Update the Makefile of project

Makefile

@@ -2,7 +2,7 @@
 # Builds all available modules and examples
 
 # Default target
-.PHONY: all clean test help module1 module2 module3 module4 module5 module6 module7 module8 module9
+.PHONY: all clean test debug profile help module1 module2 module3 module4 module5 module6 module7 module8 module9
 
 # Build all available modules
 all: module1 module2 module3 module4 module5 module6 module7 module8 module9
@@ -83,6 +83,84 @@ test-module9:
 	@echo "Testing Module 9..."
 	@$(MAKE) -C modules/module9/examples test
 
+# Debug builds for all modules
+debug: debug-module1 debug-module2 debug-module3 debug-module4 debug-module5 debug-module6 debug-module7 debug-module8 debug-module9
+
+debug-module1:
+	@echo "Debug build Module 1..."
+	@$(MAKE) -C modules/module1/examples debug
+
+debug-module2:
+	@echo "Debug build Module 2..."
+	@$(MAKE) -C modules/module2/examples debug
+
+debug-module3:
+	@echo "Debug build Module 3..."
+	@$(MAKE) -C modules/module3/examples debug
+
+debug-module4:
+	@echo "Debug build Module 4..."
+	@$(MAKE) -C modules/module4/examples debug
+
+debug-module5:
+	@echo "Debug build Module 5..."
+	@$(MAKE) -C modules/module5/examples debug
+
+debug-module6:
+	@echo "Debug build Module 6..."
+	@$(MAKE) -C modules/module6/examples debug
+
+debug-module7:
+	@echo "Debug build Module 7..."
+	@$(MAKE) -C modules/module7/examples debug
+
+debug-module8:
+	@echo "Debug build Module 8..."
+	@$(MAKE) -C modules/module8/examples debug
+
+debug-module9:
+	@echo "Debug build Module 9..."
+	@$(MAKE) -C modules/module9/examples debug
+
+# Profile builds for all modules  
+profile: profile-module1 profile-module2 profile-module3 profile-module4 profile-module5 profile-module6 profile-module7 profile-module8 profile-module9
+
+profile-module1:
+	@echo "Profile build Module 1..."
+	@$(MAKE) -C modules/module1/examples profile
+
+profile-module2:
+	@echo "Profile build Module 2..."
+	@$(MAKE) -C modules/module2/examples profile
+
+profile-module3:
+	@echo "Profile build Module 3..."
+	@$(MAKE) -C modules/module3/examples profile
+
+profile-module4:
+	@echo "Profile build Module 4..."
+	@$(MAKE) -C modules/module4/examples profile
+
+profile-module5:
+	@echo "Profile build Module 5..."
+	@$(MAKE) -C modules/module5/examples profile
+
+profile-module6:
+	@echo "Profile build Module 6..."
+	@$(MAKE) -C modules/module6/examples profile
+
+profile-module7:
+	@echo "Profile build Module 7..."
+	@$(MAKE) -C modules/module7/examples profile
+
+profile-module8:
+	@echo "Profile build Module 8..."
+	@$(MAKE) -C modules/module8/examples profile
+
+profile-module9:
+	@echo "Profile build Module 9..."
+	@$(MAKE) -C modules/module9/examples profile
+
 # Clean all builds
 clean:
 	@echo "Cleaning all modules..."
@@ -193,6 +271,8 @@ help:
 	@echo "  all          - Build all available modules"
 	@echo "  clean        - Clean all build artifacts"
 	@echo "  test         - Run all available tests"
+	@echo "  debug        - Build all modules with debug flags"
+	@echo "  profile      - Build all modules with profiling flags"
 	@echo "  help         - Show this help message"
 	@echo ""
 	@echo "Module targets:"

modules/module1/examples/Makefile

@@ -185,12 +185,52 @@ debug: CUDA_FLAGS = $(CUDA_DEBUG_FLAGS)
 debug: HIP_FLAGS = $(HIP_DEBUG_FLAGS)
 debug: all
 
+# Profile builds with actual profiling
+.PHONY: profile
+profile: CUDA_FLAGS += -lineinfo
+profile: HIP_FLAGS += -g
+profile: all
+	@echo "Generating profile data..."
+	@mkdir -p $(PROFILE_DIR)
+ifeq ($(BUILD_HIP),1)
+	@echo "Running HIP profiling..."
+	@for target in $(HIP_TARGETS); do \
+		if [ -f $$target ]; then \
+			echo "Profiling $$target..."; \
+			rocprofv3 --runtime-trace --output-format csv -d $(PROFILE_DIR) -o $$(basename $$target).csv -- $$target 2>/dev/null || echo "rocprofv3 completed"; \
+		fi; \
+	done
+endif
+ifeq ($(BUILD_CUDA),1)
+	@echo "Running CUDA profiling..."
+	@for target in $(CUDA_TARGETS); do \
+		if [ -f $$target ]; then \
+			echo "Profiling $$target..."; \
+			nvprof --csv -o $(PROFILE_DIR)/$$(basename $$target).csv $$target 2>/dev/null || echo "nvprof completed"; \
+		fi; \
+	done
+endif
+	@echo "Profile data saved to $(PROFILE_DIR)/"
+	@ls -la $(PROFILE_DIR)/
+
 # Clean
 .PHONY: clean
 clean:
 	@echo "Cleaning build artifacts..."
 	rm -rf $(BUILD_DIR) $(PROFILE_DIR)
 
+# Test target - run built examples
+.PHONY: test
+test: all
+	@echo "Running Module 1 Tests..."
+	@for target in $(ALL_TARGETS); do \
+		if [ -f $$target ]; then \
+			echo "Testing $$target..."; \
+			$$target || echo "Test completed with exit code $$?"; \
+			echo ""; \
+		fi; \
+	done
+
 # Help
 .PHONY: help
 help:
@@ -200,5 +240,7 @@ help:
 	@echo "  cuda    - Build CUDA examples (requires NVIDIA GPU)"
 	@echo "  hip     - Build HIP examples (requires AMD GPU)"
 	@echo "  debug   - Build with debug flags"
+	@echo "  profile - Build with profiling flags"
+	@echo "  test    - Run all built examples"
 	@echo "  clean   - Remove build artifacts"
 	@echo "  help    - Show this help message"

modules/module2/examples/Makefile

@@ -138,6 +138,34 @@ debug: CUDA_FLAGS = $(CUDA_DEBUG_FLAGS)
 debug: HIP_FLAGS = $(HIP_DEBUG_FLAGS)
 debug: all
 
+# Profile builds
+.PHONY: profile
+profile: CUDA_FLAGS += -lineinfo
+profile: HIP_FLAGS += -g
+profile: all
+	@echo "Generating profile data..."
+	@mkdir -p $(PROFILE_DIR)
+ifeq ($(BUILD_HIP),1)
+	@echo "Running HIP profiling..."
+	@for target in $(HIP_TARGETS); do \
+		if [ -f $$target ]; then \
+			echo "Profiling $$target..."; \
+			rocprofv3 --runtime-trace --output-format csv -d $(PROFILE_DIR) -o $$(basename $$target).csv -- $$target 2>/dev/null || echo "rocprofv3 completed"; \
+		fi; \
+	done
+endif
+ifeq ($(BUILD_CUDA),1)
+	@echo "Running CUDA profiling..."
+	@for target in $(CUDA_TARGETS); do \
+		if [ -f $$target ]; then \
+			echo "Profiling $$target..."; \
+			nvprof --csv -o $(PROFILE_DIR)/$$(basename $$target).csv $$target 2>/dev/null || echo "nvprof completed"; \
+		fi; \
+	done
+endif
+	@echo "Profile data saved to $(PROFILE_DIR)/"
+	@ls -la $(PROFILE_DIR)/
+
 # Clean
 .PHONY: clean
 clean:
@@ -174,15 +202,15 @@ test_cuda: cuda
 	@if command -v nvidia-smi > /dev/null; then \
 		echo "=== Testing Advanced Memory Management Examples ==="; \
 		echo "1. Shared Memory Transpose..."; \
-		./01_shared_memory_transpose_cuda || echo "✗ Shared memory transpose failed"; \
+		$(BUILD_DIR)/01_shared_memory_transpose_cuda || echo "✗ Shared memory transpose failed"; \
 		echo "2. Memory Coalescing Analysis..."; \
-		./02_memory_coalescing_cuda || echo "✗ Memory coalescing failed"; \
+		$(BUILD_DIR)/02_memory_coalescing_cuda || echo "✗ Memory coalescing failed"; \
 		echo "3. Texture Memory Examples..."; \
-		./03_texture_memory_cuda || echo "✗ Texture memory failed"; \
+		$(BUILD_DIR)/03_texture_memory_cuda || echo "✗ Texture memory failed"; \
 		echo "4. Unified Memory Examples..."; \
-		./04_unified_memory_cuda || echo "✗ Unified memory failed"; \
+		$(BUILD_DIR)/04_unified_memory_cuda || echo "✗ Unified memory failed"; \
 		echo "5. Bandwidth Optimization..."; \
-		./05_memory_bandwidth_optimization_cuda || echo "✗ Bandwidth optimization failed"; \
+		$(BUILD_DIR)/05_memory_bandwidth_optimization_cuda || echo "✗ Bandwidth optimization failed"; \
 		echo "✓ Module 2 CUDA tests completed"; \
 	else \
 		echo "No NVIDIA GPU detected, skipping CUDA tests"; \
@@ -193,9 +221,9 @@ test_hip: hip
 	@if command -v rocm-smi > /dev/null || command -v nvidia-smi > /dev/null; then \
 		echo "=== Testing HIP Memory Examples ==="; \
 		echo "1. Shared Memory Transpose..."; \
-		./01_shared_memory_transpose_hip || echo "✗ HIP shared memory transpose failed"; \
+		$(BUILD_DIR)/01_shared_memory_transpose_hip || echo "✗ HIP shared memory transpose failed"; \
 		echo "2. Memory Coalescing Analysis..."; \
-		./02_memory_coalescing_hip || echo "✗ HIP memory coalescing failed"; \
+		$(BUILD_DIR)/02_memory_coalescing_hip || echo "✗ HIP memory coalescing failed"; \
 		echo "✓ Module 2 HIP tests completed"; \
 	else \
 		echo "No compatible GPU detected, skipping HIP tests"; \

modules/module3/examples/Makefile

@@ -54,6 +54,11 @@ endif
 # Add detected GPU architecture to HIP flags
 HIP_FLAGS += --offload-arch=$(GPU_ARCH)
 HIP_DEBUG_FLAGS += --offload-arch=$(GPU_ARCH)
+
+# ROCm library linking for advanced examples
+HIP_LIB_DIR := $(ROCM_PATH)/lib
+HIP_LDFLAGS := -L$(HIP_LIB_DIR) -lrocblas -Wl,-rpath,$(HIP_LIB_DIR)
+
 CXX_FLAGS = -std=c++17 -O2
 
 # Directories
@@ -129,7 +134,7 @@ endif
 ifeq ($(BUILD_HIP),1)
 $(BUILD_DIR)/%_hip: $(EXAMPLES_DIR)/%_hip.cpp
 	@echo "Building HIP example: $@"
-	$(HIPCC) $(HIP_FLAGS) $< -o $@
+	$(HIPCC) $(HIP_FLAGS) $< -o $@ $(HIP_LDFLAGS)
 endif
 
 # Debug builds
@@ -138,6 +143,32 @@ debug: CUDA_FLAGS = $(CUDA_DEBUG_FLAGS)
 debug: HIP_FLAGS = $(HIP_DEBUG_FLAGS)
 debug: all
 
+# Profile builds
+.PHONY: profile
+profile: CUDA_FLAGS += -lineinfo
+profile: HIP_FLAGS += -g
+profile: all
+	@echo "Generating profile data..."
+	@mkdir -p $(PROFILE_DIR)
+ifeq ($(BUILD_HIP),1)
+	@echo "Running HIP profiling..."
+	@for target in $(HIP_TARGETS); do \
+		if [ -f $$target ]; then \
+			echo "Profiling $$target..."; \
+			rocprofv3 --runtime-trace --output-format csv -d $(PROFILE_DIR) -o $$(basename $$target).csv -- $$target 2>/dev/null || echo "rocprofv3 completed"; \
+		fi; \
+	done
+endif
+ifeq ($(BUILD_CUDA),1)
+	@echo "Running CUDA profiling..."
+	@for target in $(CUDA_TARGETS); do \
+		if [ -f $$target ]; then \
+			echo "Profiling $$target..."; \
+			nvprof --csv -o $(PROFILE_DIR)/$$(basename $$target).csv $$target 2>/dev/null || echo "nvprof completed"; \
+		fi; \
+	done
+endif
+
 # Clean\n.PHONY: clean\nclean:\n\t@echo \"Cleaning build artifacts...\"\n\trm -rf $(BUILD_DIR) $(PROFILE_DIR)
 
 # Help
@@ -172,19 +203,19 @@ test_cuda: cuda
 	@if command -v nvidia-smi > /dev/null; then \
 		echo "=== Testing Advanced Algorithm Examples ==="; \
 		echo "1. Reduction Algorithms..."; \
-		./01_reduction_algorithms_cuda || echo "✗ Reduction algorithms failed"; \
+		$(BUILD_DIR)/01_reduction_algorithms_cuda || echo "✗ Reduction algorithms failed"; \
 		echo "2. Scan (Prefix Sum)..."; \
-		./02_scan_prefix_sum_cuda || echo "✗ Scan algorithms failed"; \
+		$(BUILD_DIR)/02_scan_prefix_sum_cuda || echo "✗ Scan algorithms failed"; \
 		echo "3. Sorting Algorithms..."; \
-		./03_sorting_algorithms_cuda || echo "✗ Sorting algorithms failed"; \
+		$(BUILD_DIR)/03_sorting_algorithms_cuda || echo "✗ Sorting algorithms failed"; \
 		echo "4. Convolution/Stencil..."; \
-		./04_convolution_stencil_cuda || echo "✗ Convolution failed"; \
+		$(BUILD_DIR)/04_convolution_stencil_cuda || echo "✗ Convolution failed"; \
 		echo "5. Matrix Operations..."; \
-		./05_matrix_operations_cuda || echo "✗ Matrix operations failed"; \
+		$(BUILD_DIR)/05_matrix_operations_cuda || echo "✗ Matrix operations failed"; \
 		echo "6. Graph Algorithms..."; \
-		./06_graph_algorithms_cuda || echo "✗ Graph algorithms failed"; \
+		$(BUILD_DIR)/06_graph_algorithms_cuda || echo "✗ Graph algorithms failed"; \
 		echo "7. Cooperative Groups..."; \
-		./07_cooperative_groups_cuda || echo "✗ Cooperative groups failed"; \
+		$(BUILD_DIR)/07_cooperative_groups_cuda || echo "✗ Cooperative groups failed"; \
 		echo "✓ Module 3 CUDA tests completed"; \
 	else \
 		echo "No NVIDIA GPU detected, skipping CUDA tests"; \
@@ -195,13 +226,13 @@ test_hip: hip
 	@if command -v rocm-smi > /dev/null || command -v nvidia-smi > /dev/null; then \
 		echo "=== Testing HIP Algorithm Examples ==="; \
 		echo "1. Reduction Algorithms..."; \
-		./01_reduction_algorithms_hip || echo "✗ HIP reduction algorithms failed"; \
+		$(BUILD_DIR)/01_reduction_algorithms_hip || echo "✗ HIP reduction algorithms failed"; \
 		echo "2. Scan (Prefix Sum)..."; \
-		./02_scan_prefix_sum_hip || echo "✗ HIP scan algorithms failed"; \
+		$(BUILD_DIR)/02_scan_prefix_sum_hip || echo "✗ HIP scan algorithms failed"; \
 		echo "3. Sorting Algorithms..."; \
-		./03_sorting_algorithms_hip || echo "✗ HIP sorting algorithms failed"; \
+		$(BUILD_DIR)/03_sorting_algorithms_hip || echo "✗ HIP sorting algorithms failed"; \
 		echo "4. Convolution/Stencil..."; \
-		./04_convolution_stencil_hip || echo "✗ HIP convolution failed"; \
+		$(BUILD_DIR)/04_convolution_stencil_hip || echo "✗ HIP convolution failed"; \
 		echo "✓ Module 3 HIP tests completed"; \
 	else \
 		echo "No compatible GPU detected, skipping HIP tests"; \