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

[SveEmitter] Add builtins for svlen 

The svlen builtins return the number of elements in a vector
and are implemented using `llvm.vscale`.

Reviewed By: efriedma

Differential Revision: https://reviews.llvm.org/D78755
This commit is contained in:
Sander de Smalen 2020-04-27 21:16:17 +01:00
parent ce7eb72a3c
commit e4872d7f08
3 changed files with 131 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
clang/include/clang/Basic/arm_sve.td
View File

@ -851,6 +851,8 @@ def SVCNTH : SInst<"svcnth", "n", "", MergeNone, "aarch64_sve_cnth", [IsAppendSV
def SVCNTW : SInst<"svcntw", "n", "", MergeNone, "aarch64_sve_cntw", [IsAppendSVALL, IsOverloadNone]>; def SVCNTW : SInst<"svcntw", "n", "", MergeNone, "aarch64_sve_cntw", [IsAppendSVALL, IsOverloadNone]>;
def SVCNTD : SInst<"svcntd", "n", "", MergeNone, "aarch64_sve_cntd", [IsAppendSVALL, IsOverloadNone]>; def SVCNTD : SInst<"svcntd", "n", "", MergeNone, "aarch64_sve_cntd", [IsAppendSVALL, IsOverloadNone]>;
def SVLEN : SInst<"svlen[_{d}]", "nd", "csilUcUsUiUlhfd", MergeNone>;
//////////////////////////////////////////////////////////////////////////////// ////////////////////////////////////////////////////////////////////////////////
// Saturating scalar arithmetic // Saturating scalar arithmetic

19
clang/lib/CodeGen/CGBuiltin.cpp
View File

@ -7956,6 +7956,25 @@ Value *CodeGenFunction::EmitAArch64SVEBuiltinExpr(unsigned BuiltinID,
return nullptr; return nullptr;
case SVE::BI__builtin_sve_svpfalse_b: case SVE::BI__builtin_sve_svpfalse_b:
return ConstantInt::getFalse(Ty); return ConstantInt::getFalse(Ty);
case SVE::BI__builtin_sve_svlen_f16:
case SVE::BI__builtin_sve_svlen_f32:
case SVE::BI__builtin_sve_svlen_f64:
case SVE::BI__builtin_sve_svlen_s8:
case SVE::BI__builtin_sve_svlen_s16:
case SVE::BI__builtin_sve_svlen_s32:
case SVE::BI__builtin_sve_svlen_s64:
case SVE::BI__builtin_sve_svlen_u8:
case SVE::BI__builtin_sve_svlen_u16:
case SVE::BI__builtin_sve_svlen_u32:
case SVE::BI__builtin_sve_svlen_u64: {
SVETypeFlags TF(Builtin->TypeModifier);
auto VTy = cast<llvm::VectorType>(getSVEType(TF));
auto NumEls = llvm::ConstantInt::get(Ty, VTy->getElementCount().Min);
Function *F = CGM.getIntrinsic(Intrinsic::vscale, Ty);
return Builder.CreateMul(NumEls, Builder.CreateCall(F));
}
} }
/// Should not happen /// Should not happen

110
clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_len.c Normal file
View File

@ -0,0 +1,110 @@
// RUN: %clang_cc1 -D__ARM_FEATURE_SVE -triple aarch64-none-linux-gnu -target-feature +sve -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -D__ARM_FEATURE_SVE -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +sve -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
#include <arm_sve.h>
#ifdef SVE_OVERLOADED_FORMS
// A simple used,unused... macro, long enough to represent any SVE builtin.
#define SVE_ACLE_FUNC(A1,A2_UNUSED,A3,A4_UNUSED) A1##A3
#else
#define SVE_ACLE_FUNC(A1,A2,A3,A4) A1##A2##A3##A4
#endif
uint64_t test_svlen_s8(svint8_t op)
{
// CHECK-LABEL: test_svlen_s8
// CHECK: %[[VSCALE:.*]] = call i64 @llvm.vscale.i64()
// CHECK: %[[SHL:.*]] = shl i64 %[[VSCALE]], 4
// CHECK: ret i64 %[[SHL]]
return SVE_ACLE_FUNC(svlen,_s8,,)(op);
}
uint64_t test_svlen_s16(svint16_t op)
{
// CHECK-LABEL: test_svlen_s16
// CHECK: %[[VSCALE:.*]] = call i64 @llvm.vscale.i64()
// CHECK: %[[SHL:.*]] = shl i64 %[[VSCALE]], 3
// CHECK: ret i64 %[[SHL]]
return SVE_ACLE_FUNC(svlen,_s16,,)(op);
}
uint64_t test_svlen_s32(svint32_t op)
{
// CHECK-LABEL: test_svlen_s32
// CHECK: %[[VSCALE:.*]] = call i64 @llvm.vscale.i64()
// CHECK: %[[SHL:.*]] = shl i64 %[[VSCALE]], 2
// CHECK: ret i64 %[[SHL]]
return SVE_ACLE_FUNC(svlen,_s32,,)(op);
}
uint64_t test_svlen_s64(svint64_t op)
{
// CHECK-LABEL: test_svlen_s64
// CHECK: %[[VSCALE:.*]] = call i64 @llvm.vscale.i64()
// CHECK: %[[SHL:.*]] = shl i64 %[[VSCALE]], 1
// CHECK: ret i64 %[[SHL]]
return SVE_ACLE_FUNC(svlen,_s64,,)(op);
}
uint64_t test_svlen_u8(svuint8_t op)
{
// CHECK-LABEL: test_svlen_u8
// CHECK: %[[VSCALE:.*]] = call i64 @llvm.vscale.i64()
// CHECK: %[[SHL:.*]] = shl i64 %[[VSCALE]], 4
// CHECK: ret i64 %[[SHL]]
return SVE_ACLE_FUNC(svlen,_u8,,)(op);
}
uint64_t test_svlen_u16(svuint16_t op)
{
// CHECK-LABEL: test_svlen_u16
// CHECK: %[[VSCALE:.*]] = call i64 @llvm.vscale.i64()
// CHECK: %[[SHL:.*]] = shl i64 %[[VSCALE]], 3
// CHECK: ret i64 %[[SHL]]
return SVE_ACLE_FUNC(svlen,_u16,,)(op);
}
uint64_t test_svlen_u32(svuint32_t op)
{
// CHECK-LABEL: test_svlen_u32
// CHECK: %[[VSCALE:.*]] = call i64 @llvm.vscale.i64()
// CHECK: %[[SHL:.*]] = shl i64 %[[VSCALE]], 2
// CHECK: ret i64 %[[SHL]]
return SVE_ACLE_FUNC(svlen,_u32,,)(op);
}
uint64_t test_svlen_u64(svuint64_t op)
{
// CHECK-LABEL: test_svlen_u64
// CHECK: %[[VSCALE:.*]] = call i64 @llvm.vscale.i64()
// CHECK: %[[SHL:.*]] = shl i64 %[[VSCALE]], 1
// CHECK: ret i64 %[[SHL]]
return SVE_ACLE_FUNC(svlen,_u64,,)(op);
}
uint64_t test_svlen_f16(svfloat16_t op)
{
// CHECK-LABEL: test_svlen_f16
// CHECK: %[[VSCALE:.*]] = call i64 @llvm.vscale.i64()
// CHECK: %[[SHL:.*]] = shl i64 %[[VSCALE]], 3
// CHECK: ret i64 %[[SHL]]
return SVE_ACLE_FUNC(svlen,_f16,,)(op);
}
uint64_t test_svlen_f32(svfloat32_t op)
{
// CHECK-LABEL: test_svlen_f32
// CHECK: %[[VSCALE:.*]] = call i64 @llvm.vscale.i64()
// CHECK: %[[SHL:.*]] = shl i64 %[[VSCALE]], 2
// CHECK: ret i64 %[[SHL]]
return SVE_ACLE_FUNC(svlen,_f32,,)(op);
}
uint64_t test_svlen_f64(svfloat64_t op)
{
// CHECK-LABEL: test_svlen_f64
// CHECK: %[[VSCALE:.*]] = call i64 @llvm.vscale.i64()
// CHECK: %[[SHL:.*]] = shl i64 %[[VSCALE]], 1
// CHECK: ret i64 %[[SHL]]
return SVE_ACLE_FUNC(svlen,_f64,,)(op);
}