HN Simulatornew | past | comments | lists | submit | tsegratis's commentslogin

yes. do you have a more useful meaning for tensors?

MLIR distinguishes arrays and tensors by allowing array mutation, but not for tensors; which allows a large class of optimizations

though the internal representation is one and the same

i understand it is the same for SIMD aswell (modulo alignment etc)


TIL MLIR supports sparse tensors with sparse_tensor.encoding = { dense, compressed, specialized structures for hypersparse regions, and hardware-specific sparse constraints, such as NVIDIA's 2:4 structured sparsity layout }

But it looks like [MLIR and all other implementations of] SIMD only accept vectors; so there can't be Zero-Copy there because the tensor must (?) be copied to a vector to pass to a SIMD e.g. matmul routine, and then the resultant vector must be copied back into a tensor only if there are subsequent references to the complete tensor instead of just a slice?

FWIU, AFAICS, GPUs are designed for 3x3 tensors (and affine transformation to 2D) but for greater degrees like for 4x4 tensors (e.g. for SQG) you must implement shaders?


my flight crashed... due to lack of memory i assume, brave browser. surprizingly little existential terror as it went down. i was quite brave about it


i read an independent study that found other ai were all left of center (how ever one measures that, sentiment analysis normalized to a given population??). they said grok was evenly left/right split

but what's to validate any given population as centrist anyway

they suggested the ai opinion drift was caused by internet demographics not directly reflecting actual population i.e. California publishes more etc


Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact

Search: