He's referring to the fact that the GeForce line of consumer grade GPUs and the professional line of Tesla HPC Compute cards are probably using the same silicon.
I thought Tesla GPUs are tested to higher standards (e.g. Stable at higher clock speed) and don't have disabled/faulty cores. Consumer GPUs have GPU cores disabled permitting higher silicon production yields.
Core disabling and under clocking are what's known as "product binning" and it's why you have 4, 6, 8, and 12 core CPUs. Tesla GPUs are probably the cream of the crop but they're still cut from the same cloth.
