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

优化 compute_rhs_bssn 热点路径并加入 NaN 检查开关

Browse Source 
- 用 DEBUG_NAN_CHECK 宏按需启用 NaN 检查，并在输入/宏生成器中新增 Debug_NaN_Check 配置
  - 逆度量改为先求行列式再乘法展开，减少除法；并在 Gam^i/Christoffel 处提取公共子表达式
  - 预置批量 fderivs 辅助例程，便于后续矢量化/合并导数计算
  - 将默认 MPI_processes 调整为 8

  变更涉及：

  - AMSS_NCKU_source/bssn_rhs.f90
  - generate_macrodef.py
  - AMSS_NCKU_Input.py
  - AMSS_NCKU_Input_Mini.py
  - inputfile_example/AMSS_NCKU_Input.py
  - AMSS_NCKU_source/diff_new.f90

TODO: fmisc.f90 polint()
This commit is contained in:
CGH0S7
2026-01-20 19:37:26 +08:00
parent ae7b77e44c
commit ef96766e22
6 changed files with 1536 additions and 1188 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
AMSS_NCKU_Input.py
View File

@@ -16,12 +16,14 @@ import numpy
File_directory = "GW150914" ## output file directory
Output_directory = "binary_output" ## binary data file directory
## The file directory name should not be too long
MPI_processes = 48 ## number of mpi processes used in the simulation
MPI_processes = 8 ## number of mpi processes used in the simulation
GPU_Calculation = "no" ## Use GPU or not
## (prefer "no" in the current version, because the GPU part may have bugs when integrated in this Python interface)
CPU_Part = 1.0
GPU_Part = 0.0
Debug_NaN_Check = 0 ## enable NaN checks in compute_rhs_bssn: 0 (off) or 1 (on)
#################################################

1
AMSS_NCKU_Input_Mini.py
View File

@@ -37,6 +37,7 @@ Equation_Class = "BSSN" ## Evolution Equation: choose
Initial_Data_Method = "Ansorg-TwoPuncture" ## initial data method: choose "Ansorg-TwoPuncture", "Lousto-Analytical", "Cao-Analytical", "KerrSchild-Analytical"
Time_Evolution_Method = "runge-kutta-45" ## time evolution method: choose "runge-kutta-45"
Finite_Diffenence_Method = "4th-order" ## finite-difference method: choose "2nd-order", "4th-order", "6th-order", "8th-order"
Debug_NaN_Check = 0 ## enable NaN checks in compute_rhs_bssn: 0 (off) or 1 (on)
#################################################

2396
AMSS_NCKU_source/bssn_rhs.f90
View File

File diff suppressed because it is too large Load Diff

306
AMSS_NCKU_source/diff_new.f90
View File

@@ -1939,6 +1939,309 @@
return
end subroutine fddyz
subroutine fderivs_batch4(ex,f1,f2,f3,f4, &
f1x,f1y,f1z,f2x,f2y,f2z,f3x,f3y,f3z,f4x,f4y,f4z, &
X,Y,Z,SYM1,SYM2,SYM3,symmetry,onoff)
implicit none
integer, intent(in ):: ex(1:3),symmetry,onoff
real*8, dimension(ex(1),ex(2),ex(3)), intent(in ):: f1,f2,f3,f4
real*8, dimension(ex(1),ex(2),ex(3)), intent(out):: f1x,f1y,f1z
real*8, dimension(ex(1),ex(2),ex(3)), intent(out):: f2x,f2y,f2z
real*8, dimension(ex(1),ex(2),ex(3)), intent(out):: f3x,f3y,f3z
real*8, dimension(ex(1),ex(2),ex(3)), intent(out):: f4x,f4y,f4z
real*8, intent(in) :: X(ex(1)),Y(ex(2)),Z(ex(3))
real*8, intent(in ):: SYM1,SYM2,SYM3
!~~~~~~ other variables
real*8 :: dX,dY,dZ
real*8,dimension(-1:ex(1),-1:ex(2),-1:ex(3)) :: fh1,fh2,fh3,fh4
real*8, dimension(3) :: SoA
integer :: imin,jmin,kmin,imax,jmax,kmax,i,j,k
real*8 :: d12dx,d12dy,d12dz,d2dx,d2dy,d2dz
integer, parameter :: NO_SYMM = 0, EQ_SYMM = 1, OCTANT = 2
real*8, parameter :: ZEO=0.d0,ONE=1.d0
real*8, parameter :: TWO=2.d0,EIT=8.d0
real*8, parameter :: F12=1.2d1
dX = X(2)-X(1)
dY = Y(2)-Y(1)
dZ = Z(2)-Z(1)
imax = ex(1)
jmax = ex(2)
kmax = ex(3)
imin = 1
jmin = 1
kmin = 1
if(Symmetry > NO_SYMM .and. dabs(Z(1)) < dZ) kmin = -1
if(Symmetry > EQ_SYMM .and. dabs(X(1)) < dX) imin = -1
if(Symmetry > EQ_SYMM .and. dabs(Y(1)) < dY) jmin = -1
SoA(1) = SYM1
SoA(2) = SYM2
SoA(3) = SYM3
call symmetry_bd(2,ex,f1,fh1,SoA)
call symmetry_bd(2,ex,f2,fh2,SoA)
call symmetry_bd(2,ex,f3,fh3,SoA)
call symmetry_bd(2,ex,f4,fh4,SoA)
d12dx = ONE/F12/dX
d12dy = ONE/F12/dY
d12dz = ONE/F12/dZ
d2dx = ONE/TWO/dX
d2dy = ONE/TWO/dY
d2dz = ONE/TWO/dZ
f1x = ZEO; f1y = ZEO; f1z = ZEO
f2x = ZEO; f2y = ZEO; f2z = ZEO
f3x = ZEO; f3y = ZEO; f3z = ZEO
f4x = ZEO; f4y = ZEO; f4z = ZEO
do k=1,ex(3)-1
do j=1,ex(2)-1
do i=1,ex(1)-1
if(i+2 <= imax .and. i-2 >= imin .and. &
j+2 <= jmax .and. j-2 >= jmin .and. &
k+2 <= kmax .and. k-2 >= kmin) then
f1x(i,j,k)=d12dx*(fh1(i-2,j,k)-EIT*fh1(i-1,j,k)+EIT*fh1(i+1,j,k)-fh1(i+2,j,k))
f1y(i,j,k)=d12dy*(fh1(i,j-2,k)-EIT*fh1(i,j-1,k)+EIT*fh1(i,j+1,k)-fh1(i,j+2,k))
f1z(i,j,k)=d12dz*(fh1(i,j,k-2)-EIT*fh1(i,j,k-1)+EIT*fh1(i,j,k+1)-fh1(i,j,k+2))
f2x(i,j,k)=d12dx*(fh2(i-2,j,k)-EIT*fh2(i-1,j,k)+EIT*fh2(i+1,j,k)-fh2(i+2,j,k))
f2y(i,j,k)=d12dy*(fh2(i,j-2,k)-EIT*fh2(i,j-1,k)+EIT*fh2(i,j+1,k)-fh2(i,j+2,k))
f2z(i,j,k)=d12dz*(fh2(i,j,k-2)-EIT*fh2(i,j,k-1)+EIT*fh2(i,j,k+1)-fh2(i,j,k+2))
f3x(i,j,k)=d12dx*(fh3(i-2,j,k)-EIT*fh3(i-1,j,k)+EIT*fh3(i+1,j,k)-fh3(i+2,j,k))
f3y(i,j,k)=d12dy*(fh3(i,j-2,k)-EIT*fh3(i,j-1,k)+EIT*fh3(i,j+1,k)-fh3(i,j+2,k))
f3z(i,j,k)=d12dz*(fh3(i,j,k-2)-EIT*fh3(i,j,k-1)+EIT*fh3(i,j,k+1)-fh3(i,j,k+2))
f4x(i,j,k)=d12dx*(fh4(i-2,j,k)-EIT*fh4(i-1,j,k)+EIT*fh4(i+1,j,k)-fh4(i+2,j,k))
f4y(i,j,k)=d12dy*(fh4(i,j-2,k)-EIT*fh4(i,j-1,k)+EIT*fh4(i,j+1,k)-fh4(i,j+2,k))
f4z(i,j,k)=d12dz*(fh4(i,j,k-2)-EIT*fh4(i,j,k-1)+EIT*fh4(i,j,k+1)-fh4(i,j,k+2))
elseif(i+1 <= imax .and. i-1 >= imin .and. &
j+1 <= jmax .and. j-1 >= jmin .and. &
k+1 <= kmax .and. k-1 >= kmin) then
f1x(i,j,k)=d2dx*(-fh1(i-1,j,k)+fh1(i+1,j,k))
f1y(i,j,k)=d2dy*(-fh1(i,j-1,k)+fh1(i,j+1,k))
f1z(i,j,k)=d2dz*(-fh1(i,j,k-1)+fh1(i,j,k+1))
f2x(i,j,k)=d2dx*(-fh2(i-1,j,k)+fh2(i+1,j,k))
f2y(i,j,k)=d2dy*(-fh2(i,j-1,k)+fh2(i,j+1,k))
f2z(i,j,k)=d2dz*(-fh2(i,j,k-1)+fh2(i,j,k+1))
f3x(i,j,k)=d2dx*(-fh3(i-1,j,k)+fh3(i+1,j,k))
f3y(i,j,k)=d2dy*(-fh3(i,j-1,k)+fh3(i,j+1,k))
f3z(i,j,k)=d2dz*(-fh3(i,j,k-1)+fh3(i,j,k+1))
f4x(i,j,k)=d2dx*(-fh4(i-1,j,k)+fh4(i+1,j,k))
f4y(i,j,k)=d2dy*(-fh4(i,j-1,k)+fh4(i,j+1,k))
f4z(i,j,k)=d2dz*(-fh4(i,j,k-1)+fh4(i,j,k+1))
endif
enddo
enddo
enddo
return
end subroutine fderivs_batch4
!-----------------------------------------------------------------------------
! batch first derivatives (3 fields), same symmetry setup
!-----------------------------------------------------------------------------
subroutine fderivs_batch3(ex,f1,f2,f3, &
f1x,f1y,f1z,f2x,f2y,f2z,f3x,f3y,f3z, &
X,Y,Z,SYM1,SYM2,SYM3,symmetry,onoff)
implicit none
integer, intent(in ):: ex(1:3),symmetry,onoff
real*8, dimension(ex(1),ex(2),ex(3)), intent(in ):: f1,f2,f3
real*8, dimension(ex(1),ex(2),ex(3)), intent(out):: f1x,f1y,f1z
real*8, dimension(ex(1),ex(2),ex(3)), intent(out):: f2x,f2y,f2z
real*8, dimension(ex(1),ex(2),ex(3)), intent(out):: f3x,f3y,f3z
real*8, intent(in) :: X(ex(1)),Y(ex(2)),Z(ex(3))
real*8, intent(in ):: SYM1,SYM2,SYM3
!~~~~~~ other variables
real*8 :: dX,dY,dZ
real*8,dimension(-1:ex(1),-1:ex(2),-1:ex(3)) :: fh1,fh2,fh3
real*8, dimension(3) :: SoA
integer :: imin,jmin,kmin,imax,jmax,kmax,i,j,k
real*8 :: d12dx,d12dy,d12dz,d2dx,d2dy,d2dz
integer, parameter :: NO_SYMM = 0, EQ_SYMM = 1, OCTANT = 2
real*8, parameter :: ZEO=0.d0,ONE=1.d0
real*8, parameter :: TWO=2.d0,EIT=8.d0
real*8, parameter :: F12=1.2d1
dX = X(2)-X(1)
dY = Y(2)-Y(1)
dZ = Z(2)-Z(1)
imax = ex(1)
jmax = ex(2)
kmax = ex(3)
imin = 1
jmin = 1
kmin = 1
if(Symmetry > NO_SYMM .and. dabs(Z(1)) < dZ) kmin = -1
if(Symmetry > EQ_SYMM .and. dabs(X(1)) < dX) imin = -1
if(Symmetry > EQ_SYMM .and. dabs(Y(1)) < dY) jmin = -1
SoA(1) = SYM1
SoA(2) = SYM2
SoA(3) = SYM3
call symmetry_bd(2,ex,f1,fh1,SoA)
call symmetry_bd(2,ex,f2,fh2,SoA)
call symmetry_bd(2,ex,f3,fh3,SoA)
d12dx = ONE/F12/dX
d12dy = ONE/F12/dY
d12dz = ONE/F12/dZ
d2dx = ONE/TWO/dX
d2dy = ONE/TWO/dY
d2dz = ONE/TWO/dZ
f1x = ZEO; f1y = ZEO; f1z = ZEO
f2x = ZEO; f2y = ZEO; f2z = ZEO
f3x = ZEO; f3y = ZEO; f3z = ZEO
do k=1,ex(3)-1
do j=1,ex(2)-1
do i=1,ex(1)-1
if(i+2 <= imax .and. i-2 >= imin .and. &
j+2 <= jmax .and. j-2 >= jmin .and. &
k+2 <= kmax .and. k-2 >= kmin) then
f1x(i,j,k)=d12dx*(fh1(i-2,j,k)-EIT*fh1(i-1,j,k)+EIT*fh1(i+1,j,k)-fh1(i+2,j,k))
f1y(i,j,k)=d12dy*(fh1(i,j-2,k)-EIT*fh1(i,j-1,k)+EIT*fh1(i,j+1,k)-fh1(i,j+2,k))
f1z(i,j,k)=d12dz*(fh1(i,j,k-2)-EIT*fh1(i,j,k-1)+EIT*fh1(i,j,k+1)-fh1(i,j,k+2))
f2x(i,j,k)=d12dx*(fh2(i-2,j,k)-EIT*fh2(i-1,j,k)+EIT*fh2(i+1,j,k)-fh2(i+2,j,k))
f2y(i,j,k)=d12dy*(fh2(i,j-2,k)-EIT*fh2(i,j-1,k)+EIT*fh2(i,j+1,k)-fh2(i,j+2,k))
f2z(i,j,k)=d12dz*(fh2(i,j,k-2)-EIT*fh2(i,j,k-1)+EIT*fh2(i,j,k+1)-fh2(i,j,k+2))
f3x(i,j,k)=d12dx*(fh3(i-2,j,k)-EIT*fh3(i-1,j,k)+EIT*fh3(i+1,j,k)-fh3(i+2,j,k))
f3y(i,j,k)=d12dy*(fh3(i,j-2,k)-EIT*fh3(i,j-1,k)+EIT*fh3(i,j+1,k)-fh3(i,j+2,k))
f3z(i,j,k)=d12dz*(fh3(i,j,k-2)-EIT*fh3(i,j,k-1)+EIT*fh3(i,j,k+1)-fh3(i,j,k+2))
elseif(i+1 <= imax .and. i-1 >= imin .and. &
j+1 <= jmax .and. j-1 >= jmin .and. &
k+1 <= kmax .and. k-1 >= kmin) then
f1x(i,j,k)=d2dx*(-fh1(i-1,j,k)+fh1(i+1,j,k))
f1y(i,j,k)=d2dy*(-fh1(i,j-1,k)+fh1(i,j+1,k))
f1z(i,j,k)=d2dz*(-fh1(i,j,k-1)+fh1(i,j,k+1))
f2x(i,j,k)=d2dx*(-fh2(i-1,j,k)+fh2(i+1,j,k))
f2y(i,j,k)=d2dy*(-fh2(i,j-1,k)+fh2(i,j+1,k))
f2z(i,j,k)=d2dz*(-fh2(i,j,k-1)+fh2(i,j,k+1))
f3x(i,j,k)=d2dx*(-fh3(i-1,j,k)+fh3(i+1,j,k))
f3y(i,j,k)=d2dy*(-fh3(i,j-1,k)+fh3(i,j+1,k))
f3z(i,j,k)=d2dz*(-fh3(i,j,k-1)+fh3(i,j,k+1))
endif
enddo
enddo
enddo
return
end subroutine fderivs_batch3
!-----------------------------------------------------------------------------
! batch first derivatives (2 fields), same symmetry setup
!-----------------------------------------------------------------------------
subroutine fderivs_batch2(ex,f1,f2, &
f1x,f1y,f1z,f2x,f2y,f2z, &
X,Y,Z,SYM1,SYM2,SYM3,symmetry,onoff)
implicit none
integer, intent(in ):: ex(1:3),symmetry,onoff
real*8, dimension(ex(1),ex(2),ex(3)), intent(in ):: f1,f2
real*8, dimension(ex(1),ex(2),ex(3)), intent(out):: f1x,f1y,f1z
real*8, dimension(ex(1),ex(2),ex(3)), intent(out):: f2x,f2y,f2z
real*8, intent(in) :: X(ex(1)),Y(ex(2)),Z(ex(3))
real*8, intent(in ):: SYM1,SYM2,SYM3
!~~~~~~ other variables
real*8 :: dX,dY,dZ
real*8,dimension(-1:ex(1),-1:ex(2),-1:ex(3)) :: fh1,fh2
real*8, dimension(3) :: SoA
integer :: imin,jmin,kmin,imax,jmax,kmax,i,j,k
real*8 :: d12dx,d12dy,d12dz,d2dx,d2dy,d2dz
integer, parameter :: NO_SYMM = 0, EQ_SYMM = 1, OCTANT = 2
real*8, parameter :: ZEO=0.d0,ONE=1.d0
real*8, parameter :: TWO=2.d0,EIT=8.d0
real*8, parameter :: F12=1.2d1
dX = X(2)-X(1)
dY = Y(2)-Y(1)
dZ = Z(2)-Z(1)
imax = ex(1)
jmax = ex(2)
kmax = ex(3)
imin = 1
jmin = 1
kmin = 1
if(Symmetry > NO_SYMM .and. dabs(Z(1)) < dZ) kmin = -1
if(Symmetry > EQ_SYMM .and. dabs(X(1)) < dX) imin = -1
if(Symmetry > EQ_SYMM .and. dabs(Y(1)) < dY) jmin = -1
SoA(1) = SYM1
SoA(2) = SYM2
SoA(3) = SYM3
call symmetry_bd(2,ex,f1,fh1,SoA)
call symmetry_bd(2,ex,f2,fh2,SoA)
d12dx = ONE/F12/dX
d12dy = ONE/F12/dY
d12dz = ONE/F12/dZ
d2dx = ONE/TWO/dX
d2dy = ONE/TWO/dY
d2dz = ONE/TWO/dZ
f1x = ZEO; f1y = ZEO; f1z = ZEO
f2x = ZEO; f2y = ZEO; f2z = ZEO
do k=1,ex(3)-1
do j=1,ex(2)-1
do i=1,ex(1)-1
if(i+2 <= imax .and. i-2 >= imin .and. &
j+2 <= jmax .and. j-2 >= jmin .and. &
k+2 <= kmax .and. k-2 >= kmin) then
f1x(i,j,k)=d12dx*(fh1(i-2,j,k)-EIT*fh1(i-1,j,k)+EIT*fh1(i+1,j,k)-fh1(i+2,j,k))
f1y(i,j,k)=d12dy*(fh1(i,j-2,k)-EIT*fh1(i,j-1,k)+EIT*fh1(i,j+1,k)-fh1(i,j+2,k))
f1z(i,j,k)=d12dz*(fh1(i,j,k-2)-EIT*fh1(i,j,k-1)+EIT*fh1(i,j,k+1)-fh1(i,j,k+2))
f2x(i,j,k)=d12dx*(fh2(i-2,j,k)-EIT*fh2(i-1,j,k)+EIT*fh2(i+1,j,k)-fh2(i+2,j,k))
f2y(i,j,k)=d12dy*(fh2(i,j-2,k)-EIT*fh2(i,j-1,k)+EIT*fh2(i,j+1,k)-fh2(i,j+2,k))
f2z(i,j,k)=d12dz*(fh2(i,j,k-2)-EIT*fh2(i,j,k-1)+EIT*fh2(i,j,k+1)-fh2(i,j,k+2))
elseif(i+1 <= imax .and. i-1 >= imin .and. &
j+1 <= jmax .and. j-1 >= jmin .and. &
k+1 <= kmax .and. k-1 >= kmin) then
f1x(i,j,k)=d2dx*(-fh1(i-1,j,k)+fh1(i+1,j,k))
f1y(i,j,k)=d2dy*(-fh1(i,j-1,k)+fh1(i,j+1,k))
f1z(i,j,k)=d2dz*(-fh1(i,j,k-1)+fh1(i,j,k+1))
f2x(i,j,k)=d2dx*(-fh2(i-1,j,k)+fh2(i+1,j,k))
f2y(i,j,k)=d2dy*(-fh2(i,j-1,k)+fh2(i,j+1,k))
f2z(i,j,k)=d2dz*(-fh2(i,j,k-1)+fh2(i,j,k+1))
endif
enddo
enddo
enddo
return
end subroutine fderivs_batch2
#elif (ghost_width == 4)
! sixth order code
@@ -2077,6 +2380,9 @@
end subroutine fderivs
!-----------------------------------------------------------------------------
! batch first derivatives (4 fields), same symmetry setup
!-----------------------------------------------------------------------------
!-----------------------------------------------------------------------------
!
! single derivatives dx
!

14
generate_macrodef.py
View File

@@ -392,6 +392,17 @@ def generate_macrodef_fh():
print( "# Finite_Difference_Method #define ghost_width setting error!!!", file=file1 )
print( file=file1 )
# Define macro DEBUG_NAN_CHECK
# 0: off (default), 1: on
debug_nan_check = getattr(input_data, "Debug_NaN_Check", 0)
if debug_nan_check:
print( "#define DEBUG_NAN_CHECK 1", file=file1 )
print( file=file1 )
else:
print( "#define DEBUG_NAN_CHECK 0", file=file1 )
print( file=file1 )
# Whether to use a shell-patch grid
# use shell or not
@@ -514,6 +525,9 @@ def generate_macrodef_fh():
print( " 6th order: 4", file=file1 )
print( " 8th order: 5", file=file1 )
print( file=file1 )
print( "define DEBUG_NAN_CHECK", file=file1 )
print( " 0: off (default), 1: on", file=file1 )
print( file=file1 )
print( "define WithShell", file=file1 )
print( " use shell or not", file=file1 )
print( file=file1 )

3
inputfile_example/AMSS_NCKU_Input.py
View File

@@ -35,7 +35,8 @@ Equation_Class = "BSSN" ## Evolution Equation: choose
## If "BSSN-EScalar" is chosen, it is necessary to set other parameters below
Initial_Data_Method = "Ansorg-TwoPuncture" ## initial data method: choose "Ansorg-TwoPuncture", "Lousto-Analytical", "Cao-Analytical", "KerrSchild-Analytical"
Time_Evolution_Method = "runge-kutta-45" ## time evolution method: choose "runge-kutta-45"
Finite_Diffenence_Method = "4th-order" ## finite-difference method: choose "2nd-order", "4th-order", "6th-order", "8th-order"
Finite_Diffenence_Method = "4th-order" ## finite-difference method: choose "2nd-order", "4th-order", "6th-order", "8th-order"
Debug_NaN_Check = 0 ## enable NaN checks in compute_rhs_bssn: 0 (off) or 1 (on)
#################################################