MSI GeForce RTX 3080 Suprim X Review – The Biggest Graphics Card in the World

Source: Tech Power Up added 20th Nov 2020

  • msi-geforce-rtx-3080-suprim-x-review-–-the-biggest-graphics-card-in-the-world

Introduction

MSI GeForce RTX 3080 Suprim X graphics is the company’s new premium custom-design implementation of the RTX 3080 “Ampere.” With this, the company is debuting its new “Suprim” brand extension, which is positioned a notch above the Gaming X Trio line of graphics cards by MSI. It’s likely that Suprim X is the new Gaming Z, as the company probably in the past had to fight the perception that Gaming Z is just an overclocked Gaming X (when in fact it would usually come with certain physical improvements). In addition to a more upmarket design than the Gaming X Trio, the RTX 3080 Suprim X comes with higher clock speeds, and a handful exclusive features. MSI is reserving the Suprim X treatment only to high-end GPUs, beginning with the RTX 3090, RTX 3080, and RTX 3070. In this review, we take a look at the RTX 3080 Suprim X, we’ll also have a review of the RTX 3090 Suprim for you soon.

The GeForce RTX 3080 is the first “Ampere” graphics card, based on NVIDIA’s first consumer graphics architecture in close to two years. The company was first to introduce real-time raytracing for gaming with its path-breaking RTX 20-series “Turing” in 2018, and “Ampere” is an exercise in making raytracing have much less of a performance impact than it did with the previous generation. While purely raytraced interactive 3D remains a very long-term engineering goal due to the enormity of compute power required, NVIDIA realized that conventional raster 3D can be combined with certain raytraced elements, such as lighting, shadows, reflections, global illumination, and ambient occlusion, to uplift graphics realism way beyond what’s possible with raster 3D, even with the latest DirectX 12 feature-set, and innovated the RTX technology. With “Ampere,” NVIDIA is introducing its 2nd generation, which adds even more hardware-accelerated RTX effects, and improves performance. The RTX 3080 is designed to make AAA gaming with raytracing possible at 4K UHD at 60 Hz.

The new GeForce “Ampere” graphics architecture marks the debut of the 2nd generation RTX, which combines new “Ampere” CUDA cores that double throughput over the previous generation by leveraging concurrent FP32+INT32 math operations per clock cycle; new 2nd generation RT cores which double the BVH traversal and intersection performance over “Turing” RT cores, and add new fixed-function hardware that enables raytraced motion-blur; and the new 3rd generation Tensor core, inspired by the cores that power the A100 Tensor Core HPC processor, which leverage the sparsity phenomenon in deep-learning neural networks, to increase AI inference performance by an order of magnitude over the previous generation. NVIDIA leverages AI to power its raytracing denoiser, and to enable its DLSS performance enhancement. With “Ampere,” NVIDIA is introducing 8K DLSS, letting you play at 8K resolutions.

The GeForce RTX 3080 features close to triple the number of CUDA cores as the RTX 2080, at 8,704 vs. 2,944. It also features 68 2nd Gen RT cores, 272 3rd Gen Tensor cores, 272 TMUs, and 96 ROPs. To keep all this compute muscle fed with a steady stream of data, NVIDIA partnered with Micron Technology to innovate an exclusive new memory technology it calls GDDR6X, which on the RTX 3080, offers staggering data rates of 19 Gbps (compared to the up to 16 Gbps of conventional GDDR6). NVIDIA is also widening the memory bus to 320-bit, and increasing the memory amount to 10 GB, compared to the previous generation. The RTX 3080 enjoys 760 GB/s of memory bandwidth. There several other next-gen technologies, such as support for the new PCI-Express 4.0 x16 bus, the latest DisplayPort 1.4a and HDMI 2.1 connectors that support 8K over a single cable; and AV1 decode acceleration. The RTX 3080 is based on the same “big” silicon as the RTX 3090, the “GA102,” built on the Samsung 8 FFN silicon fabrication process.

The MSI GeForce RTX 3080 Suprim X is possibly the only custom-design card that can give the NVIDIA Founders Edition a run for its money in a beauty contest. Top-grade brushed aluminium finishes off the cooler shroud and backplate, crafted to perfection, under which is a meaty aluminium fin-stack heatsink that pulls heat over squared “core pipe” heat-pipes which make better contact with the GPU over a nickel-plated copper base plate; and high conductivity thermal compound. The fin-stack is ventilated by a trio of evenly sized TorX 4.0 fans that feature webbed impellers for guided axial airflow, and double-ball bearings. The cooler also features a flattened heat pipe dedicated to pull heat from the memory chips on the PCB.

MSI is giving the RTX 3080 Suprim X its highest factory overclock thus far, with the GPU Boost set at 1905 MHz (compared to 1710 MHz reference and 1815 MHz of the RTX 3080 Gaming X Trio). It’s also the most expensive air-cooled RTX 3080 from MSI, priced at $900, a $200 premium over the Founders Edition, and $140 premium over the Gaming X Trio. In this review, we take a very close look at the MSI GeForce RTX 3080 Suprim X to tell you if this huge premium is justified.

GeForce RTX 3080 Market Segment Analysis
  Price Shader

Units
ROPs Core

Clock
Boost

Clock
Memory

Clock
GPU Transistors Memory
GTX 1080 Ti $650 3584 88 1481 MHz 1582 MHz 1376 MHz GP102 12000M 11 GB, GDDR5X, 352-bit
RX 5700 XT $370 2560 64 1605 MHz 1755 MHz 1750 MHz Navi 10 10300M 8 GB, GDDR6, 256-bit
RTX 2070 $340 2304 64 1410 MHz 1620 MHz 1750 MHz TU106 10800M 8 GB, GDDR6, 256-bit
RTX 2070 Super $450 2560 64 1605 MHz 1770 MHz 1750 MHz TU104 13600M 8 GB, GDDR6, 256-bit
Radeon VII $680 3840 64 1802 MHz N/A 1000 MHz Vega 20 13230M 16 GB, HBM2, 4096-bit
RTX 2080 $600 2944 64 1515 MHz 1710 MHz 1750 MHz TU104 13600M 8 GB, GDDR6, 256-bit
RTX 2080 Super $690 3072 64 1650 MHz 1815 MHz 1940 MHz TU104 13600M 8 GB, GDDR6, 256-bit
RTX 2080 Ti $1000 4352 88 1350 MHz 1545 MHz 1750 MHz TU102 18600M 11 GB, GDDR6, 352-bit
RTX 3070 $500 5888 96 1500 MHz 1725 MHz 1750 MHz GA104 17400M 8 GB, GDDR6, 256-bit
RX 6800 $580 3840 96 1815 MHz 2105 MHz 2000 MHz Navi 21 23000M 16 GB, GDDR6, 256-bit
RX 6800 XT $650 4608 128 2015 MHz 2250 MHz 2000 MHz Navi 21 23000M 16 GB, GDDR6, 256-bit
RTX 3080 $700 8704 96 1440 MHz 1710 MHz 1188 MHz GA102 28000M 10 GB, GDDR6X, 320-bit
MSI RTX 3080

Suprim X
$900 8704 96 1440 MHz 1905 MHz 1188 MHz GA102 28000M 10 GB, GDDR6X, 320-bit
RTX 3090 $1500 10496 112 1395 MHz 1695 MHz 1219 MHz GA102 28000M 24 GB, GDDR6X, 384-bit
Read the full article at Tech Power Up

brands: Micron  MSI  NVIDIA  RTX  Samsung  
media: Tech Power Up  
keywords: 4K  8K  Gaming  Memory  Review  Samsung  

Related posts


Notice: Undefined variable: all_related in /var/www/vhosts/rondea.com/httpdocs/wp-content/themes/rondea-2-0/single-article.php on line 88

Notice: Undefined variable: all_related in /var/www/vhosts/rondea.com/httpdocs/wp-content/themes/rondea-2-0/single-article.php on line 88

Related Products



Notice: Undefined variable: all_related in /var/www/vhosts/rondea.com/httpdocs/wp-content/themes/rondea-2-0/single-article.php on line 91

Warning: Invalid argument supplied for foreach() in /var/www/vhosts/rondea.com/httpdocs/wp-content/themes/rondea-2-0/single-article.php on line 91