Abstract: One embodiment provides for a graphics processing unit to accelerate machine-learning operations, the graphics processing unit comprising a multiprocessor having a single instruction, multiple thread (SIMT) architecture, the multiprocessor to execute at least one single instruction; and a first compute unit included within the multiprocessor, the at least one single instruction to cause the first compute unit to perform a two-dimensional matrix multiply and accumulate operation, wherein to perform the two-dimensional matrix multiply and accumulate operation includes to compute an intermediate product of 16-bit operands and to compute a 32-bit sum based on the intermediate product.

Abstract: Clamping forceps and associated methods are provided that generally include a head section including first and second clamp members configured to cooperatively clamp so as to at least partially encircle a tumor or other structure, an elongated body section in cooperation with the head section, and a clamping mechanism at least partially movably mounted with respect to the elongated body section. The clamping forceps may include a control mechanism for variably controlling the clamping force, at least one sensor mounted with respect to the clamp member(s), means for fixating the clamp member(s) relative to tissue, the first and second clamp members structured to define a variable perimeter extent, and a clamping mechanism which accommodates variable rates of clamping action. Actuation of the clamping mechanism generally maintains substantially parallel actuation of the first and second clamp members with respect to the tumor or the other anatomical structure.