Mojo module
mma_nvidia_sm100
This module includes utilities for working with the SM100 MMA instructions.
Structs
-
MMASmemDescriptor: Descriptor for shared memory operands tcgen05 mma instructions. -
UMMAInsDescriptor: Descriptor for UMMA instructions. -
UMMAKind: Struct for UMMA instruction types.
Functions
-
mma: Perform a matrix multiply-accumulate operation using the tcgen05.mma instruction. -
mma_arrive: Arrive at the mbar pointer for the MMA instruction. -
mma_arrive_multicast: Arrive at the mbar pointer for the MMA instruction for multiple ctas.
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!