[FRONTEND][BACKEND] Fixes for cat / reshape / addptr (#959)
Most notably, this PR: - changes the traits (and assembly format) of addptr so it can handle offsets that have arbitrary integer width. - adds support for `cat`
This commit is contained in:
@@ -35,8 +35,8 @@ func @matmul_loop(%lb : index, %ub : index, %step : index, %A : !tt.ptr<f16>, %B
|
||||
|
||||
%c = tt.dot %a, %b, %prev_c {allowTF32 = true, transA = false, transB = false} : tensor<128x32xf16, #A_DOT> * tensor<32x128xf16, #B_DOT> -> tensor<128x128xf32, #C>
|
||||
|
||||
%next_a_ptr = tt.addptr %a_ptr, %a_off : tensor<128x32x!tt.ptr<f16>, #AL>
|
||||
%next_b_ptr = tt.addptr %b_ptr, %b_off : tensor<32x128x!tt.ptr<f16>, #BL>
|
||||
%next_a_ptr = tt.addptr %a_ptr, %a_off : tensor<128x32x!tt.ptr<f16>, #AL>, tensor<128x32xi32, #AL>
|
||||
%next_b_ptr = tt.addptr %b_ptr, %b_off : tensor<32x128x!tt.ptr<f16>, #BL>, tensor<32x128xi32, #BL>
|
||||
scf.yield %next_a_ptr, %next_b_ptr, %c : tensor<128x32x!tt.ptr<f16>, #AL>, tensor<32x128x!tt.ptr<f16>, #BL>, tensor<128x128xf32, #C>
|
||||
}
|
||||
return
|
||||
|
Reference in New Issue
Block a user