Gemm - 11 vs 13#

Next section compares an older to a newer version of the same operator after both definition are converted into markdown text. Green means an addition to the newer version, red means a deletion. Anything else is unchanged.

Files changed (1) hide show
  1. Gemm11 → Gemm13 +0 -1
Gemm11 → Gemm13 RENAMED
@@ -1 +1 @@
1
1
  General Matrix multiplication:
2
2
  https://en.wikipedia.org/wiki/Basic_Linear_Algebra_Subprograms#Level_3
3
3
  A' = transpose(A) if transA else A
4
4
  B' = transpose(B) if transB else B
5
5
  Compute Y = alpha * A' * B' + beta * C, where input tensor A has shape (M, K) or (K, M),
6
6
  input tensor B has shape (K, N) or (N, K), input tensor C is broadcastable to shape (M, N),
7
7
  and output tensor Y has shape (M, N). A will be transposed before doing the
8
8
  computation if attribute transA is non-zero, same for B and transB.
9
9
  This operator supports **unidirectional broadcasting** (tensor C should be unidirectional broadcastable to tensor A * B); for more details please check Broadcasting in ONNX <https://github.com/onnx/onnx/blob/master/docs/Broadcasting.md>_.
10
10
  This operator has **optional** inputs/outputs. See ONNX <https://github.com/onnx/onnx/blob/master/docs/IR.md>_ for more details about the representation of optional arguments. An empty string may be used in the place of an actual argument's name to indicate a missing argument. Trailing optional arguments (those not followed by an argument that is present) may also be simply omitted.
11
11
  **Attributes**
12
12
  * **alpha**:
13
13
  Scalar multiplier for the product of input tensors A * B.
14
14
  * **beta**:
15
15
  Scalar multiplier for input tensor C.
16
16
  * **transA**:
17
17
  Whether A should be transposed
18
18
  * **transB**:
19
19
  Whether B should be transposed
20
20
  **Inputs**
21
21
  Between 2 and 3 inputs.
22
22
  * **A** (heterogeneous) - **T**:
23
23
  Input tensor A. The shape of A should be (M, K) if transA is 0, or
24
24
  (K, M) if transA is non-zero.
25
25
  * **B** (heterogeneous) - **T**:
26
26
  Input tensor B. The shape of B should be (K, N) if transB is 0, or
27
27
  (N, K) if transB is non-zero.
28
28
  * **C** (optional, heterogeneous) - **T**:
29
29
  Optional input tensor C. If not specified, the computation is done
30
30
  as if C is a scalar 0. The shape of C should be unidirectional
31
31
  broadcastable to (M, N).
32
32
  **Outputs**
33
33
  * **Y** (heterogeneous) - **T**:
34
34
  Output tensor of shape (M, N).
35
35
  **Type Constraints**
36
36
  * **T** in (
37
- tensor(bfloat16),
38
37
  tensor(double),
39
38
  tensor(float),
40
39
  tensor(float16),
41
40
  tensor(int32),
42
41
  tensor(int64),
43
42
  tensor(uint32),
44
43
  tensor(uint64)
45
44
  ):
46
45
  Constrain input and output types to float/int tensors.