Productive, portable, and performant GPU programming in Python.
COMMITS
/ tests/cpp/transforms/half2_vectorization_test.cpp July 27, 2023
魔
July 10, 2023
L
[lang] Add arg_depth property to Expressions and Statements
listerily committed
June 1, 2023
Z
[Lang] Merge irpass::half2_vectorize() with irpass::scalarize() (#8102)
Zhanlue Yang committed
April 21, 2023
A
[refactor] Get rid of unused is_grad in ArgLoadStmt
Ailing Zhang committed
April 20, 2023
L
[refactor] Add the shape of the Ndarray to the argument struct
lin-hitonami committed
L
[refactor] Compile the Ndarray argument to a struct
lin-hitonami committed
April 19, 2023
Z
[lang] Postpone scalarize and lower_matrix_ptr to after full_simplify I (#7798)
Zhanlue Yang committed
April 11, 2023
L
[ir] Add 'create_load' to ArgLoadStmt
lin-hitonami committed
March 20, 2023
A
[opt] Constant folding for unary ops on host (#7573)
Ailing committed
March 2, 2023
Z
[opt] Enable half2 optimization for atomic_add operations on CUDA backend (#7465)
Zhanlue Yang committed