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

Accidentally committed some temporary changes on my branch when reverting patches. 

llvm-svn: 114936
This commit is contained in:
Bill Wendling 2010-09-28 01:28:56 +00:00
parent 5a369128f6
commit 11191f11b8
3 changed files with 75 additions and 75 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

63
clang/lib/CodeGen/CGBuiltin.cpp
View File

@ -1869,33 +1869,6 @@ Value *CodeGenFunction::EmitARMBuiltinExpr(unsigned BuiltinID,
}
}
llvm::Value *
CodeGenFunction::BuildVector(const llvm::SmallVectorImpl<llvm::Value*> &Ops) {
assert((Ops.size() & (Ops.size() - 1)) == 0 &&
"Not a power-of-two sized vector!");
bool AllConstants = true;
for (unsigned I = 0, E = Ops.size(); I != E && AllConstants; ++I)
AllConstants &= isa<Constant>(Ops[I]);
// If this is a constant vector, create a ConstantVector.
if (AllConstants) {
std::vector<Constant*> CstOps;
for (unsigned I = 0, E = Ops.size(); I != E; ++I)
CstOps.push_back(cast<Constant>(Ops[I]));
return ConstantVector::get(CstOps);
}
// Otherwise, insertelement the values to build the vector.
Value *Result =
llvm::UndefValue::get(llvm::VectorType::get(Ops[0]->getType(), Ops.size()));
for (unsigned I = 0, E = Ops.size(); I != E; ++I)
Result = Builder.CreateInsertElement(Result, Ops[I],
llvm::ConstantInt::get(llvm::Type::getInt32Ty(VMContext), I));
return Result;
}
Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID,
const CallExpr *E) {
@ -2013,11 +1986,6 @@ Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID,
llvm::Function *F = CGM.getIntrinsic(ID);
return Builder.CreateCall(F, &Ops[0], &Ops[0] + Ops.size(), name);
}
case X86::BI__builtin_ia32_vec_init_v8qi:
case X86::BI__builtin_ia32_vec_init_v4hi:
case X86::BI__builtin_ia32_vec_init_v2si:
return Builder.CreateBitCast(BuildVector(Ops),
llvm::Type::getX86_MMXTy(VMContext));
case X86::BI__builtin_ia32_cmpps: {
llvm::Function *F = CGM.getIntrinsic(Intrinsic::x86_sse_cmp_ps);
return Builder.CreateCall(F, &Ops[0], &Ops[0] + Ops.size(), "cmpps");
@ -2067,6 +2035,37 @@ Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID,
Ops[0] = Builder.CreateBitCast(Ops[0], PtrTy);
return Builder.CreateStore(Ops[1], Ops[0]);
}
case X86::BI__builtin_ia32_palignr: {
unsigned shiftVal = cast<llvm::ConstantInt>(Ops[2])->getZExtValue();
// If palignr is shifting the pair of input vectors less than 9 bytes,
// emit a shuffle instruction.
if (shiftVal <= 8) {
llvm::SmallVector<llvm::Constant*, 8> Indices;
for (unsigned i = 0; i != 8; ++i)
Indices.push_back(llvm::ConstantInt::get(Int32Ty, shiftVal + i));
Value* SV = llvm::ConstantVector::get(Indices.begin(), Indices.size());
return Builder.CreateShuffleVector(Ops[1], Ops[0], SV, "palignr");
}
// If palignr is shifting the pair of input vectors more than 8 but less
// than 16 bytes, emit a logical right shift of the destination.
if (shiftVal < 16) {
// MMX has these as 1 x i64 vectors for some odd optimization reasons.
const llvm::Type *VecTy = llvm::VectorType::get(Int64Ty, 1);
Ops[0] = Builder.CreateBitCast(Ops[0], VecTy, "cast");
Ops[1] = llvm::ConstantInt::get(VecTy, (shiftVal-8) * 8);
// create i32 constant
llvm::Function *F = CGM.getIntrinsic(Intrinsic::x86_mmx_psrl_q);
return Builder.CreateCall(F, &Ops[0], &Ops[0] + 2, "palignr");
}
// If palignr is shifting the pair of vectors more than 32 bytes, emit zero.
return llvm::Constant::getNullValue(ConvertType(E->getType()));
}
case X86::BI__builtin_ia32_palignr128: {
unsigned shiftVal = cast<llvm::ConstantInt>(Ops[2])->getZExtValue();

3
clang/lib/CodeGen/CodeGenFunction.h
View File

@ -536,9 +536,6 @@ public:
llvm::BasicBlock *getInvokeDestImpl();
// Build a vector out of the supplied Values.
llvm::Value *BuildVector(const llvm::SmallVectorImpl<llvm::Value*> &Ops);
public:
/// ObjCEHValueStack - Stack of Objective-C exception values, used for
/// rethrows.

84
clang/lib/Headers/mmintrin.h
View File

@ -43,13 +43,14 @@ _mm_empty(void)
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_cvtsi32_si64(int __i)
{
return (__m64)__builtin_ia32_vec_init_v2si(__i, 0);
return (__m64)(__v2si){__i, 0};
}
static __inline__ int __attribute__((__always_inline__, __nodebug__))
_mm_cvtsi64_si32(__m64 __m)
{
return __builtin_ia32_vec_ext_v2si((__v2si)__m, 0);
__v2si __mmx_var2 = (__v2si)__m;
return __mmx_var2[0];
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
@ -85,55 +86,59 @@ _mm_packs_pu16(__m64 __m1, __m64 __m2)
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_unpackhi_pi8(__m64 __m1, __m64 __m2)
{
return (__m64)__builtin_ia32_punpckhbw((__v8qi)__m1, (__v8qi)__m2);
return (__m64)__builtin_shufflevector((__v8qi)__m1, (__v8qi)__m2, 4, 8+4, 5,
8+5, 6, 8+6, 7, 8+7);
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_unpackhi_pi16(__m64 __m1, __m64 __m2)
{
return (__m64)__builtin_ia32_punpckhwd((__v4hi)__m1, (__v4hi)__m2);
return (__m64)__builtin_shufflevector((__v4hi)__m1, (__v4hi)__m2, 2, 4+2, 3,
4+3);
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_unpackhi_pi32(__m64 __m1, __m64 __m2)
{
return (__m64)__builtin_ia32_punpckhdq((__v2si)__m1, (__v2si)__m2);
return (__m64)__builtin_shufflevector((__v2si)__m1, (__v2si)__m2, 1, 2+1);
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_unpacklo_pi8(__m64 __m1, __m64 __m2)
{
return (__m64)__builtin_ia32_punpcklbw((__v8qi)__m1, (__v8qi)__m2);
return (__m64)__builtin_shufflevector((__v8qi)__m1, (__v8qi)__m2, 0, 8+0, 1,
8+1, 2, 8+2, 3, 8+3);
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_unpacklo_pi16(__m64 __m1, __m64 __m2)
{
return (__m64)__builtin_ia32_punpcklwd((__v4hi)__m1, (__v4hi)__m2);
return (__m64)__builtin_shufflevector((__v4hi)__m1, (__v4hi)__m2, 0, 4+0, 1,
4+1);
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_unpacklo_pi32(__m64 __m1, __m64 __m2)
{
return (__m64)__builtin_ia32_punpckldq((__v2si)__m1, (__v2si)__m2);
return (__m64)__builtin_shufflevector((__v2si)__m1, (__v2si)__m2, 0, 2+0);
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_add_pi8(__m64 __m1, __m64 __m2)
{
return (__m64)__builtin_ia32_paddb((__v8qi)__m1, (__v8qi)__m2);
return (__m64)((__v8qi)__m1 + (__v8qi)__m2);
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_add_pi16(__m64 __m1, __m64 __m2)
{
return (__m64)__builtin_ia32_paddw((__v4hi)__m1, (__v4hi)__m2);
return (__m64)((__v4hi)__m1 + (__v4hi)__m2);
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_add_pi32(__m64 __m1, __m64 __m2)
{
return (__m64)__builtin_ia32_paddd((__v2si)__m1, (__v2si)__m2);
return (__m64)((__v2si)__m1 + (__v2si)__m2);
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
@ -163,19 +168,19 @@ _mm_adds_pu16(__m64 __m1, __m64 __m2)
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_sub_pi8(__m64 __m1, __m64 __m2)
{
return (__m64)__builtin_ia32_psubb((__v8qi)__m1, (__v8qi)__m2);
return (__m64)((__v8qi)__m1 - (__v8qi)__m2);
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_sub_pi16(__m64 __m1, __m64 __m2)
{
return (__m64)__builtin_ia32_psubw((__v4hi)__m1, (__v4hi)__m2);
return (__m64)((__v4hi)__m1 - (__v4hi)__m2);
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_sub_pi32(__m64 __m1, __m64 __m2)
{
return (__m64)__builtin_ia32_psubd((__v2si)__m1, (__v2si)__m2);
return (__m64)((__v2si)__m1 - (__v2si)__m2);
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
@ -217,7 +222,7 @@ _mm_mulhi_pi16(__m64 __m1, __m64 __m2)
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_mullo_pi16(__m64 __m1, __m64 __m2)
{
return (__m64)__builtin_ia32_pmullw((__v4hi)__m1, (__v4hi)__m2);
return (__m64)((__v4hi)__m1 * (__v4hi)__m2);
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
@ -247,13 +252,13 @@ _mm_slli_pi32(__m64 __m, int __count)
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_sll_si64(__m64 __m, __m64 __count)
{
return (__m64)__builtin_ia32_psllq(__m, __count);
return __builtin_ia32_psllq(__m, __count);
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_slli_si64(__m64 __m, int __count)
{
return (__m64)__builtin_ia32_psllqi(__m, __count);
return __builtin_ia32_psllqi(__m, __count);
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
@ -313,67 +318,67 @@ _mm_srl_si64(__m64 __m, __m64 __count)
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_srli_si64(__m64 __m, int __count)
{
return (__m64)__builtin_ia32_psrlqi(__m, __count);
return __builtin_ia32_psrlqi(__m, __count);
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_and_si64(__m64 __m1, __m64 __m2)
{
return __builtin_ia32_pand(__m1, __m2);
return __m1 & __m2;
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_andnot_si64(__m64 __m1, __m64 __m2)
{
return __builtin_ia32_pandn(__m1, __m2);
return ~__m1 & __m2;
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_or_si64(__m64 __m1, __m64 __m2)
{
return __builtin_ia32_por(__m1, __m2);
return __m1 | __m2;
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_xor_si64(__m64 __m1, __m64 __m2)
{
return __builtin_ia32_pxor(__m1, __m2);
return __m1 ^ __m2;
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_cmpeq_pi8(__m64 __m1, __m64 __m2)
{
return (__m64)__builtin_ia32_pcmpeqb((__v8qi)__m1, (__v8qi)__m2);
return (__m64)((__v8qi)__m1 == (__v8qi)__m2);
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_cmpeq_pi16(__m64 __m1, __m64 __m2)
{
return (__m64)__builtin_ia32_pcmpeqw((__v4hi)__m1, (__v4hi)__m2);
return (__m64)((__v4hi)__m1 == (__v4hi)__m2);
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_cmpeq_pi32(__m64 __m1, __m64 __m2)
{
return (__m64)__builtin_ia32_pcmpeqd((__v2si)__m1, (__v2si)__m2);
return (__m64)((__v2si)__m1 == (__v2si)__m2);
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_cmpgt_pi8(__m64 __m1, __m64 __m2)
{
return (__m64)__builtin_ia32_pcmpgtb((__v8qi)__m1, (__v8qi)__m2);
return (__m64)((__v8qi)__m1 > (__v8qi)__m2);
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_cmpgt_pi16(__m64 __m1, __m64 __m2)
{
return (__m64)__builtin_ia32_pcmpgtw((__v4hi)__m1, (__v4hi)__m2);
return (__m64)((__v4hi)__m1 > (__v4hi)__m2);
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_cmpgt_pi32(__m64 __m1, __m64 __m2)
{
return (__m64)__builtin_ia32_pcmpgtd((__v2si)__m1, (__v2si)__m2);
return (__m64)((__v2si)__m1 > (__v2si)__m2);
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
@ -385,58 +390,57 @@ _mm_setzero_si64(void)
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_set_pi32(int __i1, int __i0)
{
return (__m64)__builtin_ia32_vec_init_v2si(__i0, __i1);
return (__m64)(__v2si){ __i0, __i1 };
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_set_pi16(short __s3, short __s2, short __s1, short __s0)
{
return (__m64)__builtin_ia32_vec_init_v4hi(__s0, __s1, __s2, __s3);
return (__m64)(__v4hi){ __s0, __s1, __s2, __s3 };
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_set_pi8(char __b7, char __b6, char __b5, char __b4, char __b3, char __b2,
char __b1, char __b0)
{
return (__m64)__builtin_ia32_vec_init_v8qi(__b0, __b1, __b2, __b3,
__b4, __b5, __b6, __b7);
return (__m64)(__v8qi){ __b0, __b1, __b2, __b3, __b4, __b5, __b6, __b7 };
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_set1_pi32(int __i)
{
return _mm_set_pi32(__i, __i);
return (__m64)(__v2si){ __i, __i };
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_set1_pi16(short __w)
_mm_set1_pi16(short __s)
{
return _mm_set_pi16(__w, __w, __w, __w);
return (__m64)(__v4hi){ __s, __s, __s, __s };
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_set1_pi8(char __b)
{
return _mm_set_pi8(__b, __b, __b, __b, __b, __b, __b, __b);
return (__m64)(__v8qi){ __b, __b, __b, __b, __b, __b, __b, __b };
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_setr_pi32(int __i1, int __i0)
{
return _mm_set_pi32(__i1, __i0);
return (__m64)(__v2si){ __i1, __i0 };
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_setr_pi16(short __w3, short __w2, short __w1, short __w0)
_mm_setr_pi16(short __s3, short __s2, short __s1, short __s0)
{
return _mm_set_pi16(__w3, __w2, __w1, __w0);
return (__m64)(__v4hi){ __s3, __s2, __s1, __s0 };
}
static __inline__ __m64 __attribute__((__always_inline__, __nodebug__))
_mm_setr_pi8(char __b7, char __b6, char __b5, char __b4, char __b3, char __b2,
char __b1, char __b0)
{
return _mm_set_pi8(__b7, __b6, __b5, __b4, __b3, __b2, __b1, __b0);
return (__m64)(__v8qi){ __b7, __b6, __b5, __b4, __b3, __b2, __b1, __b0 };
}