Graphcore’s first chip,
the Colossus
Bloomberg Businessweek|SoonerThanYouThink June 10, 2019
Tohelpbigcorporatecustomersfigure
out how to build the next-gen comput-
ers required to use the chipsproperly,
Graphcore offers server blueprintsand
packagesitsproductswithfreesoftware
tools.“We’llgiveyoutherecipeforthecom-
puterdesignandthensellyoutheingredi-
ents,”Toonsays.IPUsrelyona concept
knownas parallelcomputing.The basic
ideaisthat programsneedtobewritten
foreachprocessorforit tofunction,butas
processorsbuiltinto chipsproliferate—a
largeGraphcoreinstallationincludesabout
5 millionprocessorcoresandiscapableof
runningalmost 30 millionprogramsatonce—
this coding taskhassuperseded human
authorship,meaningprograminghastobe
automatedfortheprocessorstoexecute
independently.Inlayman’sterms,Graphcore
hasslicedupmammothcomputingundertak-
ingsintominidataproblems,whichareeach
handledseparatelyonthose“tinyislands
ofprocessors,”beforetheysyncuplikea
Marinemarchingbandtosharewhatthey
learnatthemostefficientmoment.
TobiasJahn,principalinvestoratBMW’s
venturecapitalarm,envisionsGraphcore
chipsintheautomaker’sdatacentersand
perhapsitscars.“BMWhasaninterestin
Graphcorebecominga large-scale,world-
widesiliconsupplier,”Jahnsays.Theimme-
diacy with which autonomous vehicles must
execute so many critical tasks makes them
a key market for something like an IPU, given
the lag time that so often accompanies
work in the cloud. Arm Holdings co-founderHauser, now a partner at Amadeus Capital,
estimatesthateachdriverlesscarmayneed
twoIPUs.Graphcoresaysit’sontrackto
reach$50million in revenue in 2019.
Big-name rivals are crowding into the
field, too. Tesla Inc. recently applied for pat-
ents on its own AI chips. Google last year
unveileda classofmicroprocessorsdesigned
formachinelearning.AndNvidiahasbeen
modifying its dominantGPU chipdesigns
sothey’relesspreciseandmoreefficient—
more like Graphcore’s. “Everyone else is
sort of knocking at Nvidia’s door,” says Alan
Priestley, an analyst at researcher Gartner
Inc. “Graphcore has a good position, but
it’s still a very small competitor compared to
Nvidia’smarketpresence.Soalthoughtheir
IPUsmaybebetterthanNvidia’sGPUsfor
theseworkloads, the risk they face is custom-
erschoosing‘goodenough’over‘brilliant.’”
Another significant challenge is the
ethical dilemma IPUs present if, as prom-
ised, they enable machines to operate 100
times more powerfully than today’s com-
puters. Toon and Knowles are wary of the
dangers, particularly how such technology
could be misused for weapons and authori-
tarian surveillance. Ultimately, though, they
say governments will need to be the ones to
set limits. “Machine power gave us airlines
and cars,” Knowles says. “But it also gave
us tanks. Society will have to determine the
balance of good and evil over time.”
For now, Graphcore is focused on devel-
oping more software that will open cus-
tomers’ eyes to the power of IPUs, while
expanding its business toward what the
co-founders see as an eventual pub-
licoffering.Thecompanypopsa bottleof
Champagneforeachmajormilestone,such
asa $50millionfundingroundinlate 2017
anda $10million sales order in 2018. Signs
of this growth are all around Graphcore’s
office in the form of larger and larger empty
bottles of bubbly. Knowles and Toon always
start with Winston Churchill’s favorite brand
of Pol Roger, which they say represents their
pride that they might give Britain its first
tech giant on the order of Apple or Alibaba
Group Holding Ltd. “Start with Pol and end
with Pol,” Knowles says, chuckling again
while doting over a recently consumed 9-liter
Salmanazar of Champagne. “By the time you
IPO, you pop the biggest bottle.” <BW>63