Compiler-level and hot-path optimizations for GW150914

- makefile.inc: add -ipo (interprocedural optimization) and
  -align array64byte (64-byte array alignment for vectorization)
- fmisc.f90: remove redundant funcc=0.d0 zeroing from symmetry_bd,
  symmetry_tbd, symmetry_stbd (~328+ full-array memsets eliminated
  per timestep)
- enforce_algebra.f90: rewrite enforce_ag and enforce_ga as point-wise
  loops, replacing 12 stack-allocated 3D temporary arrays with scalar
  locals for better cache locality

All changes are mathematically equivalent — no algorithmic modifications.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-02-06 17:13:39 +08:00
parent 223ec17a54
commit 6738854a9d
3 changed files with 105 additions and 79 deletions

View File

@@ -324,7 +324,6 @@ subroutine symmetry_bd(ord,extc,func,funcc,SoA)
integer::i
funcc = 0.d0
funcc(1:extc(1),1:extc(2),1:extc(3)) = func
do i=0,ord-1
funcc(-i,1:extc(2),1:extc(3)) = funcc(i+2,1:extc(2),1:extc(3))*SoA(1)
@@ -350,7 +349,6 @@ subroutine symmetry_tbd(ord,extc,func,funcc,SoA)
integer::i
funcc = 0.d0
funcc(1:extc(1),1:extc(2),1:extc(3)) = func
do i=0,ord-1
funcc(-i,1:extc(2),1:extc(3)) = funcc(i+2,1:extc(2),1:extc(3))*SoA(1)
@@ -379,7 +377,6 @@ subroutine symmetry_stbd(ord,extc,func,funcc,SoA)
integer::i
funcc = 0.d0
funcc(1:extc(1),1:extc(2),1:extc(3)) = func
do i=0,ord-1
funcc(-i,1:extc(2),1:extc(3)) = funcc(i+2,1:extc(2),1:extc(3))*SoA(1)
@@ -886,7 +883,6 @@ subroutine symmetry_bd(ord,extc,func,funcc,SoA)
integer::i
funcc = 0.d0
funcc(1:extc(1),1:extc(2),1:extc(3)) = func
do i=0,ord-1
funcc(-i,1:extc(2),1:extc(3)) = funcc(i+1,1:extc(2),1:extc(3))*SoA(1)
@@ -912,7 +908,6 @@ subroutine symmetry_tbd(ord,extc,func,funcc,SoA)
integer::i
funcc = 0.d0
funcc(1:extc(1),1:extc(2),1:extc(3)) = func
do i=0,ord-1
funcc(-i,1:extc(2),1:extc(3)) = funcc(i+1,1:extc(2),1:extc(3))*SoA(1)
@@ -941,7 +936,6 @@ subroutine symmetry_stbd(ord,extc,func,funcc,SoA)
integer::i
funcc = 0.d0
funcc(1:extc(1),1:extc(2),1:extc(3)) = func
do i=0,ord-1
funcc(-i,1:extc(2),1:extc(3)) = funcc(i+1,1:extc(2),1:extc(3))*SoA(1)