[not for land, ci only] fake_quant: add a more memory efficient version #50849

vkuzo · 2021-01-20T22:25:42Z

Summary:

Not for review yet, a bunch of TODOs need finalizing.

tl;dr; add an alternative implementation of fake_quantize which saves
a ask during the forward pass and uses it to calculate the backward.

There are two benefits:

the backward function no longer needs the input Tensor, and it can be
gc'ed earlier by autograd. On MobileNetV2, this reduces QAT overhead
by ~15% (TODO: link, and absolute numbers). We add an additional mask Tensor
to pass around, but its size is 4x smaller than the input tensor. A
future optimization would be to pack the mask bitwise and unpack in the
backward.
the computation of qval can be done only once in the forward and
reused in the backward. No perf change observed, TODO verify with better
matrics.

TODO: describe in more detail

Test Plan:

OSS / torchvision / MobileNetV2

python references/classification/train_quantization.py
  --print-freq 1
  --data-path /data/local/packages/ai-group.imagenet-256-smallest-side/prod/
  --output-dir ~/nfs/pytorch_vision_tests/
  --backend qnnpack
  --epochs 5
TODO paste results here

TODO more

Reviewers:

Subscribers:

Tasks:

Tags:

ghstack-source-id: f932055ee57b6a4e419d3896fb605c58fc063668
Pull Request resolved: #50561

Fixes #{issue number}

Summary: Not for review yet, a bunch of TODOs need finalizing. tl;dr; add an alternative implementation of `fake_quantize` which saves a ask during the forward pass and uses it to calculate the backward. There are two benefits: 1. the backward function no longer needs the input Tensor, and it can be gc'ed earlier by autograd. On MobileNetV2, this reduces QAT overhead by ~15% (TODO: link, and absolute numbers). We add an additional mask Tensor to pass around, but its size is 4x smaller than the input tensor. A future optimization would be to pack the mask bitwise and unpack in the backward. 2. the computation of `qval` can be done only once in the forward and reused in the backward. No perf change observed, TODO verify with better matrics. TODO: describe in more detail Test Plan: OSS / torchvision / MobileNetV2 ``` python references/classification/train_quantization.py --print-freq 1 --data-path /data/local/packages/ai-group.imagenet-256-smallest-side/prod/ --output-dir ~/nfs/pytorch_vision_tests/ --backend qnnpack --epochs 5 TODO paste results here ``` TODO more Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: f932055ee57b6a4e419d3896fb605c58fc063668 Pull Request resolved: #50561

Summary: tl;dr; add an alternative implementation of `fake_quantize` which saves a mask of whether the input was clamped during the forward pass and uses it to calculate the backward. The math: ``` # before - forward (pseudocode) def fq_forward(x, scale, zp, qmin, qmax): q_val = clamp(nearby_int(x / scale) + zp, qmin, qmax) fq_val = (q_val - zp) * scale return fq_val # before - backward (pseudocode) def fq_backward(dy, x, scale, zp, qmin, qmax): q_val_unclamped = nearby_int(x / scale) + zp mask = qmin <= q_val_unclamped and q_val_unclamped <= qmax return dy * mask # after - forward (pseudocode) def fq_forward(x, scale, zp, qmin, qmax): q_val_unclamped = nearby_int(x / scale) + zp mask = qmin <= q_val_unclamped and q_val_unclamped <= qmax q_val = clamp(q_val_unclamped, qmin, qmax) fq_val = (q_val - zp) * scale return fq_val, mask # after - backward (pseudocode) def fq_backward(dy, mask): return dy * mask ``` This way the backward function no longer needs the input Tensor, and it can be gc'ed earlier by autograd. Instead of passing `x: FloatTensor`, we pass a `mask: BoolTensor` with the same number of elements. `BoolTensor` uses 1 byte per element, so we expect an upper bound of a 75% memory overhead reduction. We observe a 73% memory overhead reduction on torchvision's MobileNetV2 in real world tests. Packing the bools into a custom storage format to take 1 bit per element is an optimization left for the future. Performance impact of this seems negligible, I observed a 1% to 5% regression on MobileNetV2 but it's unclear if it's real. Adding this as a new function (as opposed to replacing the old implementation) for easy testing, but might be worth deleting the old fake_quant backward in a future PR. We can adjust the signature of this function to take `model.training` as an additional parameter, and skip the mask computation for eval. Test Plan: QAT on MobileNetV2 on FB infra, with `opt` build flags, batch_size = 32. Results for fbgemm settings, qnnpack results are similar. ``` # qat_fp32: model with fake_quants turned off (baseline) # qat_1: step 2 of qat, with observers disabled and fake_quants enabled (all of the overhead is the fake_quants) # before: fbgemm - qat_fp32 -> qat_1 max memory usage (mib): 3299 -> 4170 (overhead: 26.4%) latency (ms): 147 -> 181 # after: fbgemm - qat_fp32 -> qat_1 max memory usage (mib): 3302 -> 3528 (overhead: 7.1%) latency (ms): 147 -> 183 ``` Note: similar metrics are observed in an OSS / torchvision / MobileNetV2 setup, with this command: ``` python references/classification/train_quantization.py --print-freq 1 --data-path /data/local/packages/ai-group.imagenet-256-smallest-side/prod/ --output-dir ~/nfs/pytorch_vision_tests/ --backend qnnpack --epochs 5 ``` All CI tests here: #50849 Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D25918519](https://our.internmc.facebook.com/intern/diff/D25918519) [ghstack-poisoned]

Summary: tl;dr; add an alternative implementation of `fake_quantize` which saves a mask of whether the input was clamped during the forward pass and uses it to calculate the backward. The math: ``` # before - forward (pseudocode) def fq_forward(x, scale, zp, qmin, qmax): q_val = clamp(nearby_int(x / scale) + zp, qmin, qmax) fq_val = (q_val - zp) * scale return fq_val # before - backward (pseudocode) def fq_backward(dy, x, scale, zp, qmin, qmax): q_val_unclamped = nearby_int(x / scale) + zp mask = qmin <= q_val_unclamped and q_val_unclamped <= qmax return dy * mask # after - forward (pseudocode) def fq_forward(x, scale, zp, qmin, qmax): q_val_unclamped = nearby_int(x / scale) + zp mask = qmin <= q_val_unclamped and q_val_unclamped <= qmax q_val = clamp(q_val_unclamped, qmin, qmax) fq_val = (q_val - zp) * scale return fq_val, mask # after - backward (pseudocode) def fq_backward(dy, mask): return dy * mask ``` This way the backward function no longer needs the input Tensor, and it can be gc'ed earlier by autograd. Instead of passing `x: FloatTensor`, we pass a `mask: BoolTensor` with the same number of elements. `BoolTensor` uses 1 byte per element, so we expect an upper bound of a 75% memory overhead reduction. We observe a 73% memory overhead reduction on torchvision's MobileNetV2 in real world tests. Packing the bools into a custom storage format to take 1 bit per element is an optimization left for the future. Performance impact of this seems negligible, I observed a 1% to 5% regression on MobileNetV2 but it's unclear if it's real. Adding this as a new function (as opposed to replacing the old implementation) for easy testing, but might be worth deleting the old fake_quant backward in a future PR. We can adjust the signature of this function to take `model.training` as an additional parameter, and skip the mask computation for eval. Test Plan: QAT on MobileNetV2 on FB infra, with `opt` build flags, batch_size = 32. Results for fbgemm settings, qnnpack results are similar. ``` # qat_fp32: model with fake_quants turned off (baseline) # qat_1: step 2 of qat, with observers disabled and fake_quants enabled (all of the overhead is the fake_quants) # before: fbgemm - qat_fp32 -> qat_1 max memory usage (mib): 3299 -> 4170 (overhead: 26.4%) latency (ms): 147 -> 181 # after: fbgemm - qat_fp32 -> qat_1 max memory usage (mib): 3302 -> 3528 (overhead: 7.1%) latency (ms): 147 -> 183 ``` Note: similar metrics are observed in an OSS / torchvision / MobileNetV2 setup, with this command: ``` python references/classification/train_quantization.py --print-freq 1 --data-path /data/local/packages/ai-group.imagenet-256-smallest-side/prod/ --output-dir ~/nfs/pytorch_vision_tests/ --backend qnnpack --epochs 5 ``` All CI tests here: #50849 PyTorch microbenchmarks (CUDA performance about the same: https://gist.github.com/vkuzo/11a7bed73fe60e340862d37e7975e9cd) Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D25918519](https://our.internmc.facebook.com/intern/diff/D25918519) [ghstack-poisoned]

Summary: tl;dr; add an alternative implementation of `fake_quantize` which saves a mask of whether the input was clamped during the forward pass and uses it to calculate the backward. The math: ``` # before - forward (pseudocode) def fq_forward(x, scale, zp, qmin, qmax): q_val = clamp(nearby_int(x / scale) + zp, qmin, qmax) fq_val = (q_val - zp) * scale return fq_val # before - backward (pseudocode) def fq_backward(dy, x, scale, zp, qmin, qmax): q_val_unclamped = nearby_int(x / scale) + zp mask = qmin <= q_val_unclamped and q_val_unclamped <= qmax return dy * mask # after - forward (pseudocode) def fq_forward(x, scale, zp, qmin, qmax): q_val_unclamped = nearby_int(x / scale) + zp mask = qmin <= q_val_unclamped and q_val_unclamped <= qmax q_val = clamp(q_val_unclamped, qmin, qmax) fq_val = (q_val - zp) * scale return fq_val, mask # after - backward (pseudocode) def fq_backward(dy, mask): return dy * mask ``` This way the backward function no longer needs the input Tensor, and it can be gc'ed earlier by autograd. Instead of passing `x: FloatTensor`, we pass a `mask: BoolTensor` with the same number of elements. `BoolTensor` uses 1 byte per element, so we expect an upper bound of a 75% memory overhead reduction. We observe a 73% memory overhead reduction on torchvision's MobileNetV2 in real world tests. Packing the bools into a custom storage format to take 1 bit per element is an optimization left for the future. Performance impact of this seems negligible, I observed a 1% to 5% regression on MobileNetV2 but it's unclear if it's real. Adding this as a new function (as opposed to replacing the old implementation) for easy testing, but might be worth deleting the old fake_quant backward in a future PR. We can adjust the signature of this function to take `model.training` as an additional parameter, and skip the mask computation for eval. Test Plan: QAT on MobileNetV2 on FB infra, with `opt` build flags, batch_size = 32. Results for fbgemm settings, qnnpack results are similar. ``` # qat_fp32: model with fake_quants turned off (baseline) # qat_1: step 2 of qat, with observers disabled and fake_quants enabled (all of the overhead is the fake_quants) # before: fbgemm - qat_fp32 -> qat_1 max memory usage (mib): 3299 -> 4170 (overhead: 26.4%) latency (ms): 147 -> 181 # after: fbgemm - qat_fp32 -> qat_1 max memory usage (mib): 3302 -> 3528 (overhead: 7.1%) latency (ms): 147 -> 183 ``` Note: similar metrics are observed in an OSS / torchvision / MobileNetV2 setup, with this command: ``` python references/classification/train_quantization.py --print-freq 1 --data-path /data/local/packages/ai-group.imagenet-256-smallest-side/prod/ --output-dir ~/nfs/pytorch_vision_tests/ --backend qnnpack --epochs 5 ``` All CI tests here: #50849 PyTorch microbenchmarks (CUDA performance about the same: ``` cd benchmarks/operator_benchmark python -m pt.quantization_test ``` results: https://gist.github.com/vkuzo/11a7bed73fe60e340862d37e7975e9cd) Unit tests: ``` python test/test_quantization.py TestFakeQuantize ``` Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D25918519](https://our.internmc.facebook.com/intern/diff/D25918519) [ghstack-poisoned]

facebook-github-bot added the cla signed label Jan 20, 2021

vkuzo mentioned this pull request Jan 20, 2021

fake_quant: add a more memory efficient backward #50561

Closed

vkuzo closed this Feb 8, 2021

github-actions bot deleted the ci-all/vkuzo/fake_quant_test_20210120 branch February 10, 2024 01:53

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[not for land, ci only] fake_quant: add a more memory efficient version #50849

[not for land, ci only] fake_quant: add a more memory efficient version #50849

vkuzo commented Jan 20, 2021

[not for land, ci only] fake_quant: add a more memory efficient version #50849

[not for land, ci only] fake_quant: add a more memory efficient version #50849

Conversation

vkuzo commented Jan 20, 2021