https://bugs.llvm.org/show_bug.cgi?id=33614
Bug ID: 33614
Summary: [X86][SSE] Recognise v2i64 comparison patterns
Product: libraries
Version: trunk
Hardware: PC
OS: Windows NT
Status: NEW
Severity: enhancement
Priority: P
Component: Backend: X86
Assignee: unassignedbugs at nondot.org
Reporter: llvm-dev at redking.me.uk
CC: llvm-bugs at lists.llvm.org
Before SSE41/SSE42, the only way to compare eq/gt v2i64 vectors was to use the
v4i32 intrinsics:
__m128i alt_cmpeq_epi64(__m128i a, __m128i b) {
__m128i c = _mm_cmpeq_epi32(a, b);
return _mm_and_si128( c, _mm_shuffle_epi32( c, _MM_SHUFFLE(2,3,0,1) ) );
}
__m128i alt_cmpgt_epi64(__m128i a, __m128i b) {
__m128i flip = _mm_setr_epi32( 0x80000000,0x00000000,0x80000000,0x00000000 );
a = _mm_xor_si128( a, flip );
b = _mm_xor_si128( b, flip );
__m128i gt = _mm_cmpgt_epi32( a, b );
__m128i gt0 = _mm_shuffle_epi32( gt, _MM_SHUFFLE(2,2,0,0) );
__m128i gt1 = _mm_shuffle_epi32( gt, _MM_SHUFFLE(3,3,1,1) );
__m128i eq = _mm_cmpeq_epi32( a, b );
__m128i eq0 = _mm_shuffle_epi32( eq, _MM_SHUFFLE(3,3,1,1) );
return _mm_or_si128( _mm_and_si128( gt0, eq0 ), gt1 );
}
__m128i alt_cmpgt_epu64(__m128i a, __m128i b) {
__m128i flip = _mm_set1_epi32( 0x80000000 );
a = _mm_xor_si128( a, flip );
b = _mm_xor_si128( b, flip );
__m128i gt = _mm_cmpgt_epi32( a, b );
__m128i gt0 = _mm_shuffle_epi32( gt, _MM_SHUFFLE(2,2,0,0) );
__m128i gt1 = _mm_shuffle_epi32( gt, _MM_SHUFFLE(3,3,1,1) );
__m128i eq = _mm_cmpeq_epi32( a, b );
__m128i eq0 = _mm_shuffle_epi32( eq, _MM_SHUFFLE(3,3,1,1) );
return _mm_or_si128( _mm_and_si128( gt0, eq0 ), gt1 );
}
Resulting in quite a bit of legacy code that still uses this (I've only seen
this in __m128i code). We should be trying to simplify this where possible.
--
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/20170627/2a85bdee/attachment.html>