Titanic Pixels.

1 2 3ALL

In examining the diagram above.  We can instantly deduce that the basic principal of hoards of cuda cores singing in delightful unison is all but identical .  The discrepancies lie mainly in the sheer numbers of Clusters, Streaming multi-processors and Cores that Nvidia has squeezed onto the die.

Whereas the GK104 played host to four GPCs (graphics processing clusters) the GK110 incorporates five.  Moreover, four of these clusters contains an one additional SMX, making a total of three SMXs per cluster compared to the GK104’s two.  The last cluster has had one of its SMXs disbled to improve yield rates , meaning that the GK110’s grand SMX count comes to 14 instead of 15.  Nevertheless, this is almost twice as many as its little brother and should provide some impressive performance gains.

Zooming in a little reveals that the configuration within each SMX remains largely unaltered.  The same number of cores (192) and texture units (16)  are present in both but because of the GK110’s 6 additional SMXs, the cumulative tally come to 2688 texture units compared to the GK104’s 1536 and 224 texture units as against 128.

1 2 3ALL