llvm-mirror/test/CodeGen/AArch64/arm64-copy-tuple.ll
Tim Northover ca0f4dc4f0 AArch64/ARM64: move ARM64 into AArch64's place
This commit starts with a "git mv ARM64 AArch64" and continues out
from there, renaming the C++ classes, intrinsics, and other
target-local objects for consistency.

"ARM64" test directories are also moved, and tests that began their
life in ARM64 use an arm64 triple, those from AArch64 use an aarch64
triple. Both should be equivalent though.

This finishes the AArch64 merge, and everyone should feel free to
continue committing as normal now.

llvm-svn: 209577
2014-05-24 12:50:23 +00:00

147 lines
9.1 KiB
LLVM

; RUN: llc -mtriple=arm64-apple-ios -o - %s | FileCheck %s
; The main purpose of this test is to find out whether copyPhysReg can deal with
; the memmove-like situation arising in tuples, where an early copy can clobber
; the value needed by a later one if the tuples overlap.
; We use dummy inline asm to force LLVM to generate a COPY between the registers
; we want by clobbering all the others.
define void @test_D1D2_from_D0D1(i8* %addr) #0 {
; CHECK-LABEL: test_D1D2_from_D0D1:
; CHECK: mov.8b v2, v1
; CHECK: mov.8b v1, v0
entry:
%addr_v8i8 = bitcast i8* %addr to <8 x i8>*
%vec = tail call { <8 x i8>, <8 x i8> } @llvm.aarch64.neon.ld2.v8i8.p0v8i8(<8 x i8>* %addr_v8i8)
%vec0 = extractvalue { <8 x i8>, <8 x i8> } %vec, 0
%vec1 = extractvalue { <8 x i8>, <8 x i8> } %vec, 1
tail call void asm sideeffect "", "~{v2},~{v3},~{v4},~{v5},~{v6},~{v7},~{v8},~{v9},~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19},~{v20},~{v21},~{v22},~{v23},~{v24},~{v25},~{v26},~{v27},~{v28},~{v29},~{v30},~{v31}"()
tail call void @llvm.aarch64.neon.st2.v8i8.p0i8(<8 x i8> %vec0, <8 x i8> %vec1, i8* %addr)
tail call void asm sideeffect "", "~{v0},~{v3},~{v4},~{v5},~{v6},~{v7},~{v8},~{v9},~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19},~{v20},~{v21},~{v22},~{v23},~{v24},~{v25},~{v26},~{v27},~{v28},~{v29},~{v30},~{v31}"()
tail call void @llvm.aarch64.neon.st2.v8i8.p0i8(<8 x i8> %vec0, <8 x i8> %vec1, i8* %addr)
ret void
}
define void @test_D0D1_from_D1D2(i8* %addr) #0 {
; CHECK-LABEL: test_D0D1_from_D1D2:
; CHECK: mov.8b v0, v1
; CHECK: mov.8b v1, v2
entry:
%addr_v8i8 = bitcast i8* %addr to <8 x i8>*
%vec = tail call { <8 x i8>, <8 x i8> } @llvm.aarch64.neon.ld2.v8i8.p0v8i8(<8 x i8>* %addr_v8i8)
%vec0 = extractvalue { <8 x i8>, <8 x i8> } %vec, 0
%vec1 = extractvalue { <8 x i8>, <8 x i8> } %vec, 1
tail call void asm sideeffect "", "~{v0},~{v3},~{v4},~{v5},~{v6},~{v7},~{v8},~{v9},~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19},~{v20},~{v21},~{v22},~{v23},~{v24},~{v25},~{v26},~{v27},~{v28},~{v29},~{v30},~{v31}"()
tail call void @llvm.aarch64.neon.st2.v8i8.p0i8(<8 x i8> %vec0, <8 x i8> %vec1, i8* %addr)
tail call void asm sideeffect "", "~{v2},~{v3},~{v4},~{v5},~{v6},~{v7},~{v8},~{v9},~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19},~{v20},~{v21},~{v22},~{v23},~{v24},~{v25},~{v26},~{v27},~{v28},~{v29},~{v30},~{v31}"()
tail call void @llvm.aarch64.neon.st2.v8i8.p0i8(<8 x i8> %vec0, <8 x i8> %vec1, i8* %addr)
ret void
}
define void @test_D0D1_from_D31D0(i8* %addr) #0 {
; CHECK-LABEL: test_D0D1_from_D31D0:
; CHECK: mov.8b v1, v0
; CHECK: mov.8b v0, v31
entry:
%addr_v8i8 = bitcast i8* %addr to <8 x i8>*
%vec = tail call { <8 x i8>, <8 x i8> } @llvm.aarch64.neon.ld2.v8i8.p0v8i8(<8 x i8>* %addr_v8i8)
%vec0 = extractvalue { <8 x i8>, <8 x i8> } %vec, 0
%vec1 = extractvalue { <8 x i8>, <8 x i8> } %vec, 1
tail call void asm sideeffect "", "~{v1},~{v2},~{v3},~{v4},~{v5},~{v6},~{v7},~{v8},~{v9},~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19},~{v20},~{v21},~{v22},~{v23},~{v24},~{v25},~{v26},~{v27},~{v28},~{v29},~{v30}"()
tail call void @llvm.aarch64.neon.st2.v8i8.p0i8(<8 x i8> %vec0, <8 x i8> %vec1, i8* %addr)
tail call void asm sideeffect "", "~{v2},~{v3},~{v4},~{v5},~{v6},~{v7},~{v8},~{v9},~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19},~{v20},~{v21},~{v22},~{v23},~{v24},~{v25},~{v26},~{v27},~{v28},~{v29},~{v30},~{v31}"()
tail call void @llvm.aarch64.neon.st2.v8i8.p0i8(<8 x i8> %vec0, <8 x i8> %vec1, i8* %addr)
ret void
}
define void @test_D31D0_from_D0D1(i8* %addr) #0 {
; CHECK-LABEL: test_D31D0_from_D0D1:
; CHECK: mov.8b v31, v0
; CHECK: mov.8b v0, v1
entry:
%addr_v8i8 = bitcast i8* %addr to <8 x i8>*
%vec = tail call { <8 x i8>, <8 x i8> } @llvm.aarch64.neon.ld2.v8i8.p0v8i8(<8 x i8>* %addr_v8i8)
%vec0 = extractvalue { <8 x i8>, <8 x i8> } %vec, 0
%vec1 = extractvalue { <8 x i8>, <8 x i8> } %vec, 1
tail call void asm sideeffect "", "~{v2},~{v3},~{v4},~{v5},~{v6},~{v7},~{v8},~{v9},~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19},~{v20},~{v21},~{v22},~{v23},~{v24},~{v25},~{v26},~{v27},~{v28},~{v29},~{v30},~{v31}"()
tail call void @llvm.aarch64.neon.st2.v8i8.p0i8(<8 x i8> %vec0, <8 x i8> %vec1, i8* %addr)
tail call void asm sideeffect "", "~{v1},~{v2},~{v3},~{v4},~{v5},~{v6},~{v7},~{v8},~{v9},~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19},~{v20},~{v21},~{v22},~{v23},~{v24},~{v25},~{v26},~{v27},~{v28},~{v29},~{v30}"()
tail call void @llvm.aarch64.neon.st2.v8i8.p0i8(<8 x i8> %vec0, <8 x i8> %vec1, i8* %addr)
ret void
}
define void @test_D2D3D4_from_D0D1D2(i8* %addr) #0 {
; CHECK-LABEL: test_D2D3D4_from_D0D1D2:
; CHECK: mov.8b v4, v2
; CHECK: mov.8b v3, v1
; CHECK: mov.8b v2, v0
entry:
%addr_v8i8 = bitcast i8* %addr to <8 x i8>*
%vec = tail call { <8 x i8>, <8 x i8>, <8 x i8> } @llvm.aarch64.neon.ld3.v8i8.p0v8i8(<8 x i8>* %addr_v8i8)
%vec0 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8> } %vec, 0
%vec1 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8> } %vec, 1
%vec2 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8> } %vec, 2
tail call void asm sideeffect "", "~{v3},~{v4},~{v5},~{v6},~{v7},~{v8},~{v9},~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19},~{v20},~{v21},~{v22},~{v23},~{v24},~{v25},~{v26},~{v27},~{v28},~{v29},~{v30},~{v31}"()
tail call void @llvm.aarch64.neon.st3.v8i8.p0i8(<8 x i8> %vec0, <8 x i8> %vec1, <8 x i8> %vec2, i8* %addr)
tail call void asm sideeffect "", "~{v0},~{v1},~{v5},~{v6},~{v7},~{v8},~{v9},~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19},~{v20},~{v21},~{v22},~{v23},~{v24},~{v25},~{v26},~{v27},~{v28},~{v29},~{v30},~{v31}"()
tail call void @llvm.aarch64.neon.st3.v8i8.p0i8(<8 x i8> %vec0, <8 x i8> %vec1, <8 x i8> %vec2, i8* %addr)
ret void
}
define void @test_Q0Q1Q2_from_Q1Q2Q3(i8* %addr) #0 {
; CHECK-LABEL: test_Q0Q1Q2_from_Q1Q2Q3:
; CHECK: mov.16b v0, v1
; CHECK: mov.16b v1, v2
; CHECK: mov.16b v2, v3
entry:
%addr_v16i8 = bitcast i8* %addr to <16 x i8>*
%vec = tail call { <16 x i8>, <16 x i8>, <16 x i8> } @llvm.aarch64.neon.ld3.v16i8.p0v16i8(<16 x i8>* %addr_v16i8)
%vec0 = extractvalue { <16 x i8>, <16 x i8>, <16 x i8> } %vec, 0
%vec1 = extractvalue { <16 x i8>, <16 x i8>, <16 x i8> } %vec, 1
%vec2 = extractvalue { <16 x i8>, <16 x i8>, <16 x i8> } %vec, 2
tail call void asm sideeffect "", "~{v0},~{v4},~{v5},~{v6},~{v7},~{v8},~{v9},~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19},~{v20},~{v21},~{v22},~{v23},~{v24},~{v25},~{v26},~{v27},~{v28},~{v29},~{v30},~{v31}"()
tail call void @llvm.aarch64.neon.st3.v16i8.p0i8(<16 x i8> %vec0, <16 x i8> %vec1, <16 x i8> %vec2, i8* %addr)
tail call void asm sideeffect "", "~{v3},~{v4},~{v5},~{v6},~{v7},~{v8},~{v9},~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19},~{v20},~{v21},~{v22},~{v23},~{v24},~{v25},~{v26},~{v27},~{v28},~{v29},~{v30},~{v31}"()
tail call void @llvm.aarch64.neon.st3.v16i8.p0i8(<16 x i8> %vec0, <16 x i8> %vec1, <16 x i8> %vec2, i8* %addr)
ret void
}
define void @test_Q1Q2Q3Q4_from_Q30Q31Q0Q1(i8* %addr) #0 {
; CHECK-LABEL: test_Q1Q2Q3Q4_from_Q30Q31Q0Q1:
; CHECK: mov.16b v4, v1
; CHECK: mov.16b v3, v0
; CHECK: mov.16b v2, v31
; CHECK: mov.16b v1, v30
%addr_v16i8 = bitcast i8* %addr to <16 x i8>*
%vec = tail call { <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8> } @llvm.aarch64.neon.ld4.v16i8.p0v16i8(<16 x i8>* %addr_v16i8)
%vec0 = extractvalue { <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8> } %vec, 0
%vec1 = extractvalue { <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8> } %vec, 1
%vec2 = extractvalue { <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8> } %vec, 2
%vec3 = extractvalue { <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8> } %vec, 3
tail call void asm sideeffect "", "~{v2},~{v3},~{v4},~{v5},~{v6},~{v7},~{v8},~{v9},~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19},~{v20},~{v21},~{v22},~{v23},~{v24},~{v25},~{v26},~{v27},~{v28},~{v29}"()
tail call void @llvm.aarch64.neon.st4.v16i8.p0i8(<16 x i8> %vec0, <16 x i8> %vec1, <16 x i8> %vec2, <16 x i8> %vec3, i8* %addr)
tail call void asm sideeffect "", "~{v0},~{v5},~{v6},~{v7},~{v8},~{v9},~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19},~{v20},~{v21},~{v22},~{v23},~{v24},~{v25},~{v26},~{v27},~{v28},~{v29},~{v30},~{v31}"()
tail call void @llvm.aarch64.neon.st4.v16i8.p0i8(<16 x i8> %vec0, <16 x i8> %vec1, <16 x i8> %vec2, <16 x i8> %vec3, i8* %addr)
ret void
}
declare { <8 x i8>, <8 x i8> } @llvm.aarch64.neon.ld2.v8i8.p0v8i8(<8 x i8>*)
declare { <8 x i8>, <8 x i8>, <8 x i8> } @llvm.aarch64.neon.ld3.v8i8.p0v8i8(<8 x i8>*)
declare { <16 x i8>, <16 x i8>, <16 x i8> } @llvm.aarch64.neon.ld3.v16i8.p0v16i8(<16 x i8>*)
declare { <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8> } @llvm.aarch64.neon.ld4.v16i8.p0v16i8(<16 x i8>*)
declare void @llvm.aarch64.neon.st2.v8i8.p0i8(<8 x i8>, <8 x i8>, i8*)
declare void @llvm.aarch64.neon.st3.v8i8.p0i8(<8 x i8>, <8 x i8>, <8 x i8>, i8*)
declare void @llvm.aarch64.neon.st3.v16i8.p0i8(<16 x i8>, <16 x i8>, <16 x i8>, i8*)
declare void @llvm.aarch64.neon.st4.v16i8.p0i8(<16 x i8>, <16 x i8>, <16 x i8>, <16 x i8>, i8*)