Files
composable_kernel/script/tools/ck-configure
Max Podkorytov 83b6155354 Add ck-rocprof: GPU profiling tool for rocprof-compute (#3627)
* Decouple configure/build/test tools from Docker

Create a two-layer tool architecture:
- Core tools (ck-configure, ck-build, ck-test): Environment-agnostic,
  work on any system with ROCm - no Docker dependency
- Container tools (ck-docker): Manage Docker containers and delegate
  to core tools via docker exec

Changes:
- Add ck-configure: New CMake configuration tool with preset support,
  native GPU detection, and flexible options
- Refactor ck-build: Remove Docker dependency, add --configure and
  --list options, call ninja directly
- Refactor ck-test: Remove Docker dependency, add CTest integration
  with --smoke/--regression/--all options
- Enhance common.sh: Add native GPU detection, build directory utils,
  and output helpers
- Update ck-docker: Add configure/build/test/exec commands that
  delegate to core tools inside container

This enables:
- Native development on ROCm hosts without Docker
- Simpler CI/CD integration
- Consistent behavior inside and outside containers

Co-Authored-By: Claude <noreply@anthropic.com>

* Add ck-rocprof: GPU profiling tool for rocprof-compute

Adds a command-line profiling tool to simplify GPU performance
analysis workflow using AMD rocprof-compute.

Features:
- Easy setup with automatic Python venv configuration
- Simple CLI: setup, run, analyze, compare, list
- Automatic GPU architecture detection
- Focus on LDS metrics (Block 12) for bank conflict analysis
- Comprehensive documentation with examples and troubleshooting

Usage:
  ck-rocprof setup                    # One-time environment setup
  ck-rocprof run <name> <executable>  # Profile executable
  ck-rocprof analyze <name> [block]   # Analyze metrics
  ck-rocprof compare <name1> <name2>  # Compare two runs
  ck-rocprof list                     # List available runs

* Make ck-rocprof documentation concise and improve Docker integration

- Streamlined documentation from 416 to 157 lines (62% reduction)
- Focused on essential commands, metrics, and workflows
- Enhanced script to run all operations inside Docker containers
- Fixed workload directory path and improved container management
- Added automatic rocprofiler-compute installation and dependency handling

* Add --no-roof flag to ck-rocprof profile command

Skip roofline analysis by default to speed up profiling. Roofline
analysis can add significant time to profiling runs but is not
needed for most LDS bank conflict analysis workflows.

* Make ck-rocprof work independently of Docker

Add native execution mode that runs rocprof-compute directly on the host
system when available, falling back to Docker mode when not.

Key changes:
- Auto-detect native mode when rocprof-compute is in PATH or common locations
- Add execution mode wrappers (exec_cmd, file_exists, dir_exists, etc.)
- Native mode stores venv at .ck-rocprof-venv in project root
- Native mode stores workloads at build/workloads/
- Support user-installed rocprofiler-compute (e.g., ~/.local/rocprofiler-compute)
- Add CK_FORCE_DOCKER env var to force Docker mode
- Update help message to show current execution mode
- Maintain full backward compatibility with existing Docker workflow

Tested successfully with rocprofiler-compute 3.4.0 installed from source
on MI300X GPU in native mode.

Co-Authored-By: Claude <noreply@anthropic.com>

* Add clean/status commands and improve ck-rocprof robustness

- Add 'clean' command to remove profiling runs (supports --all)
- Add 'status' command to show configuration and environment info
- Add workload name validation to prevent path traversal attacks
- Fix uv installation to use pip instead of curl for reliability
- Add cross-platform stat support for macOS compatibility
- Consolidate ROCPROF_CANDIDATES to avoid code duplication
- Expand help documentation with all profiling block descriptions
- Fix Docker wrapper script escaping issues

Co-Authored-By: Claude <noreply@anthropic.com>

* Fix analyze command to use correct workload path

rocprof-compute stores results directly in the workload directory
(pmc_perf.csv) rather than in a GPU architecture subdirectory.
Updated find_workload_path to detect this correctly.

Co-Authored-By: Claude <noreply@anthropic.com>

* Address PR review security and robustness issues

Security fixes:
- Escape executable path in cmd_run to prevent shell injection
- Add workload name validation to cmd_analyze and cmd_compare

Robustness improvements:
- Add error checking for uv package manager installation
- Use consistent project root detection (find_project_root || get_project_root)
- Use /opt/rocm instead of hardcoded /opt/rocm-7.0.1 in Docker mode
- Derive ROCM_REQUIREMENTS path from ROCPROF_BIN for flexibility
- Use gfx950 as fallback GPU consistent with common.sh

Documentation updates:
- Fix env var name GPU_TARGET -> CK_GPU_TARGET
- Update storage layout to reflect current structure (workloads/<name>/)
- Document clean and status commands
- Clarify native vs Docker default paths

Co-Authored-By: Claude <noreply@anthropic.com>

* Simplify ck-rocprof to native-only mode

Remove Docker mode from ck-rocprof. Docker users should run the tool
via `ck-docker exec ck-rocprof ...` instead.

This simplification:
- Removes ~210 lines of Docker-specific code
- Eliminates mode detection complexity
- Makes the script easier to maintain
- Provides clearer error messages when rocprof-compute is not found

The setup command now lists all searched locations when rocprof-compute
is not found, helping users understand how to install it.

Co-Authored-By: Claude <noreply@anthropic.com>

* Add rocprofiler-compute source installation fallback

When rocprof-compute is not found in system locations, automatically
install rocprofiler-compute 3.4.0 from source as a fallback. This
eliminates the hard dependency on system ROCm packages.

Implementation details:
- Clone rocprofiler-compute from GitHub to ~/.local/
- Install dependencies via requirements.txt (not editable install)
- Create wrapper that sets PYTHONPATH to source directory
- Execute source script directly rather than importing as module

This approach matches the project's development workflow and works
around the incomplete pyproject.toml that prevents editable installs.

Co-Authored-By: Claude <noreply@anthropic.com>

---------

Co-authored-by: Claude <noreply@anthropic.com>
2026-01-29 17:20:22 -08:00

188 lines
4.8 KiB
Bash
Executable File

#!/bin/bash
# Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
# SPDX-License-Identifier: MIT
# CK Configure - Configure CMake build for Composable Kernel
# Environment-agnostic: works natively on ROCm hosts or inside containers
set -e
set -o pipefail
# Find script directory and load common utilities
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
source "${SCRIPT_DIR}/common.sh"
# Initialize configuration
PROJECT_ROOT=$(find_project_root "${SCRIPT_DIR}" || get_project_root "${SCRIPT_DIR}")
BUILD_DIR=$(get_build_dir "${PROJECT_ROOT}")
# Help message
show_help() {
cat << EOF
CK Configure - Configure CMake build for Composable Kernel
Usage: ck-configure [options]
Options:
-h, --help Show this help message
--preset <name> Use CMake preset (dev, dev-gfx908, dev-gfx90a, dev-gfx942, dev-gfx950)
--gpu <target> Override GPU_TARGETS (auto-detected if not specified)
--dtypes <types> Set DTYPES (e.g., fp16,fp32,bf16)
--build-type <type> CMAKE_BUILD_TYPE (default: Release)
--build-dir <dir> Build directory (default: ./build)
--clean Remove existing build directory before configuring
--list-presets List available CMake presets
-D <VAR>=<value> Pass additional CMake variable
Environment:
CK_GPU_TARGET - Override GPU target detection (e.g., gfx950, gfx942)
CK_BUILD_DIR - Override build directory
Examples:
ck-configure # Auto-detect GPU and configure
ck-configure --preset dev-gfx950 # Use CMake preset
ck-configure --gpu gfx942 # Configure for specific GPU
ck-configure --clean --preset dev # Clean and reconfigure
ck-configure -D BUILD_DEV=ON # Pass CMake variable
EOF
}
# Parse arguments
preset=""
gpu_target=""
dtypes=""
build_type="Release"
clean=false
list_presets=false
cmake_vars=()
while [[ $# -gt 0 ]]; do
case $1 in
-h|--help)
show_help
exit 0
;;
--preset)
require_arg "$1" "${2:-}"
preset="$2"
shift 2
;;
--gpu)
require_arg "$1" "${2:-}"
gpu_target="$2"
shift 2
;;
--dtypes)
require_arg "$1" "${2:-}"
dtypes="$2"
shift 2
;;
--build-type)
require_arg "$1" "${2:-}"
build_type="$2"
shift 2
;;
--build-dir)
require_arg "$1" "${2:-}"
BUILD_DIR="$2"
shift 2
;;
--clean)
clean=true
shift
;;
--list-presets)
list_presets=true
shift
;;
-D)
require_arg "$1" "${2:-}"
cmake_vars+=("-D$2")
shift 2
;;
-D*)
cmake_vars+=("$1")
shift
;;
*)
error "Unknown option: $1"
echo ""
show_help
exit 1
;;
esac
done
# Handle --list-presets
if [ "$list_presets" = true ]; then
echo "Available CMake presets:"
presets=$(list_cmake_presets "${PROJECT_ROOT}" 2>/dev/null)
if [ -n "$presets" ]; then
echo "$presets" | sed 's/^/ /'
else
echo " (No CMakePresets.json found or jq not available)"
fi
exit 0
fi
# Clean build directory if requested
if [ "$clean" = true ]; then
if [ -d "${BUILD_DIR}" ]; then
info "Removing existing build directory: ${BUILD_DIR}"
rm -rf "${BUILD_DIR}"
fi
fi
# Create build directory
mkdir -p "${BUILD_DIR}"
# Change to project root for CMake
cd "${PROJECT_ROOT}"
# Build CMake command
cmake_cmd=(cmake -S . -B "${BUILD_DIR}" -GNinja)
# Use preset if specified
if [ -n "$preset" ]; then
cmake_cmd+=(--preset "${preset}")
info "Using CMake preset: ${preset}"
else
# Manual configuration
# Detect GPU target if not specified
if [ -z "$gpu_target" ]; then
gpu_target=$(detect_gpu_native)
info "Auto-detected GPU target: ${gpu_target}"
else
info "Using specified GPU target: ${gpu_target}"
fi
cmake_cmd+=(-DGPU_TARGETS="${gpu_target}")
cmake_cmd+=(-DCMAKE_BUILD_TYPE="${build_type}")
cmake_cmd+=(-DCMAKE_CXX_COMPILER=/opt/rocm/llvm/bin/clang++)
cmake_cmd+=(-DBUILD_TESTING=ON)
# Add DTYPES if specified
if [ -n "$dtypes" ]; then
cmake_cmd+=(-DDTYPES="${dtypes}")
info "Using DTYPES: ${dtypes}"
fi
fi
# Add any additional CMake variables
for var in "${cmake_vars[@]}"; do
cmake_cmd+=("$var")
done
# Run CMake
info "Configuring build in: ${BUILD_DIR}"
echo "Running: ${cmake_cmd[*]}"
echo ""
"${cmake_cmd[@]}"
echo ""
info "Configuration complete. Build directory: ${BUILD_DIR}"
info "Next: run 'ck-build' to build targets"