Tensor Memory Allocation and Management Instructions Instructions
3 PTX instructions in this category - click any row for encoding, pseudocode, and full documentation.
| Mnemonic | Syntax | PTX Version | Summary |
|---|---|---|---|
| tcgen05.alloc | tcgen05.alloc.cta_group.sync.aligned{.shared::cta}.b32 [dst], nCols; | PTX ISA 8.6 | tcgen05.alloc is a blocking instruction which dynamically allocates the specified number of columns in the Tensor Memory and writes the address of the allocated Tensor Memory into shared memory at the location specified by address operand dst. |
| tcgen05.dealloc | tcgen05.dealloc.cta_group.sync.aligned.b32 taddr, nCols; | PTX ISA 8.6 | tcgen05.dealloc is a blocking instruction which de-allocates the Tensor Memory specified by the Tensor Memory address taddr. The operand nCols specifies the number of columns to be de-allocated. |
| tcgen05.relinquish_alloc_permit | tcgen05.relinquish_alloc_permit.cta_group.sync.aligned; | PTX ISA 8.6 | tcgen05.relinquish_alloc_permit specifies that the CTA of the executing thread is relinquishing the right to allocate Tensor Memory. |