A while ago, I spoke with my sources at TSMC, who were quite decisive to make it to the front on the field of chip manufacturing. Heads of this Taiwanese giant decided to invest more than 10 billion USD in order to become world’s most advanced manufacturer, and their roadmap is more aggressive than anyone in the industry.
The results of that investment are slowly coming to life, and as of today, TSMC has more advanced manufacturing process than any other competitor in the manufacturing business. Intel will argue its (very important, though) Hafnium or High-K material, but ever since I became a journalist, Intel touted its manufacturing capabilities and ability to go small “sooner than anyone else”. Well, that is about to change.
For instance, Intel will introduce 32nm process in late 2009, and mass production in 2010. Due to separation between AMD and “MAD AMD” (The Foundry Company) will introduce 32nm (bulkPG, not for CPUs) only at the end of 2009, with 2010 being the year of mass production. If all things go well, that is.
During that same time, TSMC will introduce 32nm (Q4’2009), 28nm (Q2’2010) and 22nm will debut in first half of 2011. This is very, very aggressive roadmap that will give Nvidia and ATI leverage in development of graphics parts.
This also does not sound good for Intel’s own Larrabee, which will rely on Intel’s own manufacturing capabilities. While this was viewed as a huge strength in the previous years, TSMC may actually give AMD and Nvidia more than a fighting chance – a winning cost/die ratio.
As a case of demonstration, my source gave me a comparison while using Nvidia’s GT200 chip. This estimated comparison gave me shivers, because in 28nm (available in a bit more than a year), die size for 1.4 billion transistors would drop to incredible 160mm2. Of course, don’t expect that ATI or Nvidia will stand still. They will keep making big GPUs and put more and more core logic inside.
GT200 die through different TSMC manufacturing processes (“wild” estimate):
65nm: 576 mm2 (GT200)
55nm: 470 mm2 (GT206)
40nm: 320 mm2 (GT212)
32nm: 220 mm2 (die-shrink estimate)
28nm: 150 mm2 (die-shrink estimate)
Given this table, we can see that if Nvidia would want to keep the 500mm2 die size, it could manufacture a chip with 500 processors in 40nm, 700 processors in 32nm or massive 1200 shader processors using 28nm process. But don’t expect that either ATI or Nvidia will go linear with their GPUs.
What I personally expect is 512-bit bus, GDDR5 memory controller for both companies (regardless of what ATI is saying now), and increasing the capabilities of shaders. Currently, ATI is supporting FP64 DP format through their 80 shader lines (e.g. in RV780, you have 80 shader pipelines with 10 units in each – you can either output one FP64 Dual Precision or ten FP32 Single Precision number formats). Nvidia features one FP64 DualPrecision unit on eight of their regular shader cores.
With 32nm available in 2009 and 28nm available a year later, it is easy to predict that we will see a tremendous increase in processing power not through the sheer number of shaders, but rather increasing existing shader capabilities.
My $0.02 is that we will see 4-10TFLOPS parts coming in next 24 months, essentially increasing the computational power by anywhere between four and ten times. All thanks to massive effort put in by TSMC.
For now, Nvidia can announce the mass production of Tegra mobile SoC chips and its notebook lineup, while ATI can launch their notebook line-up. 40nm High-Performance arrives in Q1’2009, and you can expect GT212 and RV870 coming “your way in May”.