ATI launch Radeon HD 4850 and HD 4870

Monday 23rd June 2008, 08:00:00 AM, written by Rys

Early this morning GMT saw AMD officially set free a new generation of Radeon products based on a brand new GPU.  Radeon HD 4850 and Radeon HD 4870 go head to head with refreshed and new G92- and GT200-based GeForces from NVIDIA, and the GPU used to create the new Radeon products is an absolute stormer.

Appearance and on-paper figures can be deceiving, since despite having diminuitive dimensions for the die and a comparatively small external memory bus width, RV770 punches harder than any other GPU the Graphics Products Group at AMD have seen fit to release.

The near 960M transistor chip is a svelte 260mm square, and packs a scarcely believable 800 scalar shader processors, arranged in R600- and RV670-like SIMD arrays of 80 each, via the same 16 x 5-way arrangement.  Each SIMD array packs a data sampler unit capable of 16 scalar fetches and a quartet of bilinearly filtered results per clock.

HD 4870 uses brand new GDDR5 for its external DRAM pool, AMD working closely with JEDEC partners to make it happen.  In fact, it leads the JEDEC committee that created the new graphics memory standard, and the new memory controller design for RV770 is tailored to work as well as possible with the new memories.

With 512MiB of 3.6GHz GDDR5 (115GB/sec from 256-bits is enormous) and a 750MHz core clock, Radeon HD 4870 is the faster of the two launch configurations using RV770, and it gives the product some NVIDIA-worrying performance on-paper.  The chip is capable of realisable rates that hit 1.2Tflops of FP32 compute, 24Gtexels/sec of INT8 bilinearly filtered samples, and the 4 quad ROPs will write Z only at 48Gpixels/sec.

Radeon HD 4850 uses 512MiB of GDDR3 (64GB/sec from 256-bit at 2GHz) with a 625MHz clock, giving 1Tflop/sec of FP32 compute, 20Gtexels/sec of INT8 filtering and 40Gpixel/sec Z-only writes.

Implementation details include 1/4 speed FP64 compute ability (industry leading rates therefore result), half speed FP16 filtering (1/2 RV670 per sampler per clock) and full speed FP16 colour writes (2x RV670 per ROP per clock).  So the ratios of compute/sample/ROP change compared to the older generation, while sharing the same basic architecture.

We'll cover as much of those details as we can in our upcoming architecture evaluation, just as soon as we've spent more time with the hardware.

Real-world gaming performance evaluations from our friends at Tech Report and Hardware.fr mean the $199 and $299 products are very attractive when compared to the competition.  The $239 GeForce 9800 GTX+ looks to be a minor waste of NVIDIA's time, Radeon HD 4850 more than a match, with HD 4870 taking on the $399 and $649 (LOL) GeFroce GTX 260 and GTX 280 and often beating the $649 part, especially when a reasonable level of AA gets turned on.

Put simply, NVIDIA are in an immediate position of having overpriced new hardware almost straight out of the gate, with the $649 asking price of GTX 280 a significantly difficult sell for a gamer.

We look forward to looking more closely at the chip architecture soon.  AMD have produced a monstrous chip, putting them right back on the 3D graphics roadmap after a serious spell in NVIDIA's shadow.

Discuss on the forums

Tagging

ati ± radeon, rv770, amd, hd, 4870, 4850, d3d10.1, gddr5, wavey

Related ati News

ATI shoots a Bolt through its GPU compute stack
AMD releases CodeXL 1.0
ATI 69xx Series launches - Crocodile Dundee beware
ATI 68xx Series Launches
ATI releases OpenGL4.0 preview driver, for great justice
ATI 5830 launched, baffled looks follow
ATI Cypress Gaming Performance Analysis
ATI Catalyst 10.1 Display Driver
ATI Radeon HD 5670 released, bringing DX11 for less than $100
ATI 5970 comes out to play, completes ATI's lineup