llvm-6502/test/CodeGen/X86/avx512-vec-cmp.ll
Elena Demikhovsky 1f0a0e314d AVX-512: Added implementation of CONCAT_VECTORS for v8i1 vectors (by Alexey Bader).
Added implementation of "truncate" from integer type (i64/i32/i16/i8) to i1.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@197482 91177308-0d34-0410-b5e6-96231b3b80d8
2013-12-17 08:33:15 +00:00

125 lines
3.4 KiB
LLVM

; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=knl | FileCheck %s
; CHECK-LABEL: test1
; CHECK: vcmpleps
; CHECK: vmovups
; CHECK: ret
define <16 x float> @test1(<16 x float> %x, <16 x float> %y) nounwind {
%mask = fcmp ole <16 x float> %x, %y
%max = select <16 x i1> %mask, <16 x float> %x, <16 x float> %y
ret <16 x float> %max
}
; CHECK-LABEL: test2
; CHECK: vcmplepd
; CHECK: vmovupd
; CHECK: ret
define <8 x double> @test2(<8 x double> %x, <8 x double> %y) nounwind {
%mask = fcmp ole <8 x double> %x, %y
%max = select <8 x i1> %mask, <8 x double> %x, <8 x double> %y
ret <8 x double> %max
}
; CHECK-LABEL: test3
; CHECK: vpcmpeqd (%rdi)
; CHECK: vmovdqu32
; CHECK: ret
define <16 x i32> @test3(<16 x i32> %x, <16 x i32> %x1, <16 x i32>* %yp) nounwind {
%y = load <16 x i32>* %yp, align 4
%mask = icmp eq <16 x i32> %x, %y
%max = select <16 x i1> %mask, <16 x i32> %x, <16 x i32> %x1
ret <16 x i32> %max
}
; CHECK-LABEL: @test4_unsigned
; CHECK: vpcmpnltud
; CHECK: vmovdqu32
; CHECK: ret
define <16 x i32> @test4_unsigned(<16 x i32> %x, <16 x i32> %y) nounwind {
%mask = icmp uge <16 x i32> %x, %y
%max = select <16 x i1> %mask, <16 x i32> %x, <16 x i32> %y
ret <16 x i32> %max
}
; CHECK-LABEL: test5
; CHECK: vpcmpeqq {{.*}}%k1
; CHECK: vmovdqu64 {{.*}}%k1
; CHECK: ret
define <8 x i64> @test5(<8 x i64> %x, <8 x i64> %y) nounwind {
%mask = icmp eq <8 x i64> %x, %y
%max = select <8 x i1> %mask, <8 x i64> %x, <8 x i64> %y
ret <8 x i64> %max
}
; CHECK-LABEL: test6_unsigned
; CHECK: vpcmpnleuq {{.*}}%k1
; CHECK: vmovdqu64 {{.*}}%k1
; CHECK: ret
define <8 x i64> @test6_unsigned(<8 x i64> %x, <8 x i64> %y) nounwind {
%mask = icmp ugt <8 x i64> %x, %y
%max = select <8 x i1> %mask, <8 x i64> %x, <8 x i64> %y
ret <8 x i64> %max
}
; CHECK-LABEL: test7
; CHECK: xor
; CHECK: vcmpltps
; CHECK: vblendvps
; CHECK: ret
define <4 x float> @test7(<4 x float> %a, <4 x float> %b) {
%mask = fcmp olt <4 x float> %a, zeroinitializer
%c = select <4 x i1>%mask, <4 x float>%a, <4 x float>%b
ret <4 x float>%c
}
; CHECK-LABEL: test8
; CHECK: xor
; CHECK: vcmpltpd
; CHECK: vblendvpd
; CHECK: ret
define <2 x double> @test8(<2 x double> %a, <2 x double> %b) {
%mask = fcmp olt <2 x double> %a, zeroinitializer
%c = select <2 x i1>%mask, <2 x double>%a, <2 x double>%b
ret <2 x double>%c
}
; CHECK-LABEL: test9
; CHECK: vpcmpeqd
; CHECK: vpblendmd
; CHECK: ret
define <8 x i32> @test9(<8 x i32> %x, <8 x i32> %y) nounwind {
%mask = icmp eq <8 x i32> %x, %y
%max = select <8 x i1> %mask, <8 x i32> %x, <8 x i32> %y
ret <8 x i32> %max
}
; CHECK-LABEL: test10
; CHECK: vcmpeqps
; CHECK: vblendmps
; CHECK: ret
define <8 x float> @test10(<8 x float> %x, <8 x float> %y) nounwind {
%mask = fcmp oeq <8 x float> %x, %y
%max = select <8 x i1> %mask, <8 x float> %x, <8 x float> %y
ret <8 x float> %max
}
; CHECK-LABEL: test11_unsigned
; CHECK: vpmaxud
; CHECK: ret
define <8 x i32> @test11_unsigned(<8 x i32> %x, <8 x i32> %y) nounwind {
%mask = icmp ugt <8 x i32> %x, %y
%max = select <8 x i1> %mask, <8 x i32> %x, <8 x i32> %y
ret <8 x i32> %max
}
; CHECK-LABEL: test12
; CHECK: vpcmpeqq %zmm2, %zmm0, [[LO:%k[0-7]]]
; CHECK: vpcmpeqq %zmm3, %zmm1, [[HI:%k[0-7]]]
; CHECK: kunpckbw [[LO]], [[HI]], {{%k[0-7]}}
define i16 @test12(<16 x i64> %a, <16 x i64> %b) nounwind {
%res = icmp eq <16 x i64> %a, %b
%res1 = bitcast <16 x i1> %res to i16
ret i16 %res1
}