The CSIRO has announced an upgrade to its GPU cluster to a hefty 134 nodes powered by 268 Intel E5-2650 processors and 390 NVidia Tesla 2050 GPU cards. The 2,144 CPU core, 174,720 GPU core thumper will, according to the science agency’s head of Computation and Simulation Sciences Dr John Taylor, deliver up to 120 Teraflops of …
Now we know what all that wifi patent money went on!
Preparing for Crysis 3
“Just about every area of CSIRO is able to make use of the cluster,”
Department of Mining Surveying at Taxpayer's Expense for Large Wealthy Companies
Department of Sheepdip Engineering
Department of Rainmaking
Department of Remembering When We Launched Rockets
Department of Yet More Fiscal Jiggerypokery For Government Enquiries Into Fiscal Jiggerypokery
To be fair, the CSIRO do some wonderful work, but unfortunately they are largely directed by Earth's lowest form of life - Austfailian politicians.
Pretty awesome, and even more cool is how cheap it is... only a million? Lesson for these billion dollar IT cons... err projects.
174,720 GPU cores? Try again.
The number of "cores" in a GPU is highly misleading, and it's a shame to see El Reg perpetuating this confusion. For @#$'s sake, those aren't cores, or anything close, they're 32-bit wide ALUs. Is each lane of a vector processor called a core? No. Is each Xeon E5-2xxx a 64 core processor because it has 8 processors each with 8-way SIMD execution (AVX)? No.
A Fermi SM (Streaming Multiprocessor) is more analogous to a core. Instruction decode and issue happens at the SM level, as does any branching or control flow (beyond basic predication); each SM has 32 ALUs, which are what this article calls cores. Each Tesla GPU has 16 SMs, (14 of which are active in the x2050 products).
Lets get this shit together, because SIMD issue width != core count, and its meaningless marketing drivel to say otherwise.