void foo (int * restrict a, int * restrict b, int * restrict c)
{
int i;
for(i = 0; i < 100; i+=4)
{
a[i] = b[i] * c[i];
a[i+1] = b[i+1] * c[i+1];
a[i+2] = b[i+2] * c[i+2];
a[i+3] = b[i+3] * c[i+3];
}
}
Trunk x86-64 compiler (162821) produces code that later load instructions are
not scheduled before the previous store instructions as expected. Clearly,
restrict qualifier is not used here.
~/work/install-x86/bin/gcc tst3.c -O2 -S -std=c99 -da -fschedule-insns
-frename-registers
.L2:
movl (%rdx,%rax), %r10d
imull (%rsi,%rax), %r10d
movl %r10d, (%rdi,%rax)
movl 4(%rdx,%rax), %r9d
imull 4(%rsi,%rax), %r9d
movl %r9d, 4(%rdi,%rax)
movl 8(%rdx,%rax), %r8d
imull 8(%rsi,%rax), %r8d
movl %r8d, 8(%rdi,%rax)
movl 12(%rdx,%rax), %ecx
imull 12(%rsi,%rax), %ecx
movl %ecx, 12(%rdi,%rax)
addq $16, %rax
cmpq $400, %rax
Richard has a patch and it seems to work for this example.
Index: expr.c
===================================================================
--- expr.c (revision 162841)
+++ expr.c (working copy)
@@ -8665,7 +8665,7 @@ expand_expr_real_1 (tree exp, rtx target
set_mem_addr_space (temp, as);
base = get_base_address (TMR_ORIGINAL (exp));
if (base
- && INDIRECT_REF_P (base)
+ && (INDIRECT_REF_P (base) || TREE_CODE (base) == MEM_REF)
&& TMR_BASE (exp)
&& TREE_CODE (TMR_BASE (exp)) == SSA_NAME
&& POINTER_TYPE_P (TREE_TYPE (TMR_BASE (exp))))
The code generated:
.L2:
movl (%rdx,%rax), %r10d
movl 4(%rdx,%rax), %r9d
imull (%rsi,%rax), %r10d
imull 4(%rsi,%rax), %r9d
movl 8(%rdx,%rax), %r8d
movl 12(%rdx,%rax), %ecx
imull 8(%rsi,%rax), %r8d
imull 12(%rsi,%rax), %ecx
movl %r10d, (%rdi,%rax)
movl %r9d, 4(%rdi,%rax)
movl %r8d, 8(%rdi,%rax)
movl %ecx, 12(%rdi,%rax)
addq $16, %rax
cmpq $400, %rax
jne .L2
--
Summary: restrict qualifier is not used in a manually unrolled
loop
Product: gcc
Version: 4.6.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: c
AssignedTo: unassigned at gcc dot gnu dot org
ReportedBy: bmei at broadcom dot com
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=45176
