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

ARM64: add a few bits of polynomial intrinsic codegen. 

llvm-svn: 205303
This commit is contained in:
Tim Northover 2014-04-01 12:23:08 +00:00
parent 4f1dd58e2e
commit b17f9a4609
3 changed files with 73 additions and 33 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
clang/lib/CodeGen/CGBuiltin.cpp
View File

@ -2608,6 +2608,7 @@ static NeonIntrinsicInfo ARM64SISDIntrinsicMap[] = {
NEONMAP1(vminvq_f64, arm64_neon_fminv, AddRetType | Add1ArgType),
NEONMAP1(vminvq_s32, arm64_neon_sminv, AddRetType | Add1ArgType),
NEONMAP1(vminvq_u32, arm64_neon_uminv, AddRetType | Add1ArgType),
NEONMAP1(vmull_p64, arm64_neon_pmull64, 0),
NEONMAP1(vmulxd_f64, arm64_neon_fmulx, Add1ArgType),
NEONMAP1(vmulxs_f32, arm64_neon_fmulx, Add1ArgType),
NEONMAP1(vpaddd_s64, arm64_neon_uaddv, AddRetType | Add1ArgType),
@ -5190,6 +5191,16 @@ Value *CodeGenFunction::EmitARM64BuiltinExpr(unsigned BuiltinID,
// Handle non-overloaded intrinsics first.
switch (BuiltinID) {
default: break;
case NEON::BI__builtin_neon_vldrq_p128: {
llvm::Type *Int128PTy = llvm::Type::getIntNPtrTy(getLLVMContext(), 128);
Value *Ptr = Builder.CreateBitCast(EmitScalarExpr(E->getArg(0)), Int128PTy);
return Builder.CreateLoad(Ptr);
}
case NEON::BI__builtin_neon_vstrq_p128: {
llvm::Type *Int128PTy = llvm::Type::getIntNPtrTy(getLLVMContext(), 128);
Value *Ptr = Builder.CreateBitCast(Ops[0], Int128PTy);
return Builder.CreateStore(EmitScalarExpr(E->getArg(1)), Ptr);
}
case NEON::BI__builtin_neon_vcvts_u32_f32:
case NEON::BI__builtin_neon_vcvtd_u64_f64:
usgn = true;

26
clang/test/CodeGen/aarch64-poly128.c
View File

@ -1,6 +1,11 @@
// REQUIRES: aarch64-registered-target
// REQUIRES: arm64-registered-target
// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +neon \
// RUN: -ffp-contract=fast -S -O3 -o - %s | FileCheck %s
// RUN: -ffp-contract=fast -S -O3 -o - %s | FileCheck %s --check-prefix=CHECK \
// RUN: --check-prefix=CHECK-AARCH64
// RUN: %clang_cc1 -triple arm64-none-linux-gnu \
// RUN: -ffp-contract=fast -S -O3 -o - %s | FileCheck %s --check-prefix=CHECK \
// RUN: --check-prefix=CHECK-ARM64
// Test new aarch64 intrinsics with poly128
// FIXME: Currently, poly128_t equals to uint128, which will be spilt into
@ -14,22 +19,29 @@
void test_vstrq_p128(poly128_t * ptr, poly128_t val) {
// CHECK-LABEL: test_vstrq_p128
vstrq_p128(ptr, val);
// CHECK: str {{x[0-9]+}}, [{{x[0-9]+}}, #8]
// CHECK-NEXT: str {{x[0-9]+}}, [{{x[0-9]+}}]
// CHECK-AARCH64: str {{x[0-9]+}}, [{{x[0-9]+}}, #8]
// CHECK-AARCH64-NEXT: str {{x[0-9]+}}, [{{x[0-9]+}}]
// CHECK-ARM64: stp {{x[0-9]+}}, {{x[0-9]+}}, [x0]
}
poly128_t test_vldrq_p128(poly128_t * ptr) {
// CHECK-LABEL: test_vldrq_p128
return vldrq_p128(ptr);
// CHECK: ldr {{x[0-9]+}}, [{{x[0-9]+}}]
// CHECK-NEXT: ldr {{x[0-9]+}}, [{{x[0-9]+}}, #8]
// CHECK-AARCH64: ldr {{x[0-9]+}}, [{{x[0-9]+}}]
// CHECK-AARCH64-NEXT: ldr {{x[0-9]+}}, [{{x[0-9]+}}, #8]
// CHECK-ARM64: ldp {{x[0-9]+}}, {{x[0-9]+}}, [x0]
}
void test_ld_st_p128(poly128_t * ptr) {
// CHECK-LABEL: test_ld_st_p128
vstrq_p128(ptr+1, vldrq_p128(ptr));
// CHECK: ldr {{q[0-9]+}}, [{{x[0-9]+}}]
// CHECK-NEXT: str {{q[0-9]+}}, [{{x[0-9]+}}, #16]
// CHECK-AARCH64: ldr {{q[0-9]+}}, [{{x[0-9]+}}]
// CHECK-AARCH64-NEXT: str {{q[0-9]+}}, [{{x[0-9]+}}, #16]
// CHECK-ARM64: ldp [[PLO:x[0-9]+]], [[PHI:x[0-9]+]], [{{x[0-9]+}}]
// CHECK-ARM64-NEXT: stp [[PLO]], [[PHI]], [{{x[0-9]+}}, #16]
}
poly128_t test_vmull_p64(poly64_t a, poly64_t b) {

69
clang/test/CodeGen/aarch64-poly64.c
View File

@ -1,6 +1,11 @@
// REQUIRES: aarch64-registered-target
// REQUIRES: arm64-registered-target
// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +neon \
// RUN: -ffp-contract=fast -S -O3 -o - %s | FileCheck %s
// RUN: -ffp-contract=fast -S -O3 -o - %s | FileCheck %s --check-prefix=CHECK \
// RUN: --check-prefix=CHECK-AARCH64
// RUN: %clang_cc1 -triple arm64-none-linux-gnu \
// RUN: -ffp-contract=fast -S -O3 -o - %s | FileCheck %s --check-prefix=CHECK \
// RUN: --check-prefix=CHECK-ARM64
// Test new aarch64 intrinsics with poly64
@ -69,7 +74,9 @@ poly64x2_t test_vsetq_lane_p64(poly64_t a, poly64x2_t v) {
poly64x1_t test_vcopy_lane_p64(poly64x1_t a, poly64x1_t b) {
// CHECK-LABEL: test_vcopy_lane_p64
return vcopy_lane_p64(a, 0, b, 0);
// CHECK: fmov {{d[0-9]+}}, {{d[0-9]+}}
// CHECK-AARCH64: fmov {{d[0-9]+}}, {{d[0-9]+}}
// CHECK-ARM64: orr v0.16b, v1.16b, v1.16b
}
poly64x2_t test_vcopyq_lane_p64(poly64x2_t a, poly64x1_t b) {
@ -81,7 +88,7 @@ poly64x2_t test_vcopyq_lane_p64(poly64x2_t a, poly64x1_t b) {
poly64x2_t test_vcopyq_laneq_p64(poly64x2_t a, poly64x2_t b) {
// CHECK-LABEL: test_vcopyq_laneq_p64
return vcopyq_laneq_p64(a, 1, b, 1);
// CHECK: ins {{v[0-9]+}}.d[1], {{v[0-9]+}}.d[1]
// CHECK-AARCH64: ins {{v[0-9]+}}.d[1], {{v[0-9]+}}.d[1]
}
poly64x1_t test_vcreate_p64(uint64_t a) {
@ -128,97 +135,101 @@ poly64x2_t test_vcombine_p64(poly64x1_t low, poly64x1_t high) {
poly64x1_t test_vld1_p64(poly64_t const * ptr) {
// CHECK-LABEL: test_vld1_p64
return vld1_p64(ptr);
// CHECK: ld1 {{{v[0-9]+}}.1d}, [{{x[0-9]+|sp}}]
// CHECK-AARCH64: ld1 {{{v[0-9]+}}.1d}, [{{x[0-9]+|sp}}]
// CHECK-ARM64: ldr {{d[0-9]+}}, [{{x[0-9]+|sp}}]
}
poly64x2_t test_vld1q_p64(poly64_t const * ptr) {
// CHECK-LABEL: test_vld1q_p64
return vld1q_p64(ptr);
// CHECK: ld1 {{{v[0-9]+}}.2d}, [{{x[0-9]+|sp}}]
// CHECK-AARCH64: ld1 {{{v[0-9]+}}.2d}, [{{x[0-9]+|sp}}]
// CHECK-ARM64: ldr {{q[0-9]+}}, [{{x[0-9]+|sp}}]
}
void test_vst1_p64(poly64_t * ptr, poly64x1_t val) {
// CHECK-LABEL: test_vst1_p64
return vst1_p64(ptr, val);
// CHECK: st1 {{{v[0-9]+}}.1d}, [{{x[0-9]+|sp}}]
// CHECK-AARCH64: st1 {{{v[0-9]+}}.1d}, [{{x[0-9]+|sp}}]
// CHECK-ARM64: str {{d[0-9]+}}, [{{x[0-9]+|sp}}]
}
void test_vst1q_p64(poly64_t * ptr, poly64x2_t val) {
// CHECK-LABEL: test_vst1q_p64
return vst1q_p64(ptr, val);
// CHECK: st1 {{{v[0-9]+}}.2d}, [{{x[0-9]+|sp}}]
// CHECK-AARCH64: st1 {{{v[0-9]+}}.2d}, [{{x[0-9]+|sp}}]
// CHECK-ARM64: str {{q[0-9]+}}, [{{x[0-9]+|sp}}]
}
poly64x1x2_t test_vld2_p64(poly64_t const * ptr) {
// CHECK-LABEL: test_vld2_p64
return vld2_p64(ptr);
// CHECK: ld1 {{{v[0-9]+}}.1d, {{v[0-9]+}}.1d}, [{{x[0-9]+|sp}}]
// CHECK: ld1 {{{ *v[0-9]+.1d, v[0-9]+.1d *}}}, [{{x[0-9]+|sp}}]
}
poly64x2x2_t test_vld2q_p64(poly64_t const * ptr) {
// CHECK-LABEL: test_vld2q_p64
return vld2q_p64(ptr);
// CHECK: ld2 {{{v[0-9]+}}.2d, {{v[0-9]+}}.2d}, [{{x[0-9]+|sp}}]
// CHECK: ld2 {{{ *v[0-9]+.2d, v[0-9]+.2d *}}}, [{{x[0-9]+|sp}}]
}
poly64x1x3_t test_vld3_p64(poly64_t const * ptr) {
// CHECK-LABEL: test_vld3_p64
return vld3_p64(ptr);
// CHECK: ld1 {{{v[0-9]+}}.1d, {{v[0-9]+}}.1d, {{v[0-9]+}}.1d}, [{{x[0-9]+|sp}}]
// CHECK: ld1 {{{ *v[0-9]+.1d, v[0-9]+.1d, v[0-9]+.1d *}}}, [{{x[0-9]+|sp}}]
}
poly64x2x3_t test_vld3q_p64(poly64_t const * ptr) {
// CHECK-LABEL: test_vld3q_p64
return vld3q_p64(ptr);
// CHECK: ld3 {{{v[0-9]+}}.2d, {{v[0-9]+}}.2d, {{v[0-9]+}}.2d}, [{{x[0-9]+|sp}}]
// CHECK: ld3 {{{ *v[0-9]+.2d, v[0-9]+.2d, v[0-9]+.2d *}}}, [{{x[0-9]+|sp}}]
}
poly64x1x4_t test_vld4_p64(poly64_t const * ptr) {
// CHECK-LABEL: test_vld4_p64
return vld4_p64(ptr);
// CHECK: ld1 {{{v[0-9]+}}.1d, {{v[0-9]+}}.1d, {{v[0-9]+}}.1d, {{v[0-9]+}}.1d}, [{{x[0-9]+|sp}}]
// CHECK: ld1 {{{ *v[0-9]+.1d, v[0-9]+.1d, v[0-9]+.1d, v[0-9]+.1d *}}}, [{{x[0-9]+|sp}}]
}
poly64x2x4_t test_vld4q_p64(poly64_t const * ptr) {
// CHECK-LABEL: test_vld4q_p64
return vld4q_p64(ptr);
// CHECK: ld4 {{{v[0-9]+}}.2d, {{v[0-9]+}}.2d, {{v[0-9]+}}.2d, {{v[0-9]+}}.2d}, [{{x[0-9]+|sp}}]
// CHECK: ld4 {{{ *v[0-9]+.2d, v[0-9]+.2d, v[0-9]+.2d, v[0-9]+.2d *}}}, [{{x[0-9]+|sp}}]
}
void test_vst2_p64(poly64_t * ptr, poly64x1x2_t val) {
// CHECK-LABEL: test_vst2_p64
return vst2_p64(ptr, val);
// CHECK: st1 {{{v[0-9]+}}.1d, {{v[0-9]+}}.1d}, [{{x[0-9]+|sp}}]
// CHECK: st1 {{{ *v[0-9]+.1d, v[0-9]+.1d *}}}, [{{x[0-9]+|sp}}]
}
void test_vst2q_p64(poly64_t * ptr, poly64x2x2_t val) {
// CHECK-LABEL: test_vst2q_p64
return vst2q_p64(ptr, val);
// CHECK: st2 {{{v[0-9]+}}.2d, {{v[0-9]+}}.2d}, [{{x[0-9]+|sp}}]
// CHECK: st2 {{{ *v[0-9]+.2d, v[0-9]+.2d *}}}, [{{x[0-9]+|sp}}]
}
void test_vst3_p64(poly64_t * ptr, poly64x1x3_t val) {
// CHECK-LABEL: test_vst3_p64
return vst3_p64(ptr, val);
// CHECK: st1 {{{v[0-9]+}}.1d, {{v[0-9]+}}.1d, {{v[0-9]+}}.1d}, [{{x[0-9]+|sp}}]
// CHECK: st1 {{{ *v[0-9]+.1d, v[0-9]+.1d, v[0-9]+.1d *}}}, [{{x[0-9]+|sp}}]
}
void test_vst3q_p64(poly64_t * ptr, poly64x2x3_t val) {
// CHECK-LABEL: test_vst3q_p64
return vst3q_p64(ptr, val);
// CHECK: st3 {{{v[0-9]+}}.2d, {{v[0-9]+}}.2d, {{v[0-9]+}}.2d}, [{{x[0-9]+|sp}}]
// CHECK: st3 {{{ *v[0-9]+.2d, v[0-9]+.2d, v[0-9]+.2d *}}}, [{{x[0-9]+|sp}}]
}
void test_vst4_p64(poly64_t * ptr, poly64x1x4_t val) {
// CHECK-LABEL: test_vst4_p64
return vst4_p64(ptr, val);
// CHECK: st1 {{{v[0-9]+}}.1d, {{v[0-9]+}}.1d, {{v[0-9]+}}.1d, {{v[0-9]+}}.1d}, [{{x[0-9]+|sp}}]
// CHECK: st1 {{{ *v[0-9]+.1d, v[0-9]+.1d, v[0-9]+.1d, v[0-9]+.1d *}}}, [{{x[0-9]+|sp}}]
}
void test_vst4q_p64(poly64_t * ptr, poly64x2x4_t val) {
// CHECK-LABEL: test_vst4q_p64
return vst4q_p64(ptr, val);
// CHECK: st4 {{{v[0-9]+}}.2d, {{v[0-9]+}}.2d, {{v[0-9]+}}.2d, {{v[0-9]+}}.2d}, [{{x[0-9]+|sp}}]
// CHECK: st4 {{{ *v[0-9]+.2d, v[0-9]+.2d, v[0-9]+.2d, v[0-9]+.2d *}}}, [{{x[0-9]+|sp}}]
}
poly64x1_t test_vext_p64(poly64x1_t a, poly64x1_t b) {
@ -230,43 +241,49 @@ poly64x1_t test_vext_p64(poly64x1_t a, poly64x1_t b) {
poly64x2_t test_vextq_p64(poly64x2_t a, poly64x2_t b) {
// CHECK-LABEL: test_vextq_p64
return vextq_p64(a, b, 1);
// CHECK: ext {{v[0-9]+}}.16b, {{v[0-9]+}}.16b, {{v[0-9]+}}.16b, #0x8
// CHECK: ext {{v[0-9]+}}.16b, {{v[0-9]+}}.16b, {{v[0-9]+}}.16b, {{#0x8|#8}}
}
poly64x2_t test_vzip1q_p64(poly64x2_t a, poly64x2_t b) {
// CHECK-LABEL: test_vzip1q_p64
return vzip1q_p64(a, b);
// CHECK: ins {{v[0-9]+}}.d[1], {{v[0-9]+}}.d[0]
// CHECK-AARCH64: ins {{v[0-9]+}}.d[1], {{v[0-9]+}}.d[0]
// CHECK-ARM64: zip1 {{v[0-9]+}}.2d, {{v[0-9]+}}.2d, {{v[0-9]+}}.2d
}
poly64x2_t test_vzip2q_p64(poly64x2_t a, poly64x2_t b) {
// CHECK-LABEL: test_vzip2q_p64
return vzip2q_u64(a, b);
// CHECK: ins {{v[0-9]+}}.d[0], {{v[0-9]+}}.d[1]
// CHECK-AARCH64: ins {{v[0-9]+}}.d[0], {{v[0-9]+}}.d[1]
// CHECK-ARM64: zip2 {{v[0-9]+}}.2d, {{v[0-9]+}}.2d, {{v[0-9]+}}.2d
}
poly64x2_t test_vuzp1q_p64(poly64x2_t a, poly64x2_t b) {
// CHECK-LABEL: test_vuzp1q_p64
return vuzp1q_p64(a, b);
// CHECK: ins {{v[0-9]+}}.d[1], {{v[0-9]+}}.d[0]
// CHECK-AARCH64: ins {{v[0-9]+}}.d[1], {{v[0-9]+}}.d[0]
// CHECK-ARM64: zip1 {{v[0-9]+}}.2d, {{v[0-9]+}}.2d, {{v[0-9]+}}.2d
}
poly64x2_t test_vuzp2q_p64(poly64x2_t a, poly64x2_t b) {
// CHECK-LABEL: test_vuzp2q_p64
return vuzp2q_u64(a, b);
// CHECK: ins {{v[0-9]+}}.d[0], {{v[0-9]+}}.d[1]
// CHECK-AARCH64: ins {{v[0-9]+}}.d[0], {{v[0-9]+}}.d[1]
// CHECK-ARM64: zip2 {{v[0-9]+}}.2d, {{v[0-9]+}}.2d, {{v[0-9]+}}.2d
}
poly64x2_t test_vtrn1q_p64(poly64x2_t a, poly64x2_t b) {
// CHECK-LABEL: test_vtrn1q_p64
return vtrn1q_p64(a, b);
// CHECK: ins {{v[0-9]+}}.d[1], {{v[0-9]+}}.d[0]
// CHECK-AARCH64: ins {{v[0-9]+}}.d[1], {{v[0-9]+}}.d[0]
// CHECK-ARM64: zip1 {{v[0-9]+}}.2d, {{v[0-9]+}}.2d, {{v[0-9]+}}.2d
}
poly64x2_t test_vtrn2q_p64(poly64x2_t a, poly64x2_t b) {
// CHECK-LABEL: test_vtrn2q_p64
return vtrn2q_u64(a, b);
// CHECK: ins {{v[0-9]+}}.d[0], {{v[0-9]+}}.d[1]
// CHECK-AARCH64: ins {{v[0-9]+}}.d[0], {{v[0-9]+}}.d[1]
// CHECK-ARM64: zip2 {{v[0-9]+}}.2d, {{v[0-9]+}}.2d, {{v[0-9]+}}.2d
}
poly64x1_t test_vsri_n_p64(poly64x1_t a, poly64x1_t b) {