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

tests/opencl/vecadd/Makefile

@@ -1,71 +1,7 @@
-XLEN ?= 32
-
-LLVM_PREFIX ?= /opt/llvm-riscv
-RISCV_TOOLCHAIN_PATH ?= /opt/riscv-gnu-toolchain
-SYSROOT ?= $(RISCV_TOOLCHAIN_PATH)/riscv32-unknown-elf
-POCL_CC_PATH ?= /opt/pocl/compiler
-POCL_RT_PATH ?= /opt/pocl/runtime
-
-OPTS ?= -n64
-
-VORTEX_DRV_PATH ?= $(realpath ../../../driver)
-VORTEX_RT_PATH ?= $(realpath ../../../runtime)
-
-K_LLCFLAGS += "-O3 -march=riscv32 -target-abi=ilp32f -mcpu=generic-rv32 -mattr=+m,+f -mattr=+vortex -float-abi=hard -code-model=small"
-K_CFLAGS   += "-v -O3 --sysroot=$(SYSROOT) --gcc-toolchain=$(RISCV_TOOLCHAIN_PATH) -march=rv32imf -mabi=ilp32f -Xclang -target-feature -Xclang +vortex -I$(VORTEX_RT_PATH)/include -fno-rtti -fno-exceptions -ffreestanding -nostartfiles -fdata-sections -ffunction-sections"
-K_LDFLAGS  += "-Wl,-Bstatic,-T$(VORTEX_RT_PATH)/linker/vx_link$(XLEN).ld -Wl,--gc-sections $(VORTEX_RT_PATH)/libvortexrt.a -lm"
-
-CXXFLAGS += -std=c++11 -Wall -Wextra -Wfatal-errors
-
-CXXFLAGS += -Wno-deprecated-declarations -Wno-unused-parameter -Wno-narrowing
-
-CXXFLAGS += -I$(POCL_RT_PATH)/include
-
-LDFLAGS += -L$(POCL_RT_PATH)/lib -L$(VORTEX_DRV_PATH)/stub -lOpenCL -lvortex
-
-# Debugigng
-ifdef DEBUG
-	CXXFLAGS += -g -O0
-else    
-	CXXFLAGS += -O2 -DNDEBUG
-endif
-
 PROJECT = vecadd
 
 SRCS = main.cc
 
-all: $(PROJECT) kernel.pocl
+OPTS ?= -n64
 
-kernel.pocl: kernel.cl
-	LLVM_PREFIX=$(LLVM_PREFIX) POCL_DEBUG=all LD_LIBRARY_PATH=$(LLVM_PREFIX)/lib:$(POCL_CC_PATH)/lib $(POCL_CC_PATH)/bin/poclcc -LLCFLAGS $(K_LLCFLAGS) -CFLAGS $(K_CFLAGS) -LDFLAGS $(K_LDFLAGS) -o kernel.pocl kernel.cl
- 
-$(PROJECT): $(SRCS)
-	$(CXX) $(CXXFLAGS) $^ $(LDFLAGS) -o $@
-
-run-fpga: $(PROJECT) kernel.pocl   
-	LD_LIBRARY_PATH=$(POCL_RT_PATH)/lib:$(VORTEX_DRV_PATH)/fpga:$(LD_LIBRARY_PATH) ./$(PROJECT) $(OPTS)
-
-run-asesim: $(PROJECT) kernel.pocl   
-	LD_LIBRARY_PATH=$(POCL_RT_PATH)/lib:$(VORTEX_DRV_PATH)/asesim:$(LD_LIBRARY_PATH) ./$(PROJECT) $(OPTS)
-	
-run-vlsim: $(PROJECT) kernel.pocl   
-	LD_LIBRARY_PATH=$(POCL_RT_PATH)/lib:$(VORTEX_DRV_PATH)/vlsim:$(LD_LIBRARY_PATH) ./$(PROJECT) $(OPTS)
-
-run-simx: $(PROJECT) kernel.pocl   
-	LD_LIBRARY_PATH=$(POCL_RT_PATH)/lib:$(VORTEX_DRV_PATH)/simx:$(LD_LIBRARY_PATH) ./$(PROJECT) $(OPTS)
-
-run-rtlsim: $(PROJECT) kernel.pocl   
-	LD_LIBRARY_PATH=$(POCL_RT_PATH)/lib:$(VORTEX_DRV_PATH)/rtlsim:$(LD_LIBRARY_PATH) ./$(PROJECT) $(OPTS)
-
-.depend: $(SRCS)
-	$(CXX) $(CXXFLAGS) -MM $^ > .depend;
-
-clean:
-	rm -rf $(PROJECT) *.o .depend 
-
-clean-all: clean
-	rm -rf *.pocl *.dump
-
-ifneq ($(MAKECMDGOALS),clean)
-    -include .depend
-endif
+include ../common.mk

tests/opencl/vecadd/main.cc

@@ -142,8 +142,9 @@ int main (int argc, char **argv) {
   c_memobj = CL_CHECK2(clCreateBuffer(context, CL_MEM_WRITE_ONLY, nbytes, NULL, &_err));
 
   printf("Create program from kernel source\n");
-  program = CL_CHECK2(clCreateProgramWithBinary(
-    context, 1, &device_id, &kernel_size, (const uint8_t**)&kernel_bin, &binary_status, &_err));
+  cl_int _err;
+  program = clCreateProgramWithBinary(
+    context, 1, &device_id, &kernel_size, (const uint8_t**)&kernel_bin, &binary_status, &_err);
   if (program == NULL) {
     cleanup();
     return -1;
@@ -182,9 +183,8 @@ int main (int argc, char **argv) {
 
   printf("Execute the kernel\n");
   size_t global_work_size[1] = {size};
-  size_t local_work_size[1] = {1};
   auto time_start = std::chrono::high_resolution_clock::now();
-  CL_CHECK(clEnqueueNDRangeKernel(commandQueue, kernel, 1, NULL, global_work_size, local_work_size, 0, NULL, NULL));
+  CL_CHECK(clEnqueueNDRangeKernel(commandQueue, kernel, 1, NULL, global_work_size, NULL, 0, NULL, NULL));
   CL_CHECK(clFinish(commandQueue));
   auto time_end = std::chrono::high_resolution_clock::now();
   double elapsed = std::chrono::duration_cast<std::chrono::milliseconds>(time_end - time_start).count();