Could someone explain me these considerable performance differences between these expressions which I would expect to give similar performance. I'm compiling with Apple LLVM version 5.1 (clang-503.0.38) (based on LLVM 3.4svn) in release mode.
Here's my test code (just change CASE to 1, 2, 3 or 4 to test yourself):
#include <iostream>
#include <chrono>
#define CASE 1
inline int foo(int n) {
return
#if CASE == 1
(n % 2) ? 9 : 6
#elif CASE == 2
(n % 2) == true ? 9 : 6
#elif CASE == 3
6 + (n % 2) * 3
#elif CASE == 4
6 + bool(n % 2) * 3
#endif
;
}
int main(int argc, const char* argv[])
{
std::chrono::time_point<std::chrono::system_clock> start, end;
start = std::chrono::system_clock::now();
int n = argc;
for (int i = 0; i < 100000000; ++i) {
n += foo(n);
}
end = std::chrono::system_clock::now();
std::chrono::duration<double> elapsed_seconds = end-start;
std::cout << "elapsed time: " << elapsed_seconds.count() << "\n";
std::cout << "value: " << n << "\n";
return 0;
}
And here are the timings I get:
CASE EXPRESSION TIME
1 (n % 2) ? 9 : 6 0.1585
2 (n % 2) == true ? 9 : 6 0.3491
3 6 + (n % 2) * 3 0.2559
4 6 + bool(n % 2) * 3 0.1906
Here's the difference in assembly between CASE 1 and CASE 2:
CASE 1:
Ltmp12:
LBB0_1: ## =>This Inner Loop Header: Depth=1
##DEBUG_VALUE: main:argv <- RSI
##DEBUG_VALUE: i <- 0
.loc 1 24 0 ## /Test/main.cpp:24:0
movl %ebx, %ecx
andl $1, %ecx
leal (%rcx,%rcx,2), %ecx
Ltmp13:
.loc 1 48 14 ## /Test/main.cpp:48:14
leal 6(%rbx,%rcx), %ebx
CASE 2:
Ltmp12:
LBB0_1: ## =>This Inner Loop Header: Depth=1
##DEBUG_VALUE: main:argv <- RSI
##DEBUG_VALUE: i <- 0
.loc 1 24 0 ## /Test/main.cpp:24:0
movl %ebx, %ecx
shrl $31, %ecx
addl %ebx, %ecx
andl $-2, %ecx
movl %ebx, %edx
subl %ecx, %edx
cmpl $1, %edx
sete %cl
movzbl %cl, %ecx
leal (%rcx,%rcx,2), %ecx
Ltmp13:
.loc 1 48 14 ## /Test/main.cpp:48:14
leal 6(%rbx,%rcx), %ebx
And here's the difference in assembly between CASE 3 and CASE 4:
CASE 3:
Ltmp12:
LBB0_1: ## =>This Inner Loop Header: Depth=1
##DEBUG_VALUE: main:argv <- RSI
##DEBUG_VALUE: i <- 0
.loc 1 24 0 ## /Test/main.cpp:24:0
movl %ebx, %ecx
shrl $31, %ecx
addl %ebx, %ecx
andl $-2, %ecx
movl %ebx, %edx
subl %ecx, %edx
leal (%rdx,%rdx,2), %ecx
Ltmp13:
.loc 1 48 14 ## /Test/main.cpp:48:14
leal 6(%rbx,%rcx), %ebx
CASE 4:
Ltmp12:
LBB0_1: ## =>This Inner Loop Header: Depth=1
##DEBUG_VALUE: main:argv <- RSI
##DEBUG_VALUE: i <- 0
.loc 1 24 0 ## /Test/main.cpp:24:0
movl %ebx, %ecx
andl $1, %ecx
negl %ecx
andl $3, %ecx
Ltmp13:
.loc 1 48 14 ## /Test/main.cpp:48:14
leal 6(%rbx,%rcx), %ebx
