maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/X86/ctpop-combine.ll

41 lines
967 B
LLVM
Raw Normal View History

The LIT tests below do not specify the exact cpu model and fail on AVX2 machines, because we select different instructions such as vbroadcast, new shuffles, etc. Patch by Michael Liao. llvm-svn: 160129
2012-07-12 21:45:15 +08:00
; RUN: llc -march=x86-64 -mcpu=corei7 < %s | FileCheck %s
Add a DAGCombine to turn (ctpop x) u< 2 into (x & x-1) == 0. This shaves off 4 popcounts from the hacked 186.crafty source. This is enabled even when a native popcount instruction is available. The combined code is one operation longer but it should be faster nevertheless. llvm-svn: 123621
2011-01-17 20:04:57 +08:00
declare i64 @llvm.ctpop.i64(i64) nounwind readnone
define i32 @test1(i64 %x) nounwind readnone {
%count = tail call i64 @llvm.ctpop.i64(i64 %x)
%cast = trunc i64 %count to i32
%cmp = icmp ugt i32 %cast, 1
%conv = zext i1 %cmp to i32
ret i32 %conv
; CHECK: test1:
Relax expressions and add explicit triplets -linux and -win32. llvm-svn: 126200
2011-02-22 15:19:46 +08:00
; CHECK: leaq -1([[A0:%rdi|%rcx]])
Add a DAGCombine to turn (ctpop x) u< 2 into (x & x-1) == 0. This shaves off 4 popcounts from the hacked 186.crafty source. This is enabled even when a native popcount instruction is available. The combined code is one operation longer but it should be faster nevertheless. llvm-svn: 123621
2011-01-17 20:04:57 +08:00
; CHECK-NEXT: testq
; CHECK-NEXT: setne
; CHECK: ret
}
define i32 @test2(i64 %x) nounwind readnone {
%count = tail call i64 @llvm.ctpop.i64(i64 %x)
Fix an off-by-one error in ctpop combining. llvm-svn: 123664
2011-01-18 02:00:28 +08:00
%cmp = icmp ult i64 %count, 2
Add a DAGCombine to turn (ctpop x) u< 2 into (x & x-1) == 0. This shaves off 4 popcounts from the hacked 186.crafty source. This is enabled even when a native popcount instruction is available. The combined code is one operation longer but it should be faster nevertheless. llvm-svn: 123621
2011-01-17 20:04:57 +08:00
%conv = zext i1 %cmp to i32
ret i32 %conv
; CHECK: test2:
Relax expressions and add explicit triplets -linux and -win32. llvm-svn: 126200
2011-02-22 15:19:46 +08:00
; CHECK: leaq -1([[A0]])
Add a DAGCombine to turn (ctpop x) u< 2 into (x & x-1) == 0. This shaves off 4 popcounts from the hacked 186.crafty source. This is enabled even when a native popcount instruction is available. The combined code is one operation longer but it should be faster nevertheless. llvm-svn: 123621
2011-01-17 20:04:57 +08:00
; CHECK-NEXT: testq
; CHECK-NEXT: sete
; CHECK: ret
}
Fix an off-by-one error in ctpop combining. llvm-svn: 123664
2011-01-18 02:00:28 +08:00
define i32 @test3(i64 %x) nounwind readnone {
%count = tail call i64 @llvm.ctpop.i64(i64 %x)
%cast = trunc i64 %count to i6 ; Too small for 0-64
%cmp = icmp ult i6 %cast, 2
%conv = zext i1 %cmp to i32
ret i32 %conv
; CHECK: test3:
; CHECK: cmpb $2
; CHECK: ret
}