maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

Convert more NEON tests to use FileCheck. 

llvm-svn: 83497
This commit is contained in:
Bob Wilson 2009-10-07 22:30:19 +00:00
parent 267fa622fa
commit 6d850f294d
6 changed files with 118 additions and 40 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
llvm/test/CodeGen/ARM/vmax.ll
View File

@ -1,13 +1,8 @@
; RUN: llc < %s -march=arm -mattr=+neon > %t
; RUN: grep {vmax\\.s8} %t | count 2
; RUN: grep {vmax\\.s16} %t | count 2
; RUN: grep {vmax\\.s32} %t | count 2
; RUN: grep {vmax\\.u8} %t | count 2
; RUN: grep {vmax\\.u16} %t | count 2
; RUN: grep {vmax\\.u32} %t | count 2
; RUN: grep {vmax\\.f32} %t | count 2
; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
define <8 x i8> @vmaxs8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
;CHECK: vmaxs8:
;CHECK: vmax.s8
%tmp1 = load <8 x i8>* %A
%tmp2 = load <8 x i8>* %B
%tmp3 = call <8 x i8> @llvm.arm.neon.vmaxs.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
@ -15,6 +10,8 @@ define <8 x i8> @vmaxs8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
}
define <4 x i16> @vmaxs16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
;CHECK: vmaxs16:
;CHECK: vmax.s16
%tmp1 = load <4 x i16>* %A
%tmp2 = load <4 x i16>* %B
%tmp3 = call <4 x i16> @llvm.arm.neon.vmaxs.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
@ -22,6 +19,8 @@ define <4 x i16> @vmaxs16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
}
define <2 x i32> @vmaxs32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
;CHECK: vmaxs32:
;CHECK: vmax.s32
%tmp1 = load <2 x i32>* %A
%tmp2 = load <2 x i32>* %B
%tmp3 = call <2 x i32> @llvm.arm.neon.vmaxs.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
@ -29,6 +28,8 @@ define <2 x i32> @vmaxs32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
}
define <8 x i8> @vmaxu8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
;CHECK: vmaxu8:
;CHECK: vmax.u8
%tmp1 = load <8 x i8>* %A
%tmp2 = load <8 x i8>* %B
%tmp3 = call <8 x i8> @llvm.arm.neon.vmaxu.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
@ -36,6 +37,8 @@ define <8 x i8> @vmaxu8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
}
define <4 x i16> @vmaxu16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
;CHECK: vmaxu16:
;CHECK: vmax.u16
%tmp1 = load <4 x i16>* %A
%tmp2 = load <4 x i16>* %B
%tmp3 = call <4 x i16> @llvm.arm.neon.vmaxu.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
@ -43,6 +46,8 @@ define <4 x i16> @vmaxu16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
}
define <2 x i32> @vmaxu32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
;CHECK: vmaxu32:
;CHECK: vmax.u32
%tmp1 = load <2 x i32>* %A
%tmp2 = load <2 x i32>* %B
%tmp3 = call <2 x i32> @llvm.arm.neon.vmaxu.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
@ -50,6 +55,8 @@ define <2 x i32> @vmaxu32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
}
define <2 x float> @vmaxf32(<2 x float>* %A, <2 x float>* %B) nounwind {
;CHECK: vmaxf32:
;CHECK: vmax.f32
%tmp1 = load <2 x float>* %A
%tmp2 = load <2 x float>* %B
%tmp3 = call <2 x float> @llvm.arm.neon.vmaxs.v2f32(<2 x float> %tmp1, <2 x float> %tmp2)
@ -57,6 +64,8 @@ define <2 x float> @vmaxf32(<2 x float>* %A, <2 x float>* %B) nounwind {
}
define <16 x i8> @vmaxQs8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
;CHECK: vmaxQs8:
;CHECK: vmax.s8
%tmp1 = load <16 x i8>* %A
%tmp2 = load <16 x i8>* %B
%tmp3 = call <16 x i8> @llvm.arm.neon.vmaxs.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
@ -64,6 +73,8 @@ define <16 x i8> @vmaxQs8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
}
define <8 x i16> @vmaxQs16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
;CHECK: vmaxQs16:
;CHECK: vmax.s16
%tmp1 = load <8 x i16>* %A
%tmp2 = load <8 x i16>* %B
%tmp3 = call <8 x i16> @llvm.arm.neon.vmaxs.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
@ -71,6 +82,8 @@ define <8 x i16> @vmaxQs16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
}
define <4 x i32> @vmaxQs32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
;CHECK: vmaxQs32:
;CHECK: vmax.s32
%tmp1 = load <4 x i32>* %A
%tmp2 = load <4 x i32>* %B
%tmp3 = call <4 x i32> @llvm.arm.neon.vmaxs.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
@ -78,6 +91,8 @@ define <4 x i32> @vmaxQs32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
}
define <16 x i8> @vmaxQu8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
;CHECK: vmaxQu8:
;CHECK: vmax.u8
%tmp1 = load <16 x i8>* %A
%tmp2 = load <16 x i8>* %B
%tmp3 = call <16 x i8> @llvm.arm.neon.vmaxu.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
@ -85,6 +100,8 @@ define <16 x i8> @vmaxQu8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
}
define <8 x i16> @vmaxQu16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
;CHECK: vmaxQu16:
;CHECK: vmax.u16
%tmp1 = load <8 x i16>* %A
%tmp2 = load <8 x i16>* %B
%tmp3 = call <8 x i16> @llvm.arm.neon.vmaxu.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
@ -92,6 +109,8 @@ define <8 x i16> @vmaxQu16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
}
define <4 x i32> @vmaxQu32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
;CHECK: vmaxQu32:
;CHECK: vmax.u32
%tmp1 = load <4 x i32>* %A
%tmp2 = load <4 x i32>* %B
%tmp3 = call <4 x i32> @llvm.arm.neon.vmaxu.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
@ -99,6 +118,8 @@ define <4 x i32> @vmaxQu32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
}
define <4 x float> @vmaxQf32(<4 x float>* %A, <4 x float>* %B) nounwind {
;CHECK: vmaxQf32:
;CHECK: vmax.f32
%tmp1 = load <4 x float>* %A
%tmp2 = load <4 x float>* %B
%tmp3 = call <4 x float> @llvm.arm.neon.vmaxs.v4f32(<4 x float> %tmp1, <4 x float> %tmp2)

37
llvm/test/CodeGen/ARM/vmin.ll
View File

@ -1,13 +1,8 @@
; RUN: llc < %s -march=arm -mattr=+neon > %t
; RUN: grep {vmin\\.s8} %t | count 2
; RUN: grep {vmin\\.s16} %t | count 2
; RUN: grep {vmin\\.s32} %t | count 2
; RUN: grep {vmin\\.u8} %t | count 2
; RUN: grep {vmin\\.u16} %t | count 2
; RUN: grep {vmin\\.u32} %t | count 2
; RUN: grep {vmin\\.f32} %t | count 2
; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
define <8 x i8> @vmins8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
;CHECK: vmins8:
;CHECK: vmin.s8
%tmp1 = load <8 x i8>* %A
%tmp2 = load <8 x i8>* %B
%tmp3 = call <8 x i8> @llvm.arm.neon.vmins.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
@ -15,6 +10,8 @@ define <8 x i8> @vmins8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
}
define <4 x i16> @vmins16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
;CHECK: vmins16:
;CHECK: vmin.s16
%tmp1 = load <4 x i16>* %A
%tmp2 = load <4 x i16>* %B
%tmp3 = call <4 x i16> @llvm.arm.neon.vmins.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
@ -22,6 +19,8 @@ define <4 x i16> @vmins16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
}
define <2 x i32> @vmins32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
;CHECK: vmins32:
;CHECK: vmin.s32
%tmp1 = load <2 x i32>* %A
%tmp2 = load <2 x i32>* %B
%tmp3 = call <2 x i32> @llvm.arm.neon.vmins.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
@ -29,6 +28,8 @@ define <2 x i32> @vmins32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
}
define <8 x i8> @vminu8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
;CHECK: vminu8:
;CHECK: vmin.u8
%tmp1 = load <8 x i8>* %A
%tmp2 = load <8 x i8>* %B
%tmp3 = call <8 x i8> @llvm.arm.neon.vminu.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
@ -36,6 +37,8 @@ define <8 x i8> @vminu8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
}
define <4 x i16> @vminu16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
;CHECK: vminu16:
;CHECK: vmin.u16
%tmp1 = load <4 x i16>* %A
%tmp2 = load <4 x i16>* %B
%tmp3 = call <4 x i16> @llvm.arm.neon.vminu.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
@ -43,6 +46,8 @@ define <4 x i16> @vminu16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
}
define <2 x i32> @vminu32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
;CHECK: vminu32:
;CHECK: vmin.u32
%tmp1 = load <2 x i32>* %A
%tmp2 = load <2 x i32>* %B
%tmp3 = call <2 x i32> @llvm.arm.neon.vminu.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
@ -50,6 +55,8 @@ define <2 x i32> @vminu32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
}
define <2 x float> @vminf32(<2 x float>* %A, <2 x float>* %B) nounwind {
;CHECK: vminf32:
;CHECK: vmin.f32
%tmp1 = load <2 x float>* %A
%tmp2 = load <2 x float>* %B
%tmp3 = call <2 x float> @llvm.arm.neon.vmins.v2f32(<2 x float> %tmp1, <2 x float> %tmp2)
@ -57,6 +64,8 @@ define <2 x float> @vminf32(<2 x float>* %A, <2 x float>* %B) nounwind {
}
define <16 x i8> @vminQs8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
;CHECK: vminQs8:
;CHECK: vmin.s8
%tmp1 = load <16 x i8>* %A
%tmp2 = load <16 x i8>* %B
%tmp3 = call <16 x i8> @llvm.arm.neon.vmins.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
@ -64,6 +73,8 @@ define <16 x i8> @vminQs8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
}
define <8 x i16> @vminQs16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
;CHECK: vminQs16:
;CHECK: vmin.s16
%tmp1 = load <8 x i16>* %A
%tmp2 = load <8 x i16>* %B
%tmp3 = call <8 x i16> @llvm.arm.neon.vmins.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
@ -71,6 +82,8 @@ define <8 x i16> @vminQs16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
}
define <4 x i32> @vminQs32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
;CHECK: vminQs32:
;CHECK: vmin.s32
%tmp1 = load <4 x i32>* %A
%tmp2 = load <4 x i32>* %B
%tmp3 = call <4 x i32> @llvm.arm.neon.vmins.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
@ -78,6 +91,8 @@ define <4 x i32> @vminQs32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
}
define <16 x i8> @vminQu8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
;CHECK: vminQu8:
;CHECK: vmin.u8
%tmp1 = load <16 x i8>* %A
%tmp2 = load <16 x i8>* %B
%tmp3 = call <16 x i8> @llvm.arm.neon.vminu.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
@ -85,6 +100,8 @@ define <16 x i8> @vminQu8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
}
define <8 x i16> @vminQu16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
;CHECK: vminQu16:
;CHECK: vmin.u16
%tmp1 = load <8 x i16>* %A
%tmp2 = load <8 x i16>* %B
%tmp3 = call <8 x i16> @llvm.arm.neon.vminu.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
@ -92,6 +109,8 @@ define <8 x i16> @vminQu16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
}
define <4 x i32> @vminQu32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
;CHECK: vminQu32:
;CHECK: vmin.u32
%tmp1 = load <4 x i32>* %A
%tmp2 = load <4 x i32>* %B
%tmp3 = call <4 x i32> @llvm.arm.neon.vminu.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
@ -99,6 +118,8 @@ define <4 x i32> @vminQu32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
}
define <4 x float> @vminQf32(<4 x float>* %A, <4 x float>* %B) nounwind {
;CHECK: vminQf32:
;CHECK: vmin.f32
%tmp1 = load <4 x float>* %A
%tmp2 = load <4 x float>* %B
%tmp3 = call <4 x float> @llvm.arm.neon.vmins.v4f32(<4 x float> %tmp1, <4 x float> %tmp2)

22
llvm/test/CodeGen/ARM/vmla.ll
View File

@ -1,10 +1,8 @@
; RUN: llc < %s -march=arm -mattr=+neon > %t
; RUN: grep {vmla\\.i8} %t | count 2
; RUN: grep {vmla\\.i16} %t | count 2
; RUN: grep {vmla\\.i32} %t | count 2
; RUN: grep {vmla\\.f32} %t | count 2
; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
define <8 x i8> @vmlai8(<8 x i8>* %A, <8 x i8>* %B, <8 x i8> * %C) nounwind {
;CHECK: vmlai8:
;CHECK: vmla.i8
%tmp1 = load <8 x i8>* %A
%tmp2 = load <8 x i8>* %B
%tmp3 = load <8 x i8>* %C
@ -14,6 +12,8 @@ define <8 x i8> @vmlai8(<8 x i8>* %A, <8 x i8>* %B, <8 x i8> * %C) nounwind {
}
define <4 x i16> @vmlai16(<4 x i16>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind {
;CHECK: vmlai16:
;CHECK: vmla.i16
%tmp1 = load <4 x i16>* %A
%tmp2 = load <4 x i16>* %B
%tmp3 = load <4 x i16>* %C
@ -23,6 +23,8 @@ define <4 x i16> @vmlai16(<4 x i16>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind
}
define <2 x i32> @vmlai32(<2 x i32>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind {
;CHECK: vmlai32:
;CHECK: vmla.i32
%tmp1 = load <2 x i32>* %A
%tmp2 = load <2 x i32>* %B
%tmp3 = load <2 x i32>* %C
@ -32,6 +34,8 @@ define <2 x i32> @vmlai32(<2 x i32>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind
}
define <2 x float> @vmlaf32(<2 x float>* %A, <2 x float>* %B, <2 x float>* %C) nounwind {
;CHECK: vmlaf32:
;CHECK: vmla.f32
%tmp1 = load <2 x float>* %A
%tmp2 = load <2 x float>* %B
%tmp3 = load <2 x float>* %C
@ -41,6 +45,8 @@ define <2 x float> @vmlaf32(<2 x float>* %A, <2 x float>* %B, <2 x float>* %C) n
}
define <16 x i8> @vmlaQi8(<16 x i8>* %A, <16 x i8>* %B, <16 x i8> * %C) nounwind {
;CHECK: vmlaQi8:
;CHECK: vmla.i8
%tmp1 = load <16 x i8>* %A
%tmp2 = load <16 x i8>* %B
%tmp3 = load <16 x i8>* %C
@ -50,6 +56,8 @@ define <16 x i8> @vmlaQi8(<16 x i8>* %A, <16 x i8>* %B, <16 x i8> * %C) nounwind
}
define <8 x i16> @vmlaQi16(<8 x i16>* %A, <8 x i16>* %B, <8 x i16>* %C) nounwind {
;CHECK: vmlaQi16:
;CHECK: vmla.i16
%tmp1 = load <8 x i16>* %A
%tmp2 = load <8 x i16>* %B
%tmp3 = load <8 x i16>* %C
@ -59,6 +67,8 @@ define <8 x i16> @vmlaQi16(<8 x i16>* %A, <8 x i16>* %B, <8 x i16>* %C) nounwind
}
define <4 x i32> @vmlaQi32(<4 x i32>* %A, <4 x i32>* %B, <4 x i32>* %C) nounwind {
;CHECK: vmlaQi32:
;CHECK: vmla.i32
%tmp1 = load <4 x i32>* %A
%tmp2 = load <4 x i32>* %B
%tmp3 = load <4 x i32>* %C
@ -68,6 +78,8 @@ define <4 x i32> @vmlaQi32(<4 x i32>* %A, <4 x i32>* %B, <4 x i32>* %C) nounwind
}
define <4 x float> @vmlaQf32(<4 x float>* %A, <4 x float>* %B, <4 x float>* %C) nounwind {
;CHECK: vmlaQf32:
;CHECK: vmla.f32
%tmp1 = load <4 x float>* %A
%tmp2 = load <4 x float>* %B
%tmp3 = load <4 x float>* %C

20
llvm/test/CodeGen/ARM/vmlal.ll
View File

@ -1,12 +1,8 @@
; RUN: llc < %s -march=arm -mattr=+neon > %t
; RUN: grep {vmlal\\.s8} %t | count 1
; RUN: grep {vmlal\\.s16} %t | count 1
; RUN: grep {vmlal\\.s32} %t | count 1
; RUN: grep {vmlal\\.u8} %t | count 1
; RUN: grep {vmlal\\.u16} %t | count 1
; RUN: grep {vmlal\\.u32} %t | count 1
; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
define <8 x i16> @vmlals8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
;CHECK: vmlals8:
;CHECK: vmlal.s8
%tmp1 = load <8 x i16>* %A
%tmp2 = load <8 x i8>* %B
%tmp3 = load <8 x i8>* %C
@ -15,6 +11,8 @@ define <8 x i16> @vmlals8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
}
define <4 x i32> @vmlals16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind {
;CHECK: vmlals16:
;CHECK: vmlal.s16
%tmp1 = load <4 x i32>* %A
%tmp2 = load <4 x i16>* %B
%tmp3 = load <4 x i16>* %C
@ -23,6 +21,8 @@ define <4 x i32> @vmlals16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind
}
define <2 x i64> @vmlals32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind {
;CHECK: vmlals32:
;CHECK: vmlal.s32
%tmp1 = load <2 x i64>* %A
%tmp2 = load <2 x i32>* %B
%tmp3 = load <2 x i32>* %C
@ -31,6 +31,8 @@ define <2 x i64> @vmlals32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind
}
define <8 x i16> @vmlalu8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
;CHECK: vmlalu8:
;CHECK: vmlal.u8
%tmp1 = load <8 x i16>* %A
%tmp2 = load <8 x i8>* %B
%tmp3 = load <8 x i8>* %C
@ -39,6 +41,8 @@ define <8 x i16> @vmlalu8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
}
define <4 x i32> @vmlalu16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind {
;CHECK: vmlalu16:
;CHECK: vmlal.u16
%tmp1 = load <4 x i32>* %A
%tmp2 = load <4 x i16>* %B
%tmp3 = load <4 x i16>* %C
@ -47,6 +51,8 @@ define <4 x i32> @vmlalu16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind
}
define <2 x i64> @vmlalu32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind {
;CHECK: vmlalu32:
;CHECK: vmlal.u32
%tmp1 = load <2 x i64>* %A
%tmp2 = load <2 x i32>* %B
%tmp3 = load <2 x i32>* %C

22
llvm/test/CodeGen/ARM/vmls.ll
View File

@ -1,10 +1,8 @@
; RUN: llc < %s -march=arm -mattr=+neon > %t
; RUN: grep {vmls\\.i8} %t | count 2
; RUN: grep {vmls\\.i16} %t | count 2
; RUN: grep {vmls\\.i32} %t | count 2
; RUN: grep {vmls\\.f32} %t | count 2
; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
define <8 x i8> @vmlsi8(<8 x i8>* %A, <8 x i8>* %B, <8 x i8> * %C) nounwind {
;CHECK: vmlsi8:
;CHECK: vmls.i8
%tmp1 = load <8 x i8>* %A
%tmp2 = load <8 x i8>* %B
%tmp3 = load <8 x i8>* %C
@ -14,6 +12,8 @@ define <8 x i8> @vmlsi8(<8 x i8>* %A, <8 x i8>* %B, <8 x i8> * %C) nounwind {
}
define <4 x i16> @vmlsi16(<4 x i16>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind {
;CHECK: vmlsi16:
;CHECK: vmls.i16
%tmp1 = load <4 x i16>* %A
%tmp2 = load <4 x i16>* %B
%tmp3 = load <4 x i16>* %C
@ -23,6 +23,8 @@ define <4 x i16> @vmlsi16(<4 x i16>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind
}
define <2 x i32> @vmlsi32(<2 x i32>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind {
;CHECK: vmlsi32:
;CHECK: vmls.i32
%tmp1 = load <2 x i32>* %A
%tmp2 = load <2 x i32>* %B
%tmp3 = load <2 x i32>* %C
@ -32,6 +34,8 @@ define <2 x i32> @vmlsi32(<2 x i32>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind
}
define <2 x float> @vmlsf32(<2 x float>* %A, <2 x float>* %B, <2 x float>* %C) nounwind {
;CHECK: vmlsf32:
;CHECK: vmls.f32
%tmp1 = load <2 x float>* %A
%tmp2 = load <2 x float>* %B
%tmp3 = load <2 x float>* %C
@ -41,6 +45,8 @@ define <2 x float> @vmlsf32(<2 x float>* %A, <2 x float>* %B, <2 x float>* %C) n
}
define <16 x i8> @vmlsQi8(<16 x i8>* %A, <16 x i8>* %B, <16 x i8> * %C) nounwind {
;CHECK: vmlsQi8:
;CHECK: vmls.i8
%tmp1 = load <16 x i8>* %A
%tmp2 = load <16 x i8>* %B
%tmp3 = load <16 x i8>* %C
@ -50,6 +56,8 @@ define <16 x i8> @vmlsQi8(<16 x i8>* %A, <16 x i8>* %B, <16 x i8> * %C) nounwind
}
define <8 x i16> @vmlsQi16(<8 x i16>* %A, <8 x i16>* %B, <8 x i16>* %C) nounwind {
;CHECK: vmlsQi16:
;CHECK: vmls.i16
%tmp1 = load <8 x i16>* %A
%tmp2 = load <8 x i16>* %B
%tmp3 = load <8 x i16>* %C
@ -59,6 +67,8 @@ define <8 x i16> @vmlsQi16(<8 x i16>* %A, <8 x i16>* %B, <8 x i16>* %C) nounwind
}
define <4 x i32> @vmlsQi32(<4 x i32>* %A, <4 x i32>* %B, <4 x i32>* %C) nounwind {
;CHECK: vmlsQi32:
;CHECK: vmls.i32
%tmp1 = load <4 x i32>* %A
%tmp2 = load <4 x i32>* %B
%tmp3 = load <4 x i32>* %C
@ -68,6 +78,8 @@ define <4 x i32> @vmlsQi32(<4 x i32>* %A, <4 x i32>* %B, <4 x i32>* %C) nounwind
}
define <4 x float> @vmlsQf32(<4 x float>* %A, <4 x float>* %B, <4 x float>* %C) nounwind {
;CHECK: vmlsQf32:
;CHECK: vmls.f32
%tmp1 = load <4 x float>* %A
%tmp2 = load <4 x float>* %B
%tmp3 = load <4 x float>* %C

20
llvm/test/CodeGen/ARM/vmlsl.ll
View File

@ -1,12 +1,8 @@
; RUN: llc < %s -march=arm -mattr=+neon > %t
; RUN: grep {vmlsl\\.s8} %t | count 1
; RUN: grep {vmlsl\\.s16} %t | count 1
; RUN: grep {vmlsl\\.s32} %t | count 1
; RUN: grep {vmlsl\\.u8} %t | count 1
; RUN: grep {vmlsl\\.u16} %t | count 1
; RUN: grep {vmlsl\\.u32} %t | count 1
; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
define <8 x i16> @vmlsls8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
;CHECK: vmlsls8:
;CHECK: vmlsl.s8
%tmp1 = load <8 x i16>* %A
%tmp2 = load <8 x i8>* %B
%tmp3 = load <8 x i8>* %C
@ -15,6 +11,8 @@ define <8 x i16> @vmlsls8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
}
define <4 x i32> @vmlsls16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind {
;CHECK: vmlsls16:
;CHECK: vmlsl.s16
%tmp1 = load <4 x i32>* %A
%tmp2 = load <4 x i16>* %B
%tmp3 = load <4 x i16>* %C
@ -23,6 +21,8 @@ define <4 x i32> @vmlsls16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind
}
define <2 x i64> @vmlsls32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind {
;CHECK: vmlsls32:
;CHECK: vmlsl.s32
%tmp1 = load <2 x i64>* %A
%tmp2 = load <2 x i32>* %B
%tmp3 = load <2 x i32>* %C
@ -31,6 +31,8 @@ define <2 x i64> @vmlsls32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind
}
define <8 x i16> @vmlslu8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
;CHECK: vmlslu8:
;CHECK: vmlsl.u8
%tmp1 = load <8 x i16>* %A
%tmp2 = load <8 x i8>* %B
%tmp3 = load <8 x i8>* %C
@ -39,6 +41,8 @@ define <8 x i16> @vmlslu8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
}
define <4 x i32> @vmlslu16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind {
;CHECK: vmlslu16:
;CHECK: vmlsl.u16
%tmp1 = load <4 x i32>* %A
%tmp2 = load <4 x i16>* %B
%tmp3 = load <4 x i16>* %C
@ -47,6 +51,8 @@ define <4 x i32> @vmlslu16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind
}
define <2 x i64> @vmlslu32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind {
;CHECK: vmlslu32:
;CHECK: vmlsl.u32
%tmp1 = load <2 x i64>* %A
%tmp2 = load <2 x i32>* %B
%tmp3 = load <2 x i32>* %C