armando-canales-lima: Implemented optimized matrix multiplication with CUDA

Makefile

@@ -0,0 +1,181 @@
+# CMAKE generated file: DO NOT EDIT!
+# Generated by "Unix Makefiles" Generator, CMake Version 3.28
+
+# Default target executed when no arguments are given to make.
+default_target: all
+.PHONY : default_target
+
+# Allow only one "make -f Makefile2" at a time, but pass parallelism.
+.NOTPARALLEL:
+
+#=============================================================================
+# Special targets provided by cmake.
+
+# Disable implicit rules so canonical targets will work.
+.SUFFIXES:
+
+# Disable VCS-based implicit rules.
+% : %,v
+
+# Disable VCS-based implicit rules.
+% : RCS/%
+
+# Disable VCS-based implicit rules.
+% : RCS/%,v
+
+# Disable VCS-based implicit rules.
+% : SCCS/s.%
+
+# Disable VCS-based implicit rules.
+% : s.%
+
+.SUFFIXES: .hpux_make_needs_suffix_list
+
+# Command-line flag to silence nested $(MAKE).
+$(VERBOSE)MAKESILENT = -s
+
+#Suppress display of executed commands.
+$(VERBOSE).SILENT:
+
+# A target that is always out of date.
+cmake_force:
+.PHONY : cmake_force
+
+#=============================================================================
+# Set environment variables for the build.
+
+# The shell in which to execute make rules.
+SHELL = /bin/sh
+
+# The CMake executable.
+CMAKE_COMMAND = /usr/bin/cmake
+
+# The command to remove a file.
+RM = /usr/bin/cmake -E rm -f
+
+# Escaping for special characters.
+EQUALS = =
+
+# The top-level source directory on which CMake was run.
+CMAKE_SOURCE_DIR = /Dev/parallel-programming-homework-3
+
+# The top-level build directory on which CMake was run.
+CMAKE_BINARY_DIR = /Dev/parallel-programming-homework-3
+
+#=============================================================================
+# Targets provided globally by CMake.
+
+# Special rule for the target edit_cache
+edit_cache:
+	@$(CMAKE_COMMAND) -E cmake_echo_color "--switch=$(COLOR)" --cyan "No interactive CMake dialog available..."
+	/usr/bin/cmake -E echo No\ interactive\ CMake\ dialog\ available.
+.PHONY : edit_cache
+
+# Special rule for the target edit_cache
+edit_cache/fast: edit_cache
+.PHONY : edit_cache/fast
+
+# Special rule for the target rebuild_cache
+rebuild_cache:
+	@$(CMAKE_COMMAND) -E cmake_echo_color "--switch=$(COLOR)" --cyan "Running CMake to regenerate build system..."
+	/usr/bin/cmake --regenerate-during-build -S$(CMAKE_SOURCE_DIR) -B$(CMAKE_BINARY_DIR)
+.PHONY : rebuild_cache
+
+# Special rule for the target rebuild_cache
+rebuild_cache/fast: rebuild_cache
+.PHONY : rebuild_cache/fast
+
+# The main all target
+all: cmake_check_build_system
+	$(CMAKE_COMMAND) -E cmake_progress_start /Dev/parallel-programming-homework-3/CMakeFiles /Dev/parallel-programming-homework-3//CMakeFiles/progress.marks
+	$(MAKE) $(MAKESILENT) -f CMakeFiles/Makefile2 all
+	$(CMAKE_COMMAND) -E cmake_progress_start /Dev/parallel-programming-homework-3/CMakeFiles 0
+.PHONY : all
+
+# The main clean target
+clean:
+	$(MAKE) $(MAKESILENT) -f CMakeFiles/Makefile2 clean
+.PHONY : clean
+
+# The main clean target
+clean/fast: clean
+.PHONY : clean/fast
+
+# Prepare targets for installation.
+preinstall: all
+	$(MAKE) $(MAKESILENT) -f CMakeFiles/Makefile2 preinstall
+.PHONY : preinstall
+
+# Prepare targets for installation.
+preinstall/fast:
+	$(MAKE) $(MAKESILENT) -f CMakeFiles/Makefile2 preinstall
+.PHONY : preinstall/fast
+
+# clear depends
+depend:
+	$(CMAKE_COMMAND) -S$(CMAKE_SOURCE_DIR) -B$(CMAKE_BINARY_DIR) --check-build-system CMakeFiles/Makefile.cmake 1
+.PHONY : depend
+
+#=============================================================================
+# Target rules for targets named app
+
+# Build rule for target.
+app: cmake_check_build_system
+	$(MAKE) $(MAKESILENT) -f CMakeFiles/Makefile2 app
+.PHONY : app
+
+# fast build rule for target.
+app/fast:
+	$(MAKE) $(MAKESILENT) -f CMakeFiles/app.dir/build.make CMakeFiles/app.dir/build
+.PHONY : app/fast
+
+main.o: main.cu.o
+.PHONY : main.o
+
+# target to build an object file
+main.cu.o:
+	$(MAKE) $(MAKESILENT) -f CMakeFiles/app.dir/build.make CMakeFiles/app.dir/main.cu.o
+.PHONY : main.cu.o
+
+main.i: main.cu.i
+.PHONY : main.i
+
+# target to preprocess a source file
+main.cu.i:
+	$(MAKE) $(MAKESILENT) -f CMakeFiles/app.dir/build.make CMakeFiles/app.dir/main.cu.i
+.PHONY : main.cu.i
+
+main.s: main.cu.s
+.PHONY : main.s
+
+# target to generate assembly for a file
+main.cu.s:
+	$(MAKE) $(MAKESILENT) -f CMakeFiles/app.dir/build.make CMakeFiles/app.dir/main.cu.s
+.PHONY : main.cu.s
+
+# Help Target
+help:
+	@echo "The following are some of the valid targets for this Makefile:"
+	@echo "... all (the default if no target is provided)"
+	@echo "... clean"
+	@echo "... depend"
+	@echo "... edit_cache"
+	@echo "... rebuild_cache"
+	@echo "... app"
+	@echo "... main.o"
+	@echo "... main.i"
+	@echo "... main.s"
+.PHONY : help
+
+
+
+#=============================================================================
+# Special targets to cleanup operation of make.
+
+# Special rule to run CMake to check the build system integrity.
+# No rule that depends on this can have commands that come from listfiles
+# because they might be regenerated.
+cmake_check_build_system:
+	$(CMAKE_COMMAND) -S$(CMAKE_SOURCE_DIR) -B$(CMAKE_BINARY_DIR) --check-build-system CMakeFiles/Makefile.cmake 0
+.PHONY : cmake_check_build_system
+

README.md

@@ -205,3 +205,23 @@ git push origin student-name
 
 Good luck, and enjoy accelerating matrix multiplication with CUDA!
 
+
+---
+
+# Results
+
+**v. Armando Canales Lima**
+
+| Test Case | Dimensions (m × n × p) | Naive Time (s) | Blocked Time (s) | Parallel Time (s) | Tiled CUDA Time (s) | Speedup vs. Naive CUDA | Speedup vs. Parallel CPU |
+| --------- | ---------------------- | -------------- | ---------------- | ----------------- | ------------------- | ---------------------- | ------------------------ |
+| 0         | 64 × 64 × 64           | 0.0009391      | 0.0009271        | 0.0005915         | 0.000094656         | **1912.49×**           | **6.25×**                |
+| 1         | 128 × 64 × 128         | 0.0036451      | 0.0037321        | 0.0010113         | 0.000129632         | **276.78×**            | **7.80×**                |
+| 2         | 100 × 128 × 56         | 0.0024653      | 0.0025529        | 0.0007842         | 0.000213344         | **151.47×**            | **3.68×**                |
+| 3         | 128 × 64 × 128         | 0.0035558      | 0.0037061        | 0.0012246         | 0.000098784         | **341.43×**            | **12.40×**               |
+| 4         | 32 × 128 × 32          | 0.0005984      | 0.0004421        | 0.0005571         | 0.000056768         | **586.45×**            | **9.82×**                |
+| 5         | 200 × 100 × 256        | 0.0223089      | 0.0194391        | 0.0031179         | 0.000111328         | **272.51×**            | **28.00×**               |
+| 6         | 256 × 256 × 256        | 0.0798916      | 0.0600181        | 0.0089990         | 0.000267968         | **115.84×**            | **33.57×**               |
+| 7         | 256 × 300 × 256        | 0.0932562      | 0.0720682        | 0.0116580         | 0.000306016         | **106.83×**            | **38.11×**               |
+| 8         | 64 × 128 × 64          | 0.0019189      | 0.0018024        | 0.0007125         | 0.000144128         | **204.63×**            | **4.94×**                |
+| 9         | 256 × 256 × 257        | 0.1010160      | 0.0604076        | 0.0079931         | 0.00025808          | **127.22×**            | **30.97×**               |
+