From deea0be070d67734f7cc113b38e4fa71965744ef Mon Sep 17 00:00:00 2001
From: Olivier BICHLER <olivier.bichler@cea.fr>
Date: Mon, 29 Jan 2024 09:29:50 +0100
Subject: [PATCH] makeContiguous optimization (single copy for contiguous
chuncks of memory)
---
src/data/Tensor.cpp | 20 +++++++++++++++++---
1 file changed, 17 insertions(+), 3 deletions(-)
diff --git a/src/data/Tensor.cpp b/src/data/Tensor.cpp
index 6ab096201..d45dee563 100644
--- a/src/data/Tensor.cpp
+++ b/src/data/Tensor.cpp
@@ -45,10 +45,24 @@ void Aidge::Tensor::makeContiguous() {
{
// Create a new storage that will be contiguous
std::shared_ptr<TensorImpl> newImpl = Registrar<Tensor>::create({mImpl->backend(), mDataType})(mImpl->device().second, mSize);
- // Copy elements one by one from old to new storage
- for (size_t idx = 0; idx < mSize; ++idx) {
+ // Copy elements from old to new storage
+ size_t idx = 0;
+ while (idx < mSize) {
const size_t storageIdx = getStorageIdx(getCoord(idx));
- newImpl->copy(mImpl->rawPtr(mImplOffset + storageIdx), 1, idx);
+
+ // Determine the size of the contiguous chunk
+ size_t copySize = 1;
+ while (idx + copySize < mSize &&
+ getStorageIdx(getCoord(idx + copySize)) == storageIdx + copySize)
+ {
+ ++copySize;
+ }
+
+ // Perform a single copy for the contiguous chunk
+ newImpl->copy(mImpl->rawPtr(mImplOffset + storageIdx), copySize, idx);
+
+ // Move to the next index after the contiguous chunk
+ idx += copySize;
}
// Replace old storage by new, contiguous, storage
setImpl(newImpl);
--
GitLab