Vortex 2.0 changes:

+ Microarchitecture optimizations
+ 64-bit support
+ Xilinx FPGA support
+ LLVM-16 support
+ Refactoring and quality control fixes

minor update

minor update

minor update

minor update

minor update

minor update

cleanup

cleanup

cache bindings and memory perf refactory

minor update

minor update

hw unit tests fixes

minor update

minor update

minor update

minor update

minor update

minor udpate

minor update

minor update

minor update

minor update

minor update

minor update

minor update

minor updates

minor updates

minor update

minor update

minor update

minor update

minor update

minor update

minor updates

minor updates

minor updates

minor updates

minor update

minor update

perf/.gitignore

@@ -0,0 +1 @@
+**/*.log

perf/cache/cache_perf.log

@@ -0,0 +1,3 @@
+CONFIGS=-DNUM_CLUSTERS=1 -DNUM_CORES=1 -DNUM_WARPS=2 -DNUM_THREADS=2   -DPERF_ENABLE -DICACHE_NUM_WAYS=1
+running: CONFIGS=-DNUM_CLUSTERS=1 -DNUM_CORES=1 -DNUM_WARPS=2 -DNUM_THREADS=2 -DPERF_ENABLE -DICACHE_NUM_WAYS=1 make -C ./ci/../driver/rtlsim
+verilator --build --exe --cc Vortex --top-module Vortex --language 1800-2009 --assert -Wall -Wpedantic -Wno-DECLFILENAME -Wno-REDEFMACRO --x-initial unique --x-assign unique verilator.vlt -I../../hw/rtl -I../../hw/dpi -I../../hw/rtl/libs -I../../hw/rtl/interfaces -I../../hw/rtl/cache -I../../hw/rtl/simulate -I../../hw/rtl/fp_cores -I../../third_party/fpnew/src/common_cells/include -I../../third_party/fpnew/src/common_cells/src -I../../third_party/fpnew/src/fpu_div_sqrt_mvp/hdl -I../../third_party/fpnew/src -I../../hw/rtl/tex_unit -I../../hw/rtl/raster_unit -I../../hw/rtl/rop_unit -DNUM_CLUSTERS=1 -DNUM_CORES=1 -DNUM_WARPS=2 -DNUM_THREADS=2   -DPERF_ENABLE -DICACHE_NUM_WAYS=1 -j 64 -DNDEBUG -DIMUL_DPI -DIDIV_DPI -DFPU_DPI ../common/util.cpp ../common/mem.cpp ../common/rvfloats.cpp ../../hw/dpi/util_dpi.cpp ../../hw/dpi/float_dpi.cpp processor.cpp -CFLAGS '-std=c++11 -Wall -Wextra -Wfatal-errors -Wno-array-bounds -fPIC -Wno-maybe-uninitialized -I../../../hw -I../../common -I../../../third_party/softfloat/source/include -I../../../third_party -DNUM_CLUSTERS=1 -DNUM_CORES=1 -DNUM_WARPS=2 -DNUM_THREADS=2   -DPERF_ENABLE -DICACHE_NUM_WAYS=1 -O2 -DNDEBUG' -LDFLAGS '-shared ../../../third_party/softfloat/build/Linux-x86_64-GCC/softfloat.a -L../../../third_party/ramulator -lramulator' -o ../../../driver/rtlsim/librtlsim.so

perf/cache/run.sh

@@ -0,0 +1,41 @@
+#!/bin/bash
+
+# exit when any command fails
+set -e
+
+# ensure build
+make -s
+
+sgemm()
+{
+echo "begin cache tests"
+
+CONFIGS="-DICACHE_NUM_WAYS=2" ./ci/blackbox.sh --driver=rtlsim --app=sgemm --args="-n64" --perf=1 | grep 'PERF' > ./perf/cache/cache_perf.log
+echo -e "\n**************************************\n" >> ./perf/cache/cache_perf.log
+CONFIGS="-DDCACHE_NUM_WAYS=2" ./ci/blackbox.sh --driver=rtlsim --app=sgemm --args="-n64" --perf=1 | grep 'PERF' >> ./perf/cache/cache_perf.log
+echo -e "\n**************************************\n" >> ./perf/cache/cache_perf.log 
+CONFIGS="-DICACHE_NUM_WAYS=4" ./ci/blackbox.sh --driver=rtlsim --app=sgemm --args="-n64" --perf=1 | grep 'PERF' >> ./perf/cache/cache_perf.log
+echo -e "\n**************************************\n" >> ./perf/cache/cache_perf.log
+CONFIGS="-DDCACHE_NUM_WAYS=4" ./ci/blackbox.sh --driver=rtlsim --app=sgemm --args="-n64" --perf=1 | grep 'PERF' >> ./perf/cache/cache_perf.log
+echo -e "\n**************************************\n" >> ./perf/cache/cache_perf.log
+CONFIGS="-DICACHE_NUM_WAYS=8" ./ci/blackbox.sh --driver=rtlsim --app=sgemm --args="-n64" --perf=1 | grep 'PERF' >> ./perf/cache/cache_perf.log
+echo -e "\n**************************************\n" >> ./perf/cache/cache_perf.log
+CONFIGS="-DDCACHE_NUM_WAYS=8" ./ci/blackbox.sh --driver=rtlsim --app=sgemm --args="-n64" --perf=1 | grep 'PERF' >> ./perf/cache/cache_perf.log
+
+echo "cache tests done!"
+}
+
+usage()
+{
+    echo "usage: [-s] [-h|--help]"
+}
+
+case $1 in
+    -s ) sgemm
+            ;;
+    -h | --help ) usage
+                    ;;
+    * ) sgemm
+        ;;             
+esac
+shift