sw: Restructuring of BLAS and DNN kernels

.clang-format-ignore

@@ -2,5 +2,4 @@
 # Licensed under the Apache License, Version 2.0, see LICENSE for details.
 # SPDX-License-Identifier: Apache-2.0
 
-# Ignore vendored third-party code
-./sw/math/*
+./sw/saris

.github/workflows/lint.yml

@@ -78,13 +78,6 @@ jobs:
           match_regex: true
           exclude_paths: |
             sw/snRuntime/src/omp/interface.h
-            sw/math/arch/generic/*
-            sw/math/arch/riscv64/bits/*
-            sw/math/include/*
-            sw/math/src/include/*
-            sw/math/src/internal/*
-            sw/math/src/math/*
-            sw/math/Makefile
 
   ##################
   # Lint YML Files #
@@ -129,7 +122,6 @@ jobs:
       - uses: actions/checkout@v3
       - uses: DoozyX/[email protected]
         with:
-          exclude: './sw/saris'
           clangFormatVersion: 10
 
   ######################

.gitlab-ci.yml

@@ -34,7 +34,6 @@ snitch-cluster-sw:
     - make sw
   artifacts:
     paths:
-      - sw/math/include/bits/alltypes.h
       - target/snitch_cluster/sw/**/build/*.elf
     expire_in: 1 day
 
@@ -44,7 +43,6 @@ snitch-cluster-sw-banshee:
     - make SELECT_RUNTIME=banshee sw
   artifacts:
     paths:
-      - sw/math/include/bits/alltypes.h
       - target/snitch_cluster/sw/**/build/*.elf
     expire_in: 1 day
 
@@ -103,8 +101,8 @@ snitch-cluster-vsim:
     # Test trace annotation
     - make SIM_DIR=./runs/vsim/simple annotate -j
     # Run additional, more extensive tests
-    - cd sw/apps/blas/gemm/test
-    - ./run.py runs.yaml --cfg $PWD/cfg/* --simulator vsim -j
+    - cd sw/apps/blas/gemm/test && ./test.sh && cd -
+    - cd sw/apps/dnn/transpose/test && ./test.sh && cd -
 
 # Banshee
 snitch-cluster-banshee:
@@ -129,6 +127,8 @@ snitch-cluster-fdiv-vsim:
     - make CFG_OVERRIDE=cfg/fdiv.hjson sw
     - make bin/snitch_cluster.vsim
     - ./util/run.py sw/fdiv.yaml --simulator vsim -j --run-dir runs/vsim
+    # Run additional, more extensive tests
+    - cd sw/apps/dnn/flashattention_2/test && ./test.sh && cd -
 
 # Test OmegaNet TCDM interconnect
 snitch-cluster-omega-vsim:

docs/rm/snitch_target_utils/build.md

@@ -0,0 +1 @@
+::: build

docs/rm/snitch_target_utils/run.md

@@ -0,0 +1 @@
+::: run

iis-setup.sh

@@ -4,7 +4,6 @@
 # SPDX-License-Identifier: Apache-2.0
 
 # Define environment variables
-export PYTHON=/usr/local/anaconda3-2022.05/bin/python3
 export BENDER=bender-0.27.1
 export CC=gcc-9.2.0
 export CXX=g++-9.2.0
@@ -14,7 +13,7 @@ export QUESTA_SEPP=questa-2022.3
 export LLVM_BINROOT=/usr/pack/riscv-1.0-kgf/pulp-llvm-0.12.0/bin
 
 # Create Python virtual environment with required packages
-$PYTHON -m venv .venv
+/usr/local/anaconda3-2022.05/bin/python3 -m venv .venv
 source .venv/bin/activate
 # Unpack packages in a local temporary directory which can be safely cleaned
 # after installation. Also protects against "No space left on device" errors

mkdocs.yml

@@ -25,7 +25,9 @@ plugins:
   - mkdocstrings:
       handlers:
         python:
-          paths: [util/sim]
+          paths:
+            - util/sim
+            - target/snitch_cluster/util
   - macros:
       on_error_fail: true
 use_directory_urls: false
@@ -62,6 +64,9 @@ nav:
               - rm/sim/Simulation.md
               - rm/sim/Simulator.md
               - rm/sim/Elf.md
+          - Snitch Target Utilities:
+              - run.py: rm/snitch_target_utils/run.md
+              - build.py: rm/snitch_target_utils/build.md
           - Snitch Runtime:
               - Pages: runtime/Pages/index.md
               - Files: runtime/Files/index.md

sw/README.md

@@ -11,19 +11,6 @@ This subdirectory contains the various bits and pieces of software for the Snitc
 - `snRuntime`: The fundamental, bare-metal runtime for Snitch systems. Exposes a minimal API to manage execution of code across the available cores and clusters, query information about a thread's context, and to coordinate and exchange data with other threads. Hardware configuration dependent implementations of the `snRuntime` can be found, e.g., under `target/snitch_cluster/sw/snRuntime`.
 - `snBLAS`: A minimal reference implementation of the basic linear algebra subprograms that demonstrates the use of Snitch and its extensions.
 
-#### math
-
-The math sources are taken from the musl library, patched with our own modifications. The bender vendor snippet in `Bender.yml` was used to copy in the original sources. Patches were generated using the following command (from the root of the repo):
-```
-git format-patch --relative -o sw/deps/patches/musl/ HEAD^1
-```
-And can be applied by running (in the root of the repo):
-```
-git apply sw/deps/patches/musl/0001-musl-Patch-to-build-math-library-for-Snitch.patch
-```
-
-The `all` target in `sw/math/Makefile` should be run to generate some files.
-
 ### Tests
 
 - `benchmark`: Benchmarking executables that evaluate the performance characteristics of a system.

sw/apps/atax/Makefile

@@ -20,7 +20,7 @@ DATAGEN_PY = $(MK_DIR)/scripts/datagen.py
 DATA_H     = $(DATA_DIR)/data.h
 
 $(DATA_H): $(DATAGEN_PY) $(DATA_CFG)
-	$< -c $(DATA_CFG) --section="$(SECTION)" > $@
+	$< -c $(DATA_CFG) --section="$(SECTION)" $@
 
 .PHONY: clean-data clean
 

sw/apps/correlation/Makefile

@@ -20,7 +20,7 @@ DATAGEN_PY = $(MK_DIR)/scripts/datagen.py
 DATA_H     = $(DATA_DIR)/data.h
 
 $(DATA_H): $(DATAGEN_PY) $(DATA_CFG)
-	$< -c $(DATA_CFG) --section="$(SECTION)" > $@
+	$< -c $(DATA_CFG) --section="$(SECTION)" $@
 
 .PHONY: clean-data clean
 

sw/apps/covariance/Makefile

@@ -20,7 +20,7 @@ DATAGEN_PY = $(MK_DIR)/scripts/datagen.py
 DATA_H     = $(DATA_DIR)/data.h
 
 $(DATA_H): $(DATAGEN_PY) $(DATA_CFG)
-	$< -c $(DATA_CFG) --section="$(SECTION)" > $@
+	$< -c $(DATA_CFG) --section="$(SECTION)" $@
 
 .PHONY: clean-data clean
 

sw/blas/axpy/Makefile

@@ -23,7 +23,7 @@ $(dir $(DATA_H)):
 	mkdir -p $@
 
 $(DATA_H): $(DATAGEN_PY) $(DATA_CFG) | $(dir $(DATA_H))
-	$< -c $(DATA_CFG) --section="$(SECTION)" > $@
+	$< -c $(DATA_CFG) --section="$(SECTION)" $@
 
 .PHONY: clean-data clean
 

sw/blas/dot/Makefile

@@ -21,7 +21,7 @@ $(dir $(DATA_H)):
 	mkdir -p $@
 
 $(DATA_H): $(DATAGEN_PY) $(DATA_CFG) | $(dir $(DATA_H))
-	$< -c $(DATA_CFG) --section="$(SECTION)" > $@
+	$< -c $(DATA_CFG) --section="$(SECTION)" $@
 
 .PHONY: clean-data clean
 

sw/blas/gemm/Makefile

@@ -23,7 +23,7 @@ $(dir $(DATA_H)):
 	mkdir -p $@
 
 $(DATA_H): $(DATAGEN_PY) $(DATA_CFG) | $(dir $(DATA_H))
-	$< -c $(DATA_CFG) --section="$(SECTION)" > $@
+	$< -c $(DATA_CFG) --section="$(SECTION)" $@
 
 .PHONY: clean-data clean
 

sw/blas/gemm/__init__.py

@@ -0,0 +1,9 @@
+# Copyright 2024 ETH Zurich and University of Bologna.
+# Licensed under the Apache License, Version 2.0, see LICENSE for details.
+# SPDX-License-Identifier: Apache-2.0
+#
+# Luca Colagrande <[email protected]>
+
+from .scripts import datagen
+
+__all__ = ['datagen']

sw/blas/gemm/data/params.json

@@ -1,22 +1,23 @@
-// Copyright 2023 ETH Zurich and University of Bologna.
-// Solderpad Hardware License, Version 0.51, see LICENSE for details.
-// SPDX-License-Identifier: SHL-0.51
-
-// Parameters for a GEMM
+// Copyright 2024 ETH Zurich and University of Bologna.
+// Licensed under the Apache License, Version 2.0, see LICENSE for details.
+// SPDX-License-Identifier: Apache-2.0
 
 {
-    M: 192,
+    setup_ssr: 1,
+    parallelize_m: 0,
+    parallelize_k: 0,
+    m_tiles: 2, // number of tiles in M dimension
+    n_tiles: 1, // number of tiles in N dimension
+    k_tiles: 1, // number of tiles in K dimension
+    load_a: 1,
+    load_b: 1,
+    load_c: 1,
+    transa: false,
+    transb: true, // must be true for SIMD
+    M: 16,
     N: 16,
     K: 16,
+    alpha: 1,
     beta: 0,
-    ta: false,
-    tb: true, // must be true for SIMD
-    prec: "FP64",
-    expand: 0,
-    m_tiles: 2, // number of tiles in M dimension
-    k_tiles: 1, // number of tiles in K dimension
-    n_tiles: 1, // number of tiles in N dimension
-    parallelize_k: 0,
-    parallelize_m: 0,
-    baseline: false
+    gemm_fp: "gemm_fp32_opt"
 }