Skip to content

feat: Expose accumulation mode flag via Conv2dInfo #1289

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

Open
Sqvid wants to merge 1 commit into
base: main
Choose a base branch
from
+7 −4
Open

feat: Expose accumulation mode flag via Conv2dInfo #1289

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 6 additions & 3 deletions arm_compute/runtime/FunctionDescriptors.h
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
/*
* Copyright (c) 2019-2023, 2025 Arm Limited.
* Copyright (c) 2019-2023, 2025-2026 Arm Limited.
*
* SPDX-License-Identifier: MIT
*
Expand Down Expand Up @@ -67,13 +67,15 @@ struct Conv2dInfo
const ActivationLayerInfo &act_info,
bool enable_fast_math,
unsigned int num_groups,
const WeightsInfo &weights_info = WeightsInfo())
const WeightsInfo &weights_info = WeightsInfo(),
bool use_fp32_acc = false)
: conv_info(conv_info),
dilation(dilation),
act_info(act_info),
enable_fast_math(enable_fast_math),
num_groups(num_groups),
weights_info(weights_info)
weights_info(weights_info),
use_fp32_acc(use_fp32_acc)
{
}

Expand All @@ -83,6 +85,7 @@ struct Conv2dInfo
bool enable_fast_math{false};
unsigned int num_groups{1};
WeightsInfo weights_info{};
bool use_fp32_acc{false};
Copy link
Copy Markdown
Contributor

@gunes-arm gunes-arm May 12, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you add an inline comment saying
// Relevant only for Fp16

};

/** Descriptor used by the 3d Convolution function */
Expand Down
2 changes: 1 addition & 1 deletion src/cpu/operators/CpuGemmDirectConv2d.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -93,7 +93,7 @@ cpu::AsmGemmInfo init_assembly_metadata(const Conv2dInfo &info, bool is_indirect
asm_info.fast_mode = info.enable_fast_math;
asm_info.fixed_format = info.weights_info.weight_format() != WeightFormat::UNSPECIFIED;
asm_info.weight_format = info.weights_info.weight_format();
asm_info.use_fp32_acc = !info.enable_fast_math;
asm_info.use_fp32_acc = info.use_fp32_acc;
return asm_info;
}
} // namespace
Expand Down