AMD Reveals Radeon RX 7900 XTX and 7900 XT

11/12/22, 9:38 AM AMD Reveals Radeon RX 7900 XTX and 7900 XT: First RDNA 3 Parts To Hit Shelves
t RDNA 3 Parts To Hit Shelves in December
Login
Register
ABOUT BENCH FORUMS PODCAST

PC COMPONENTS ▼ SMARTPHONES & TABLETS ▼ SYSTEMS ▼ ENTERPRISE & IT GUIDES ▼ DEALS
TRENDING TOPICS CPUS INTEL AMD GPUS MOTHERBOARDS STORAGE NVIDIA MOBILE Follow 77.6K followers
Home > GPUs

PIPELINE STORIES + SUBMIT NEWS
AMD Reveals Radeon RX 7900 XTX and 7900 XT: 158

First RDNA 3 Parts To Hit Shelves in December Comments AT Deals: Logitech MX
by Ryan Smith on November 3, 2022 4:46 PM EST + Add A
Master 3 Mouse $70 at
Comment
Posted in GPUs AMD Radeon GDDR6 Chiplets RDNA3 RX 7000 DisplayPort 2.1 Dell
AT Deals: Samsung 980 Pro 1 TB
SSD Now $120 at Amazon
AT Deals: Acer Nitro 34-Inch

Curved Monitor Now $350 at
Amazon
AT Deals: Dell 27-Inch 165 Hz IPS Now

$150 at Amazon
AT Deals: HyperX Alloy Origins Core TKL
Keyboard $53 at Amazon
AT Deals: AMD Ryzen 5 5600 CPU Lowers
to $119 at Newegg
AT Deals: LG 32-Inch QHD Monitor is
$200 at Walmart
Intel Launches Raptor Canyon: Desktop
Raptor Lake Sizzles in NUC13 Extreme
AT Deals: Acer Predator Helios 300 RTX
3060 Laptop Now $1000 at Best Buy
AT Deals: Crucial P2 1 TB SSD Drops to
With AMD’s first-wave of Zen 4 CPUs now in the books with the Ryzen 7000 series, the consumer arm of $66 at Amazon
AMD is now shifting its attention over to its graphics business. In a presentation that ended moments ago Best Internal Hard Drives: Holiday 2022
dubbed “together we advance_gaming”, Dr. Lisa Su and other AMD leaders laid out the future of AMD’s
Best AMD Motherboards: Holiday 2022
graphics products. And that future is the RDNA 3 architecture, which will be the basis of the new Radeon RX
7900 XTX and Radeon RX 7900 XT video cards.
The two cards, set to be released on December 13th, will be the first products released using the RDNA 3
architecture. According to AMD, the new flagship 7900 XTX will deliver up to 70% more performance at 4K
than their previous flagship, the 6950 XT. This performance boost comes curtesy of several architectural TWEETS
improvements in RDNA that cumulatively offer 54% higher performance per watt than RDNA 2, as well as RyanSmithAT: There's a lot of really neat
higher clockspeeds courtesy of TSMC’s 5nm (and 6nm) processes, and higher overall power consumption. stuff going on in the machine learning field,
especially this week with the official…
The full-fledged RX 7900 XTX will be hitting the streets at $999. Meanwhile the second-tier RX 7900 XT will https://t.co/wLqAOdlYbv
run for $899.
ganeshts: @tuanies Fixes almost all
complaints I had with the industrial design of
AMD Radeon RX 7000 Series Specification Comparison the Ghost / Beast / Dragon Canyon NUCs.
N… https://t.co/tzQFinGBE8
AMD Radeon RX AMD Radeon RX AMD Radeon RX AMD Radeon RX
7900 XTX 7900 XT 6950 XT 6900 XT gavbon86: @Claressashields
@Savmarshall1 You absolutely outclassed
Stream Processors 12288
10752
5120
5120
her
(96 CUs) (84 CUs) (80 CUs) (80 CUs)
RyanSmithAT: RT @HardwareUnboxed: A
ROPs 192 192 128 128 lot of you have asked why we don't
benchmark Microsoft Flight Simulator,
Game Clock 2.3GHz 2.0GHz 2100MHz 2015MHz especially for day one content, this is why…
Boost Clock 2.5GHz 2.4GHz 2310MHz 2250MHz gavbon86: @MatchroomBoxing @iam_yafai

@DAZNBoxing 3rd ranked versus 138th
Throughput (FP32) 56.5 TFLOPS 43 TFLOPS 21.5 TFLOPS 20.6 TFLOPS ranked...Amazing match up 😂
Memory Clock 20 Gbps GDDR6 20 Gbps GDDR6 18 Gbps GDDR6 16 Gbps GDDR6 ganeshts: @davezatz Short of downloading
the actual Matter specifications, I have read
Memory Bus Width 384-bit 320-bit 256-bit 256-bit
countless articles on it.
None have t…
VRAM 24GB 20GB 16GB 16GB https://t.co/Wyiww48mTk
https://www.anandtech.com/show/17638/amd-reveals-radeon-rx-7900-xtx-and-7900-xt-first-rdna-3-parts-to-hit-shelves-in-december 1/14
11/12/22, 9:38 AM AMD Reveals Radeon RX 7900 XTX and 7900 XT: First RDNA 3 Parts To Hit Shelves in December
Infinity Cache 96MB 80MB 128MB 128MB RyanSmithAT: @phatal187 @anandtech
@JamesDSneed @Locuza EFB
Total Board Power 355W 300W 335W 300W
RyanSmithAT: @phatal187 @anandtech
Manufacturing GCD: TSMC GCD: TSMC TSMC 7nm TSMC 7nm @JamesDSneed @Locuza I have walked
Process 5nm
5nm
back that bit about EFB. I can't say more

MCD: TSMC MCD: TSMC
6nm 6nm than that, but c… https://t.co/VUArGCwU3T
RyanSmithAT: @wassickt @phatal187

Transistor Count 58B 58B - (1 MCD) 26.8B 26.8B
@anandtech @JamesDSneed @Locuza You
Architecture RDNA3 RDNA3 RDNA2 RDNA2 are technically correct. That's something I'll
get better… https://t.co/DPK8kf4kFX
GPU Big Navi 3x Big Navi 3x Navi 21 Navi 21
gavbon86: RT @anandtech: Just in time for
Launch Date 12/13/2022 12/13/2022 05/10/2022 12/08/2020 storing all your holiday movies, @ganeshts
has updated his fantastic HDD buyer's guide.
Launch Price $999 $899 $1099 $999 FC-MAMR, 22TB drive…
AMD’s eagerly anticipated update to their GPU architecture comes as the company has been firing on all gavbon86: Either I haven't really put much
into Christmas in the past, or I'm now of that
cylinders for the last few years. On the CPU side of matters the Zen 3 and Zen 4 architectures in particular
age where I'm excited about traditi…
have proven very performant, and meanwhile AMD has been able to claw its way back from its graphics https://t.co/goSayBs2US
slump with the RDNA family of GPU architectures. RDNA 2, the basis of the Radeon RX 6000 series,
exceeded expectations and proved to be a very strong competitor, and now AMD is seemingly setup to gavbon86: I can't wait to see some
performance numbers on the RX 7900 XTX.
exceed expectations once again, with RDNA 3’s 54% performance-per-watt coming in ahead of AMD’s
This AMD Advantage Desktop stuff, is this
earliest promises of a 50% gain. where AM… https://t.co/oV8Ehh773f
AMD Goes Chiplets For GPUs ganeshts: @TheKanter Take care with the
left-hand side drive, and be careful with the
While today’s reveal from AMD was a more closely guarded event than the Ryzen 7000 unveil a couple of posted speed limits. Enforcement is very
months ago, AMD has still given us a quite a bit of detail on the RDNA 3 architecture and the cards – more strict.
than we have time to cover here – so let’s get started from the top, with the construction of the first RDNA 3
ganeshts: @TheKanter This was the itinerary
GPU. I took along with activities when I did the trip
around 10 years back (part of a…
The Navi 3x GPU (AMD is not confirming the specific GPU name at this time) breaks new ground for AMD not
https://t.co/cy7YXwa3Mw
only on the performance front, but in terms of its construction. For the first time from any of the big 3 GPU
manufacturers, AMD is utilizing chiplets in the construction of the GPU. ganeshts: @Sabrent Which notebook is this?
Follow @ANANDTECH
Gallery: Big Navi 3x GPU
Chiplets are in some respects the holy grail of GPU construction, because they give GPU designers options
for breaking apart complex monolithic GPU designs into multiple smaller parts – allowing for new options for
scaling, as well as mixing and matching the process node used in manufacturing. That said, it’s also a holy
grail because the immense amount of data that must be passed between different parts of a GPU (on the
order of terabytes per second) is very hard to do – and very necessary to do if you want a multi-chip GPU to
be able to present itself as a single device.
For their big Navi 3x chip, AMD has assembled two types of chiplets, essentially breaking off the memory
functions from a classic GPU into their own chiplets. This means that the core functions of the GPU are
housed in what AMD is calling the Graphics Compute Die (GCD), which houses all of the ALU/compute
hardware, the graphics hardware, as well as ancillary blocks like the display and media engines.
Because the GCD houses the performance-critical aspects of the overall GPU, it’s being built on TSMC’s 5nm
process. This gives AMD the best density, power consumption, and clockspeeds for these parts, though
obviously at a higher manufacturing cost. The GCD die size measures 300mm2.
Meanwhile the new Memory Cache Die (MCD) houses AMD’s infinity cache (L3 cache), as well as a 64-bit
(technically 2x32-bit) GDDR6 memory controllers. The MCD is one of the scalable aspects of the chiplet
design, as Big Navi 3x GPU SKUs can be configured by paring them with more or fewer MCDs. A full
configuration in this case is 6 active MCDs, which is what we see in the 7900 XTX. Meanwhile the 7900 XT
will have 5 active MCDs, with a 6th defective/spacer MCD present for salvaging purposes and physical
package stability.
An individual MCD is 37mm2 in die size, and is built on TSMC’s 6nm process. This is an example of AMD’s
process node flexibility, putting the less critical GDDR6 memory controllers and Infinity Cache on a cheaper
process node. GDDR6 controllers are one of those classic examples of a technology that doesn’t scale very
well with smaller process geometries (like most forms of I/O), so it’s easy to see why AMD would want to
avoid building it on 5nm for minimal benefits.
In the full 6 MCD configuration (7900 XTX), Big Navi 3x offers a 384-bit GDDR6 memory bus, along with
96MB of L3 cache. Meanwhile a 5 MCD (7900 XT) offers a 320-bit GDDR6 memory bus and 80MB of L3
cache.
For the purposes of today’s announcement, AMD has not gone into great depth on how they managed to
make a chiplet-based GPU work, but they have confirmed a few important details. First and foremost, in order
to offer the die-to-die bandwidth needed have the memory subsystem located off-chip, AMD is using an
unspecified fanout bridge technology. their Elevated Fanout Bridge (EFB) packaging technology, which AMD
first used for their Instinct MI200 series accelerators (CDNA2). On those accelerator parts it was used to hook
up the monolithic GPUs to each other, as well as HBM2e memory. On RDNA 3, it’s being used to hook up the
MCDs to the GCD.
Notably, fanout bridges are a non-organic packaging technology, which is to say it’s complex. That AMD is
able to get 5.3TB/second of die-to-die bandwidth via it underscores its utility, but it also means that AMD is
undoubtedly paying a good deal more for packaging on Big Navi 3x than they were on Navi 21 (or Ryzen
7000).
Internally, AMD is calling this memory-to-graphics link Infinity Link. Which, as the name implies, is responsible
for (transparently) routing AMD’s Infinity Fabric between dies.
As mentioned before, the cumulative bandwidth here between the MCDs and GCD is 5.3TB/second. It’s
unclear if the constraining factor is the bandwidth of the Infinity Link, or that the combined Infinity Cache +
GDDR6 memory controllers cannot move enough data to fully saturate the link. But regardless, it means
there’s essentially just shy of 900GB/second of bandwidth between an individual MCD and GCD – more than
all of the combined off-die memory bandwidth of the last-generation Radeon RX 6950 XT (and 2.7x more than
Navi 21’s on-die bandwidth).
While we’re on the subject of AMD’s L3 Infinity Cache, it’s notable here that it’s actually a bit smaller on Big
Navi 3x than it was on Navi 21, with a maximum capacity of 96MB versus 128MB on the former. According to
AMD they’ve made further improvements to improve data reuse on the Infinity Cache to offset this drop in
capacity. At this point it’s not clear if the change is a function of software algorithms, or if they’ve made more
fundamental hardware changes.
Finally, while AMD is quoting die sizes for the GCD and MCD, they aren’t quoting individual transistor counts.
So while we know that a complete 6 MCD Big Navi 3x configuration is comprised of 58 billion transistors
(2.16x more than Navi 21), we don’t know how much of that is the GCD versus the MCDs.
AMD RDNA 3 Compute & Graphics Architecture: Bringing Back ILP & Improving RT
Diving down a level, let’s take a look at the actual graphics and compute architecture backing RDNA 3 and
Big Navi 3x.
While still clearly sharing many of the core design elements of AMD’s overarching RDNA architecture, RDNA
3 is in some respects a much bigger shift in architectural design than RDNA 2 was. Whereas RDNA 2’s
compute core was essentially unchanged from RDNA (1)’s, RDNA 3 makes a few big changes.
The biggest impact is how AMD is organizing their ALUs. In short, AMD has doubled the number of ALUs
(Stream Processors) within a CU, going from 64 ALUs in a single Dual Compute Unit to 128 inside the same
unit. AMD is accomplishing this not by doubling up on the Dual Compute Units, but instead by giving the Dual
Compute Units the ability to dual-issue instructions. In short, each SIMD lane can now execute up to two
instructions per cycle.
But, as with all dual-issue configurations, there is a trade-off involved. The SIMDs can only issue a second
instruction when AMD’s hardware and software can extract a second instruction from the current wavefront.
This means that RDNA 3 is now explicitly reliant on extracting Instruction Level Parallelism (ILP) from
wavefronts in order to hit maximum utilization. If the next instruction in a wavefront cannot be executed in
parallel with the current instruction, then those additional ALUs will go unfilled.
This is a notable change because AMD developed RDNA (1) in part to get away from a reliance on ILP, which
was identified as a weakness of GCN – which was why AMD’s real-world throughput was not as fast as their
on-paper FLOPS numbers would indicated. So AMD has, in some respects, walked backwards on that
change by re-introducing an ILP dependence.
We’re still waiting on more information from AMD outlining why they made this change. But dual-issue is
typically a cheap way to add more throughput to a processor design (you don’t have to do all the instruction
tracking required for a fully separate Dual Compute Unit), and it can be worthwhile tradeoff if you can ensure
you’ll be able to dual-issue most of the time. But it means that AMD’s real-world ALU utilization rate is likely
lower on RDNA 3 than RDNA 2, due to the bubbles from not being able to dual-issue.
Which to bring things back to gaming and the products at hand, it means that the FLOPS numbers between
RDNA 3 and RDNA 2 parts are not going to be entirely comparable. 7900 XTX may push 2.6x as many FP32
FLOPs as 6950 XTX on paper, but the real world advantage on anything less than ideal code is going to be
less. Which is one of the reasons why AMD is only promoting a real-world performance uplift of 1.7x for the
7900 XTX.
In any case, SIMDs aren’t the only changes to the core compute architecture of RDNA 3. Feeding the beast,
AMD has made the Vector General Purpose Register (VGPR) bank 50% larger than on RDNA 2.
More significant than that is that AMD is finally integrating dedicated silicon for AI processing on their
consumer GPUs. This is an area where both of AMD’s competitors (NVIDIA and Intel) have already made the
investment on their consumer parts, and as the use of GPU inference in workloads continues to grow, it’s not
something AMD can ignore any longer.
Given the gaming-centric focus of today’s presentation, AMD did not spend much time talking about the new
AI units. Each RDNA 3 CU will have 2 of these units, and they will support new AI instructions (some kind of
INT8 tensor operation seems like a given). All told, AMD is saying that the new AI units give the Radeon RX
7900 XTX 2.7x the AI performance, which AMD is measuring as bfloat16 performance versus the RX 6950
XT.
Overall, the importance of this to gamers is something that remains to be seen. AMD isn’t currently using AI
units for FSR 2 (unlike NVIDIA’s DLSS 2). But that could change for future projects. Otherwise, for more
professional users (or anyone who likes to mess with Stable Diffusion), this is an addition that’s good news.
Moving on, AMD has also updated their raytracing hardware for RDNA 3. The second-generation RT
accelerator, as AMD calls it, can handle 1.5x more rays in flight. There are also new hardware box sorting and
traversal features that weren’t present in RDNA 2’s initial RT functionality. AMD’s presentation gave the
technical details a light treatment, but it certainly looks like AMD is moving to doing a bigger part of the ray
tracing process in dedicated hardware. Which in turn would help improve their performance, and keep
performance steadier by not stealing quite so many resources from the rest of the CU.
AMD’s own performance slides tout anywhere between a 47% and 84% increase in RT performance. Though
it should be noted that AMD’s numbers are with FSR enabled; so we cannot divorce these gains from any
changes that improve FSR performance on the 7900 XTX.
Last, but not least, AMD has made an interesting decision with clockspeeds on the RDNA 3. In short, AMD
has decoupled their clocks; rather than running the entire GCD at the same clockspeed, AMD will be running
the shaders and front-end at different clockspeeds. In the case of the 7900 XTX, this will see the shaders
running at 2.3GHz (the advertised game clock speed), while the front-end will run at a slightly speedier
2.5GHz (about 9% faster).
AMD did not go into great detail on why they’ve made this change, but at a high level it’s all about balancing
performance versus power consumption. The shaders could run at 2.5GHz as well (indeed, the 7900 XTX’s
rated boost clock is 2.5GHz), but as we’ve seen time and time again, those final clocks are the most
expensive in terms of power as you go up the v/f curve. So AMD has made the choice to give up a bit of
potential performance to save a lot on power, as 96 CUs/12288 ALUs is a lot of silicon to light up. Conversely,
the front-end is relatively small, and with AMD having beefed up their CUs by so much, spending a bit more
power on the front-end is presumably worth it to keep them from bottlenecking the rest of the GPU.
RDNA 3 Display & Media Engines: The Latest and the Greatest
AMD’s core compute/graphics architecture was not the only part of the RDNA 3 architecture to get an update
in this generation. AMD has also used the opportunity to upgrade their display and media engines to support
new features and new formats.
On the display engine front, AMD’s display engine, which they are now calling the “AMD Radiance Display
Engine” has been upgraded to support DisplayPort 2.1. Specifically, AMD has added support for the
DisplayPort 2.x feature suite as well as the UHBR 10 and UHBR 13.5 data rates. This means that RDNA 3
cards can offer 2x the DisplayPort bandwidth of their DisplayPort 1.4-enabled predecessors, which in turn
allows for higher resolutions and higher refresh rates. Notably, this ever so slightly exceeds HDMI 2.1’s
bandwidth as well, putting DisplayPort back into the lead, at least on AMD cards.
Unsurprisingly, AMD is using this functionality to push forthcoming higher resolution and higher refresh rate
gaming monitors, including a Samsung ultrawide display set to launch in 2023 with a horizonal 8K resolution.
So it’s not just for showing off specs, and AMD and its partners are intending to put it to good use.
AMD has not said anything about the total number of supported displays. So at this point I expect it’s still a
maximum of 4 displays.
Meanwhile on the media engine front, AMD has given RDNA 3 support for the latest and greatest video
codecs. Along with the usual H.264 and H.265 support, RDNA 3’s media engines also add full AV1 encode
and decode support, making this the latest GPU family to roll out support for the next-generation open format
codec. RDNA 3 will be able to encode and decode AV1 at up to 8Kp60.
The overall performance of the media engine has been increased significantly. According to AMD the media
engine runs 80% faster than it did on RDNA 2 parts, allowing for simultaneous encoding (or decoding) of up
to two H.264/H.265 streams. Though it’s unclear if that also applies to AV1.
Finally on the subject of AMD’s GPU uncore, while not explicitly called out in AMD’s presentation, it’s worth
noting that AMD has not updated their PCIe controller. So RDNA 3 still maxes out at PCIe 4.0 speeds, with
Big Navi 3x offering the usual 16 lanes. This means that even though AMD’s latest Ryzen platform supports
PCIe 5.0 for graphics (and other PCIe cards), their video cards won’t be reciprocating in this generation. In
fact, this means that no one will have a PCIe 5.0 consumer video card.
Radeon RX 7900 XTX & Radeon RX 7900 XT: Launching December 13th
Bringing today’s reveal full circle, let’s turn back to the cards themselves, the Radeon RX 7900 XTX and RX
7900 XT.
AMD’s flagship card will be the Radeon RX 7900 XTX. While we’re still waiting on confirmation of this, this
would seem to be a fully-enabled Big Navi 3x part, with all of the blocks in both the GCDs and the individual
MCDs themselves enabled. As mentioned previously, AMD is touting a broad performance uplift of up to 70%
versus the previous-generation flagship, the RX 6950 XT.
Internally, this means 96CUs and 96MB of L3 Infinity Cache will be available on the card. The game clock
(average clockspeed) will be 2.3GHz, while based on other AMD figures, we can infer that the boost
(maximum) clockspeed will be 2.5GHz. The game clock in particular is a ~10% improvement over the 6950
XT, so AMD is enjoying a modest frequency uplift generation-over-generation, but nothing too massive. Most
of the heavy lifting will come courtesy of the architecture and memory changes.
Gallery: AMD Radeon RX 7900 XTX
Speaking of memory, the RX 7900 XTX will be paired with 24GB of GDDR6 memory running at (at least)
20Gbps. Apparently, AMD’s partners have the headroom to go even higher than this with factory
overclocking, but the floor value for the part will be 20Gbps overall. This is a modest increase in memory
clockspeeds versus the 6950 XT (11%). Instead, the bulk of the VRAM bandwidth gains will come from the
50% larger memory bus, with the 7900 XTX moving to a sizable 384-bit bus. In total, this means the 7900
XTX will have 960GB/sec of memory bandwidth, 66% more than its predecessor. AMD got their “free”
memory subsystem performance boost in the last generation with Infinity Cache, so for this time around, they
are back to needing to add more physical memory bandwidth to keep the ever-growing beast properly fed.
Meanwhile, the 7900 XT will be a chip off the block, with fewer CUs, less VRAM, and lower clockspeeds. All
told we’re looking at 84CUs paired with 20GB of 20Gbps GDDR6, and backed by an 80MB infinity cache. The
card’s game clockspeed rating is 2.0GHz, and we do not have any information on the boost clockspeed. The
combination of a 13% drop in clockspeeds and 13% drop in CUs adds up to what is, on paper, a 24% deficit
in compute/shading performance. That said, AMD’s pricing indicates that the real-world performance gap
shouldn’t be this high, and we’re still missing some important details such as ROP counts. So for better or
worse, we don’t have a good frame of reference fright now for how the 7900 XT will perform relative to
anything else, current-generation or last.
Gallery: AMD Radeon RX 7900 XT
Unsurprisingly, power consumption at the high end will be going up. The 7900 XTX will be a 355W card, up
20W from the 335W 6950 XT (and 55W from the 300W 6900 XT). This is a more modest power requirement
than on NVIDIA’s high-end RTX 4090 Ti (450W), but we’re still talking about a card well north of 300W. For
gamers with a slightly smaller appetite for large power bills, the 7900 XT will be holding the line at 300W. Both
cards will require 2 8-pin PCIe power connectors.
AMD has also sent over pictures of both the reference 7900 XTX and 7900 XT. Of particular note, both cards
will feature a USB-C port for display outputs. This is a feature that AMD introduced with the RX 6000 series
and has opted to carry forward into the RX 7000 series. As with the previous-gen cards, the presence of the
USB-C port is for directly hooking up monitors that rely on DisplayPort Alt Mode over USB-C. Meanwhile,
rounding out the collection will be a paid of DisplayPorts (2.1) and an HDMI 2.1 port.
Both cards are using a new triple fan blower design from AMD. We’re still waiting on further details here, but
AMD has told us that the 7900 XTX measures 287mm long, and is 2.5 slots wide.
Wrapping things up, both cards will be launching on December 13th, with AMD planning on having both
reference and AIB partners’ cards on the shelf for launch day. The 7900 XTX will start at $999, meanwhile the
7900 XT will be right behind it at $899. AMD isn’t offering any performance comparisons versus NVIDIA
cards, but at this juncture it seems like the wildcard is the soon-to-launch GeForce RTX 4080 16GB. By the
time AMD launches in December, we should have a much better idea of where AMD and NVIDIA’s dueling
lineups stand in comparison to each other.
Gallery: AMD RDNA 3 Launch Slide Deck
Like 84 Share Tweet PRINT THIS ARTICLE
158 Comments POST A COMMENT

View All Comments
Threska - Thursday, November 3, 2022 - link

The prices for both aren't out of line for what one gets.
REPLY
Kangal - Thursday, November 3, 2022 - link

I don't know, AMD is more likely to give consumers a fair price or discount. And with the launch of Nvidia's
cards already, they know what they're competing against both price-wise and performance.
I feel like the RX-7000 is going to be great, but it's not going to have as much uplift as the RTX-4000
series.
But we don't know everything, especially with the cryptomining mostly behind us. Who wins is a different
answer depending on your perspective.
REPLY
Khanan - Friday, November 4, 2022 - link

He meant both of the AMD GPUs not Nvidias. Lol. No Nvidias prices are insane and laughable
compared to this. I bet this will destroy the 4080 and that for 200$ less. Nvidia should quickly adjust
pricing on all their cards, and fix their broken power connectors that are just a train wreck. Even cables
burn, no adapter used.
REPLY
haukionkannel - Saturday, November 5, 2022 - link

Nvidia don´t have to reduce prices, because their GPU sell well enough even if they are much more
expensive!
I am sure that Nvidia will release 4080ti that is about the same speed as 7900XTX and cost
$200-$300 more (Nvidia tax) and reduce 4080 price to the same as 7900XTX and 4080 will sell more
than 7900XTX even it is slower, because it is Nvidia...
"Buy the real Nvidia at the same price as the imposter!" "The more you buy the more you save!"
Nvidia marketing will win also in this time, just look the sell numbers.
But it is good to the rest of us that AMD did make reasonable priced GPUs so we don´t have to buy
Nvidia gpus.
REPLY
Khanan - Saturday, November 5, 2022 - link

That’s your opinion and nothing more. The 4080 is certainly too expensive if it’s slower than
7900XTX and XT, so no, I don’t agree. Many people will share my opinion. Only the 4090 as a
halo product can be overpriced, the rest can not.
REPLY
Skiddywinks - Sunday, November 6, 2022 - link

The thing is the numbers play out this way. Whether you agree or disagree is irrelevant; nVidia
sell more cards even when they don't make as much sense.
This time it does seem like a more dramatic value advantage than in last year's, so clearly
AMD are hoping to really start their "Zen moment" for RDNA, and I think they will definitely
sway more of the market than usual. But at the end of the day, nVidia have a lot of (in my
opinion undeserved) mindshare. That's hard to compete with.
REPLY
meacupla - Monday, November 7, 2022 - link

AMD is getting their Zen moment for RDNA3 right now.
The performance is there, the drivers are mature, and the chiplet design is significantly cheaper
to produce than what nvidia is offering. There is an added benefit of AMD being power efficient,
which is looking like it will be a factor in some areas.
nvidia likely cannot lower prices all that much, if they keep using monolithic dies with the latest
and greatest process node from TSMC. nvidia doesn't have a chiplet design for at least 2
generations of cards, and this is likely going to tank them.
REPLY
Threska - Monday, November 7, 2022 - link

The enterprise market hasn't disappeared, and currently they dominate there. Plus all the
things you mentioned don't matter as much in those spaces. So no I don't think it will "tank
them" any more than AMDs mistakes back in the day "tanked them".
REPLY
Khanan - Thursday, November 10, 2022 - link

AMDs Zen Moment was already with RX 6000, as it brought parity to Nvidia. To be precise, it
was like their Zen 1 moment. A Zen 3 Moment still didn’t happen, as AMDs still not faster. RX
6000/7000 are at best comparable to Zen1, Zen 2 was already better than Intel in many
regards as it had way more cores, just not in purely gaming but fast enough. That is not
happening here. If anything, Radeon is like Zen 2 gaming wise while Instinct is very competitive
to Nvidia or faster, so all in all it’s not comparable to the CPU space. For me a true Zen
moment would be if they can surpass Nvidia, didn’t really happen unless you only care about
1080/1440p gaming.
REPLY
Khanan - Thursday, November 10, 2022 - link

As long as sheep are there, that are mindless and buy everything, yes. But sheep aren’t
shopping for 1200++ cards so you are wrong. 4080 might not be such a huge seller, it’s
overpriced as hell. 500$ extra over last Gen and a smaller chip not the biggest anymore.
REPLY
1 2 3 4 5 6 16 ▶
LINKS TOPICS FOLLOW

Home CPUs Displays Facebook
About Motherboards Mac
Forums SSD/HDD Systems Twitter
RSS GPUs Cloud
Pipeline News Mobile Trade Shows RSS
Bench Enterprise & IT Guides
Terms of Use Smartphones
Contact Us Memory
Accessibility Statement Cases/Cooling/PSU(s)
The Most Trusted in Tech Since 1997 About

Advertising
Privacy Policy
COPYRIGHT © 2022. ALL RIGHTS RESERVED.

AMD Reveals Radeon RX 7900 XTX and 7900 XT

Uploaded by

Copyright:

Available Formats

AMD Reveals Radeon RX 7900 XTX and 7900 XT

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

AMD Reveals Radeon RX 7900 XTX and 7900 XT

Uploaded by

Copyright:

Available Formats

11/12/22, 9:38 AM AMD Reveals Radeon RX 7900 XTX and 7900 XT: First RDNA 3 Parts To Hit Shelves

t RDNA 3 Parts To Hit Shelves in December

ABOUT BENCH FORUMS PODCAST

PC COMPONENTS ▼ SMARTPHONES & TABLETS ▼ SYSTEMS ▼ ENTERPRISE & IT GUIDES ▼ DEALS

Home > GPUs

AMD Reveals Radeon RX 7900 XTX and 7900 XT: 158

AT Deals: Acer Nitro 34-Inch

AT Deals: Dell 27-Inch 165 Hz IPS Now

Boost Clock 2.5GHz 2.4GHz 2310MHz 2250MHz gavbon86: @MatchroomBoxing @iam_yafai

back that bit about EFB. I can't say more

RyanSmithAT: @wassickt @phatal187

Gallery: Big Navi 3x GPU

Gallery: AMD Radeon RX 7900 XTX

Gallery: AMD Radeon RX 7900 XT

Gallery: AMD RDNA 3 Launch Slide Deck

Like 84 Share Tweet PRINT THIS ARTICLE

158 Comments POST A COMMENT

Threska - Thursday, November 3, 2022 - link

Kangal - Thursday, November 3, 2022 - link

Khanan - Friday, November 4, 2022 - link

haukionkannel - Saturday, November 5, 2022 - link

Khanan - Saturday, November 5, 2022 - link

Skiddywinks - Sunday, November 6, 2022 - link

meacupla - Monday, November 7, 2022 - link

Threska - Monday, November 7, 2022 - link

Khanan - Thursday, November 10, 2022 - link

Khanan - Thursday, November 10, 2022 - link

LINKS TOPICS FOLLOW

The Most Trusted in Tech Since 1997 About

COPYRIGHT © 2022. ALL RIGHTS RESERVED.

You might also like