| 60 | class DstEngine, class DstLayout, |
| 61 | class BinaryOp = cute::plus> |
| 62 | CUTE_HOST_DEVICE constexpr |
| 63 | void |
| 64 | batch_reduce(Tensor<SrcEngine, SrcLayout> const& src, // (RedMode, BatchMode) |
| 65 | Tensor<DstEngine, DstLayout> & dst, // (BatchMode) |
| 66 | BinaryOp op = {}) |
| 67 | { |
| 68 | // Precondition |
| 69 | CUTE_STATIC_ASSERT_V(rank(src) == Int<2>{}); |
| 70 | assert(size<1>(src) == size(dst)); |
| 71 | |
| 72 | for (int i = 0; i < size(dst); ++i) { |
| 73 | dst(i) = reduce(src(_,i), dst(i), op); |
| 74 | } |
| 75 | } |
| 76 | |
| 77 | |
| 78 | // Reduce @src tensor along selected modes specified in @target_profile using binary reduction operator @op |
no test coverage detected