Review and testing of video cards MSI GeForce RTX 4070 Ti SUPRIM X

This time the company’s new video card is participating in our test. MSI GeForce RTX 4070 Ti SUPRIM X, , kindly provided to us by the company MSI.

This subsection of our review highlights the main aspects of the MSI GeForce RTX 4070 Ti SUPRIM X, such as appearance and hardware configuration.

The MSI GeForce RTX 4070 Ti SUPRIM X comes in the same packaging as the MSI GeForce RTX 4080 SUPRIM X along with a gaming mouse pad.

The MSI GeForce RTX 4070 Ti SUPRIM X kit includes the video card itself, a power adapter, and a bracket for supporting video cards.

On the side we have a 12-pin power connector and a BIOS switch.

The MSI GeForce RTX 4070 Ti SUPRIM X cooling system is based on 6 heat pipes.

The video card has 4 video outputs – 1 HDMI and 3 DisplayPort, all of them support 8K resolution and 60 Hz. At 4K resolution we can get a screen refresh rate of 144Hz.

On the reverse side of the MSI GeForce RTX 4070 Ti SUPRIM X there is a rather immodest cutout – for greater air flow capacity, in general the design is the same for allx 4080/4090.

MSI GeForce RTX 4070 Ti SUPRIM X compared to ASUS TUF Gaming GeForce RTX 4070 Ti OC looks like a real giant…

The MSI GeForce RTX 4070 Ti SUPRIM X (parva) is almost identical to the MSI GeForce RTX 4090 SUPRIM X (left). The MSI GeForce RTX 4090 SUPRIM X is only slightly larger and has 7 heat pipes, while the MSI GeForce RTX 4070 Ti SUPRIM X has only six.

The GeForce RTX 4070 Ti is based on the AD104 GPU and features 7680 CUDA cores delivering 40 FP32-precision shader teraflops for graphics rendering, 240 fourth-generation Tensor Cores offering 641 trillion sparse matrix operations for AI and DLSS processing, 60 third-generation RT cores generation Ada architecture with 93 RT-TFLOPS performance for next-generation ray-traced graphics acceleration and 12 GB of GDDR6X memory. Like all GeForce RTX 40 series GPUs, the RTX 4070 Ti is equipped with Ada innovations including Shader Execution Reordering (SER), a new optical flow engine, new RT cores and DLSS 3.

NVIDIA Ada Architecture

The NVIDIA Ada architecture is a giant leap in performance. Numerous improvements make it the fastest and most advanced. The RTX 4070 Ti is manufactured using TSMC’s custom 4N process and contains 35,8 billion transistors and 7680 CUDA cores. Hardware-accelerated tracing, fourth-generation Tensor Cores for improved AI performance, eighth-generation encoders with support for AV1 encoding and decoding, and DLSS enhancements that deliver high frame rates in competitive gaming and at ultra settings with ray tracing enabled.

NVIDIA Ada streaming multiprocessor

RTX video cards have three main processors: programmable universal CUDA cores on which shaders and general-purpose CUDA applications are processed, RT cores for accelerating calculations of intersections of rays with triangles and bounding volumes, in the RT cores of the Ada architecture they doubled the rate of calculation of intersections with triangles, the latter processor type – artificial intelligence processing pipeline called tensor cores.

Ada improves all three RTX processors

Programmable Shaders: 40 shader teraflops compared to 21,7 teraflops on the RTX 3070 Ti. The Ada shader processor includes an important new technology called Shader Execution Reordering (SER), which reorders work on the fly, providing up to XNUMXx speedup for ray tracing shaders. SER is as big a innovation for GPUs as out-of-order execution once was for CPUs.

4th Generation Tensor Cores: The new Tensor Core in Ada includes the NVIDIA Hopper FP8 Transformer Engine, delivering up to 641 tensor teraflops with FP8 precision on sparse matrices in the RTX 4070 Ti for AI training and inference, up from 174 tensor teraflops on sparse matrices in the RTX 3070 Ti. Compared to FP16, FP8 halves memory requirements and doubles AI performance.

Gen 3 RT Cores: The new Opacity Micromap Engine speeds up intersection calculations on average by half for texture transparency test surfaces when developers use this feature, and the new Micro-Mesh Engine increases geometric detail without the cost of assembly and BVH storage. Ada’s throughput on intersection tests is 93 RT-TFLOPS, compared to 42,5 RT-TFLOPS for the 3070 Ti.

4th Generation Tensor Cores

Tensor cores are high-performance computing cores specialized and adapted for matrix multiplication and addition operations, used in artificial intelligence and high-performance computing applications. Tensor cores provide breakthrough performance for matrix computations, which are critical for training multilayer neural networks and inference of already trained networks. Examples of inference applications include NVIDIA DLSS 3 technology for gamers, in which a separate neural network is responsible for generating high-quality frames, all powered by NVIDIA’s Tensor Core. DLSS has become so popular that there are already more than 250 games that support this technology, in which gamers can double their performance with one click. In addition, many creative apps have begun to use artificial intelligence features to help artists create content faster and with better quality. Today, more than 110 popular creative applications use acceleration on the Tensor and RT cores of RTX graphics cards. And exclusive NVIDIA applications such as Broadcast и Canvas, offer tools for removing noise, creating virtual backgrounds, and many other AI-powered effects for video streaming and conferencing.

The fourth-generation Ada tensor core builds on the capabilities of previous Ampere GPUs, which supported many new data types and added structured sparsity acceleration to double the throughput of previous Turing cores. Generation Ada Tensor Cores support the new FP8 data format, first introduced in the NVIDIA Hopper GPU architecture. Compared to FP16, FP8 halves storage requirements and doubles AI performance. With the new FP8 format and sparsity feature, the GeForce RTX 4070 Ti delivers 641 TFLOPS of performance for AI workloads.

3rd generation RT cores

Ada’s third-generation RT cores are specialized hardware units for accelerating BVH traversal and ray-triangle intersection calculations, which are critical to accelerating ray tracing. The RT cores of RTX video cards are completely independent, they perform all BVH traversal and intersection calculations, thereby offloading SM streaming multiprocessors with CUDA cores and freeing them up to perform other tasks such as pixel shading, vertex shading and general purpose calculations.

Ada’s RT cores deliver up to 2x faster ray-triangle intersection testing compared to NVIDIA Ampere GPUs, allowing developers to add more detail to their virtual worlds. Ada’s RT cores also include new Opacity Micromap Engine blocks that speed up geometry tracing with alpha testing by up to 2x, helping developers speed up tracing-intensive scenes with vegetation and particle effects by up to 2x. The new RT cores also include Displaced MicroMesh Engine blocks, which generate micro meshes on the fly to create additional geometry.

All of these technologies to improve ray tracing performance give the Ada architecture a lot of room for the future. As new games come out using Ada technologies to increase performance, RTX 40 series video cards will undoubtedly become faster and all break away from the previous generation of RTX 30 series video cards. A recent remaster can be cited as an example. Portal with RTX based on RTX Remix, in which NVIDIA uses new features of the Ada architecture, such as the OMM and SER engines (which, by the way, can be disabled in the settings), together they allow the RTX 4090 to be up to 3 times faster than the RTX 3080 Ti without using DLSS, but with Using the DLSS 3 frame generator, the advantage can be up to 5 times.

Design

The second iteration of SUPRIM inherits the exterior design philosophy of its predecessor with a brushed metal cover, octagonal fan cutouts, and LED lighting on each fan. The beveled edges are polished several times to achieve a mirror finish. Clean, sharp lines highlight the thoughtful design.

The straight line motif continues around the fans with octagonal cutouts with polished 45-degree beveled edges.

Cooling system TRI FROZR 3S

Updated fans, airflow control and other thermal innovations make TRI-FROZR 3S the best air cooling solution MSI TORX FAN 5.0 features design enhancements resulting in +23% more airflow than a conventional fan.

When temperatures are relatively low and active cooling is not required, the fans stop completely using Zero Frozr technology, eliminating all noise. Fans will automatically spin when key components become hot during gaming.

TORX FAN 5.0 fans and Zero Frozr technology

Each TORX FAN 5.0 fan is equipped with dual ball bearings for years of reliable performance. When temperatures are relatively low and active cooling is not required, the fans stop completely using Zero Frozr technology, eliminating all noise. Fans will automatically spin when key components become hot during gaming.

Evaporation chamber

The vapor chamber is great for quickly equalizing temperature on a flat surface. The GPU and video memory are covered with an evaporation chamber, which quickly transfers heat to the heat pipes. Precision machined CORE PIPE heatpipes provide maximum contact area with the GPU vapor chamber and distribute heat along the entire length of the radiator.

Sections of different radiator fins break up unwanted airflow harmonics and reduce noise. Updated heat pipe routing provides more space for additional heatsink fins. The radiator fins are arranged in a V-shape along the airflow path. The optimized tilt angle directs the air resistance vector closer to the center of the radiator, resulting in an increase in the rate at which warm air is expelled.

Highly efficient technological base

Improvements in materials in chokes have culminated in the highly efficient carbonyl inductors. One-piece molding allows this design to operate with less throttle noise and better electrical filtration.

Smart Power Stages (SPS) are highly efficient and allow precise current regulation with less resistance. This results in less power wasted and less heat generated by the power system. Additional fuses located on a specially designed circuit board provide additional protection against electrical damage.

MSI Center

MSI Center software allows you to monitor and configure MSI products in real time.

Mystic Light allows you to control lighting for both MSI products and compatible third-party RGB products.

The gluttony test of the MSI GeForce RTX 4070 Ti SUPRIM X was carried out in conjunction with an Intel Core i9 13900K 3.2 GHz + Z690 AORUS MASTER in a closed Thermaltake Core V51 case:

In “Donut” in stock mode, the MSI GeForce RTX 4070 Ti SUPRIM X shows 60 degrees, consumption is 276 Watts. The system consumes about 449 watts from the outlet. IN Cyberpunk 2077 in stock mode, the MSI GeForce RTX 4070 Ti SUPRIM X shows 6 degrees, consumption 256 Watts. The system consumes about 418 watts from the outlet.

Now let’s put these temperature and energy consumption indicators into tables, with the results we obtained earlier:

As we can see, in FurMark the power consumption of the MSI GeForce RTX 4070 Ti SUPRIM X card is almost the same as the consumption in the games themselves.

The temperature of the MSI GeForce RTX 4070 Ti SUPRIM X card reaches a maximum of 61 degrees. In games, the card is a little warmer, but at the same time it is absolutely silent, which indicates a balanced temperature control of the fans.

Testing took place at maximum quality settings and with ray tracing. Our test segment.

Rђ RІRѕS,  in this game MSI GeForce RTX 4070 Ti SUPRIM X slightly behind Radeon RX 7900 XT.

Testing took place at maximum+ quality settings. Our test segment.

In God of War MSI GeForce RTX 4070 Ti SUPRIM X is noticeably faster GeForce RTX 3080 Ti. 

Testing took place at maximum+ quality settings with RT. Our test segment.

In Dying Light 2 Stay Human, the MSI GeForce RTX 4070 Ti SUPRIM X graphics card is second only to the MSI GeForce RTX 4080 SUPRIM X.

Testing took place at maximum quality settings (with ray tracing). Our test section.

In this game MSI GeForce RTX 4070 Ti SUPRIM X is almost equal GeForce RTX 3080 Ti.

Testing took place at maximum quality settings and with ray tracing. Our test segment.

In F1 22  performance MSI GeForce RTX 4070 Ti SUPRIM X performs better than GeForce RTX 3080 Ti.

Testing took place at maximum quality settings and with ray tracing. Our test segment.

In Marvel’s Spider-Man Remastered The performance of the MSI GeForce RTX 4070 Ti SUPRIM X is higher than that of the Radeon RX 7900 XTX.

Testing took place at maximum quality settings and with ray tracing. Our test segment.

В Gotham Knights MSI GeForce RTX 4070 Ti SUPRIM X performs better than GeForce RTX 3080 Ti.

And finally, testing the MSI GeForce RTX 4070 Ti SUPRIM X in games with DLSS 3.0

Testing took place at maximum quality settings and with ray tracing. Our test segment.

Пproductivity MSI GeForce RTX 4070 Ti SUPRIM X with DLSS 3.0 slightly higher than that  GeForce RTX 4080 SUPRIM X with DLSS and GeForce RTX 4090 SUPRIM X.

Testing took place at maximum quality settings and with ray tracing. Our test segment.

In the Spider The performance of the MSI GeForce RTX 4070 Ti SUPRIM X with DLSS 3.0 is also slightly higher than that of  GeForce RTX 4080 SUPRIM X with DLSS and GeForce RTX 4090 SUPRIM X.

Testing took place at maximum quality settings and with ray tracing. Our test segment.

In The Witcher The performance of MSI GeForce RTX 4070 Ti SUPRIM X with DLSS 3.0 is slightly higher than that of the third time  GeForce RTX 4080 SUPRIM X with DLSS.

Well, based on testing the MSI GeForce RTX 4070 Ti SUPRIM X, we can conclude that the card was a success in all aspects – it is productive, very quiet and cool. Its only drawback is the dimensions of the entire GeForce RTX 40XX SUPRIM X series, where it is contraindicated for compact cases.

Advantages

– excellent cooling system that provides comfortable temperatures and comfortable noise levels in games

– low power supply requirements

– excellent performance with RT

– DLSS 3.0 support

Disadvantages

– Dimensions of the SUPRIM X top level