Introduction

We have with us the ASUS ROG Astral GeForce RTX 5090 OC graphics card, which debuts the new ROG Astral brand for ASUS. Designed to provide the best of ASUS thermal engineering and industrial design, the ROG Astral brand is positioned a notch above the ROG Strix brand, providing the company's best air cooling solution, a premium set of materials, and the new Quad Fan Force arrangement of no less than four fans. Aesthetically, ROG Astral graphics cards pair well not just with ASUS ROG Strix series motherboards, but also the more premium ROG Maximus and ROG Crosshair lines. The GeForce RTX 5090 is designed to crunch through any of today and tomorrow's games with maxed out settings, at 4K Ultra HD.



The Blackwell graphics architecture powering the RTX 5090 introduces neural rendering, a breakthrough new concept where generative AI works more collaboratively with classic raster 3D graphics. You've had a taste of generative AI, and its ability to conjure up photorealistic images and videos. Now imagine AI drawing parts of your 3D scene in real time, complete with geometric detail and ray tracing effects. Making this possible is API-level standardization that allows games to access Tensor cores, and the ability for the GPU to accelerate a generative AI model and render games in tandem, thanks to a new hardware scheduling component called AMP.

Perhaps the most interesting aspect about Blackwell is that GPUs in its generation do not introduce a new foundry node, all chips in the RTX 50-series are built on the existing TSMC 4N process, which is an NVIDIA-specific variant of the 5 nm EUV node. Whatever generational improvements in efficiency you see are purely thanks to advances made by the graphics architecture itself, and a re-architected power management system.

The RTX 5090 is based on the GB202 ASIC, a massive 750 mm² slab of silicon featuring over 92 billion transistors, 192 Blackwell streaming multiprocessors, a PCI-Express 5.0 x16 interface, and a mammoth 512-bit GDDR7 memory interface, belting out 1.79 TB/s of memory bandwidth. The trend across the RTX 50-series is large increases in bandwidth thanks to GDDR7, because neural rendering and the new DLSS 4 Multi Frame Generation are memory sensitive technologies. The RTX 5090 is carved out of the GB202 by enabling 170 out of those 192 SM, and enabling 96 MB out of the 128 MB on-die L2 cache available. This results in 21,760 CUDA cores, 680 Tensor cores, and 170 RT cores, across 11 GPCs, and this doesn't even max out the GB202. The card comes with 32 GB of 28 Gbps GDDR7 memory.

The Blackwell graphics architecture introduces a new generation streaming multiprocessor with concurrent FP32 and INT32 capability across all its 128 CUDA cores, shader execution reordering with awareness for neural shaders, and the new 5th Gen Tensor core that's capable of FP4 data formats for 32x the throughput of the original Tensor core. The new generation RT core has the hardware groundwork for Mega Geometry, the ability to give ray traced object significantly higher poly counts, or those many triangles onto which rays should interact with. DLSS Multi Frame Generation is a technology that uses AI to predict not just every other frame following a conventionally rendered one, but up to three frames following it, effectively quadrupling frame-rates (or at least the smoothness of output).

The ASUS ROG Astral RTX 5090 OC doesn't just come with a heavy cooling solution that fits into the dimensions of the previous generation RTX 40-series ROG Strix graphics cards, but also dials things up a notch with the introduction of a fourth fan arranged along the tail end of the backplate where you normally expect a cutout to be, for airflow from the third fan to go through. This fourth fan acts as a "pull" fan, increasing the overall airflow volume of the heatsink by around 20%. There's plenty of tastefully executed dual-tone surfaces, rich metal alloy textures, and ARGB LED lighting. Innovations you expect from ROG Strix series cards are also here, such as dual-BIOS, case fan headers, and ARGB headers. ASUS is giving the RTX 5090 a factory overclock of 2580 MHz compared to the 2410 MHz reference GPU Boost frequency. The cooling solution is tasked with ensuring higher boost frequency residency and lower noise. Since this is the company's most premium air-cooled custom design RTX 5090, ASUS is pricing it at USD $2,800, an astounding 40% premium over the NVIDIA baseline price.

NVIDIA Blackwell Architecture

The GeForce Blackwell graphics architecture heralds NVIDIA's 4th generation of RTX, the late-2010s re-invention of the modern GPU that sees a fusion of real time ray traced objects with conventional raster 3D graphics. With Blackwell, NVIDIA is helping add another dimension, neural rendering, the ability for the GPU to leverage a generative AI to create portions of a frame. This is different from DLSS, where an AI model is used to reconstruct details in an upscaled frame based on its training date, temporal frames, and motion vectors. At the heart of the GeForce RTX 5090 we are reviewing today is the mammoth 5 nm GB202 silicon. This is one of the largest monolithic dies ever designed by NVIDIA, measuring 750 mm², compared to the 608.5 mm² of the AD102 die. The process is unchanged between the two generations—it's still an NVIDIA-specific variant of TSMC 5 nm EUV, dubbed TSMC 4N. The GB202 rocks 92.2 billion transistors, a 20% increase over the AD102.


The GB202 silicon is laid out essentially in the same component hierarchy as past generations of NVIDIA GPUs, but with a few notable changes. The GPU features PCI-Express 5.0 x16, making it the first gaming GPU to do so. PCIe Gen 5 has been around since Intel's 12th Gen Core "Alder Lake" and AMD's Ryzen 7000 "Zen 4," so there is a sizable install-base of systems that can take advantage of it. The GPU is of course compatible with older generations of PCIe. Whether this affects performance is a question we cover in our separate RTX 5090 PCIe Scaling Article. The GB202 is also the first GPU to implement the new GDDR7 memory standard, which doubles speeds over GDDR6 while lowering the energy cost of bandwidth. NVIDIA left no half-measures with the GB202, and gave it a broad 512-bit GDDR7 memory interface. On the RTX 5090, this is configured with 32 GB of 28 Gbps GDDR7. Upcoming RTX 50-series SKUs could have narrower memory interfaces but with higher memory speeds, and some professional graphics cards based on the GB202 could even use high-density memory chips.

The GigaThread Engine is the main graphics rendering workload allocation logic on the GB202, but there's a new addition, a dedicated serial processor for managing all AI acceleration resources on the GPU, NVIDIA calls this AMP (AI management processor). Other components at the global level are the Optical Flow Processor, a component involved in older versions of DLSS frame generation and for video encoding; and a vast media acceleration engine consisting of four NVENC encode accelerators, and four NVDEC decode accelerators. The new 9th Gen NVENC video encode accelerators come with 4:2:2 AV1 and HEVC encoding support. The RTX 5090 has 3 out of 4 NVENC and 2 out of 4 NVDEC units enabled. The central region of the GPU has the single largest common component, the 128 MB L2 cache. The RTX 5090 is configured with 96 MB of it.


Each graphics processing cluster (GPC) is a subdivision of the GPU with nearly all components needed for graphics rendering. On the GB202, a GPC consists of 16 streaming multiprocessors (SM) across 8 texture processing clusters (TPCs), and a raster engine consisting of 16 ROPs. Each SM contains 128 CUDA cores. Unlike the Ada generation SM that each had 64 FP32+INT32 and 64 purely-FP32 SIMD units, the new Blackwell generation SM features concurrent FP32+INT32 capability on all 128 SIMD units. These 128 CUDA cores are arranged in four slices, each with a register file, a level-0 instruction cache, a warp scheduler, two sets of load-store units, and a special function unit (SFU) handling some special math functions such as trigonometry, exponents, logarithms, reciprocals, and square-root. The four slices share a 128 KB L1 data cache, and four TMUs. The most exotic components of the Blackwell SM are the four 5th Gen Tensor cores, and a 4th Gen RT core.


Perhaps the biggest change to the way the SM handles work introduced with Blackwell is the concept of neural shaders—treating portions of the graphics rendering workload done by a generative AI model as shaders. Microsoft has laid the groundwork for standardization of neural shaders with its Cooperative Vectors API, in the latest update to DirectX 12. The Tensor cores are now accessible for workloads through neural shaders, and the shader execution reordering (SER) engine of the Blackwell SM is able to more accurately reorder workloads for the CUDA cores and the Tensor core in an SM.


The new 5th Gen Tensor core introduces support for FP4 data format (1/8 precision) to fast moving atomic workloads, providing 32 times the throughput of the very first Tensor core introduced with the Volta architecture. Over the generations, AI models leveraged lesser precision data formats, and sparsity, to improve performance. The AI management processor (AMP) is what enables simultaneous AI and graphics workloads at the highest levels of the GPU, so it could be simultaneously rendering real time graphics for a game, while running an LLM, without either affecting the performance of the other. AMP is a specialized hardware scheduler for all the AI acceleration resources on the silicon. This plays a crucial role for DLSS 4 multi-frame generation to work.


The 4th Gen RT core not just offers a generational increase in ray testing and ray intersection performance, which lowers the performance cost of enabling path tracing and ray traced effects; but also offers a potential generational leap in performance with the introduction of Mega Geometry. This allows for ray traced objects with extremely high polygon counts, increasing their detail. Poly count and ray tracing present linear increases in performance costs, as each triangle has to intersect with a ray, and there should be sufficient rays to intersect with each of them. This is achieved by adopting clusters of triangles in an object as first-class primitives, and cluster-level acceleration structures. The new RT cores introduce a component called a triangle cluster intersection engine, designed specifically for handling mega geometry. The integration of a triangle cluster compression format and a lossless decompression engine allows for more efficient processing of complex geometry.


The GB202 and the rest of the GeForce Blackwell GPU family is built on the exact same TSMC "NVIDIA 4N" foundry node, which is actually 5 nm, as previous-generation Ada, so NVIDIA directed efforts to finding innovative new ways to manage power and thermals. This is done through a re-architected power management engine that relies on clock gating, power gating, and rail gating of the individual GPCs and other top-level components. It also worked on the speed at which the GPU makes power-related decisions.


The quickest way to drop power is by adjusting the GPU clock speed, and with Blackwell, NVIDIA introduced a means for rapid clock adjustments at the SM-level.


NVIDIA updated both the display engine and the media engine of Blackwell over the previous generation Ada, which drew some flack for holding on to older display I/O standards such as DisplayPort 1.4, while AMD and Intel had moved on to DisplayPort 2.1. The good news is that Blackwell supports DP 2.1 with UHBR20, enabling 8K 60 Hz with a single cable. The company also updated NVDEC and NVENC, which now support AV1 UHQ, double the H.264 decode performance, MV-HEVC, and 4:2:2 formats.

Neural Rendering

Neural Rendering promises to be as transformative to modern graphics as programmable shaders itself. 3D Graphics rendering evolved from fixed-function over the turn of the century, to programmable shaders, HLSL, geometry shaders, compute shaders, and ray tracing, over the past couple of decades. In 2025, NVIDIA is writing the next chapter in this journey with Blackwell neural shaders. This allows for a host of neural-driven effects, including neural materials, neural volumes, and even neural radiance fields. Microsoft introduced the new Cooperative Vectors API for DirectX in a recent update, making it possible to access Tensor cores within a graphics API. Combined with a new shading language, Slang, this breakthrough enables developers to integrate neural techniques directly into their workflows, potentially replacing parts of the traditional graphics pipeline. Slang splits large, complex functions into smaller pieces that are easier to handle. Given that this is a DirectX standard API feature, there is nothing that stops AMD and Intel from integrating Neural Rendering (Cooperative Vectors) into their graphics drivers.

RTX Neural Materials works to significantly reduce the memory footprint of materials in 3D scenes. Under conventional rendering, the memory footprint of a material is bloated from complex shader code. Neural materials convert shader code and texture layers into a compressed neural representation. This results in up to a 7:1 compression ratio and enables small neural networks to generate stunning, film-like materials in real-time. For example, silk rendered with traditional shaders might lack the multicolored sheen seen in real life. Neural materials, however, capture intricate details like color variation and reflections, bringing such surfaces to life with unparalleled realism—and at a fraction of the memory cost.


The new Neural Radiance Cache, which dynamically trains a neural network during gameplay using the user's GPU, allowing light transport to be cached spatially, enabling near-infinite light bounces in a scene. This results in realistic indirect lighting and shadows with minimal performance impact. NRC partially traces 1 or 2 rays before storing them in a radiance cache, and infers an infinite amount of rays and bounces for a more accurate representation of indirect lighting in the game scene.

DLSS 4 and Multi Frame Generation

DLSS 4 introduces a major leap in image quality and performance. It isn't just a version bump with the introduction of a new feature, namely Multi Frame Generation, but introduces updates to nearly all DLSS sub-features. DLSS from its very beginning relied on AI to reconstruct details in super resolution, and with DLSS 4, NVIDIA is introducing a new transformer-based AI model to succeed the convolutional neural networks previous used, for double the parameters, four times the compute performance, and significantly improved image quality. Ray Reconstruction, introduced with DLSS 3.5, gets a significant image quality update with the new transformer-based model.


To understand Multi Frame Generation, you need to understand how DLSS Frame Generation, introduced with GeForce Ada, works. An Optical Flow Accelerator component gives the DLSS algorithm data to generate an entire frame using a neural network, using information from a previous rendered frame, effectively doubling frame rate. In Multi Frame Generation, AI takes over the functions of optical flow, to predict up to three frames following a conventionally rendered frame, effectively drawing four frames form the rendering effort of one.


Now, assuming this rendered frame is a product of Super Resolution, with the maximum performance setting generating 4x the pixels from a single rendered pixel, you're looking at a possibility where the rendering effort of 1/4th a frame goes into drawing 4 frames, or 15 in every 16 pixels being generated entirely by DLSS. When generating so many frames, Frame Pacing becomes a problem—irregular frame intervals impact smoothness. DLSS 4 addresses these issues by using a dedicated hardware unit inside Blackwell, which takes care of flip metering, reducing frame display variability by 5-10x. The Display Engine of Blackwell contains the hardware for flip metering.

NVIDIA Reflex 2

The original NVIDIA Reflex brought about a significant improvement to the responsiveness of maxed out graphics in competitive online gameplay, by compacting the rendering queue with the goal of reducing the whole system latency by up to 50%. Reflex is mandatory in DLSS 3 Frame Generation, given the latency cost imposed by the technology. Multi-frame generation calls for an equally savvy piece of technology, so we hence have Reflex 2. NVIDIA claims to have achieved a 75% reduction in latency with Frame Warp, which updates the camera (viewport) positions based on user inputs in real-time, and then uses temporal information to reconstruct the frame to display.

Packaging

The Card

The ASUS RTX 5090 Astral looks fantastic, thanks to a beautiful color theme that works perfectly with the all-metal cooler construction. Most of the surfaces use a matte paint which feels extremely nice to the touch. On the back you get a metal backplate with a cutout for air to flow through and a fan to move additional air.


Dimensions of the card are 35.0 x 15.0 cm, and it weighs 3038 g.


Installation requires four slots in your system. We measured the card's width to be 80 mm.


Display connectivity includes three standard DisplayPort 2.1b and two HDMI 2.1b.

Standard for all GeForce RTX 50-series Blackwell cards is a new display engine that supports three DisplayPort 2.1b outputs, each capable of UHBR20; and one HDMI 2.1a. Both interfaces support DSC (display stream compression). With DSC enabled, a single DisplayPort on this card can drive 4K 12-bit HDR at 480 Hz; or 8K 12-bit HDR at up to 165 Hz. The RTX 5090 features an updated media acceleration engine with support for 4:2:2 video formats, AV1 UHQ, and MV-HEVC. There are three independent NVENC units, and two NVDEC.


The card uses a single 16-pin connector, which allows a maximum power draw of 600 W.


ASUS has installed adjustable RGB lighting zones along the top edge of the card.


This dual BIOS switch lets you toggle between the default "performance" BIOS and a "silent" BIOS with a more relaxed fan curve. To the right of the BIOS switch you have two fan headers that let you synchronize case fans with the fans on the graphics card, including fan stop.