https://gcc.gnu.org/bugzilla/show_bug.cgi?id=96234
Bug ID: 96234
Summary: Sub-optimal register allocation with a signed integer
literal.
Product: gcc
Version: unknown
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: target
Assignee: unassigned at gcc dot gnu.org
Reporter: maxim.yegorushkin at gmail dot com
Target Milestone: ---
The following code:
#include <time.h>
#include <stdint.h>
namespace A {
inline uint64_t as_nanoseconds(struct timespec* ts) {
return ts->tv_sec * 1000000000L + ts->tv_nsec;
}
uint64_t f(uint64_t c, struct timespec* a, struct timespec* b) {
return c + (as_nanoseconds(a) - as_nanoseconds(b));
}
}
namespace B {
inline uint64_t as_nanoseconds(struct timespec* ts) {
return ts->tv_sec * 1000000000UL + ts->tv_nsec;
}
uint64_t f(uint64_t c, struct timespec* a, struct timespec* b) {
return c + (as_nanoseconds(a) - as_nanoseconds(b));
}
}
When compiled with `gcc-10.1 -O3 -march=skylake` produces a superflows
instruction in the version a signed constant `1000000000L`:
A::f(unsigned long, timespec*, timespec*):
mov r8, rdx <----------------------------- superflows
instruction
imul rax, QWORD PTR [rsi], 1000000000
imul rdx, QWORD PTR [rdx], 1000000000
add rax, QWORD PTR [rsi+8]
add rdx, QWORD PTR [r8+8]
sub rax, rdx
add rax, rdi
ret
B::f(unsigned long, timespec*, timespec*):
imul rax, QWORD PTR [rsi], 1000000000
add rdi, QWORD PTR [rsi+8]
sub rdi, QWORD PTR [rdx+8]
imul rdx, QWORD PTR [rdx], 1000000000
add rax, rdi
sub rax, rdx
ret
`clang` produces the same code for both versions and also optimizes away one
multiplication:
A::f(unsigned long, timespec*, timespec*): # @A::f(unsigned
long, timespec*, timespec*)
mov rax, qword ptr [rsi]
sub rax, qword ptr [rdx]
imul rax, rax, 1000000000
add rdi, qword ptr [rsi + 8]
sub rdi, qword ptr [rdx + 8]
add rax, rdi
ret
B::f(unsigned long, timespec*, timespec*): # @B::f(unsigned
long, timespec*, timespec*)
mov rax, qword ptr [rsi]
sub rax, qword ptr [rdx]
imul rax, rax, 1000000000
add rdi, qword ptr [rsi + 8]
sub rdi, qword ptr [rdx + 8]
add rax, rdi
ret
https://gcc.godbolt.org/z/Kf4q7z
