Introduction

Out with the old, in with the new. Let's welcome the newest kid on the block, the Radeon HD 7970, part of AMD's spanking new Southern Islands GPU family. This card is the industry's first with a few things, it uses the first ever high-performance GPU built on the 28 nanometer silicon fabrication process; Radeon HD 7970 is the industry's first card compliant with Microsoft's DirectX 11.1 API, which will ship with the next major version of Windows; and is the first card to use the PCI Express 3.0 x16 bus, that doubles system interface bandwidth to 32 Gb/s and is touted by motherboard manufacturers as the next big thing since PCI.

New generations of GPUs naturally bring with them performance increments, some times even 100% that of preceding generations, they also serve as launch-vehicles for new features that quickly go on to become industry standards, and help the technology grow. The Radeon HD 7970 has both of these responsibilities resting on its shoulders: to score performance wins, and pack some killer new features that matter to the end-user.

Product Positioning

The AMD Radeon HD 7970 is a unique card from a market-positioning standpoint. After Radeon HD 2900 series, and the completion of ATI's merger with AMD, the company took up a unique model of product development that ensured it could have competitive products out in the market targeting every segment, while not having to spend much on making large GPUs. Its goal with a new GPU architecture always involved making a killer high-performance (not high-end) GPU, and using it both ways: in dual-GPU cards as high-end products, and by disabling some components/features to carve out cheaper/cost-effective products.

The AMD Radeon HD 7970, particularly the GPU behind it, codenamed "Tahiti", is stretching that model a little towards the higher-end. Tahiti is bigger than what AMD's typical "high-performance" GPU is supposed to be. For one, it features a 384-bit wide memory interface. AMD was the first to market with GDDR5 memory standard, which it initially sought as a way to circumvent the need for a GDDR3/4 memory bus wider than 256-bits. With NVIDIA catching up with the memory standard, and implementing a 384-bit GDDR5 memory interface on its GeForce Fermi 100/110 GPUs, AMD felt the pinch for doing something to increase the memory bandwidth of the HD 7970, to keep up with the increasing compute performance of their GPUs. The company chose slightly faster GDDR5 memory chips with HD 6900 series, but it could only yield small bandwidth gains. The only option left without having to switch memory architecture to the lesser known XDR2, was to increase the memory bus width physically by 50%, hence 384-bit. Coupled with the faster 5.5 GT/s memory chips it used on the HD 6900, and appropriate clock speeds, it yields around 260 GB/s of memory bandwidth.



The unconventionally-wider memory bus of the Radeon HD 7970, combined with a brand new math-processing machinery contribute to the HD 7970's product placement, which is between the previous-generation single-GPU Radeon HD 6970, and previous-generation dual-GPU HD 6990, tilting closer towards the HD 6990.