RTX 4090 has been released, and various non-public version products have also met you. Today, we are bringing the AORUS GeForce RTX 4090 MASTER brought by the veteran graphics card manufacturer Gigabyte . It is a representative product with outstanding workmanship and heat dissipation in non-public version graphics cards.
Although the supply of RTX 40 series has not been completely stabilized, players' purchasing enthusiasm will slowly calm down over time, and gradually transition from the purchasing idea of "whoever has the goods to whom" to "whoever is better to buy whoever". And this returns to the field that non-public graphics cards are best at.
Gigabyte graphics card is divided into many series such as Falcon, Magic Eagle, Small Eagle, Big Eagle, Super Eagle, Water Eagle, etc. The one we reviewed this time is Super Eagle, which belongs to the flagship series.
As the first GeForce RTX 4090 graphics card released by the RTX 40 series, the biggest feature is the 24GB super large video memory. In fact, according to previous rules, the "90" level graphics card belongs to the TITAN series and is more of a productivity tool.
However, NVIDIA in the RTX 40 series made it "head" and focused on its gaming performance, so this time we will also focus on the related test of DLSS 3. First, let's take a look at the appearance of the product.
1 AORUS GeForce RTX 4090 MASTER Overview
Friends who are familiar with Gigabyte know that each generation of Super Sculpture series graphics cards focuses on both cooling and light effects, and this generation is no exception.
AORUS GeForce RTX 4090 MASTER adopts a gray and black appearance design. The three surface technology designs are used only on the front of the graphics card, including matte, lines, and cutting texture. The centers of the three fans use the English name and graphic LOGO appearance of AORUS respectively. In terms of
size, this generation's super sculpture also made another breakthrough, reaching 358.5×162.8×75.1mm. Such a graphics card cannot be controlled by even a smaller hand.
AORUS GeForce RTX 4090 MASTER adopts a new generation of wind power cooling system design. The front of the graphics card is equipped with three 110mm diameter bionic shark fans. The new bionic shark fans have a texture design like the shield scales on the surface of the fan blade, achieving a 3dB noise drop and a 30% wind pressure increase.
The left and right sides rotate clockwise, while the fan in the middle uses counterclockwise rotation, which avoids the eddy currents between the three fans interfering with each other and increases the air intake. All fans support 3D start-stop technology, which does not rotate or slow down at low loads for lower noise performance.
On the internal cooling module, the AORUS GeForce RTX 4090 MASTER uses a 140.4x122mm heat-smoothing plate that directly touches the GPU and video memory, and is combined with 13 composite heat pipes, and provides higher heat dissipation efficiency with the cooling fan , allowing the core and video memory to maintain stable performance output under overclocking. The word "AORUS" in the upper right corner of the
graphics card adopts an RGB luminous design. The classic three-ring lighting effect is retained around the three fans. The GIGABY TECONTROL CENTER (GCC) can achieve rich lighting effect control and can also achieve light effect synchronization with other devices.
Below the fan in the middle, Gigabyte also brings a set of RGB effects with "colorful light wheels" that can have a brilliant visual effect when viewed at different angles, which is very personalized. The back of
AORUS GeForce RTX 4090 MASTER also uses brushed and matte processes. The silver metal brushed and gray matte design are integrated, and the effect is very cool with the "AORUS" brand mark that can be luminous in the center. On the right side of the back panel is a hollow scale cooling window, which cooperates with the front cooling fan to form a smooth and efficient cooling channel.
AORUS GeForce RTX 4090 MASTER Although it adopts a standard dual-slot design, it provides three DP1.4 and 1 HDMI2.1 display output interface. According to NVIDIA's requirements, the radiator of this generation of RTX 4090 graphics cards has become larger and needs to occupy about 4 PCIE slots, so users of small chassis should pay attention. As for the DP2.0, which is highly popular, most consumer-grade gaming monitors are not currently installed, and the DP1.4a standard can also support 8K60Hz refresh rate monitors. So, overall, it is definitely enough.
metal back plate extends to the top of graphics card , further improving the structural strength of the graphics card.
AORUS GeForce RTX 4090 MASTER retains a personalized LCD screen. Users can customize the display content on this screen, which can not only display the temperature of the graphics card, but also upload GIF animations and other contents by themselves.
AORUS GeForce RTX 4090 MASTER also uses a new 16pin power supply interface, and provides a power status indicator on the PCB board. It will light up when there is a problem with the power supply of the graphics card to prompt the cause of the failure. The official suggests that the power supply is 1000W, which is basically the same as other RTX4090 graphics cards. High-power power supply is definitely inevitable for users who have installed this year.
Some power supply manufacturers have released the latest ATX3.0 standard high-end power supply, with its own 16pin power supply interface of 12VHPWR, and a single port can support up to 600W of power supply. So if nothing unexpected happens, perhaps the next generation of graphics cards will also use such a single 16pin to power it. It should also be noted that the 12pin interface and power adapter currently suitable for the RTX30 series are incompatible with the RTX40 series graphics cards.
AORUS GeForce RTX 4090 MASTER provides dual BIOS options, and users can switch between silent mode and OC mode by themselves. In terms of
accessories, in addition to the necessary 16pin power adapter cable, Gigabyte also brings the official graphics card holder installation kit and screws, so there is no need to buy third-party brand stands.
2 Who is Ada Lovelace?
Let’s take a look at the launch of the NVIDIA Ada Lovelace architecture. Let’s start with Ada Lovelace. Compared to Ampere, this person seems to be more unfamiliar with everyone.
Ada Lovelace (1815-1852) is a British mathematician and founder of computer programs. He established the concept of loop and subroutine . is known as the world's first programmer .
Ada has had a very high talent in mathematics since childhood. Her father called her the "parallelogram princess", and her later partner Charles Babbage called her the "digital witch". At the age of 19, Ada married her former science tutor, and after marriage, she remained enthusiastic about mathematics.
From 1842 to 1843, it took 9 months to translate Babbage's "Introduction to Analysis Machines" and wrote many notes, which gave a detailed explanation of using a computer to solve the Bernoulli number. Therefore, Ada is widely regarded as the world's first programmer.
The language named after her - ada language has become the language used by the US military to develop cutting-edge weapons such as fighter jets.
From a few lines of short life introduction, it is not difficult to see that although Ada's life has only experienced 37 short springs and autumns, it is enough to be remembered by future generations.
This is why the slogan "respecting legends with the future" was used in the premier publicity of NVIDIA RTX 40. Let's analyze in detail what innovations and transcendences there are in this Ada Lovelace.
3 NVIDIA Ada Lovelace architecture
The GeForce RTX 40 series graphics card released this time is built by the brand new NVIDIA Ada Lovelace architecture, using TSMC 4nm customization process (TSMC 4nm NVIDIA Custom Process). The flagship core AD102 has reached a terrifying 76 billion transistors, while 28 billion in RTX 30 series graphics cards.
Compared with the previous generation NVIDIA Ampere, NVIDIA Ada Lovelace has more than 2 times the performance improvement at the same power. The shader data throughput can reach the maximum 90-TFLOPS, while the GeForce RTX 4090 released this time reaches 83-TFLOPs, compared with the previous generation of NVIDIA Ampere, it only has 40-TFOPs.
The complete AD102 core has 18432 CUDA, including 12 graphics processing clusters (GPCs), 72 texture processing clusters (TPCs), and 144 streaming multiprocessors (SMs). 144 third-generation ray tracing cores (RT cores), and 576 fourth-generation tensor cores (Tensor Cores). In addition, we can see that the Boost frequency has also increased from 1.9GHz to 2.5GHz.
Another point that is not reflected in the architecture diagram is that the AD102 core also contains 288 FP64 double-precision floating-point cores (2 per SM), which are used to ensure that the FP64 code is correctly processed, including the FP64 tensor core code.
Generally speaking, single-precision floating-point operation will be used for deep learning model training, while double-precision floating-point operation is used for numerical simulation work. Usually, the game card will cut off FP64, which not only saves costs but also has no impact on the game itself. Professional cards retain FP64 for higher accuracy training and calculation.
This information only mentioned that the AD102 core is equipped with 288 FP64s, and it is not known whether there will be any changes in the subsequent products launched.
has learned about the complete GA102 core. Let’s take a look at the core of RTX 4090. In fact, if we know the parameters of RTX 4090, we can probably understand what the difference is in the "Ti" series that may be launched in the future.
Compared with the complete GA102, RTX 4090 has 16384 CUDA, including 11 GPCs, 64 TPCs and 128 SM units, 128 third-generation RT Cores, and 512 fourth-generation Tensor Cores.
can actually be seen from the complete architecture diagram that the overall structural changes of the Ada architecture this time are not much, which can be clearly confirmed from the SM unit, the same FP32 CUDA core, the same FP32/INT32 hybrid CUDA core, the same L1 level cache, etc. Of course, the Tensor Core inside each SM cell is upgraded to the fourth generation. However, the most significant change is the third generation ray tracing core. We look at it in combination with the two generations of architectures. In the second generation of ray tracing core, the Box Intersection Engine engine is responsible for boundary cross-testing, and the Triangle Intersection Engine engine is responsible for triangle cross-testing.
. In the third generation of ray tracing core, two new engines have been added: Opacity Micro-Map Engines (OMM) and Displaced Micro-Mesh Engines (DMM). These two new hardware units can greatly improve ray tracing performance (specific principles are introduced in detail later).
At this point, every 2 SM units form a TPC unit, and every 6 groups of TPC units form a complete GPC top-level unit (in some cores, 5 groups of TPCs form a GPC unit).
, and each GPC unit is equipped with an independent raster engine and two sets of ROP partitions (each group contains 8 ROP units). The too many
will not be introduced. After all, the overall aspect of the architecture diagram is basically the same as the NVIDIA Ampere architecture. Let’s take a look at what other upgrades are besides the performance Ada architecture.
Shader Execution Reordering (SER) Shader performs reordering
SER's main function is to improve the performance of the shader, which can dynamically reorganize inefficient workloads into more efficient workloads. The performance improvements mainly for ray tracing are very large.
Simply put, GPU is most efficient when performing similar work. But as the ray tracing effect becomes more and more powerful, millions of light may shine on different materials in each scene, and we know that the reflectivity of and of different materials are also different. So this creates a large number of divergent, inefficient workloads for the shader.
SER can reclassify these messy instructions and dynamically reorganize them into more efficient workloads. According to NVIDIA, SER can improve shader performance up to 2 times and increase the game frame rate up to 25%.
To give a simple example, when the light is a very regular ray from the first time from the emission end to the collision end, and the secondary ray tracing after collision with the object will appear, a large number of divergent and irregular reflections will occur, which is very high for the ray tracing load. As you can see from the figure, SER can sort these instructions in a quadratic order to maximize the performance of the shader.
Fortunately, such practical functions are not patented by the RTX 40 series. It is an easy-to-integrate SDK and currently requires game developers to integrate into the game. In addition, since it is a general logic, it is possible to directly integrate into the Windows API in the future, so that game developers can directly call the system API without special references.
It can be said that SER is a great blessing for N-card users who hold RTX 20 series and above (can enable ray tracing). After all, who doesn’t like the free-to-improve ray tracing performance?
The third generation RT Cores
RT Core lies in faster ray tracing computing power. If it is a bit difficult to enjoy 4K high frame rate games in RTX 30 series graphics cards, then it will be easy in RTX 40 series graphics cards.
has achieved 191 RT-TFLOPs processing power on the GeForce RTX 4090 graphics card, while the fastest processing power of the RTX 30 series graphics card is 78 RT-TFLOPs, which is 2.4 times. And according to NVIDIA's official statement, the peak RT-TFLOPs of the third-generation RT Core is 2.8 times higher than the previous generation. This can only show that this 4090 is not the final form of the Ada Lovelace architecture.
Opacity Micro-Map Engines (OMM)
has introduced two important hardware units in the third generation RT Cores. The first is Opacity Micro-Map Engines, which can be understood as a micromap transparency engine. Its main function is to optimize ray tracing rendering and can greatly reduce the work burden of shaders.
For complex objects such as leaves, different rays will affect their performance status and the rebound of light between leaves, so the calculation amount of ray tracing is huge.
However, Opacity Micro-Map Engines can bake ray tracing features into opaque masks, so those irregularly shaped and translucent objects can be rendered faster and more accurately, greatly reducing the work burden of the shader.
Displaced Micro-Mesh Engines (DMM)
Displaced Micro-Mesh Engines can be understood as a micro-mesh replacement engine. It can build ray tracing BVH (Bounding volume hierarchy) by 10 times faster! The video memory used has been reduced by 20 times!
DMM is processed locally by the third generation RT core, and compared to previous generations, it only uses basic triangles to render complex geometry, greatly reducing storage and processing needs. The specific working principle of
is clear from the figure. The new DMM can simplify complex graphics with a very large number of faces and create a simple model, but the overall ray tracing effect remains unchanged.
Through some model data, we can see in detail how much the new DMM simplifies the model. The original model of 11 million triangle facets has only about 150,000 microgrids after simplification, and the construction speed of BVH has been increased by 8.5 times and 6.5 times smaller.
, and this is not the most exaggerated. The more complex the model is, the better the optimization effect. In these sets of comparison examples shown by the official, the fastest speed can be improved by more than 15 times and the capacity is simplified by 20 times.
Fourth Generation Tensor Cores
In addition to the upgrade of ray tracing units, the upgrade of the fourth generation tensor core is even more terrifying. It uses the new FP8 tensor engine, and the throughput reaches 1.32 Tensor petaFLOPs on the GeForce RTX 4090 graphics card, a 5-fold increase.
Note the unit here - petaFLOPs. Previously, TFLOPs were trillions of floating-point operations, while petaFLOPs were tens of trillions of floating-point operations.
DLSS 3 Neural Network Rendering New Era
The DLSS 3 launched this time is also a major selling point of the RTX 40 series. From DLSS 2.3 to directly enter the 3.0 version, we can also see how great the upgrade this time is. DLSS 3 is also officially called the new era of neural network rendering by NVIDIA.
The new DLSS 3 has added optical multi-frame generation technology to generate brand new frames, unlike the original DLSS super resolution.
DLSS 3 combines three major technologies: DLSS super resolution, DLSS frame generation and NVIDIA Reflex, which can rebuild seven-eighth of pixels and greatly improve performance.
In games with GPU restricted, such as 2K resolution and above, DLSS 2 can increase the frame rate by 2 times, and DLSS 3 can increase the frame rate by 4 times.
This time, DLSS 3 spans a large version, and has been upgraded again in terms of ideas and principles. The technology of "guessing" 1 frame is simple to explain, but it requires a lot of reasoning and calculations to implement, as well as absolutely advanced ideas.
is not the 1 frame generated "out of thin air", which is definitely higher in latency than DLSS 2. So in this complete DLSS 3, NVIDIA Reflex is bundled with, which can effectively help reduce latency.
This does not disappoint NVIDIA, which gave it the name of "a new era of neural network rendering".Looking at the XeSS and FSR technologies currently on the market, DLSS can definitely be called "the shoulders of giants". Of course, the hardest thing for years of innovation is that players who hold the previous generation of graphics cards want to experience the frame generation of DLSS 3. The only way at present is to buy an RTX 40 series graphics card.
New Optical Flow Accelerator
New Optical Flow Accelerator optical flow accelerator is the latest introduction in the fourth generation of Tensor Cores, which is why frame generation in DLSS 3 is exclusive to RTX 40 series graphics cards. Based on the original DLSS 2, the
optical flow accelerator can also calculate the optical flow field within two consecutive frames, which can capture the direction and speed of the game screen from the first frame to the second frame, and capture pixel information such as particles, reflections and lights from it. The motion vector and optical flow are calculated separately to obtain accurate shadow reconstruction effect.
Take "Cyberpunk 2077" as an example. In the first frame, the optical flow accelerator will capture information such as particles, reflections and light in each pixel. And find the matching pixel area in the second frame and calculate the difference between the frames.
If DLSS 2 can "guess" the remaining pixels in a picture, then DLSS 3 can also "guess" the picture of the next frame in addition to these.
In addition, since the frame generation of DLSS 3 is processed and run in the GPU, even if the game encounters the CPU bottleneck, AI can also increase the frame rate. This is why it is said in this press conference that DLSS 3 can break through the CPU limit to increase frame count.
Dual AV1 Encoder
The eighth generation NVENC encoder upgraded this time can be said to be a great blessing for live broadcast, video, and post-production workers. It has added support for AV1 encoding for the first time, and the most obvious effect is live broadcast. Compared with traditional H.264 encoding, the AV1 encoding efficiency has been improved by 40% on average, and the AV1 encoding quality will be better at the same code rate. Currently, the resolution and clarity of most live broadcasts are limited by the maximum bit rate specified by the platform. Taking the 8Mbps limited by Twitch as an example, you can see that under the same bandwidth, the picture with the same 2K 60 frames, the clarity of AV1 encoding is significantly higher than that of H.264.
Speaking of live broadcast, I believe everyone is familiar with OBS. In the upcoming patch in October, OBS added the AV1 encoding support for NVENC for
. Of course, live broadcast is just an advantage of AV1 that is easier for us to see. In all aspects of video work, AV1 encoding can bring great improvements.
So, as seen in the figure. NVIDIA has laid a complete ecosystem for the majority of users, from encoding API, software, platform to players, it will fully support AV1 encoding.
Also, let’s talk about the dual AV1 encoding that NVIDIA has always emphasized. As the name suggests, some graphics cards are equipped with two encoders, and the effects it brings are also obvious.
First of all, according to the official promotion, RTX 4090 is 2.2 times that of RTX 3090 Ti in terms of export speed of 4K H.265; 2.5 times the export speed of 8K H.265. The improvements in this part are also applicable to the cut-and-image , which everyone uses. Interested users may wish to experience it for themselves.
In addition to the export speed, recording of 8K 60 frames of video was unimaginable in the past. The advantage of a dual encoder is that it can divide the image into two, and the two encoders process the image information of 7680×2160 respectively, and finally put it intact.
The encoding part may not be deeply felt by most users, but when one day you want to record the screen, you find that the graphics card does not support it, and you will realize its importance...
As images gradually enter the era of ultra-clear, hardware encoding and rendering have almost become an indispensable helper. Although hardware encoding is still not as good as CPU soft programming in terms of quality, soft programming has to endure infinite time for the ultimate picture quality.
Even in an 8K rendering, the time gap between the two encoding methods has reached several hours, let alone a 10-second CG animation. In the ever-advanced hardware encoding, quality and time are constantly being challenged and refreshed.
4 Introduction to the test platform
First, let’s introduce the test platform. In order to ensure the performance of AORUSGeForce RTX 4090 MASTER, our platform has also been fully updated again.
However, since there is no flagship processor on hand, it uses 12th generation mid-to-high-end products, and has focused on upgrading the power supply, using the Asus ROG Thor 2nd generation 1600W titanium gold-class full-module power supply.
First look at the parameters of GPU-Z. AORUS GeForce RTX 4090 MASTER uses AD102 core and TSMC 4nm custom process (TSMC4 nm NVIDIA Custom Process). The chip area is 608 square millimeter , which is smaller than the 628 square millimeters of GA102 of the RTX30 series.
has 16384 CUDA, which is 52% more than the RTX3090 Ti's 10752, and the Boost frequency reaches 2550MHz, which is a slight increase compared to the public version's 2520MHz.
uses 24GB GDDR6X Micron video memory, with a bit width of 384bit, video memory bandwidth reaches 1008.4GB/s, and raster units and texture units are 176 and 512.
5 Theoretical Performance Test
The following is a 3DMARKFS set used to measure the theoretical performance of graphics card DX11. The performance performance of DX11 can be referenced for many popular 3A masterpieces in the past: FS, FSE, and FSU correspond to the theoretical performance of graphics cards in 1080P, 2K, and 4K respectively. The actual test results are as follows:
In the 3DMARKFS set test for graphics card DX11 performance, AORUS GeForce RTX 4090 MASTER The improvement is amazing. You can see that the higher the resolution, the greater the improvement of this graphics card, among which FS is increased by 63%; FSE is increased by 76%; FSU is increased by 80%.
Overall, in the test of the entire FS package, the AORUS GeForce RTX 4090 MASTER has an improvement of about 73% compared to the GeForceRTX 3090 Ti. Compared with the other 4090 we have tested before, the AORUS GeForce RTX 4090 MASTER is also a lot ahead of the performance of the AORUS GeForce RTX 4090 MASTER.
In the TimeSpy and TimeSpy Extreme tests in DX12 environment, the improvements of AORUS GeForce RTX 4090 MASTER compared to GeForce RTX 3090 Ti are: TS increases by 68%; TSE increases by 74%, and the combined is about 71%. As the most mainstream graphics protocol at present, DX12's performance is of great significance to reference for various new games. The performance of AORUS GeForce RTX 4090 MASTER lives up to expectations, and the improvement over the RTX3090Ti is huge.
PortRoyal is a test item specifically for ray tracing performance in DMARK. The AORUS GeForce RTX 4090 MASTER has an increase of about 79% compared to GeForce RTX 3090 Ti. Overall, the theoretical performance of AORUS GeForce RTX 4090 MASTER is about 74% higher than that of GeForce RTX 3090 Ti.
NVIDIA's ray tracing unit has evolved twice to the 40 series generation, each bringing a complete surprise to people. The improvement of AORUS GeForce RTX 4090 MASTER compared to the previous generation can be regarded as a qualitative change.
Speed Way test is a graphics card benchmark for testing DirectX 12 Ultimate performance by 3DMARK. To run this test, the graphics card must support DirectX 12 Ultimate and include 6GB and above video memory.
This test combines real-time ray tracing and traditional rendering techniques to measure graphics card performance. The scene contains ray tracing reflection, real-time global lighting, grid shaders, volumetric lighting, particles and post-processing effects. And interestingly, the Speed Way test supports free exploration of scenes, allowing you to see how changes in lighting and camera settings affect the visual effect.
Speed Way test defaults to 2K resolution, and can be manually adjusted to 1080p or 4K resolution. Since this test item has just been launched, we will gradually enrich the data on comparing graphics cards in the future.
AORUSGeForce RTX 4090 MASTER DLSS 3 4K
In this test, we used the beta version of 3DMARK to conduct relevant tests on DLSS3. At 4K resolution, DLSS off is 57.62 frames, and DLSS3 is 171.34 frames after it is turned on.
RTX3090 Ti DLSS 2 4K
In addition, we also tested the results of GeForce RTX 3090 Ti under this program, where DLSS off is 32.73 frames. Since DLSS3 is not supported, the results under DLSS2 are 83.63 frames.
AORUS GeForce RTX 4090 MASTER After turning on DLSS3, the increase in 199% compared to shutdown; while GeForce RTX 3090 Ti is 155% compared to shutdown after turning on DLSS2. Whether it is compared with DLSS off or with the previous generation of RTX 3090Ti on DLSS2, the AORUS GeForce RTX 4090 MASTER has a very exaggerated performance improvement.
But the most incredible thing about DLSS3 is more than just the numbers. Let’s take a look at this picture again.
AORUS GeForce RTX 4090 MASTER DLSS 3 8K
In the DLSS3 test at 8K (7680x4320) resolution, the AORUS GeForce RTX 4090 MASTER had only 13.31 frames with DLSS off, and the game could no longer run normally. After turning on DLSS3, it reached a smooth level of 92.80, an increase of 597%!
This data directly proves that AORUS GeForce RTX 4090 MASTER has the ability to have close contact with 8K games. Some manufacturers have launched 8K resolution display devices, and AORUS GeForce RTX 4090 MASTER can bring the most extreme game images to these users.
6 Regular game performance test
Since the RTX 40 series has added new DLSS3 technology, it will be tested separately later. Here we still choose several mainstream 3A masterpieces for game performance comparison.
First of all, it can be seen in "Horizon 5" that not only at 1080p resolution, but even at 2K resolution, the situation of restricted CPUs is still obvious. As a standard 3A game, it can still run to 147 frames at 4K resolution, which was absolutely unimaginable before.
For racing games like "Horizon 5", which focuses on real-life graphics, AORUS GeForce RTX 4090 MASTER brings not only faster frame rates, but at 4K resolution, each frame embodies the efforts of the production team. "Game Photographers" can capture clearer light and shadow through AORUSGeForce RTX 4090 MASTER, and enjoy driving more easily in the game. In terms of performance of
, the improvements of AORUS GeForce RTX 4090 MASTER compared to GeForce RTX 3090 Ti are: 52% increase in 1080p; 55% increase in 2K; 73% increase in 4K, and 60% overall increase.
In the "Assassin's Creed: Valhalla", which was once called "Equality of All" (AORUS GeForce RTX 4090 MASTER), compared with GeForce RTX 3090Ti, the improvement of AORUS GeForce RTX 3090Ti is: 1080p is increased by 59%; 2K is increased by 73%; 4K is increased by 63%, and the overall increase is increased by 65%. For Valhalla, the fps improvement of each frame is very rare, and the AORUS GeForce RTX 4090 MASTER achieved an ultra-high frame rate of 117 at 4K resolution, giving the 4K120Hz monitor finally a place to work in this game.
In "Borderlands 3", the improvements of AORUS GeForce RTX 4090 MASTER compared to GeForceRTX 3090 Ti are: 1080p increase by 62%; 2K increase by 64%; 4K increase by 66%, and 64% comprehensive increase.
"Music of Light: Infinity"'s ray tracing testing software is a game-independent testing tool, with more ray tracing technology used in the game, and the test conditions are "RTX highest/DLSS quality". Therefore, the test frame rate is relatively low, but the actual game configuration is quite affordable. As one of the oldest ray tracing performance testing tools, "My Memory of Light: Infinity" has accompanied our three generations of graphics cards. From the initial 20 series that can be basically used, to now, 78fps at 1080P, 218fps at 149fps and 4K resolutions, we can see the super strength of AORUS GeForce RTX 4090 MASTER. In terms of performance of
, the improvements of AORUS GeForce RTX 4090 MASTER compared to GeForce RTX 3090 Ti are: 1080p increase of 74%; 2K increase of 80%; 4K increase of 73%, and comprehensive increase of 76%.
is basically the same as in the running score software of another domestic game "Border", and the test conditions are all conducted under "RTX highest/DLSS quality".
In "Border", the improvements of AORUS GeForce RTX 4090 MASTER compared to GeForce RTX 3090 Ti are: 1080p increase by 82%; 2K increase by 89%; 4K increase by 85%, and comprehensive increase by 85%.
Overall, the ray tracing performance of AORUS GeForce RTX 4090 MASTER has a qualitative leap compared to the previous generation of graphics cards, basically ensuring smooth operation at 4K resolution.
7 DLSS3 Performance Test
Due to the launch of this new technology DLSS3, 35 games will launch new DLSS3 functions in the near future. We have also obtained beta versions of some games this time.
In addition, "Super Human", "Life and Death Reincarnation", "Fu Yunting", "Microsoft Flight Simulation", and "Plague Legend: Requiem" will release versions that support DLSS3 in October.
Among them, "Cyberpunk 2077", "F122", "Plague Legend: Requiem", "Microsoft Flight Simulation", and "Against the Cold" conducted DLSS3 tests. In addition, Unity and Unreal Engine also provided this test program.
The DLSS3 test chart is quite cumbersome, and 1%Low FPS and delayed tests are added. Ordinary FPS is easy to understand, so what does this 1%Low FPS mean?
First of all, the FPS that game Benchmark usually tests is the average game frames over a period of time. 1%Low FPS arranges the frame counts over a period of time from large to small, takes the smallest 1%, and then averages the 1% number.
In fact, simply put, neither of these two values can represent our specific feelings at which moment when we are playing, but FPS pays more attention to the overall situation, while 1%Low FPS is to average from the worst and be more cautious.
understands 1%LowFPS, let's look at this chart again. The one on the left side of the coordinate axis is delay (lower, better), and the one on the right side of the coordinate axis is frame count (higher, better). Since positive and negative coordinates are involved, the values on both sides may be different. The test result in
Frameview is three decimal places. For the sake of viewing, the frame number is rounded here, and the delay is reserved for one decimal places.
In Microsoft Flight Simulation, the scores are almost unchanged when DLSS2 is turned on and off. This game is a game that consumes extremely CPU resources. If the bottleneck is stuck on the processor, then traditional DLSS2 does not really provide more frame rate bonus.
. In DLSS3, we can clearly see a significant increase in frame count. You should know that all our DLSS3 tests are performed at 4K resolution.
However, frame generation is not without disadvantages, which is why this test has added delays. And after turning on DLSS3, NVIDIAReflex is bundled and enabled. However, compared with the increased delay of DLSS2, the experience is not strong in actual experience. The data reflection of
in "Cyberpunk 2077" is relatively real. It can be seen that with the highest ray tracing with DLSS, even the AORUS GeForce RTX 4090 MASTER graphics card has only 38 frames, and the delay reaches 52.5 milliseconds.
, and after turning on DLSS3, the number of frames is 137, an increase of 261%. Although the latency is about 9.5 milliseconds higher than DLSS2, it remains at a lower level compared to turning off DLSS.
"Plague Legend: Requiem" is an upcoming game, with the increase in frame count between DLSS3 and DLSS levels, also reaching 129%. However, in this game, the delay of DLSS3 has increased by 21.5ms compared to DLSS2, but it is still lower than when the DLSS is turned off.
Currently, there are also problems with the data testing of "F122", and there is no delayed data in both DLSS levels and DLSS2. The
group mainly depends on the increase in frame count. Among them, DLSS3 has increased by 143% compared to DLSS, and has increased by 22% compared to DLSS2.
finally is the ray tracing test of the domestic game "Against the Cold". The test demo we selected this time uses real global lighting.
After trying to turn off DLSS running, the number of frames is only single digits, and the delay is already tens of thousands. I still remember that "Infinite Memory of Light" and "Border" tested in pure ray tracing software can reach about 80 frames if there is only DLSS2 this time. The real global lighting of "Against the Cold" has only about 48 frames after DLSS2 is turned on, which is really terrifying. However, with DLSS3 enabled, the 4K resolution has reached 80 frames, which can already ensure a basic gaming experience. In terms of
picture quality, in the above picture we intercepted a role in "Cyberpunk 2077". We can see that in the two DLSS modes, there is almost no obvious change in the original picture quality compared to the original picture quality, and the light and shadow effects are different only at the fence, but for such a large frame rate increase, this flaw is almost negligible.
RTX3090 Ti real-time frame count 39 frames
AORUS GeForce RTX 4090 MASTER real-time frame count 99 frames
In Unity's test program, there is a set of real-time calculations of ray tracing + DLSS frame count comparison. After the AORUSGeForce RTX 4090 MASTER is turned on, the real-time frame count is 99; when the GeForceRTX 3090 Ti is turned on, the real-time frame count is 39 frames, which is about 154%.
DLSS Off 80 frames
DLSS2 155 frames
DLSS3 190 frames
In the test game provided by UE5, a quick test of DLSS is conveniently given. Here it is divided into three tests: DLSS Off (super resolution Off + frame generation Off + Reflex Off); DLSS2 (super resolution Performance + frame generation Off + Reflex On); DLSS3 (super resolution Performance + frame generation Off + Reflex On);
where, the number of real-time frames of AORUS GeForce RTX 4090 MASTER in DLSS is 80 frames, DLSS2 is 155 frames, and DLSS3 is 190 frames. However, the DLSS3 delay of this test in UE5 is 49.44ms, while DLSS2 is 17.18ms, which is relatively high.
Overall, the performance improvement of AORUS GeForce RTX 4090 MASTER after turning on DLSS3 is very obvious. The maximum picture fluency improvement of more than 3 times is enough to make the AORUS GeForce RTX 4090 MASTER, a graphics card that copes with large-scale 3A games now and in the next few years.
8 Professional software test
As a "90" level graphics card, it has 24GB of super large video memory, and applications in the field of content creators are indispensable. We use SPECviewperf13, an industrial and professional software to run scores.
comparison graphics cards are AORUS GeForce RTX 4090 MASTER graphics cards, the previous generation flagship GeForce RTX 3090 Ti graphics cards, and the previous generation flagship GeForce RTX 3080 Ti graphics cards.
In the software test of SPECviewperf13, each professional software has different levels of performance improvement. Among them, SW is 36% higher than RTX3090Ti, MAYA is 42% higher than RTX3090Ti, CREO is 42% higher than RTX3090Ti, CATIA is 54% higher than RTX3090Ti, and 3DSMAX is 55% higher than RTX3090Ti.
For users who have related software usage needs, the efficiency improvement brought by AORUS GeForce RTX 4090 MASTER is visible to the naked eye.
AORUSGeForce RTX 4090 MASTER Test score
RTX3090 Ti Test score
Blender is a professional three-dimensional rendering software. This time, a fixed Benchmark running score software was launched, saving the trouble of installing software and downloading materials. This scoring software only needs to download the startup program, and the software will automatically render and test the monk/junkshop/classroom for three scenarios.
The above picture shows the scores of AORUSGeForce RTX 4090 MASTER graphics card, 6376/2950/3013 points, with an average of 4113 points; the following picture shows the scores of GeForceRTX 3090 Ti graphics card, 3136/1812/1549 points, with an average of 2165 points. Through the comparison of average scores, it is not difficult to find that the improvement is very obvious. reaches 90% , which can greatly save time and improve work efficiency for animations based on frames.
9 Power consumption and temperature test
In the power consumption test, we chose FurMark software for copying test and used GPU-Z to detect the temperature. The power consumption is only calculated by the graphics card itself.
In this oven test, the AORUS GeForce RTX 4090 MASTER performed well. With a full load of 100% TDP, the power consumption reached about 450W, which is equivalent to the public version, but the power requirements are also very terrifying.
In addition, in the full-load copy machine test, the peak temperature of AORUS GeForce RTX 4090 MASTER is 60.2℃, while the peak temperature of the hot spot is 66.7℃. This is very outstanding for the RTX 4090 and AD102 cores. The strong strength of the wind power cooling system of AORUS GeForce RTX 4090 MASTER is fully demonstrated.
10 Super Engraving Opens the New Generation of
The recent generations of NVIDIA graphics cards will always bring different surprises to everyone in terms of performance, graphics technology, etc. In addition to pure performance improvement, the innovation and progress of each generation of graphics cards in graphics technology will bring new development space to the fields of gaming, creation, etc. The third-generation RTCores and fourth-generation TensorCores equipped in the RTX40 series have brought revolutionary technological evolution, bringing a qualitative leap to the performance of the RTX4090. Whether it is ray tracing performance or DLSS efficiency improvement, they are far beyond imagination.
In the past, we always said that "the 4K era is coming", and in the RTX4090 generation, coupled with the performance leap brought by DLSS3, the game screen has jumped from the passing line of 60fps to the e-sports experience of 144fps. The 4K@144Hz high refresh monitor can even become the standard monitor for all users who purchase RTX4090 graphics cards.
In fact, RTX4090 has achieved more than 60fps game screen performance at 8K resolution, which means that the advanced 8K resolution display devices on the market can also be used for gaming needs, bringing players more ultimate and clearer game screens.
For studios and creators, RTX4090 further improves the operation efficiency of professional software, reduces the waiting time for professional needs such as picture rendering and engineering production, improves the work efficiency of all dreamers, and brings more wonderful designs to our planet.
Back to the graphics card itself, AORUS GeForce RTX 4090 MASTER is a representative product of luxury stacking and super heat dissipation in non-public graphics cards. With its strong performance and stable temperature control, AORUS GeForce RTX 4090 MASTER perfectly demonstrates the strength of AD102. Although his calibration frequency is only a little higher than that of the public version card, from the actual test performance, its actual performance is even stronger than some cards that claim to be overclocked, and its temperature and power consumption control is also quite perfect.
is arguably one of the most worthy of attention among first-tier non-public cards. At present, AORUS GeForce RTX 4090 MASTER has been launched, so please don’t miss it if you are interested.
(8050815)
