llvm/llvm-project

[X86][SSE] Recognise v2i64 comparison patterns

Open

#32,961 opened on Jun 27, 2017

View on GitHub
 (9 comments) (0 reactions) (1 assignee)C++ (26,378 stars) (10,782 forks)batch import
backend:X86bugzillaconfirmedgood first issuellvm:instcombine

Description
Bugzilla Link 33614
Version trunk
OS Windows NT
CC @nikic,@rotateright

Extended Description

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.

Contributor guide

Tech stack
cpp
Domain
backend
Issue type
feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
mostly clear
Prerequisites
understanding of LLVM's X86 targetfamiliarity with SSE intrinsics
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
20
Research direction
Investigate the X86 target directory in LLVM (lib/Target/X86) to find existing pattern matching for vector comparisons. Look at files like X86InstrSSE.td and X86ISelLowering.cpp for similar patterns. The issue describes C code patterns; see if there are already recognizers for v4i32 comparisons and extend them to v2i64. Check the linked Bugzilla and any comments for additional context.