Gemm - 1 vs 6#
Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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.
- Gemm1 → Gemm6 +1 -1
Gemm1 → Gemm6
RENAMED
|
@@ -1 +1 @@
|
|
|
1
1
|
General Matrix multiplication:
|
|
2
2
|
https://en.wikipedia.org/wiki/Basic_Linear_Algebra_Subprograms#Level_3
|
|
3
3
|
Compute Y = alpha * A * B + beta * C, where input tensor A has
|
|
4
4
|
dimension (M X K), input tensor B has dimension (K X N), input tensor C and
|
|
5
5
|
output tensor Y have dimension (M X N).
|
|
6
6
|
If attribute broadcast is non-zero, input tensor C will be broadcasted to match
|
|
7
7
|
the dimension requirement. A will be transposed before doing the computation
|
|
8
8
|
if attribute transA is non-zero, same for B and transB.
|
|
9
9
|
**Attributes**
|
|
10
10
|
* **alpha**:
|
|
11
11
|
Scalar multiplier for the product of input tensors A * B, the
|
|
12
12
|
default value is 1.0.
|
|
13
13
|
* **beta**:
|
|
14
14
|
Scalar multiplier for input tensor C, the default value is 1.0.
|
|
15
15
|
* **broadcast**:
|
|
16
16
|
Whether C should be broadcasted
|
|
17
17
|
* **transA**:
|
|
18
18
|
Whether A should be transposed
|
|
19
19
|
* **transB**:
|
|
20
20
|
Whether B should be transposed
|
|
21
21
|
**Inputs**
|
|
22
22
|
* **A** (heterogeneous) - **T**:
|
|
23
23
|
Input tensor A
|
|
24
24
|
* **B** (heterogeneous) - **T**:
|
|
25
25
|
Input tensor B
|
|
26
26
|
* **C** (heterogeneous) - **T**:
|
|
27
|
-
Input tensor C
|
|
27
|
+
Input tensor C, can be inplace.
|
|
28
28
|
**Outputs**
|
|
29
29
|
* **Y** (heterogeneous) - **T**:
|
|
30
30
|
Output tensor.
|
|
31
31
|
**Type Constraints**
|
|
32
32
|
* **T** in (
|
|
33
33
|
tensor(double),
|
|
34
34
|
tensor(float),
|
|
35
35
|
tensor(float16)
|
|
36
36
|
):
|
|
37
37
|
Constrain input and output types to float tensors.
|