Speaking of delivery, it is worth noting that AMD did not transition the RDNA 3 platform to a new or different power connector like NVIDIA. AMD has been very clear that it did not want users to have to replace existing cabling or need to swap out power supplies in order to upgrade to a modern GPU.
When it comes to physical dimensions, the RX 7900 XT measures in at 10.86 inches long (276mm) with a height of 4.44 inches (113mm), weighing in at 3.33 lbs (1.51 kg). The 7900 XTX is a bit chonkier at 3.97 lbs (1.80 kg), extending a bit longer than the XT at 11.29 inches long (287mm) with a height of 4.84 inches (123mm). Both GPUs are labeled as 2.5 slot cards, but they don’t muscle their way far beyond the second slot.
This is great news if you need room for other PCIe cards! Speaking of dimensions, it is worth noting that the reference RX 7900 Series GPUs from AMD don’t dominate the cases they’re in. I was a little concerned about the size until I tried it out in one of my favourite smaller mid tower instances.
For context and comparability, the RTX 4080 is a three-slot card, roughly 11.96 inches lengthy (304mm) with a peak of 5.39 inches (137mm). Now, these dimensions are the reference or Founders Version GPUs, so the scale of add-in-board (AIB) associate playing cards (ASUS, Gigabyte, ASRock, and many others.) will range considerably.
As for connectivity, each RX 7900 Sequence GPUs have two DisplayPort 2.1 ports, a single HDMI 2.1a port, and a USB-C with DisplayPort 2.1 connection.
All of this seems to be nice on paper, however how does it work?
Huge Numbers: RDNA 3 Efficiency And Energy
I do know what you’re right here for; you need to know what sort of numbers these items put out. Earlier than we will current our findings, let me share a peek behind the curtains to provide you some context for the numbers you’re about to see.
To gather our knowledge from the Radeon RX 7900 Sequence, we utilized a take a look at bench with the next elements: a Ryzen 9 7950X CPU, X670E AORUS Grasp motherboard, 32 GB G.Talent Trident Z5 NEO DDR5-6000 RAM, 1TB WD_Black SN770 M.2 NVMe SSD, NZXT C1000 Gold 1000W PSU, NZXT Kraken Z73 360mm all-in-one liquid cooler with three 120mm followers, and an NZXT H7 Elite mid-tower PC case geared up with 4 140mm followers.
For our testing, we selected 5 titles that make the most of quite a lot of trendy graphics applied sciences, together with ray tracing and AMD’s FidelityFX Tremendous Decision (FSR). In every title, we recorded knowledge throughout a number of passes of the benchmarks at 1080p, 1440p, and 4K, accumulating outcomes throughout every decision with ray tracing on and off and with FSR enabled and disabled. When enabled, we used FSR’s High quality or Extremely High quality settings.
As we undergo this knowledge, we can be speaking about rasterization first after which shifting on to ray tracing.
It is usually value noting that we didn’t have NVIDIA’s RTX 4080 available for comparability, so we recorded knowledge from an in depth value competitor to the RX 7900 Sequence, the RTX 3090. Spec-wise, it shares various similarities to the RX 7900 XTX – 384-bit reminiscence interface, 24GB of GDDR (although, the 3090 has a bonus with GDDR6X), and an influence ranking of 350W. It’s not a precise match, but it surely’s shut sufficient the place the comparability is related.
Here’s what we discovered:
We ran every take a look at at Extremely settings and the RX 7900 Sequence met every job with a reasonably robust displaying total. The one exception to that assertion can be Metro Exodus at 4K. Whereas we’ve seen this take a look at take even the strongest of GPUs to job at its most excessive settings, the remainder of the info reveals a promising image.
At 4K, the RX 7900 XT persistently put out body charges over 60 FPS in most titles. Other than Metro Exodus, Cyberpunk 2077 did experience that line in pure rasterization, however that is on the highest settings with out the help of FSR. With FSR enabled at its High quality setting, the 7900 XTX crossed that threshold and held averages above 60 frames per second. Nonetheless, if 4K isn’t the purpose, however 1440p is, the 7900 XT pushed persistently past 100 FPS usually, together with Cyberpunk 2077.
Once we have a look at the RX 7900 XTX, we see an 18% improve in efficiency over the RX 7900 XT in Cyberpunk 2077, 20% in Borderlands 3, ~18% in Far Cry 6, and 13% in Forza Horizon 5 – and that is earlier than FSR. When enabled, we see a efficiency distinction of 13% in Cyberpunk 2077, 12.5% in Far Cry 6, and, once more, ~13% in Forza Horizon 5.
Once we begin trying on the numbers in comparison with the RTX 3090, in pure rasterization we see the RX 7900 XT leap forward of the 3090 by practically 21% in Borderlands, ~18% in Cyberpunk 2077, and 17.5% in Forza – with Metro Exodus useless even throughout all playing cards at 4K. That hole will get wider as soon as we begin introducing the RX 7900 XTX into the image. For our assessments, we see a mean efficiency improve of round 35% from the RTX 3090 to the RX 7900 XTX.
Not unhealthy, Crew Crimson, however can it run Crysis… I imply, can it ray hint?
The reply is a professional sure.
Within the titles we examined, the RX 7900 Sequence GPUs had been capable of put up robust numbers in ray tracing functions. Nonetheless, at 4K, we noticed a couple of instances the place they lagged behind the ray tracing capabilities of the RTX 3090. Whereas Metro Exodus served because the equalizer in rasterization, Cyberpunk 2077 takes the title of “Most Punishing Ray Tracing Benchmark.”
With none help from FSR, the 7900 XTX struggled to hit a mean of 20 frames per second at Cyberpunk’s highest ray tracing settings. Whereas it is just a 2-frame distinction, the uplift with FSR nonetheless has each GPUs averaging decrease than 60 frames per second. Now, to be truthful, the RTX 3090 isn’t far forward; even with DLSS enabled, it solely led the 7900 XTX by 3 frames per second.
We did see the RX 7900 XT lag behind the RTX 3090 in Far Cry 6 by ~6% at 4K and Metro Exodus by ~5% at 1440p and ~11% at 4K, however in any other case the RX 7900 Sequence GPUs held their floor and posted spectacular body charges at 1080p, 1440p, and 4K with ray tracing options enabled. When FSR is enabled, nonetheless, that adjustments the story.
Productiveness Efficiency:
In relation to productiveness assessments, we bumped into some fascinating obstacles for direct comparability, particularly when utilizing rendering assessments like Blender. With its 3.0 launch, Blender eliminated the OpenCL possibility for GPU rendering, leaving NVIDIA’s CUDA and Optix as the one GPU-bound choices for rendering. Nonetheless, AMD has been serving to to rewrite CUDA code to HIP (or Heterogeneous Interface for Portability) to mesh with Radeon GPU expertise.
Here’s what we discovered:
Inside Blender, a picture of everybody’s favourite shiny crimson BMW rendered at a breezy 14 seconds on the RX 7900 XT and 12 seconds on the RX 7900 XTX. It was spectacular, however NVIDIA did shave a second off of the RX 7900 XTX’s time by using CUDA, after which it halved the 7900 XT’s time with Optix. This isn’t essentially unhealthy information for Crew Crimson – they’re all good numbers, however NVIDIA does have a slight leg up right here.
The story is just like OpenCL efficiency metrics in Geekbench 5. The RX 7900 Sequence falls barely in need of the RTX 3090, however takes a powerful lead in Vulkan efficiency measurements. In different phrases, the RX 7900 Sequence excels at gaming and does effectively sufficient for itself in computational duties.
Vitality Effectivity and Thermal Efficiency
With all the speak about pace and energy, we’ve to look again at AMD’s purpose with RDNA 3: incredible efficiency at an inexpensive energy and value. We have now seen some incredible efficiency knowledge from each RX 7900 GPUs, however what about energy consumption and warmth?
Whereas we had been operating our benchmarks, we saved an in depth eye on the RX 7900 Sequence to maintain AMD sincere in its claims. In spite of everything, we noticed Ryzen 7000 Sequence CPUs hit some fairly excessive numbers, so we wished to make it possible for the “excessive performance-per-watt” claims didn’t simply imply that RDNA 3 was going to devour a considerable amount of wattage.
So, we measured the ability consumption and warmth throughout our 4K assessments. This could make sure that the duties had been using as a lot of the GPU’s energy as potential. What we discovered was stunning.
In each common energy supply and at their peak, the ability consumption of each RX 7900 XT and RX 7900 XTX stayed significantly decrease than the RTX 3090. Once you begin to have a look at the quantity of energy consumed versus body price output, you can begin to see that AMD isn’t taking part in round with smoke and mirrors; its playing cards are offering spectacular ends in gaming environments whereas trailing the competitors by a couple of 50W margin throughout energy supply averages. Trailing is an effective factor on this circumstance.
In relation to thermal efficiency, the comparisons get rather less clear. We’re coping with two very totally different cooler varieties between the RTX 3090 Founders Version and AMD’s retail editions of RX 7900 Sequence.
That’s to not say that the numbers are unhealthy; the RX 7900 XT and RX 7900 XTX maintained peak temperatures below 70 levels Celsius through the heaviest hundreds, with averages on the GPU itself hovering within the mid- to higher 60s. Now, there may be one catch to those numbers that’s not mirrored within the charts:
Whereas recording thermal knowledge, we observed that the temperature readings on the GPU itself stayed comparatively cool, however the reminiscence thermal junction was a unique story altogether. Proper now, with minimal efficiency load on the GPU, the reminiscence thermal junction temperature is hovering round 85 levels Celsius.
We noticed one thing related with the most recent Ryzen CPUs, and that is by design. In response to AMD, these junctions can deal with temperatures as much as 110 levels Celsius. Scorching junctions for that sizzling and sweaty efficiency!
This can be a results of the chiplet design. Afterall, the GCD is surrounded by the MCDs; warmth from the GCD (the place we had been recording our knowledge from) might be bleeding over into these junctions. That’s purely my hypothesis.
The Huge Query: Is RDNA 3 Proper For You?
Whereas AMD particularly said that it’s not punching at RTX 4090 territory, the pricing, efficiency, and energy draw of the RX 7900 Sequence actually takes some heavy swings in that course, particularly on pure gaming efficiency. These punches, nonetheless, can be far more practical if these RDNA 3 GPUs can maintain to the final a part of AMD’s pursuit: “an inexpensive value.”
Now, GPU costs round $1,000 are already tough to abdomen, however AMD has clearly aimed on the fanatic market with this launch. For me, the RX 7900 Sequence represents a proof-of-concept. That idea? That AMD can ship killer excessive finish GPUs that may hold on the excessive floor at a fraction of the value… with a concession or two.
Technology over technology, AMD has made some distinctive strides in the case of ray tracing, however NVIDIA nonetheless has a leg up on the home of Su. FidelityFX Tremendous Decision is a promising expertise and the adoption price is growing. Whereas efficiency uplift total matches DLSS, DLSS produces a prettier image and smoother expertise. Then, there may be entry to issues like CUDA and Optix.
The actual query is that this: if you’re available in the market for a brand new GPU, do you want these issues? In the event you don’t and also you simply need excessive body charges on a (barely) decrease finances, then the RX 7900 Sequence could be best for you. Each GPUs present distinctive entry to gaming efficiency with some added quick futureproofing options like AV1 {hardware} acceleration and DisplayPort 2.1. RDNA 3 additionally makes a robust case to construct a Crew Crimson system with AMD Sensible Know-how.
If that sounds such as you and it’s good to construct now, pair the Radeon RX 7900 XT with the Ryzen 7 7700X. This mixture gives entry to trendy applied sciences whereas offering a promising improve platform for years to come back. Keep in mind although, that is nonetheless an estimated $899 USD for the GPU alone.
That’s not for anybody however energy hounds, however given the RTX 4090’s $1,599 value, even probably the most discerning of players may do worse. I can let you know this: pairing the Radeon RX 7900 XTX with the Ryzen 9 7950X is an beautiful expertise. At 4K and under, the body charges are very good.
Nonetheless, in case you’re nonetheless on the fence and all of that is too wealthy for you, the excellent news is that that is solely the start of RDNA 3. With this robust of a displaying on the high degree, it will likely be actually thrilling to see competitors within the mid-tier warmth up!
