Last week Nvidia lifted the curtain on the performance of their new flagship, the Blackwell-based RTX 5090 as well as giving people their first look at DLSS 4. Both Founders Edition and aftermarket versions of that card hit stores on Thursday, January 30th. Also announced with the RTX 5090 was the RTX 5080, which will be hitting stores on the 30th as well, and over the past week I have had the RTX 5080 Founders Edition in the office and have put it through our benchmark suite. Today we can take a closer look at the card design and then see how it performed in those tests. It has an MSRP that is half of the RTX 5090, will it still impress with its performance? Let’s find out!

Product Name: Nvidia RTX 5080 Founders Edition

Review Sample Provided by: Nvidia

Written by: Wes Compton

Amazon Affiliate Link: HERE

 

What is new?

Nvidia announced a lot with this one so let’s try to touch on as much as we can. They of course had a few hardware announcements for the 50-Series. They have announced four cards, the RTX 5090, the RTX 5080, the RTX 5070 Ti, and the RTX 5070. That is the new 50-series RTX family. The slides below include their focus on them. The 5090 for example is targeted at 4k 240 Hz and the other three are targeted at 2k or 1440p performance. They all have GDDR7 VRAM with the flagship RTX 5090 having 32 GB and a 512-bit interface. The RTX 5080 cuts that in half to 16 GB, the RTX 5070 Ti also has 16GB, and then the RTX 5070 has 12 GB.

nvidia 2

nvidia 3

nvidia 5

nvidia 6

nvidia 7

The new GPUs are based on the Blackwell architecture and they do have new updated RT and Tensor cores with that being the 4th gen for the RT Cores and 5th gen for Tensor cores. The new tensor cores can now also handle floating point (FP) 4 along with FP8 and FP16. They also have introduced an AMP processer which is the AI Management Processor to help schedule AI tasks alongside of graphics rendering. They have increased the number of NV encoders and decoders, it now depends on the card model and isn’t a flat number of them across the entire generation of cards. They have also moved to PCIe Gen 5 and DisplayPort 2.1b including UHBR20. For pricing the RTX 5090 comes in at $1999, the RTX 5090 is half that (just like its memory) at $999. The RTX 5070 Ti is $749 and the RTX 5070 is $549.

nvidia 8

nvidia 9

Some of the main goals with Blackwell were to optimize the neural workloads and reduce the memory footprint. No big surprises there. Memory is one of the more expensive parts of the cards and anyone who has been paying attention knows that neural workloads and AI have been where Nvidia has been seeing the biggest improvements. Combining those things they have brought AI into shaders with neural shaders. The example of this they show is a hair being rendered with ray tracing and how using spheres rather than triangles helps use less data which means less VRAM and higher frame rates.

nvidia 10

nvidia 11

nvidia 12

nvidia 13

nvidia 14

Nvidia announced Transformer which replaces CNN as the model they use with Super Resolution. They have improved the design significantly to get better detail when scaling this up. On top of that, they announced DLSS 4 which has improved on the frame generation that they introduced with DLSS 3. It is now Multi Frame Generation. Where before they were able to generate every other frame, they can now do x3 or x4. This gets interesting once they add in DLSS Super Resolution as well because that is already rendering ¾ of the image. With both, they are rendering 15 of 16 pixels using AI. Of course how well this works then depends a lot on how good the renders are. But it gives huge improvements in performance and with frame generation, we know that those improvements still happen even if you are PCU limited for example. The example they show has DLSS off at 27 FPS, turning on Super Resolution it goes to 71 FPS. DLSS 3.5 gets you to 140 FPS and DLSS 4 is 248 FPS. DLSS is already supported by a LOT of games and Nvidia is saying that DLSS 4 will have 75 games and apps supporting DLSS 4 at Day 0. Some of those will be by using the Nvidia App, which can override the DLSS settings on some games. It is also important to note that some of these features will go back and work with legacy cards as well. Specifically, DLAA is going to work back to the 20 series of cards, same with the improved DLSS Super Resolution. The new multi-frame generation however only works with 50 series cards.

nvidia 15

nvidia 16

nvidia 17

nvidia 18

nvidia 19

nvidia 20

nvidia 21

nvidia 22

They also introduced a new Nvidia Reflex. Reflex helps improve responsiveness to get lower latency through the entire pipeline. Were Reflex offered 50% faster responsiveness the new Reflex 2 gets you 75% by using frame warp. They say that is coming first to 50 series and will be available in games like Valorant soon.

nvidia 23

nvidia 24

nvidia 25

nvidia 26

Below I have the specifications for the RTX 5090 as well as the last two xx90 cards. We can see that the number of GPCs hasn’t changed from the 4090 to the 5090 but they did increase the SMs from 128 to 170. The CUDA core SM count is still the same but there are now 21760 CUDA cores to the previous 16384, a 32% increase. We still have 4 Tensor SMs but the new 5th gen design has 680 cores now. For clock speed, the RTX 5090 is set lower than the RTX 4090 with a clock speed of 2407 MHz. There are 32%more RT cores which is a 32$ increase but the RT FLOPS has jumped up 66% with the new RT design. The memory has increased from 24 GB up to 32GB and it now uses GDDR7. They have also increased the memory interface up to 512-bit from 384-bit which the 3090 and 4090 both had. The memory data rate has gone from 21 Gbps up to 28 Gbps and the bandwidth increased with that and the larger pipeline from 1008 GB/sec up to 1792 GB/sec a 77% increase. The cache has increased in side with the L1 cache going from 16384 KB up to 21760 KB and the L2 increasing as well from 73728 KB up to 98304 KB. The TGP also had a big jump going from 450 watts on the RTX 4090 to 575 watts here on the RTX 5090. This is an even bigger gap when you include the RTX 3090 which was 350 watts. The manufacturing process is still the TSMC 4nm 4N process so no changes there I mentioned it earlier but all of the 50 series cards moved to PCIe gen 5 and the RTX 5090 is no different. For pricing, it has an MSRP of $1999 which is $400 more than the RTX 4090 but is similar to the RTX 3090 Ti which also launched at $1999 back in 2022.

Specifications

RTX 3080

RTX 4080

RTX 5080

RTX 5090

GPU Codename

GA102

AD103

GB203

GB202

GPU Architecture

NVIDIA Ampere

NVIDIA Ada Lovelace

NVIDIA Blackwell

NVIDIA Blackwell

GPCs

6

7

7

11

TPCs

34

38

42

85

SMs

68

76

84

170

CUDA Cores / SM

128

128

128

128

CUDA Cores / GPU

8704

9728

10752

21760

Tensor Cores / SM

4 (3rd Gen)

4 (4th Gen)

4 (5th Gen)

4 (5th Gen)

Tensor Cores / GPU

272 (3rd Gen)

304 (4th Gen)

336 (5th Gen)

680 (5th Gen)

GPU Boost Clock (MHz)

1710

2505

2617

2407

RT Cores

80 (2nd Gen)

76 (3rd Gen)

84 (4th Gen)

170 (4th Gen)

RT TFLOPS

58.1

112.7

170.6

317.5

Frame Buffer Memory Size and Type

10 GB

GDDR6X

16 GB

GDDR6X

16 GB

GDDR7

32 GB

GDDR7

Memory Interface

320-bit

256-bit

256-bit

512-bit

Memory Clock

(Data Rate)

19 Gbps

22.4 Gbps

30 Gbps

28 Gbps

Memory Bandwidth

760 GB/sec

716.8 GB/sec

960 GB/sec

1792 GB/sec

ROPs

96

112

112

176

Pixel Fill-rate (Gigapixels/sec)

164.2

280.6

293.1

423.6

Texture Units

272

304

336

680

Texel Fill-rate (Gigatexels/sec)

465.12

761.5

879.3

1636.76

L1 Data Cache/Shared Memory

8704 KB

9708 KB

10752 KB

21760 KB

L2 Cache Size

5120 KB

65536 KB

65536 KB

98304 KB

Video Engines

1 x NVENC (7th Gen)

1 x NVDEC (5th Gen)

2 x NVENC (8th Gen)

1 x NVDEC (5th Gen)

2 x NVENC (9th Gen)

2 x NVDEC (6th Gen)

3 x NVENC (9th Gen)

2 x NVDEC (6th Gen)

TGP (Total Graphics Power)

320 W

320 W

360 W

575 W

Transistor Count

28.3 Billion

45.9 Billion

45.6 Billion

92.2 Billion

Die Size

628.4 mm2

378.6 mm2

378 mm2

750 mm2

Manufacturing Process

Samsung 8 nm 8N

NVIDIA Custom

Process

TSMC 4nm 4N

NVIDIA Custom

Process

TSMC 4nm 4N

NVIDIA Custom

Process

TSMC 4nm 4N

NVIDIA Custom

Process

PCI Express Interface

Gen 4

Gen 4

Gen 5

Gen 5

Launch MSRP

$699

$1199

$999

$1999

 

Above I have a more in-depth specification listing for the RTX 5080 along with the RTX 5090 and the two previous generations of xx80 cards with the RTX 3080 and RTX 4080. The RTX 5080 is running on the GB203 GPU, not the same GPU as the 5090. It has 7 GPCs which matches the previous model (the 4080) but it does have mode TPCs with 42 over 38 and SMs with 84 over 76 but those are both significantly lower than on the RTX 5090 which had more than twice that. That can be seen as well with the CUDA cores which are at 10752 a 10.5% increase from the 4080. I was curious, the 4080 was 11.7% over the 3080 so it isn’t completely out of line from generation to generation but it is down slightly. The 5080 has the highest clock speed of the four cards at 2617 MHz. For memory, it has 16GB of GDDR7 with a clock speed of 30 Gbps, which is the same capacity as the 4080 which had 16GB as well but it did step up from GDDR6X to 7 and the clock speed was increased by 34%. It has the same 256-bit memory interface that the 4080 had but is a step down from the 320-bit on the 3080. Overall memory bandwidth has increased from 760 GB/s on the 3080 and 716 on the 4080 up to 960 GB/s. The pixel fill rate was just a small improvement from the 4080 at 4.4% but the texel fill rate is better at 15.4%. The 5080 has a little more L1 cache but is the same on the L2 cache which both look small when compared to the RTX 5090. They have also added more video engines. The RTX 5080 has 2 NVENC and 2 NVDEC engines which is one more NVDEC compared to the 4080 and one of each compared to the 3080. They are also newer versions with the NVENC being 9th gen and NVDEC being 6th gen, one step up on both compared to the 4080. For power the RTX 5080 does have a higher TGP, both the 3080 and 4080 were 320 Watts, and the 5080 is 40 watts higher at 360 watts. The 5080 and 4080 are extremely similar in both die size and transistor count with the 5080 being just slightly lower on both which is interesting. Especially given that it is made on the same manufacturing node. The RTX 5080 uses PCIe Gen 5 just like the RTX 5090. For launch pricing the MSRP has bounced around a few times here. The RTX 3080 launched at $699 and the RTX 4080 launched at $1199. The RTX 5080 is in the middle at $999 which like I said in the opening is half the price of the RT 5090.

Before getting into testing I did also run GPUz to double-check that our clock speeds matched up with the specifications. The RTX 5080 Founders Edition was running with a 2617 MHz boost clock speed and that lines up with the stock clock speed of the RTX 5080. Beyond that the driver and BIOS version are noted for future reference, I tested the 5080 Founders Editon using the Nvidia 572.02 driver. That is a beta driver that was provided to the press ahead of the launch for testing.

image 41

 

Log in to comment

We have 866 guests and one member online

supportus