Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

qnnpack quantized activations: fix memory format issues #46077

Closed
wants to merge 2 commits into from
Closed

qnnpack quantized activations: fix memory format issues #46077

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ffea8c7
qnnpack quantized activations: fix memory format issues
vkuzo Oct 9, 2020
349e579
rebase on "qnnpack quantized activations: fix memory format issues"
vkuzo Oct 9, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
5 changes: 3 additions & 2 deletions aten/src/ATen/native/quantized/cpu/qhardsigmoid.cpp
View file
Open in desktop
Expand Up @@ -43,9 +43,10 @@ Tensor qnnpack_hardsigmoid(Tensor input) {
"failed to create QNNPACK Hardsigmoid operator");
Tensor qy = at::_empty_affine_quantized(
input_contig.sizes(),
input_contig.options(),
at::device(kCPU).dtype(input_contig.dtype()),
o_scale,
o_zero_point);
o_zero_point,
input_contig.suggest_memory_format());

const pytorch_qnnp_status setupStatus = pytorch_qnnp_setup_hardsigmoid_nc_q8(
hardsigmoid_op,
Expand Down
5 changes: 3 additions & 2 deletions aten/src/ATen/native/quantized/cpu/qsigmoid.cpp
View file
Open in desktop
Expand Up @@ -48,9 +48,10 @@ Tensor qnnpack_sigmoid(
"failed to create QNNPACK sigmoid operator");
qy = at::_empty_affine_quantized(
input_contig.sizes(),
input.options(),
at::device(kCPU).dtype(input_contig.dtype()),
output_scale,
output_zero_point);
output_zero_point,
input_contig.suggest_memory_format());

const pytorch_qnnp_status setupStatus = pytorch_qnnp_setup_sigmoid_nc_q8(
sigmoid_op,
Expand Down
5 changes: 3 additions & 2 deletions aten/src/ATen/native/quantized/cpu/qtanh.cpp
View file
Open in desktop
Expand Up @@ -50,9 +50,10 @@ Tensor qnnpack_tanh(Tensor input) {
"failed to create QNNPACK TanH operator");
qy = at::_empty_affine_quantized(
input_contig.sizes(),
input.options(),
at::device(kCPU).dtype(input_contig.dtype()),
output_scale,
output_zero_point);
output_zero_point,
input_contig.suggest_memory_format());

const pytorch_qnnp_status setupStatus = pytorch_qnnp_setup_tanh_nc_q8(
tanh_op,
Expand Down