http://gcc.gnu.org/bugzilla/show_bug.cgi?id=49203
Summary: missed-optimization: useless expressions not moved out
of loop
Product: gcc
Version: 4.7.0
Status: UNCONFIRMED
Severity: enhancement
Priority: P3
Component: tree-optimization
AssignedTo: unassig...@gcc.gnu.org
ReportedBy: wouter.vermae...@scarlet.be
Hi all,
Below is (a simplified version of) some real code I recently
encountered. The stores to the 'output' array are written in the inner
loop, but the intention was probably to have them in the outer loop.
Gcc is able to 'correct' this programming mistake, but only partly:
the stores itself are moved to the outer loop, but the instructions that
calculate those values remain in the inner loop.
For this particular example, the best solution is of course to fix the
C code. But maybe this missed-optimization can also occur in other,
more valid, contexts.
Below I've included the generated x86_64 code for this example by
recent versions of both gcc and llvm.
///////////////////////////////////////////////////////////////////
unsigned char input[100];
unsigned char output[100];
void f() {
for (int i = 0; i < 32; i += 4) {
unsigned tmp = 0;
for (int j = 0; j < 16; ++j) {
tmp = (tmp << 2) | (input[i + j] & 0x03);
output[i + 0] = (tmp >> 24) & 0xFF;
output[i + 1] = (tmp >> 16) & 0xFF;
output[i + 2] = (tmp >> 8) & 0xFF;
output[i + 3] = (tmp >> 0) & 0xFF;
}
}
}
///////////////////////////////////////////////////////////////////
g++ (GCC) 4.7.0 20110527 (experimental)
g++ -O2 -S
movl $output, %r10d
movq %r10, %r9
.p2align 4,,10
.p2align 3
.L2:
movl %r9d, %esi
xorl %edx, %edx
xorl %eax, %eax
subl %r10d, %esi
.p2align 4,,10
.p2align 3
.L3:
leal 0(,%rax,4), %ecx
leal (%rdx,%rsi), %eax
addl $1, %edx
cltq
movzbl input(%rax), %eax
andl $3, %eax
orl %ecx, %eax
movl %eax, %r8d
movl %eax, %edi
movl %eax, %ecx
shrl $24, %r8d
shrl $16, %edi
shrl $8, %ecx
cmpl $16, %edx
jne .L3
movb %r8b, (%r9)
movb %dil, 1(%r9)
movb %cl, 2(%r9)
movb %al, 3(%r9)
addq $4, %r9
cmpq $output+32, %r9
jne .L2
rep
ret
///////////////////////////////////////////////////////////////////
clang version 3.0 (http://llvm.org/git/clang.git
855f41963e545172a935d07b4713d079e258a207)
clang++ -O2 -S
# BB#0: # %entry
xorl %eax, %eax
.align 16, 0x90
.LBB0_1: # %for.cond4.preheader
# =>This Loop Header: Depth=1
# Child Loop BB0_2 Depth 2
xorl %esi, %esi
movq $-16, %rdx
.align 16, 0x90
.LBB0_2: # %for.body7
# Parent Loop BB0_1 Depth=1
# => This Inner Loop Header: Depth=2
movl %esi, %ecx
movzbl input+16(%rdx,%rax), %edi
andl $3, %edi
leal (,%rcx,4), %esi
orl %edi, %esi
incq %rdx
jne .LBB0_2
# BB#3: # %for.inc44
# in Loop: Header=BB0_1 Depth=1
movb %sil, output+3(%rax)
movl %ecx, %edx
shrl $6, %edx
movb %dl, output+2(%rax)
movl %ecx, %edx
shrl $14, %edx
movb %dl, output+1(%rax)
shrl $22, %ecx
movb %cl, output(%rax)
addq $4, %rax
cmpq $32, %rax
jne .LBB0_1
# BB#4: # %for.end47
ret
