From ff4f06cecd0e3320678039e10f798e5144f52f77 Mon Sep 17 00:00:00 2001 From: auphelia <jakobapk@web.de> Date: Fri, 8 May 2020 14:57:25 +0100 Subject: [PATCH] [Sphinx-Documentation] Refer from network preparation to new section about mem mode --- docs/finn/internals.rst | 2 ++ docs/finn/nw_prep.rst | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/docs/finn/internals.rst b/docs/finn/internals.rst index 60d0cf04f..7a4bc687e 100644 --- a/docs/finn/internals.rst +++ b/docs/finn/internals.rst @@ -138,6 +138,8 @@ Transformation Pass A transformation passes changes (transforms) the given model, it gets the model in the ModelWrapper as input and returns the changed model (ModelWrapper) to the FINN flow. Additional the flag *model_was_changed* which indicates if a transformation has to be performed more than once, is returned. If you are interested in how to write a transformation pass for FINN, please take a look at the Jupyter notebook about how to write a transformation pass, see chapter :ref:`tutorials` for details. For more information about existing transformation passes in FINN, see module :py:mod:`finn.transformation`. +.. _mem_mode: + StreamingFCLayer *mem_mode* =========================== diff --git a/docs/finn/nw_prep.rst b/docs/finn/nw_prep.rst index 2ccbb8d0f..f9909d2be 100644 --- a/docs/finn/nw_prep.rst +++ b/docs/finn/nw_prep.rst @@ -37,7 +37,7 @@ After this transformation the ONNX model is streamlined and contains now custom Convert to HLS Layers ===================== -Pairs of binary XNORPopcountMatMul layers are converted to StreamingFCLayers and following Multithreshold layers are absorbed into the MVTU. The result is a model consisting of a mixture of HLS and non-HLS layers. For more details, see :py:mod:`finn.transformation.fpgadataflow.convert_to_hls_layers`. +Pairs of binary XNORPopcountMatMul layers are converted to StreamingFCLayers and following Multithreshold layers are absorbed into the Matrix-Vector-Activate-Unit (MVAU). The result is a model consisting of a mixture of HLS and non-HLS layers. For more details, see :py:mod:`finn.transformation.fpgadataflow.convert_to_hls_layers`. The MVAU can be implemented in two different modes, *const* and *decoupled*, see chapter :ref:`mem_mode`. Dataflow Partitioning ===================== -- GitLab