https://gcc.gnu.org/bugzilla/show_bug.cgi?id=105354
Bug ID: 105354
Summary: __builtin_shuffle for alignr generates suboptimal code
unless SSSE3 is enabled
Product: gcc
Version: 11.2.0
Status: UNCONFIRMED
Keywords: missed-optimization
Severity: normal
Priority: P3
Component: target
Assignee: unassigned at gcc dot gnu.org
Reporter: john_platts at hotmail dot com
Target Milestone: ---
The below code generates suboptimal code if SSE2 is enabled but SSSE3 is not
enabled:
#include <cstdint>
typedef std::uint8_t Simd128U8VectT __attribute__((__vector_size__(16)));
template<int RotateAmt>
static inline Simd128U8VectT RotateRightByByteAmt(Simd128U8VectT vect) noexcept
{
constexpr int NormalizedRotateAmt = RotateAmt & 15;
if constexpr(NormalizedRotateAmt == 0)
return vect;
else
return __builtin_shuffle(vect, vect, (Simd128U8VectT){
NormalizedRotateAmt, NormalizedRotateAmt + 1,
NormalizedRotateAmt + 2, NormalizedRotateAmt + 3,
NormalizedRotateAmt + 4, NormalizedRotateAmt + 5,
NormalizedRotateAmt + 6, NormalizedRotateAmt + 7,
NormalizedRotateAmt + 8, NormalizedRotateAmt + 9,
NormalizedRotateAmt + 10, NormalizedRotateAmt + 11,
NormalizedRotateAmt + 12, NormalizedRotateAmt + 13,
NormalizedRotateAmt + 14, NormalizedRotateAmt + 15 });
}
auto func1(Simd128U8VectT vect) noexcept {
return RotateRightByByteAmt<5>(vect);
}
Here is the code that is generated on GCC 11 if the -O2 -mssse3 options are
specified:
func1(unsigned char __vector(16)):
palignr xmm0, xmm0, 5
ret
Here is the code that is generated on GCC 11 if the -O2 option is specified but
the -mssse3 option is not specified on 64-bit x86 platforms:
func1(unsigned char __vector(16)):
sub rsp, 144
movd ecx, xmm0
movaps XMMWORD PTR [rsp+8], xmm0
movzx edx, BYTE PTR [rsp+20]
movzx ecx, cl
movaps XMMWORD PTR [rsp+24], xmm0
movzx eax, BYTE PTR [rsp+35]
sal rdx, 8
movaps XMMWORD PTR [rsp+40], xmm0
or rdx, rax
movzx eax, BYTE PTR [rsp+50]
movaps XMMWORD PTR [rsp+56], xmm0
sal rdx, 8
movaps XMMWORD PTR [rsp+72], xmm0
or rdx, rax
movzx eax, BYTE PTR [rsp+65]
movaps XMMWORD PTR [rsp+88], xmm0
sal rdx, 8
movaps XMMWORD PTR [rsp+104], xmm0
or rdx, rax
movzx eax, BYTE PTR [rsp+80]
movaps XMMWORD PTR [rsp-104], xmm0
sal rdx, 8
movaps XMMWORD PTR [rsp-88], xmm0
movzx edi, BYTE PTR [rsp-85]
or rdx, rax
movzx eax, BYTE PTR [rsp+95]
movaps XMMWORD PTR [rsp-72], xmm0
sal rdx, 8
movaps XMMWORD PTR [rsp-56], xmm0
or rdx, rax
movzx eax, BYTE PTR [rsp+110]
movaps XMMWORD PTR [rsp-40], xmm0
sal rdx, 8
movaps XMMWORD PTR [rsp-24], xmm0
or rdx, rax
movzx eax, BYTE PTR [rsp-100]
movaps XMMWORD PTR [rsp+120], xmm0
movzx esi, BYTE PTR [rsp+125]
movaps XMMWORD PTR [rsp-8], xmm0
sal rdx, 8
sal rax, 8
or rdx, rsi
or rax, rdi
movzx edi, BYTE PTR [rsp-70]
sal rax, 8
or rax, rdi
movzx edi, BYTE PTR [rsp-55]
sal rax, 8
or rax, rdi
sal rax, 8
or rax, rcx
movzx ecx, BYTE PTR [rsp-25]
sal rax, 8
or rax, rcx
movzx ecx, BYTE PTR [rsp-10]
sal rax, 8
or rax, rcx
movzx ecx, BYTE PTR [rsp+5]
mov QWORD PTR [rsp-120], rdx
sal rax, 8
or rax, rcx
mov QWORD PTR [rsp-112], rax
movdqa xmm0, XMMWORD PTR [rsp-120]
add rsp, 144
ret
Here is a more optimal implementation of the above code on 64-bit x86 platforms
when SSE2 is enabled but SSSE3 is not enabled:
func1(unsigned char __vector(16)):
movdqa xmm1, xmm0
psrldq xmm1, 5
pslldq xmm0, 11
por xmm0, xmm1
ret