README: Document supported compiler versions, zsh setup for macOS; RTL sim cleanup (#117)

Author: Robert Muchsel

README.md

@@ -1,6 +1,6 @@
 # MAX78000 Model Training and Synthesis
 
-_March 17, 2021_
+_March 18, 2021_
 
 The Maxim Integrated AI project is comprised of four repositories:
 
@@ -117,7 +117,7 @@ eval "$(pyenv init -)"
 eval "$(pyenv virtualenv-init -)"
 ```
 
-If you use zsh as the shell (default on macOS), add these same commands to  `~/.zshrc` in addition.
+If you use zsh as the shell (default on macOS), add these same commands to `~/.zprofile` or `~/.zshrc` in addition to adding them to the bash startup scripts.
 
 Next, close the Terminal, open a new Terminal and install Python 3.8.6.
 
@@ -157,7 +157,7 @@ For convenience, define a shell variable named `AI_PROJECT_ROOT`:
 $ export AI_PROJECT_ROOT="$HOME/Documents/Source/AI"
 ```
 
-Add this line to `~/.profile`.
+Add this line to `~/.profile` (and on macOS, to `~/.zprofile`).
 
 #### Nervana Distiller
 
@@ -326,13 +326,13 @@ With the installation of Training and Synthesis projects completed it is importa
 
 The MAX78000 SDK is a git submodule of ai8x-synthesis. It is checked out automatically to a version compatible with the project into the folder `sdk`.
 
-***If the embedded C compiler is run on Windows instead of Linux, ignore this section*** *and install the Maxim SDK executable, see https://github.com/MaximIntegratedAI/MaximAI_Documentation.*
+***If the embedded C compiler is run on Windows instead of Linux or macOS, ignore this section*** *and install the Maxim SDK executable, see https://github.com/MaximIntegratedAI/MaximAI_Documentation.*
 
-The Arm embedded compiler can be downloaded from [https://developer.arm.com/tools-and-software/open-source-software/developer-tools/gnu-toolchain/gnu-rm/downloads](https://developer.arm.com/tools-and-software/open-source-software/developer-tools/gnu-toolchain/gnu-rm/downloads).
+The Arm embedded compiler can be downloaded from [https://developer.arm.com/tools-and-software/open-source-software/developer-tools/gnu-toolchain/gnu-rm/downloads](https://developer.arm.com/tools-and-software/open-source-software/developer-tools/gnu-toolchain/gnu-rm/downloads). *The SDK has been tested with version 9-2019-q4-major of the embedded Arm compiler. Newer versions may or may not work correctly.*
 
-The RISC-V embedded compiler can be downloaded from [https://github.com/xpack-dev-tools/riscv-none-embed-gcc-xpack/releases/](https://github.com/xpack-dev-tools/riscv-none-embed-gcc-xpack/releases/).
+The RISC-V embedded compiler can be downloaded from [https://github.com/xpack-dev-tools/riscv-none-embed-gcc-xpack/releases/](https://github.com/xpack-dev-tools/riscv-none-embed-gcc-xpack/releases/). *The SDK has been tested with version 8.3.0-1.1 of the RISC-V embedded compiler. Newer versions may or may not work correctly.*
 
-Add the following to your `~/.profile`, adjusting for the actual `PATH` to the compilers:
+Add the following to your `~/.profile` (and on macOS, to `~/.zprofile`), adjusting for the actual `PATH` to the compilers:
 
 ```shell
 echo $PATH | grep -q -s "/usr/local/gcc-arm-none-eabi-9-2019-q4-major/bin"

README.pdf

@@ -6,8 +6,8 @@ COMMON_ARGS="--device $DEVICE --compact-data --mexpress --timer 0 --display-chec
 
 ./ai8xize.py --verbose --log --test-dir $TARGET --prefix mnist --checkpoint-file trained/ai85-mnist-qat8-q.pth.tar --config-file networks/mnist-chw-ai85.yaml --softmax $COMMON_ARGS "$@"
 ./ai8xize.py --verbose --log --test-dir $TARGET --prefix mnist-riscv --checkpoint-file trained/ai85-mnist-qat8-q.pth.tar --config-file networks/mnist-chw-ai85.yaml --softmax $COMMON_ARGS --riscv --riscv-debug "$@"
-./ai8xize.py --verbose --log --test-dir $TARGET --prefix cifar-10 --checkpoint-file trained/ai85-cifar10-qat8-q.pth.tar --config-file networks/cifar10-hwc-ai85.yaml --softmax $COMMON_ARGS "$@"
-./ai8xize.py --verbose --log --test-dir $TARGET --prefix cifar-100 --checkpoint-file trained/ai85-cifar100-qat8-q.pth.tar --config-file networks/cifar100-simple.yaml --softmax $COMMON_ARGS --boost 2.5 "$@"
+./ai8xize.py --verbose --log --test-dir $TARGET --prefix cifar-10 --checkpoint-file tests/ai85-cifar10-qat8-q.pth.tar --config-file networks/cifar10-hwc-ai85.yaml --softmax $COMMON_ARGS "$@"
+./ai8xize.py --verbose --log --test-dir $TARGET --prefix cifar-100 --checkpoint-file tests/ai85-cifar100-qat8-q.pth.tar --config-file networks/cifar100-simple.yaml --softmax $COMMON_ARGS --boost 2.5 "$@"
 ./ai8xize.py --verbose --log --test-dir $TARGET --prefix cifar-100-mixed --checkpoint-file trained/ai85-cifar100-qat-mixed-q.pth.tar --config-file networks/cifar100-simple.yaml --softmax $COMMON_ARGS --boost 2.5 "$@"
 ./ai8xize.py --verbose --log --test-dir $TARGET --prefix cifar-100-simplewide2x-mixed --checkpoint-file trained/ai85-cifar100-simplenetwide2x-qat-mixed-q.pth.tar --config-file networks/cifar100-simplewide2x.yaml --softmax $COMMON_ARGS --boost 2.5 "$@"
 ./ai8xize.py --verbose --log --test-dir $TARGET --prefix cifar-100-residual --checkpoint-file trained/ai85-cifar100-residual-qat8-q.pth.tar --config-file networks/cifar100-ressimplenet.yaml --softmax $COMMON_ARGS --boost 2.5 "$@"

rtldev/gen-regression-ai85.sh

@@ -155,7 +155,7 @@
 ./ai8xize.py --rtl"$PRELOAD" --verbose --autogen $TARGET --log --test-dir $TARGET --prefix $PREFIX-conv2Dk1x1 --config-file tests/test-conv2Dk1x1.yaml --device "$DEVICE" --no-wfi --debug "$@"
 ./ai8xize.py --rtl"$PRELOAD" --verbose --autogen $TARGET --log --test-dir $TARGET --prefix $PREFIX-conv2Dk1x1-b --config-file tests/test-conv2Dk1x1-b.yaml --device "$DEVICE" --debug "$@"
 ./ai8xize.py --rtl"$PRELOAD" --verbose --autogen $TARGET --log --test-dir $TARGET --prefix $PREFIX-conv2Dk1x1-b-pool --config-file tests/test-conv2Dk1x1-b-pool.yaml --device "$DEVICE" --debug "$@"
-./ai8xize.py --rtl"$PRELOAD" --verbose --autogen $TARGET --log --test-dir $TARGET --prefix $PREFIX-mlp12to2 --config-file tests/test-mlp12to2.yaml --device "$DEVICE" --debug "$@"
+./ai8xize.py --rtl"$PRELOAD" --verbose --autogen $TARGET --log --test-dir $TARGET --prefix $PREFIX-mlp12to2 --config-file tests/test-mlp12to2.yaml --no-wfi --device "$DEVICE" --debug "$@"
 ./ai8xize.py --rtl"$PRELOAD" --verbose --autogen $TARGET --log --test-dir $TARGET --prefix $PREFIX-mlpflatten12to2 --config-file tests/test-mlpflatten12to2.yaml --device "$DEVICE" --debug "$@"
 
 ./ai8xize.py --rtl"$PRELOAD" --verbose --autogen $TARGET --log --test-dir $TARGET --prefix $PREFIX-wide3to508to3 --config-file tests/test-wide3to508to3.yaml --device "$DEVICE" "$@"
@@ -426,7 +426,7 @@
 
 ./ai8xize.py --rtl"$PRELOAD" --verbose --autogen $TARGET --log --test-dir $TARGET --prefix $PREFIX-depthwise2d-k3 --config-file tests/test-depthwise2x2x2.yaml --no-wfi --stop-after 0 --device "$DEVICE" "$@"
 ./ai8xize.py --rtl"$PRELOAD" --verbose --autogen $TARGET --log --test-dir $TARGET --prefix $PREFIX-depthwise2d-k3 --config-file tests/test-depthwise3x4x4.yaml --no-wfi --stop-after 0 --device "$DEVICE" "$@"
-./ai8xize.py --rtl"$PRELOAD" --verbose --autogen $TARGET --log --test-dir $TARGET --prefix $PREFIX-depthwise2d-k1 --config-file tests/test-depthwise1x1.yaml --stop-after 0 --device "$DEVICE" "$@"
+./ai8xize.py --rtl"$PRELOAD" --verbose --autogen $TARGET --log --test-dir $TARGET --prefix $PREFIX-depthwise2d-k1 --config-file tests/test-depthwise1x1.yaml --stop-after 0 --no-wfi --device "$DEVICE" "$@"
 ./ai8xize.py --rtl"$PRELOAD" --verbose --autogen $TARGET --log --test-dir $TARGET --prefix $PREFIX-depthwise2d-k1-move --config-file tests/test-depthwise1x1-move.yaml --stop-after 0 --device "$DEVICE" "$@"
 ./ai8xize.py --rtl"$PRELOAD" --verbose --autogen $TARGET --log --test-dir $TARGET --prefix $PREFIX-depthwise1d-k3 --config-file tests/test-depthwise1d.yaml --stop-after 0 --no-wfi --device "$DEVICE" "$@"
 ./ai8xize.py --rtl"$PRELOAD" --verbose --autogen $TARGET --log --test-dir $TARGET --prefix $PREFIX-depthwise-transpose2d --config-file tests/test-depthwiset2d.yaml --stop-after 0 --device "$DEVICE" "$@"
@@ -621,3 +621,5 @@
 ./ai8xize.py --rtl"$PRELOAD" --verbose --autogen $TARGET --log --test-dir $TARGET --prefix $PREFIX-fastfifostream-x4-nopad-multipass5q2 --config-file tests/test-ffsx4-nopad-multipass5q2.yaml --fast-fifo --riscv --device "$DEVICE" "$@"
 ./ai8xize.py --rtl"$PRELOAD" --verbose --autogen $TARGET --log --test-dir $TARGET --prefix $PREFIX-fastfifostream-x4-readahead-nopad-multipass5-w8 --config-file tests/test-ffsx4readahead-nopad-multipass5-w8.yaml --fast-fifo --riscv --device "$DEVICE" --queue-name medium "$@"
 ./ai8xize.py --rtl"$PRELOAD" --verbose --autogen $TARGET --log --test-dir $TARGET --prefix $PREFIX-riscv-csv-fastfifostream-720p --config-file tests/test-fifostream-720p-hwc.yaml --device "$DEVICE" --fifo --riscv --fast-fifo --input-csv input.csv --queue-name long --timeout 8500 --input-csv-period 180 --input-sync $SHORT_LOG --debug-new-streaming "$@"
+
+./ai8xize.py --rtl"$PRELOAD" --verbose --autogen $TARGET --log --test-dir $TARGET --prefix $PREFIX-readahead-x4-power --config-file tests/test-power-ai87.yaml --device "$DEVICE" "$@"