USING GPUs TO BUILD A MORE ETHICAL SMARTPHONEOctober 11, 2012
The spread of social media has spotlighted the hazards faced by miners extracting metals and minerals for the IT industry. Yet the smartphones used to spread word about these problems utilize some of the very materials that cause the most concern.
That’s given rise to efforts to create a paper trail to certify these materials’ origins. The problem, of course: paperwork can be falsified.
Catherine McManus, chief scientist at Materialytics, has found a way to solve this problem using GPUs to help quickly verify the origins of a gem or a few ounces of raw material.
So far the 30-person company, based outside Austin, Texas, claims to be able to help identify the provenance of a wide range of different materials, including tourmaline, tin (cassiterite), coltan, diamonds, emeralds, gold, rubies, sapphires, and wolframite.
McManus starts with a technique known as laser-induced breakdown spectroscopy. The basic science can be understood by anyone who has taken high school physics: Materialytics fires a laser at the material it wants to examine, and then examines the scattered light created by the plasma that results to create a unique signature for the sample being examined.
From there, however, things get complicated: Materialytics measures each sample 64 separate times, collecting 40,000 data points each time, or more than 2.5 million data points per sample. That data piles up fast: a small scale test will gather more than 500 billion data points. Materialytics Chief Mathematician Jim Dowe says the company has accumulated terabytes of data on samples of raw material gathered from all over the world.
To make that data understandable, Materialytics relies on workstations equipped with NVIDIA Quadro GPUs. The company has created a matrix to display the data points associated with each sample along four different axes, giving users a way to visually compare and distinguish samples that may have been taken from different mines in the same region, or even different parts of the same mine.
Perhaps the biggest challenge: logistics. To match a sample with its origins precisely, the company has to start with materials from the original source. So far, the company says it has created created a collection of geological reference materials with more than 50,000 samples gathered from from 330 locations on all 7 continents.
“Getting into the areas where many of these mines are located is not simple,” McManus says. “We bring back tens and sometimes hundreds of pounds of rock.”
All that grunt work is beginning to pay off. Right now the early-stage startup is exploring a number of business models. Materialytics is exploring the idea of working with the electronics industry to verify the provenance of minerals such as coltan. It’s also talking to companies that trade in precious metals. The technology can even be used to help verify the authenticity of expensive manufactured goods – such as jet turbine blades and pharmaceuticals.
“The mineral itself certifies itself,” says Dowe. “The paperwork can be falsified along the way, but when it comes to the material itself, it cannot be anything but itself.”
To learn how people are making a difference with GPU computing, see the CUDA Spotlights page.