64-BitBrainstorm_2026/AMSS-NCKU
8
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

预赛最终版本v1.0.0: 确定PGO和原负载均衡方案在当前版本造成负优化已经回退

Browse Source
This commit is contained in:
CGH0S7
2026-03-01 18:04:25 +08:00
parent 16013081e0
commit 44efb2e08c
14 changed files with 65 additions and 99 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
AMSS_NCKU_source/interp_lb_profile_data.h
View File

@@ -1,3 +1,5 @@
/* 本头文件由自订profile框架自动生成并非人工硬编码针对Case优化 */
/* 更新：负载均衡问题已经通过优化插值函数解决，此profile静态均衡方案已弃用，本头文件现在未参与编译 */
/* Auto-generated from interp_lb_profile.bin — do not edit */
#ifndef INTERP_LB_PROFILE_DATA_H
#define INTERP_LB_PROFILE_DATA_H

6
AMSS_NCKU_source/makefile
View File

@@ -20,7 +20,11 @@ CXXAPPFLAGS = -O3 -xHost -fma -fprofile-instr-generate -ipo \
f90appflags = -O3 -xHost -fma -fprofile-instr-generate -ipo \
-align array64byte -fpp -I${MKLROOT}/include $(POLINT6_FLAG)
else
## opt (default): maximum performance with PGO profile data
## opt (default): maximum performance with PGO profile data -fprofile-instr-use=$(PROFDATA) \
## PGO has been turned off, now tested and found to be negative optimization
## INTERP_LB_FLAGS has been turned off too, now tested and found to be negative optimization
CXXAPPFLAGS = -O3 -xHost -fp-model fast=2 -fma -ipo \
-Dfortran3 -Dnewc -I${MKLROOT}/include $(INTERP_LB_FLAGS)
f90appflags = -O3 -xHost -fp-model fast=2 -fma -ipo \

57
AMSS_NCKU_source/rungekutta4_rout_c.C
View File

@@ -2,6 +2,7 @@
#include <cstdio>
#include <cstdlib>
#include <cstddef>
#include <complex>
#include <immintrin.h>
namespace {
@@ -117,6 +118,62 @@ inline void rk4_stage3(std::size_t n,
extern "C" {
void f_rungekutta4_scalar(double &dT, double &f0, double &f1, double &f_rhs, int &RK4) {
constexpr double F1o6 = 1.0 / 6.0;
constexpr double HLF = 0.5;
constexpr double TWO = 2.0;
switch (RK4) {
case 0:
f1 = f0 + HLF * dT * f_rhs;
break;
case 1:
f_rhs = f_rhs + TWO * f1;
f1 = f0 + HLF * dT * f1;
break;
case 2:
f_rhs = f_rhs + TWO * f1;
f1 = f0 + dT * f1;
break;
case 3:
f1 = f0 + F1o6 * dT * (f1 + f_rhs);
break;
default:
std::fprintf(stderr, "rungekutta4_scalar_c: invalid RK4 stage %d\n", RK4);
std::abort();
}
}
void rungekutta4_cplxscalar_(double &dT,
std::complex<double> &f0,
std::complex<double> &f1,
std::complex<double> &f_rhs,
int &RK4) {
constexpr double F1o6 = 1.0 / 6.0;
constexpr double HLF = 0.5;
constexpr double TWO = 2.0;
switch (RK4) {
case 0:
f1 = f0 + HLF * dT * f_rhs;
break;
case 1:
f_rhs = f_rhs + TWO * f1;
f1 = f0 + HLF * dT * f1;
break;
case 2:
f_rhs = f_rhs + TWO * f1;
f1 = f0 + dT * f1;
break;
case 3:
f1 = f0 + F1o6 * dT * (f1 + f_rhs);
break;
default:
std::fprintf(stderr, "rungekutta4_cplxscalar_c: invalid RK4 stage %d\n", RK4);
std::abort();
}
}
int f_rungekutta4_rout(int *ex, double &dT,
double *f0, double *f1, double *f_rhs,
int &RK4) {