[llvm-bugs] [Bug 51568] New: Better codegen for truncated bswap
via llvm-bugs
llvm-bugs at lists.llvm.org
Fri Aug 20 15:14:14 PDT 2021
https://bugs.llvm.org/show_bug.cgi?id=51568
Bug ID: 51568
Summary: Better codegen for truncated bswap
Product: libraries
Version: trunk
Hardware: PC
OS: Linux
Status: NEW
Severity: enhancement
Priority: P
Component: Scalar Optimizations
Assignee: unassignedbugs at nondot.org
Reporter: david.bolvansky at gmail.com
CC: llvm-bugs at lists.llvm.org
unsigned int swap_ull(unsigned long long value)
{
return ((value & 0x00000000000000ffull) << 56)
| ((value & 0x000000000000ff00ull) << 40)
| ((value & 0x0000000000ff0000ull) << 24)
| ((value & 0x00000000ff000000ull) << 8)
| ((value & 0x000000ff00000000ull) >> 8)
| ((value & 0x0000ff0000000000ull) >> 24)
| ((value & 0x00ff000000000000ull) >> 40)
| ((value & 0xff00000000000000ull) >> 56);
}
unsigned int swap_ull_builtin(unsigned long long value)
{
return __builtin_bswap64(value);
}
Trunk -O3:
swap_ull(unsigned long long): # @swap_ull(unsigned
long long)
movabs rax, 72057589742960640
and rax, rdi
bswap rax
shr rdi, 56
or eax, edi
ret
swap_ull_builtin(unsigned long long): #
@swap_ull_builtin(unsigned long long)
mov rax, rdi
bswap rax
ret
ICC -O3:
swap_ull(unsigned long long):
bswap rdi #10.51
mov eax, edi #10.51
ret #10.51
swap_ull_builtin(unsigned long long):
bswap rdi #15.12
mov eax, edi #15.12
ret #15.12
unsigned int swap_ull(unsigned long long value)
{
return ((value & 0x00000000000000ffull) << 56)
| ((value & 0x000000000000ff00ull) << 40)
| ((value & 0x0000000000ff0000ull) << 24)
| ((value & 0x00000000ff000000ull) << 8)
| ((value & 0x000000ff00000000ull) >> 8)
| ((value & 0x0000ff0000000000ull) >> 24)
| ((value & 0x00ff000000000000ull) >> 40)
| ((value & 0xff00000000000000ull) >> 56);
}
unsigned int swap_ull_builtin(unsigned long long value)
{
return __builtin_bswap64(value);
}
define i32 @src(i64 %0) {
%1:
%2 = and i64 %0, 72057594037927935
%3 = bswap i64 %2
%4 = lshr i64 %0, 56
%5 = or i64 %3, %4
%6 = trunc i64 %5 to i32
ret i32 %6
}
=>
define i32 @tgt(i64 %0) {
%1:
%2 = bswap i64 %0
%3 = trunc i64 %2 to i32
ret i32 %3
}
Transformation seems to be correct!
https://alive2.llvm.org/ce/z/loQjOQ
--
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/20210820/3a6e09bb/attachment.html>
More information about the llvm-bugs
mailing list