[llvm-bugs] [Bug 25277] New: Very high overhead when calling sin() with int64_t

via llvm-bugs llvm-bugs at lists.llvm.org
Wed Oct 21 16:19:52 PDT 2015


https://llvm.org/bugs/show_bug.cgi?id=25277

            Bug ID: 25277
           Summary: Very high overhead when calling sin() with int64_t
           Product: clang
           Version: 3.7
          Hardware: PC
                OS: Linux
            Status: NEW
          Severity: normal
          Priority: P
         Component: LLVM Codegen
          Assignee: unassignedclangbugs at nondot.org
          Reporter: yyc1992 at gmail.com
                CC: llvm-bugs at lists.llvm.org
    Classification: Unclassified

In the following code, when compiling with `clang++ -O2` or `-Ofast`, test_i64
takes almost twice as long as test_f64 with similar arguments. (the `extern
"C"` etc are used to benchmark it in Julia. The inline asm is to make sure the
compiler doesn't optimize the whole thing away in `-Ofast` and doesn't seem to
have a performance impact otherwise.)

```
#include <math.h>
#include <stddef.h>
#include <stdint.h>

double __attribute__((noinline))
g(int64_t a)
{
    asm volatile("" ::: "memory");
    return sin(a);
}

double __attribute__((noinline))
g(double a)
{
    asm volatile("" ::: "memory");
    return sin(a);
}

template<typename T>
static inline void
f(T a, size_t n)
{
    for (size_t i = 0;i < n;i++) {
        g(a);
    }
}

extern "C" void
test_i64(int64_t a, size_t n)
{
    f(a, n);
}

extern "C" void
test_f64(double a, size_t n)
{
    f(a, n);
}
```

On my machine, each loop takes ~ 9ns for double and ~ 14ns for int64_t. Gcc
doesn't seem to have this issue.

Gcc asm,
```
00000000000007a0 <_Z1gl>:
 7a0:   66 0f ef c0             pxor   %xmm0,%xmm0
 7a4:   f2 48 0f 2a c7          cvtsi2sd %rdi,%xmm0
 7a9:   e9 e2 fe ff ff          jmpq   690 <sin at plt>
 7ae:   66 90                   xchg   %ax,%ax

00000000000007b0 <_Z1gd>:
 7b0:   e9 db fe ff ff          jmpq   690 <sin at plt>
 7b5:   90                      nop
 7b6:   66 2e 0f 1f 84 00 00    nopw   %cs:0x0(%rax,%rax,1)
 7bd:   00 00 00 

00000000000007c0 <test_i64>:
 7c0:   48 85 f6                test   %rsi,%rsi
 7c3:   74 28                   je     7ed <test_i64+0x2d>
 7c5:   41 54                   push   %r12
 7c7:   49 89 fc                mov    %rdi,%r12
 7ca:   55                      push   %rbp
 7cb:   48 89 f5                mov    %rsi,%rbp
 7ce:   53                      push   %rbx
 7cf:   31 db                   xor    %ebx,%ebx
 7d1:   0f 1f 80 00 00 00 00    nopl   0x0(%rax)
 7d8:   4c 89 e7                mov    %r12,%rdi
 7db:   48 83 c3 01             add    $0x1,%rbx
 7df:   e8 9c fe ff ff          callq  680 <_Z1gl at plt>
 7e4:   48 39 dd                cmp    %rbx,%rbp
 7e7:   75 ef                   jne    7d8 <test_i64+0x18>
 7e9:   5b                      pop    %rbx
 7ea:   5d                      pop    %rbp
 7eb:   41 5c                   pop    %r12
 7ed:   f3 c3                   repz retq 
 7ef:   90                      nop

00000000000007f0 <test_f64>:
 7f0:   55                      push   %rbp
 7f1:   53                      push   %rbx
 7f2:   48 83 ec 18             sub    $0x18,%rsp
 7f6:   48 85 ff                test   %rdi,%rdi
 7f9:   f2 0f 11 44 24 08       movsd  %xmm0,0x8(%rsp)
 7ff:   74 23                   je     824 <test_f64+0x34>
 801:   48 89 fd                mov    %rdi,%rbp
 804:   31 db                   xor    %ebx,%ebx
 806:   66 2e 0f 1f 84 00 00    nopw   %cs:0x0(%rax,%rax,1)
 80d:   00 00 00 
 810:   f2 0f 10 44 24 08       movsd  0x8(%rsp),%xmm0
 816:   48 83 c3 01             add    $0x1,%rbx
 81a:   e8 51 fe ff ff          callq  670 <_Z1gd at plt>
 81f:   48 39 dd                cmp    %rbx,%rbp
 822:   75 ec                   jne    810 <test_f64+0x20>
 824:   48 83 c4 18             add    $0x18,%rsp
 828:   5b                      pop    %rbx
 829:   5d                      pop    %rbp
 82a:   c3                      retq   
```

clang asm
```
0000000000000750 <_Z1gl>:
 750:   f2 48 0f 2a c7          cvtsi2sd %rdi,%xmm0
 755:   e9 e6 fe ff ff          jmpq   640 <sin at plt>
 75a:   66 0f 1f 44 00 00       nopw   0x0(%rax,%rax,1)

0000000000000760 <_Z1gd>:
 760:   e9 db fe ff ff          jmpq   640 <sin at plt>
 765:   66 66 2e 0f 1f 84 00    data16 nopw %cs:0x0(%rax,%rax,1)
 76c:   00 00 00 00 

0000000000000770 <test_i64>:
 770:   41 56                   push   %r14
 772:   53                      push   %rbx
 773:   50                      push   %rax
 774:   48 89 f3                mov    %rsi,%rbx
 777:   49 89 fe                mov    %rdi,%r14
 77a:   48 85 db                test   %rbx,%rbx
 77d:   74 0e                   je     78d <test_i64+0x1d>
 77f:   90                      nop
 780:   4c 89 f7                mov    %r14,%rdi
 783:   e8 a8 fe ff ff          callq  630 <_Z1gl at plt>
 788:   48 ff cb                dec    %rbx
 78b:   75 f3                   jne    780 <test_i64+0x10>
 78d:   48 83 c4 08             add    $0x8,%rsp
 791:   5b                      pop    %rbx
 792:   41 5e                   pop    %r14
 794:   c3                      retq   
 795:   66 66 2e 0f 1f 84 00    data16 nopw %cs:0x0(%rax,%rax,1)
 79c:   00 00 00 00 

00000000000007a0 <test_f64>:
 7a0:   53                      push   %rbx
 7a1:   48 83 ec 10             sub    $0x10,%rsp
 7a5:   48 89 fb                mov    %rdi,%rbx
 7a8:   f2 0f 11 44 24 08       movsd  %xmm0,0x8(%rsp)
 7ae:   48 85 db                test   %rbx,%rbx
 7b1:   74 1d                   je     7d0 <test_f64+0x30>
 7b3:   66 66 66 66 2e 0f 1f    data16 data16 data16 nopw %cs:0x0(%rax,%rax,1)
 7ba:   84 00 00 00 00 00 
 7c0:   f2 0f 10 44 24 08       movsd  0x8(%rsp),%xmm0
 7c6:   e8 55 fe ff ff          callq  620 <_Z1gd at plt>
 7cb:   48 ff cb                dec    %rbx
 7ce:   75 f0                   jne    7c0 <test_f64+0x20>
 7d0:   48 83 c4 10             add    $0x10,%rsp
 7d4:   5b                      pop    %rbx
 7d5:   c3                      retq   
```

One noticable difference is that gcc clears the xmm0 register before doing the
i64->f64 conversion (not sure if that's the important difference).

(The same happens in JIT environment as well but it seems to be x86 (or x64)
specific...)

-- 
You are receiving this mail because:
You are on the CC list for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-bugs/attachments/20151021/fb636c8a/attachment-0001.html>


More information about the llvm-bugs mailing list