Bookmark and Share


It is not a secret that performance, cost and power efficiency of chips depend on actual design as well as on process technology. A good chip design and advanced process technology almost always result in a proper product. But to make the best chip, its design has to be tailored for process technology and vice versa. Apparently, this is exactly what Nvidia and TSMC have done to make Kepler architecture exceptionally power-efficient.

"Today, the primary constraint on processor performance is the power consumption budget. So our goal is always to develop solutions that deliver the highest performance within a fixed power budget. Having a more efficient process enabled us to add more processing cores, thus increasing performance. Put simply, greater efficiency equals greater performance and optimal performance per watt," said Joe Greco, senior vice president of the advanced technology group at Nvidia.

Kepler was in many ways an ambitious project because it introduced a new architecture at the same time as a new silicon process technology node. To maximize the efficiency of Kepler architecture, which Nvidia needed not only to sustain leading positions on the market of computer graphics, but also to continue its progress on the market of high-performance computing, Nvidia had tochange our silicon process development model with TSMC.

Back in the days Nvidia and Taiwan Semiconductor Manufacturing Company worked independently:  TSMC prepared the process technology, Nvidia worked on the design. For Kepler, Nvidia began working with TSMC three years before our product tape-out (when the processor design is complete and ready for manufacturing). Working in tandem, the two companies created a production qualification vehicle (PQV) to allow the TSMC process engineers and Nvidia design engineers to optimize the process before the product tape-out. Through repeated prototyping, the companies were able to optimize both the process and design, creating a more efficient Kepler design rather than simply a chip in a standard 28nm process.

This is not the first time when TSMC collaborates with its major customers to tailor process technology for their needs and also not the first  time when chip designs are optimized for a process technology still in development. As chips get more complex and manufacturing technologies get thinner, even closer collaboration between chip designers and contract makers of semiconductors will be needed to create great products.

TSMC’s 28nm high performance (HP) process, the foundry’s most advanced 28nm process which uses high-K metal gate (HKMG) technology and SiGe (Silicon Germanium) straining. HKMG is a process that uses a gate insulator film with a high dielectric constant which reduces power by reducing gate leakage compared to the previous generation SiON gate. SiGe straining is a chemical process to stretch the silicon atoms to improve the mobility or the effective frequency of the transistor. Both technical advances improve the performance per watt of the transistor translating to a more power efficient system.

TSMC’s 28nm HP process, seen under an electron microscope, is 30% smaller than 40nm and about 35% more energy efficient.

"We are extremely proud of what we accomplished with Kepler. It combines Nvidia’s world-class GPU engineering with TSMC’s very best 28nm process. But while Kepler was a key milestone, it is one point in a continuum. We continue to improve on what we developed and continue our collaboration with TSMC. In fact, we recently received our first version of an enhanced PQV for 20nm from TSMC. That process will yield even greater efficiency for Nvidia’s next next-generation GPUs," said Mr. Greco.

Tags: Nvidia, TSMC, 28nm, 20nm, Semiconductor, Kepler, Geforce, Tegra, Tesla, Quadro, Maxwell


Comments currently: 5
Discussion started: 04/27/12 05:20:05 AM
Latest comment: 04/30/12 01:13:05 PM
Expand all threads | Collapse all threads


It was about time TSMC received a little pad from nvidia. So far they've only been complaining.
Why is suddenly all about efficiency? For many generations ati/amd gpus had a clear lead in efficiency over nvidia. It was not even used as a benchmark in many reviews. But now, when nvidia claims first place in this discipline, its suddenly all about efficiency. amd's marketing department truly sucks...
4 1 [Posted by: tmold  | Date: 04/27/12 05:20:05 AM]
- collapse thread

Agree with you there! DAMN marketing is really taking too much caffeine shots since forever (damn junkies :D) .... They did that in the past having first nearSIMD 3DNow! x86 processor and let Intel wipe them out with their SSE, having first CoolNQuiet on desktop CPU, pushing x86-64 (AMD64) instructions and not taking any advantage and even with PowerPlay now they spoiled half empty bottle

Sucking reality is that WE -- customers pay for those bstd marketing jobs and they never fully implement those techniques for end-user but we always need additional tweakings that 99.8% of users is afraid to do just because living in mantra "BigBro knows it better than you"

I dont think that empty bigboard marketing should push their crippled campaigns higher than they usually do but instead they should stand out behind their technologies to really benefit their end-users.

And this envy's big bragging campaign ain't much of surprise really if you remember they're filthy rich by ransacking their customers (something ATi/DAMN didnt do for years until recently with sick-priced HD7000 series) ... But it's surprise that they now praise crappy TSMC 28nm node ... Probably praising for some shabby under the table deal they had with tsmc in the past to happen one more time(, oooh baby, envy is a little trashy hoo)
2 0 [Posted by: OmegaHuman  | Date: 04/27/12 09:30:17 AM]

Ooooh i love those graphs without real world variables .... ooh wait those arent graphs after all just plain old marketing bs.
3 0 [Posted by: OmegaHuman  | Date: 04/27/12 09:37:59 AM]
- collapse thread

Exactly! I don't even believe they improved leakage (whatever the percentage exactly means...) over 40 nm. This is getting worse with every shrink iteration. That's why they used finFETs (aka Tri-Gate) to reduce this.

Yeah, markteting never really was a strength of amd.. From an engineering point of view their products were really innovative, but without the proper marketing prowess, it's almost wasted effort.

As for nvidias bragging camapain: nvidia cannot bragg about their product's efficiency without mentioning the actual physical chip. On the one hand they were complaining about the manufacturing of the chip and on the other they are praising its efficiency. So I guess tsmc wanted a piece of this campaign...
0 0 [Posted by: tmold  | Date: 04/28/12 01:55:22 AM]


Add your Comment

Related news

Latest News

Wednesday, November 5, 2014

10:48 pm | LG’s Unique Ultra-Wide Curved 34” Display Finally Hits the Market. LG 34UC97 Available in the U.S. and the U.K.

Wednesday, October 8, 2014

12:52 pm | Lisa Su Appointed as New CEO of Advanced Micro Devices. Rory Read Steps Down, Lisa Su Becomes New CEO of AMD

Thursday, August 28, 2014

4:22 am | AMD Has No Plans to Reconsider Recommended Prices of Radeon R9 Graphics Cards. AMD Will Not Lower Recommended Prices of Radeon R9 Graphics Solutions

Wednesday, August 27, 2014

1:09 pm | Samsung Begins to Produce 2.13GHz 64GB DDR4 Memory Modules. Samsung Uses TSV DRAMs for 64GB DDR4 RDIMMs

Tuesday, August 26, 2014

10:41 am | AMD Quietly Reveals Third Iteration of GCN Architecture with Tonga GPU. AMD Unleashes Radeon R9 285 Graphics Cards, Tonga GPU, GCN 1.2 Architecture