https://gcc.gnu.org/bugzilla/show_bug.cgi?id=90249
Bug ID: 90249
Summary: [9 regression] Code size regression on thumb2 due to
sub-optimal register allocation.
Product: gcc
Version: 9.0
Status: UNCONFIRMED
Keywords: ra
Severity: normal
Priority: P3
Component: rtl-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: rearnsha at gcc dot gnu.org
CC: ramana.radhakrishnan at arm dot com, vmakarov at redhat dot
com,
wdijkstr at arm dot com
Target Milestone: ---
Target: arm
Created attachment 46244
--> https://gcc.gnu.org/bugzilla/attachment.cgi?id=46244&action=edit
testcase
GCC 9 has regressed on code size due to some sub-optimal register allocation.
For this example, the only difference in the output is that the assignments for
r7 and r8 have been switched, but the result is significant growth in code size
since r8 requires predominantly 32-bit instructions to be used while r7
requires predominantly 16-bit instructions.
cc1 -fpreprocessed binding2.i -quiet -dumpbase binding2.i -mthumb
-mcpu=cortex-a8 -march=armv7-a -auxbase-strip binding.o -Os -w -version
-fno-short-enums -fgnu89-inline -o binding2.s
In gcc-8 the output was
DefineConnectorBinding:
@ args = 0, pretend = 0, frame = 0
@ frame_needed = 0, uses_anonymous_args = 0
push {r0, r1, r2, r3, r4, r5, r6, r7, r8, lr}
mov r4, r1
mov r8, r0
mov r1, r2
mov r0, r4
mov r5, r2
mov r7, r3
bl LookupBinding
mov r6, r0
cbz r0, .L2
ldr r7, .L5
mov r1, r4
ldr r0, [r7] // 16-bit instruction
bl GetAtomString
mov r1, r5
mov r4, r0
ldr r0, [r7] // 16-bit instruction
bl GetAtomString
ldrh r1, [r6, #8]
mov r5, r0
ldr r0, [r7] // 16-bit instruction
bl GetAtomString
ldrh r3, [r6, #10]
ldr r2, .L5+4
movs r1, #103
str r5, [sp]
strd r0, r3, [sp, #4]
mov r3, r4
mov r0, r8
bl SemanticError
add sp, sp, #16
@ sp needed
pop {r4, r5, r6, r7, r8, pc}
.L2:
mov r3, r7
mov r2, r5
mov r1, r4
mov r0, r8
bl NewConnectorBindingTree
add sp, sp, #16
@ sp needed
pop {r4, r5, r6, r7, r8, lr}
b AddBinding
In gcc-9 we get
DefineConnectorBinding:
@ args = 0, pretend = 0, frame = 0
@ frame_needed = 0, uses_anonymous_args = 0
push {r0, r1, r2, r3, r4, r5, r6, r7, r8, lr}
mov r4, r1
mov r7, r0
mov r1, r2
mov r0, r4
mov r5, r2
mov r8, r3
bl LookupBinding
mov r6, r0
cbz r0, .L2
ldr r8, .L5+4
mov r1, r4
ldr r0, [r8] // 32-bit instruction
bl GetAtomString
mov r1, r5
mov r4, r0
ldr r0, [r8] // 32-bit instruction
bl GetAtomString
ldrh r1, [r6, #8]
mov r5, r0
ldr r0, [r8] // 32-bit instruction
bl GetAtomString
ldrh r3, [r6, #10]
ldr r2, .L5
movs r1, #103
str r5, [sp]
strd r0, r3, [sp, #4]
mov r3, r4
mov r0, r7
bl SemanticError
add sp, sp, #16
@ sp needed
pop {r4, r5, r6, r7, r8, pc}
.L2:
mov r3, r8
mov r2, r5
mov r1, r4
mov r0, r7
bl NewConnectorBindingTree
add sp, sp, #16
@ sp needed
pop {r4, r5, r6, r7, r8, lr}
b AddBinding
R8 is used more often than R7, so it seems odd that it is preferred over the
latter.
