Added propagation of not big initial stack size of master thread to workers.
Currently implemented only for non-Windows 64-bit platforms. Differential Revision: https://reviews.llvm.org/D62488 llvm-svn: 362618
This commit is contained in:
parent
de586bd1fd
commit
d47f5488cf
|
@ -3263,6 +3263,7 @@ extern void __kmp_init_random(kmp_info_t *thread);
|
|||
|
||||
extern kmp_r_sched_t __kmp_get_schedule_global(void);
|
||||
extern void __kmp_adjust_num_threads(int new_nproc);
|
||||
extern void __kmp_check_stksize(size_t *val);
|
||||
|
||||
extern void *___kmp_allocate(size_t size KMP_SRC_LOC_DECL);
|
||||
extern void *___kmp_page_allocate(size_t size KMP_SRC_LOC_DECL);
|
||||
|
|
|
@ -289,6 +289,20 @@ static void __kmp_stg_parse_bool(char const *name, char const *value,
|
|||
}
|
||||
} // __kmp_stg_parse_bool
|
||||
|
||||
// placed here in order to use __kmp_round4k static function
|
||||
void __kmp_check_stksize(size_t *val) {
|
||||
// if system stack size is too big then limit the size for worker threads
|
||||
if (*val > KMP_DEFAULT_STKSIZE * 16) // just a heuristics...
|
||||
*val = KMP_DEFAULT_STKSIZE * 16;
|
||||
if (*val < KMP_MIN_STKSIZE)
|
||||
*val = KMP_MIN_STKSIZE;
|
||||
if (*val > KMP_MAX_STKSIZE)
|
||||
*val = KMP_MAX_STKSIZE; // dead code currently, but may work in future
|
||||
#if KMP_OS_DARWIN
|
||||
*val = __kmp_round4k(*val);
|
||||
#endif // KMP_OS_DARWIN
|
||||
}
|
||||
|
||||
static void __kmp_stg_parse_size(char const *name, char const *value,
|
||||
size_t size_min, size_t size_max,
|
||||
int *is_specified, size_t *out,
|
||||
|
|
|
@ -1833,6 +1833,17 @@ void __kmp_runtime_initialize(void) {
|
|||
|
||||
__kmp_xproc = __kmp_get_xproc();
|
||||
|
||||
#if ! KMP_32_BIT_ARCH
|
||||
struct rlimit rlim;
|
||||
// read stack size of calling thread, save it as default for worker threads;
|
||||
// this should be done before reading environment variables
|
||||
status = getrlimit(RLIMIT_STACK, &rlim);
|
||||
if (status == 0) { // success?
|
||||
__kmp_stksize = rlim.rlim_cur;
|
||||
__kmp_check_stksize(&__kmp_stksize); // check value and adjust if needed
|
||||
}
|
||||
#endif /* KMP_32_BIT_ARCH */
|
||||
|
||||
if (sysconf(_SC_THREADS)) {
|
||||
|
||||
/* Query the maximum number of threads */
|
||||
|
|
|
@ -0,0 +1,65 @@
|
|||
// RUN: %libomp-compile-and-run
|
||||
|
||||
// https://bugs.llvm.org/show_bug.cgi?id=26540 requested
|
||||
// stack size to be propagated from master to workers.
|
||||
// Library implements propagation of not too big stack
|
||||
// for Linux x86_64 platform (skipped Windows for now).
|
||||
//
|
||||
// The test checks that workers can use more than 4MB
|
||||
// of stack (4MB - was historical default for
|
||||
// stack size of worker thread in runtime library).
|
||||
|
||||
#include <stdio.h>
|
||||
#include <omp.h>
|
||||
#if !defined(_WIN32)
|
||||
#include <sys/resource.h> // getrlimit
|
||||
#endif
|
||||
|
||||
#define STK 4800000
|
||||
|
||||
double foo(int n, int th)
|
||||
{
|
||||
double arr[n];
|
||||
int i;
|
||||
double res = 0.0;
|
||||
for (i = 0; i < n; ++i) {
|
||||
arr[i] = (double)i / (n + 2);
|
||||
}
|
||||
for (i = 0; i < n; ++i) {
|
||||
res += arr[i] / n;
|
||||
}
|
||||
return res;
|
||||
}
|
||||
|
||||
int main(int argc, char *argv[])
|
||||
{
|
||||
#if defined(_WIN32)
|
||||
// don't test Windows
|
||||
printf("stack propagation not implemented, skipping test...\n");
|
||||
return 0;
|
||||
#else
|
||||
int status;
|
||||
double val = 0.0;
|
||||
int m = STK / 8; // > 4800000 bytes per thread
|
||||
// read stack size of calling thread, save it as default
|
||||
struct rlimit rlim;
|
||||
status = getrlimit(RLIMIT_STACK, &rlim);
|
||||
if (sizeof(void *) > 4 && // do not test 32-bit systems,
|
||||
status == 0 && rlim.rlim_cur > STK) { // or small initial stack size
|
||||
#pragma omp parallel reduction(+:val)
|
||||
{
|
||||
val += foo(m, omp_get_thread_num());
|
||||
}
|
||||
} else {
|
||||
printf("too small stack size limit (needs about 8MB), skipping test...\n");
|
||||
return 0;
|
||||
}
|
||||
if (val > 0.1) {
|
||||
printf("passed\n");
|
||||
return 0;
|
||||
} else {
|
||||
printf("failed, val = %f\n", val);
|
||||
return 1;
|
||||
}
|
||||
#endif // _WIN32
|
||||
}
|
Loading…
Reference in New Issue