Nigel
/
mindspore
forked from mindspore-Ecosystem/mindspore
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

add int32 cal for less gpu

This commit is contained in:
root 2020-08-06 20:35:40 +08:00
parent 9940c723d5
commit 3b41023a6b
3 changed files with 24 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
mindspore/ccsrc/backend/kernel_compiler/gpu/cuda_impl/broadcast_impl.cu
View File

@ -256,6 +256,10 @@ template void Broadcast(const int &l0, const int &l1, const int &l2, const int &
const int &r2, const int &r3, const int &d0, const int &d1, const int &d2, const int &d3,
enum BroadcastOpType op, const int *input0, const int *input1, int *output,
cudaStream_t stream);
template void Broadcast(const int &l0, const int &l1, const int &l2, const int &l3, const int &r0, const int &r1,
const int &r2, const int &r3, const int &d0, const int &d1, const int &d2, const int &d3,
enum BroadcastOpType op, const int *input0, const int *input1, bool *output,
cudaStream_t stream);
template void NoBroadcast(const int &nums, enum BroadcastOpType op, const float *input0, const float *input1,
bool *output, cudaStream_t stream);
template void NoBroadcast(const int &nums, enum BroadcastOpType op, const float *input0, const float *input1,
@ -266,6 +270,8 @@ template void NoBroadcast(const int &nums, enum BroadcastOpType op, const half *
half *output, cudaStream_t stream);
template void NoBroadcast(const int &nums, enum BroadcastOpType op, const int *input0, const int *input1,
int *output, cudaStream_t stream);
template void NoBroadcast(const int &nums, enum BroadcastOpType op, const int *input0, const int *input1,
bool *output, cudaStream_t stream);
template void BroadcastTo(const int &i0, const int &i1, const int &i2, const int &i3, const int &o0, const int &o1,
const int &o2, const int &o3, const float *input_addr, float *output_addr,
cudaStream_t stream);

3
mindspore/ccsrc/backend/kernel_compiler/gpu/math/broadcast_gpu_kernel.cc
View File

@ -103,6 +103,9 @@ MS_REG_GPU_KERNEL_TWO(
BroadcastOpGpuKernel, half, half)
// int32
MS_REG_GPU_KERNEL_TWO(
Less, KernelAttr().AddInputAttr(kNumberTypeInt32).AddInputAttr(kNumberTypeInt32).AddOutputAttr(kNumberTypeBool),
BroadcastOpGpuKernel, int, bool)
MS_REG_GPU_KERNEL_TWO(
TensorAdd, KernelAttr().AddInputAttr(kNumberTypeInt32).AddInputAttr(kNumberTypeInt32).AddOutputAttr(kNumberTypeInt32),
BroadcastOpGpuKernel, int, int)

15
tests/st/ops/gpu/test_broadcast_op.py
View File

@ -29,6 +29,8 @@ def test_nobroadcast():
x1_np = np.random.rand(10, 20).astype(np.float32)
x2_np = np.random.rand(10, 20).astype(np.float32)
x1_np_int32 = np.random.randint(0, 100, (10, 20)).astype(np.int32)
x2_np_int32 = np.random.randint(0, 100, (10, 20)).astype(np.int32)
output_ms = P.Minimum()(Tensor(x1_np), Tensor(x2_np))
output_np = np.minimum(x1_np, x2_np)
@ -45,6 +47,9 @@ def test_nobroadcast():
output_ms = P.Less()(Tensor(x1_np), Tensor(x2_np))
output_np = x1_np < x2_np
assert np.allclose(output_ms.asnumpy(), output_np)
output_ms = P.Less()(Tensor(x1_np_int32), Tensor(x2_np_int32))
output_np = x1_np_int32 < x2_np_int32
assert np.allclose(output_ms.asnumpy(), output_np)
output_ms = P.Pow()(Tensor(x1_np), Tensor(x2_np))
output_np = np.power(x1_np, x2_np)
@ -71,6 +76,8 @@ def test_broadcast():
x1_np = np.random.rand(3, 1, 5, 1).astype(np.float32)
x2_np = np.random.rand(1, 4, 1, 6).astype(np.float32)
x1_np_int32 = np.random.randint(0, 100, (3, 1, 5, 1)).astype(np.int32)
x2_np_int32 = np.random.randint(0, 100, (3, 1, 5, 1)).astype(np.int32)
output_ms = P.Minimum()(Tensor(x1_np), Tensor(x2_np))
output_np = np.minimum(x1_np, x2_np)
@ -87,6 +94,9 @@ def test_broadcast():
output_ms = P.Less()(Tensor(x1_np), Tensor(x2_np))
output_np = x1_np < x2_np
assert np.allclose(output_ms.asnumpy(), output_np)
output_ms = P.Less()(Tensor(x1_np_int32), Tensor(x2_np_int32))
output_np = x1_np_int32 < x2_np_int32
assert np.allclose(output_ms.asnumpy(), output_np)
output_ms = P.Pow()(Tensor(x1_np), Tensor(x2_np))
output_np = np.power(x1_np, x2_np)
@ -113,6 +123,8 @@ def test_broadcast_diff_dims():
x1_np = np.random.rand(2).astype(np.float32)
x2_np = np.random.rand(2, 1).astype(np.float32)
x1_np_int32 = np.random.randint(0, 100, (2)).astype(np.int32)
x2_np_int32 = np.random.randint(0, 100, (2, 1)).astype(np.int32)
output_ms = P.Minimum()(Tensor(x1_np), Tensor(x2_np))
output_np = np.minimum(x1_np, x2_np)
@ -129,6 +141,9 @@ def test_broadcast_diff_dims():
output_ms = P.Less()(Tensor(x1_np), Tensor(x2_np))
output_np = x1_np < x2_np
assert np.allclose(output_ms.asnumpy(), output_np)
output_ms = P.Less()(Tensor(x1_np_int32), Tensor(x2_np_int32))
output_np = x1_np_int32 < x2_np_int32
assert np.allclose(output_ms.asnumpy(), output_np)
output_ms = P.Pow()(Tensor(x1_np), Tensor(x2_np))
output_np = np.power(x1_np, x2_np)