This caused me a lot of pain in trying to disable specific
optimizations with -O1.
$ gfortran -O1 -o dasum-1.s -S -fverbose-asm -fno-loop-optimize -fno-tree-sra
-fno-tree-ter -fno-omit-frame-pointer -fno-tree-dse -fno-tree-dominator-opts
-fno-tree-ch -fno-tree-fre -fno-merge-constants -fno-cprop-registers
-fno-if-conversion2 -fno-defer-pop -fno-tree-lrs -fno-guess-branch-probability
-fno-tree-ccp -fno-tree-copyrename -fno-tree-dce -fno-if-conversion ../dasum.f
$ gfortran -O0 -o dasum-0.s -S -fverbose-asm ../dasum.f
$ diff -u dasum-0.s dasum-1.s | head -30
--- dasum-0.s 2005-02-09 13:38:52.000000000 +0100
+++ dasum-1.s 2005-02-09 13:38:46.000000000 +0100
@@ -3,7 +3,12 @@
// GNU F95 version 4.0.0 20050130 (experimental) (ia64-unknown-linux-gnu)
// compiled by GNU C version 4.0.0 20050130 (experimental).
// GGC heuristics: --param ggc-min-expand=30 --param ggc-min-heapsize=4096
-// options passed: -ffixed-form -auxbase-strip -O0 -fverbose-asm
+// options passed: -ffixed-form -auxbase-strip -O1 -fverbose-asm
+// -fno-loop-optimize -fno-tree-sra -fno-tree-ter -fno-omit-frame-pointer
+// -fno-tree-dse -fno-tree-dominator-opts -fno-tree-ch -fno-tree-fre
+// -fno-merge-constants -fno-cprop-registers -fno-if-conversion2
+// -fno-defer-pop -fno-tree-lrs -fno-guess-branch-probability -fno-tree-ccp
+// -fno-tree-copyrename -fno-tree-dce -fno-if-conversion
// options enabled: -falign-loops -fargument-noalias-global
// -fbranch-count-reg -fcommon -feliminate-unused-debug-types
// -ffunction-cse -fgcse-lm -fident -fivopts -fkeep-static-consts
@@ -23,531 +28,280 @@
.prologue 14, 35
.save ar.pfs, r36
alloc r36 = ar.pfs, 3, 4, 2, 0 //,,,,
+ adds r16 = -8, r12 //,,
.vframe r37
mov r37 = r12 //,
- adds r12 = -80, r12 //,,
+ adds r12 = -32, r12 //,,
+ mov r17 = ar.lc //,
+ ;;
+ .savepsp ar.lc, 8
+ st8 [r16] = r17, 8 //,
mov r38 = r1 //,
As you can see from the fact that there is no differences in
the "options enabled:" list in the assembly output, the assembly
should be identical.
However, the compilation results are very different, so -O1
seems to do other, undocumented things.
$ cat ../dasum.f
double precision function dasum(n,dx,incx)
c
c takes the sum of the absolute values.
c jack dongarra, linpack, 3/11/78.
c modified 3/93 to return if incx .le. 0.
c modified 12/3/93, array(1) declarations changed to array(*)
c
double precision dx(*),dtemp
integer i,incx,m,mp1,n,nincx
c
dasum = 0.0d0
dtemp = 0.0d0
if( n.le.0 .or. incx.le.0 )return
if(incx.eq.1)go to 20
c
c code for increment not equal to 1
c
nincx = n*incx
do 10 i = 1,nincx,incx
dtemp = dtemp + dabs(dx(i))
10 continue
dasum = dtemp
return
c
c code for increment equal to 1
c
c
c clean-up loop
c
20 m = mod(n,6)
if( m .eq. 0 ) go to 40
do 30 i = 1,m
dtemp = dtemp + dabs(dx(i))
30 continue
if( n .lt. 6 ) go to 60
40 mp1 = m + 1
do 50 i = mp1,n,6
dtemp = dtemp + dabs(dx(i)) + dabs(dx(i + 1)) + dabs(dx(i + 2))
* + dabs(dx(i + 3)) + dabs(dx(i + 4)) + dabs(dx(i + 5))
50 continue
60 dasum = dtemp
return
end
--
Summary: "options passed" from -verbose-asm do not adequately
reflect optimization
Product: gcc
Version: unknown
Status: UNCONFIRMED
Severity: normal
Priority: P2
Component: driver
AssignedTo: unassigned at gcc dot gnu dot org
ReportedBy: Thomas dot Koenig at online dot de
CC: gcc-bugs at gcc dot gnu dot org
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=19848
