--- title: Roofline插桩指导 description: "Roofline分析支持手动region插桩，mode参数指定为region时，支持对应用中已经插桩的region块进行分别采集，实现function/loop级别的定量数据分析，该能力需要用户手动对待分析的源码进行插桩，并重新编译。" url: https://www.hikunpeng.com/document/detail/zh/kunpengdevkithistory/devkit_24_t50/cliuserguide/KunpengDevKitCli_0064.html sourcePath: /source/zh/kunpengdevkithistory/devkit_24_t50/cliuserguide/KunpengDevKitCli_0064.html indexId: 9e28114c6c614c54b136085c8015621c5bbfbe7644d8532c8d8262d6976f6e8885 --- # Roofline插桩指导 #### 插桩说明 Roofline分析支持手动region插桩，mode参数指定为region时，支持对应用中已经插桩的region块进行分别采集，实现function/loop级别的定量数据分析，该能力需要用户手动对待分析的源码进行插桩，并重新编译。 region插桩与分析：1. 在源代码中插入Roofline Events API。 - 以RPM安装鲲鹏DevKit命令行工具为例，默认安装路径为/usr/local/devkit， 后续以该目录为例。 - Roofline Events API定义在鲲鹏DevKit命令行工具安装路径下，即/usr/local/devkit/tuner/include/roofline_events.h或/usr/local/devkit/tuner/include/roofline_events.mod。 - roofline_events.h用于C/C++程序，roofline_events.mod用于Fortran程序。 2. 使用新的编译标志重新编译应用程序: - C/C++：-DROOFLINE_EVENTS -I /usr/local/devkit/tuner/include -L/usr/local/devkit/tuner/lib -lrfevents - Fortran：-I /usr/local/devkit/tuner/include -L/usr/local/devkit/tuner/lib -lrfevents 3. 需保证运行时动态库寻址路径包含/usr/local/devkit/tuner/lib， 比如在LD_LIBRARY_PATH中增加/usr/local/devkit/tuner/lib路径。 4. 进行Roofline分析时选择region模式，可使用命令行工具“devkit tuner roofline -m region<应用 应用参数>” 对插桩后编译生成的应用进行采集。 #### Roofline Events API介绍 数据是按线程收集，因此需注意以下规则： - 在串行代码中initialize/finalize（例如主线程）。 - 如果需要分析所有线程数据，start/stop API需要放置在并行代码中。 - 支持多个region，但不支持region之间嵌套，即同一个region的start/stop API需要成对且region之间不交错。 - region名称用于匹配线程之间的region数据。 - 以ROOFLINE_EVENTS开头的接口可以通过ROOFLINE_EVENTS编译选项进行开启和关闭，宏定义能力适用于C/C++。 - 以perf_roofline_events结尾的接口适用于C/C++/Fortran，不支持编译选项开关。 ``` #ifdef ROOFLINE_EVENTS #define ROOFLINE_EVENTS_INIT init_perf_roofline_events() #define ROOFLINE_EVENTS_START_REGION(region_label) start_perf_roofline_events(region_label) #define ROOFLINE_EVENTS_STOP_REGION(region_label) stop_perf_roofline_events(region_label) #define ROOFLINE_EVENTS_FINALIZE finalize_perf_roofline_events() #else #define ROOFLINE_EVENTS_INIT #define ROOFLINE_EVENTS_START_REGION(region_label) #define ROOFLINE_EVENTS_STOP_REGION(region_label) #define ROOFLINE_EVENTS_FINALIZE #endif #ifdef __cplusplus extern "C" { #endif // read system counters -> init // should be called in serial code before start_perf_roofline_events extern void init_perf_roofline_events(void) __attribute__((visibility("default"))); // start roofline events for current thread and provided region // should be called in parallel code extern void start_perf_roofline_events(const char* region) __attribute__((visibility("default"))); // stop roofline events for current thread and provided region // should be called in parallel code extern void stop_perf_roofline_events(const char* region) __attribute__((visibility("default"))); // summarize data for all regions // should be called in serial code after stop_perf_roofline_events for all regions/threads extern void finalize_perf_roofline_events(void) __attribute__((visibility("default"))); #ifdef __cplusplus } #endif ``` #### 插桩示例 - C源码Demo 文件名为matrix_multiply.c。 ``` #include #include #include #include #include // 使用插桩头文件 // #include "roofline_events.h" #ifdef DOUBLE_TYPE typedef double real_t; #else typedef float real_t; #endif static real_t rand_real() { #ifdef DOUBLE_TYPE const int mod = 1024; const double divider = 16.0; #else const int mod = 256; const float divider = 16.0f; #endif return ((rand() % mod) - mod / 2) / divider; } int main(int argc, char* argv[]) { size_t n = 1024; size_t i, j, k; real_t *A, *B, *B_transposed, *C; double start_time, end_time; // Get the dimension of the matrices from the command line argument if (argc >= 2) { n = atoi(argv[1]); } // 串行代码区initialize插桩事件 // ROOFLINE_EVENTS_INIT; start_time = omp_get_wtime(); // Allocate and initialize matrices A and B A = (real_t*)malloc(n * n * sizeof(real_t)); B = (real_t*)malloc(n * n * sizeof(real_t)); B_transposed = (real_t*)malloc(n * n * sizeof(real_t)); C = (real_t*)malloc(n * n * sizeof(real_t)); for (i = 0; i < n; i++) { for (j = 0; j < n; j++) { A[i * n + j] = rand_real(); B[i * n + j] = rand_real(); B_transposed[j * n + i] = B[i * n + j]; C[i * n + j] = 0.0; } } end_time = omp_get_wtime(); // Print the timings printf("Initialization time: %f seconds\n", end_time - start_time); // Perform matrix multiplication start_time = omp_get_wtime(); #pragma omp parallel { // 并行代码区start插桩事件matrix_multiply_c // ROOFLINE_EVENTS_START_REGION("matrix_multiply_c"); #pragma omp for private(i, j, k) for (i = 0; i < n; i++) { for (j = 0; j < n; j++) { for (k = 0; k < n; k++) { C[i * n + j] += A[i * n + k] * B_transposed[j * n + k]; } } } // 并行代码区stop插桩事件matrix_multiply_c // ROOFLINE_EVENTS_STOP_REGION("matrix_multiply_c"); } end_time = omp_get_wtime(); // Print the timings printf("Calculation time: %f seconds\n", end_time - start_time); // Print the result if n is less than or equal to 16 if (n <= 16) { printf("The product of A and B_transposed is:\n"); for (i = 0; i < n; i++) { for (j = 0; j < n; j++) { printf("%f ", C[i * n + j]); } printf("\n"); } } else { printf("The dimension of the matrices is too large to print.\n"); } // Deallocate matrices free(A); free(B); free(B_transposed); free(C); // 串行代码区finalize插桩事件 // ROOFLINE_EVENTS_FINALIZE; return 0; } ``` 上述demo已经添加插桩代码（注释状态），包含如下5行： 1. #include "roofline_events.h" 2. ROOFLINE_EVENTS_INIT; 3. ROOFLINE_EVENTS_START_REGION("matrix_multiply_c"); 4. ROOFLINE_EVENTS_STOP_REGION("matrix_multiply_c"); 5. ROOFLINE_EVENTS_FINALIZE; 插桩代码注释状态（未进行插桩情况下），编译命令如下： ``` gcc matrix_multiply.c -o matrix_multiply_c -fopenmp ``` 插桩代码去除注释状态（进行插桩情况下），增加插桩说明中的编译选项即可， 编译命令如下： ``` gcc matrix_multiply.c -o matrix_multiply_c -fopenmp -DROOFLINE_EVENTS -I /usr/local/devkit/tuner/include -L/usr/local/devkit/tuner/lib -lrfevents ``` - Fortran插桩Demo。 文件名为matrix_multiply.f90。 ``` program matrix_multiply ! 使用插桩模块 ! use roofline_events implicit none integer :: n = 1024 real, dimension(:,:), allocatable :: A, B, C, B_transposed integer :: i, j, k integer :: start_time, end_time, clock_rate real :: init_time, calc_time character(len=20) :: arg ! Get the dimension of the matrices from the command line argument if (iargc() .gt. 0) then call getarg(1, arg) read(arg, *) n end if ! 串行代码区initialize插桩事件 ! call init_perf_roofline_events() ! Start timing call system_clock(start_time, clock_rate) ! Allocate and initialize matrices A and B allocate(A(n,n), B(n,n), C(n,n), B_transposed(n,n)) call random_number(A) call random_number(B) ! Transpose matrix B B_transposed = transpose(B) ! End timing call system_clock(end_time) init_time = real(end_time - start_time) / real(clock_rate) print *, 'Initialization time: ', init_time, ' seconds' ! Start timing call system_clock(start_time, clock_rate) ! Perform matrix multiplication C = 0.0 !$OMP PARALLEL PRIVATE(i, j, k) SHARED(A, B_transposed, C, n) ! 并行代码区start插桩事件matrix_multiply_f ! call start_perf_roofline_events("matrix_multiply_f") !$OMP DO do i = 1, n do k = 1, n do j = 1, n C(i, k) = C(i, k) + A(i, j) * B_transposed(k, j) end do end do end do !$OMP END DO ! 并行代码区stop插桩事件matrix_multiply_f ! call stop_perf_roofline_events("matrix_multiply_f") !$OMP END PARALLEL ! End timing call system_clock(end_time) calc_time = real(end_time - start_time) / real(clock_rate) print *, 'Calculation time: ', calc_time, ' seconds' ! Print the result if n is less than or equal to 16 if (n <= 16) then print *, 'The product of A and B_transposed is:' print *, C else print *, 'The dimension of the matrices is too large to print.' end if ! Deallocate matrices deallocate(A, B, C, B_transposed) ! 串行代码区finalize插桩事件 ! call finalize_perf_roofline_events() end program matrix_multiply ``` 上述demo已添加插桩代码（注释状态），包含如下5行： 1. use roofline_events 2. call init_perf_roofline_events() 3. call start_perf_roofline_events("matrix_multiply_f") 4. call stop_perf_roofline_events("matrix_multiply_f") 5. call finalize_perf_roofline_events() 插桩代码注释状态（未进行插桩情况下），编译命令如下： ``` gfortran matrix_multiply.f90 -o matrix_multiply_f -fopenmp ``` 插桩代码去除注释状态（进行插桩情况下），增加插桩说明中的编译选项即可， 编译命令如下： ``` gfortran matrix_multiply.f90 -o matrix_multiply_f -fopenmp -I /usr/local/devkit/tuner/include -L/usr/local/devkit/tuner/lib -lrfevents ``` - region模式下Roofline采集。 采集命令如下（以C代码二进制为例），即可获取数据报告，该例中的region名为matrix_multiply_c，实际插桩过程中可以按需插入多个不同名称的region。 1 devkit tuner roofline -m region matrix_multiply_c