mirror of
https://github.com/tinygrad/tinygrad.git
synced 2026-01-09 06:58:11 -05:00
9268a8b154
* init * removed mulacc * is uoptimize the problem? * lol hax make work temporarily fix l8er * revert extra/ changes * clean up * flaky metal tests? * add back mulacc for metal * revert last commit * try skipping linearizer_failure tests * skip flammit tests... cuz tests all work locally * try narrow down exact linearizer failure test * try 2 * try 4 * generated code is the exact same wtf why CI fails * code for 15 and 17 are exact same with or without mulacc, this should pass * try only 1 failure * try garbage collecting lol... * try del variables lol * try gcing after del lol... * is diskcache the problem??? * try disabling opts cache idk * try remove hack * try disable github metal cache... * try CACHELEVEL=0 :D idk anymore * try increase newCommandQueueWithMaxCommandBufferCount_, im almost out of ideas... * revert * actually not a HACK * oops
1.5 KiB
1.5 KiB
Adding a new accelerator to tinygrad
It's pretty easy to add a new accelerator to tinygrad. All you need to do is implement a total of 20 (optionally 21) low level ops. Then tinygrad takes care of the rest, handling derivatives and syntactic sugar.
llops
These are the ops that you must implement for your accelerator of choice.
Buffer # class of memory on this device
unary_op (NOOP, EXP2, LOG2, CAST, SIN, SQRT) # A -> A
reduce_op (SUM, MAX) # A -> B (smaller size, B has 1 in shape)
binary_op (ADD, SUB, MUL, DIV, CMPEQ, MAX) # A + A -> A (all the same size)
load_op (EMPTY, CONST, FROM, CONTIGUOUS, CUSTOM) # -> A (initialize data on device)
ternary_op (WHERE) # A, A, A -> A
mlops
These are the mid level ops that handle the derivatives.
Relu, Log, Exp, Sin # unary ops
Sum, Max # reduce ops (with axis argument)
Maximum, Add, Sub, Mul, Pow, Div, Equal # binary ops (no broadcasting, use expand)
Expand, Reshape, Permute, Pad, Shrink, Flip # movement ops
Where # ternary ops
These are implemented in mlops.py.
hlops
These are the syntax sugar. They are built on top of the mlops and support most of the things that you could expect from a tensor library.
These are implemented in tensor.py.