Memory Read Bandwidth, GB/sec

Metric Description

GPU read from chip uncore (LLC) and main memory bandwidth. This metric counts all memory accesses that miss in internal GPU L3 cache, bypass it and are serviced either from uncore or main memory.

See Also

Supplemental documentation specific to a particular Intel Studio may be available at <install-dir>\<studio>\documentation\ .

For more complete information about compiler optimizations, see our Optimization Notice.