1. North Carolina State University has developed software that could make it easier for traditional software programs to take advantage of powerful GPUs. (graphical processing units) The CPU from an average computer has about 10 gigaflops of computing power – or 10 billion operations per second. That sounds like a lot until you consider that the GPU from an average modern computer has 1 teraflop of computing power – which is 1 trillion operations per second.
Zhou’s research team tested a series of standard programs to determine whether programs translated by their compiler software actually operated more efficiently than code that had been manually optimized for GPU use by leading GPU developers. Their results showed that programs translated by their compiler software ran approximately 30 percent more quickly than those optimized by the GPU developers. The paper, “A GPGPU Compiler for Memory Optimization and Parallelism Management,” was co-authored by Zhou, NC State Ph.D. student Yi Yang, and University of Central Florida Ph.D. students Ping Xiang and Jingfei Kong.
2. Supermicro and Appro have managed to fit Tesla GPUs into a 1U 19-inch rackmount chassis.
3. IBM has struck an important deal with the graphics giant Nvidia that has resulted in the creation of a GPGPU-enabled IBM datacenter.
* IBM has a new datacenter server iDataPlex DX360 M3, this new features dual PCIe X16 slots that house two Nvidia Tesla GPGPU boards. The DX360 M3 with two Tesla C2050 cards installed.
* IBM will begin shipping in the third quarter the Tesla C2070 board with 6GB GDDR5 memory.
* IBM is offering very neat future-proofing option, when either 28nm or 22nm GPUs appear on the scene.