diff options
author | Arnold Schwaighofer <aschwaighofer@apple.com> | 2013-04-04 23:26:21 +0000 |
---|---|---|
committer | Arnold Schwaighofer <aschwaighofer@apple.com> | 2013-04-04 23:26:21 +0000 |
commit | b977387112a6b89fa5ad987016194542377cdc99 (patch) | |
tree | c1f2453e80639afaffe147824826304139fbdfce /llvm/lib/CodeGen/BasicTargetTransformInfo.cpp | |
parent | bdcb4464e2bc50cc24fd5d81018c1f7ab4695f1b (diff) | |
download | bcm5719-llvm-b977387112a6b89fa5ad987016194542377cdc99.tar.gz bcm5719-llvm-b977387112a6b89fa5ad987016194542377cdc99.zip |
CostModel: Add parameter to instruction cost to further classify operand values
On certain architectures we can support efficient vectorized version of
instructions if the operand value is uniform (splat) or a constant scalar.
An example of this is a vector shift on x86.
We can efficiently support
for (i = 0 ; i < ; i += 4)
w[0:3] = v[0:3] << <2, 2, 2, 2>
but not
for (i = 0; i < ; i += 4)
w[0:3] = v[0:3] << x[0:3]
This patch adds a parameter to getArithmeticInstrCost to further qualify operand
values as uniform or uniform constant.
Targets can then choose to return a different cost for instructions with such
operand values.
A follow-up commit will test this feature on x86.
radar://13576547
llvm-svn: 178807
Diffstat (limited to 'llvm/lib/CodeGen/BasicTargetTransformInfo.cpp')
-rw-r--r-- | llvm/lib/CodeGen/BasicTargetTransformInfo.cpp | 8 |
1 files changed, 6 insertions, 2 deletions
diff --git a/llvm/lib/CodeGen/BasicTargetTransformInfo.cpp b/llvm/lib/CodeGen/BasicTargetTransformInfo.cpp index 4cd1b80dc0b..012ff8ad833 100644 --- a/llvm/lib/CodeGen/BasicTargetTransformInfo.cpp +++ b/llvm/lib/CodeGen/BasicTargetTransformInfo.cpp @@ -85,7 +85,9 @@ public: virtual unsigned getNumberOfRegisters(bool Vector) const; virtual unsigned getMaximumUnrollFactor() const; virtual unsigned getRegisterBitWidth(bool Vector) const; - virtual unsigned getArithmeticInstrCost(unsigned Opcode, Type *Ty) const; + virtual unsigned getArithmeticInstrCost(unsigned Opcode, Type *Ty, + OperandValueKind, + OperandValueKind) const; virtual unsigned getShuffleCost(ShuffleKind Kind, Type *Tp, int Index, Type *SubTp) const; virtual unsigned getCastInstrCost(unsigned Opcode, Type *Dst, @@ -193,7 +195,9 @@ unsigned BasicTTI::getMaximumUnrollFactor() const { return 1; } -unsigned BasicTTI::getArithmeticInstrCost(unsigned Opcode, Type *Ty) const { +unsigned BasicTTI::getArithmeticInstrCost(unsigned Opcode, Type *Ty, + OperandValueKind, + OperandValueKind) const { // Check if any of the operands are vector operands. int ISD = TLI->InstructionOpcodeToISD(Opcode); assert(ISD && "Invalid opcode"); |