1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-20 03:23:01 +02:00
llvm-mirror/include/llvm/Target/TargetFrameLowering.h

331 lines
14 KiB
C
Raw Normal View History

//===-- llvm/Target/TargetFrameLowering.h ---------------------------*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// Interface to describe the layout of a stack frame on the target machine.
//
//===----------------------------------------------------------------------===//
#ifndef LLVM_TARGET_TARGETFRAMELOWERING_H
#define LLVM_TARGET_TARGETFRAMELOWERING_H
#include "llvm/CodeGen/MachineBasicBlock.h"
#include <utility>
#include <vector>
namespace llvm {
class BitVector;
class CalleeSavedInfo;
class MachineFunction;
class RegScavenger;
/// Information about stack frame layout on the target. It holds the direction
/// of stack growth, the known stack alignment on entry to each function, and
/// the offset to the locals area.
///
/// The offset to the local area is the offset from the stack pointer on
/// function entry to the first location where function data (local variables,
/// spill locations) can be stored.
class TargetFrameLowering {
public:
enum StackDirection {
StackGrowsUp, // Adding to the stack increases the stack address
StackGrowsDown // Adding to the stack decreases the stack address
};
// Maps a callee saved register to a stack slot with a fixed offset.
struct SpillSlot {
unsigned Reg;
int Offset; // Offset relative to stack pointer on function entry.
};
private:
StackDirection StackDir;
unsigned StackAlignment;
unsigned TransientStackAlignment;
int LocalAreaOffset;
bool StackRealignable;
public:
TargetFrameLowering(StackDirection D, unsigned StackAl, int LAO,
unsigned TransAl = 1, bool StackReal = true)
: StackDir(D), StackAlignment(StackAl), TransientStackAlignment(TransAl),
LocalAreaOffset(LAO), StackRealignable(StackReal) {}
virtual ~TargetFrameLowering();
// These methods return information that describes the abstract stack layout
// of the target machine.
/// getStackGrowthDirection - Return the direction the stack grows
///
StackDirection getStackGrowthDirection() const { return StackDir; }
/// getStackAlignment - This method returns the number of bytes to which the
/// stack pointer must be aligned on entry to a function. Typically, this
/// is the largest alignment for any data object in the target.
///
unsigned getStackAlignment() const { return StackAlignment; }
/// alignSPAdjust - This method aligns the stack adjustment to the correct
/// alignment.
///
int alignSPAdjust(int SPAdj) const {
if (SPAdj < 0) {
SPAdj = -alignTo(-SPAdj, StackAlignment);
} else {
SPAdj = alignTo(SPAdj, StackAlignment);
}
return SPAdj;
}
/// getTransientStackAlignment - This method returns the number of bytes to
/// which the stack pointer must be aligned at all times, even between
/// calls.
///
unsigned getTransientStackAlignment() const {
return TransientStackAlignment;
}
/// isStackRealignable - This method returns whether the stack can be
/// realigned.
bool isStackRealignable() const {
return StackRealignable;
}
/// Return the skew that has to be applied to stack alignment under
/// certain conditions (e.g. stack was adjusted before function \p MF
/// was called).
virtual unsigned getStackAlignmentSkew(const MachineFunction &MF) const;
/// getOffsetOfLocalArea - This method returns the offset of the local area
/// from the stack pointer on entrance to a function.
///
int getOffsetOfLocalArea() const { return LocalAreaOffset; }
/// isFPCloseToIncomingSP - Return true if the frame pointer is close to
/// the incoming stack pointer, false if it is close to the post-prologue
/// stack pointer.
virtual bool isFPCloseToIncomingSP() const { return true; }
/// assignCalleeSavedSpillSlots - Allows target to override spill slot
/// assignment logic. If implemented, assignCalleeSavedSpillSlots() should
/// assign frame slots to all CSI entries and return true. If this method
/// returns false, spill slots will be assigned using generic implementation.
/// assignCalleeSavedSpillSlots() may add, delete or rearrange elements of
/// CSI.
virtual bool
assignCalleeSavedSpillSlots(MachineFunction &MF,
const TargetRegisterInfo *TRI,
std::vector<CalleeSavedInfo> &CSI) const {
return false;
}
/// getCalleeSavedSpillSlots - This method returns a pointer to an array of
/// pairs, that contains an entry for each callee saved register that must be
/// spilled to a particular stack location if it is spilled.
///
/// Each entry in this array contains a <register,offset> pair, indicating the
/// fixed offset from the incoming stack pointer that each register should be
/// spilled at. If a register is not listed here, the code generator is
/// allowed to spill it anywhere it chooses.
///
virtual const SpillSlot *
getCalleeSavedSpillSlots(unsigned &NumEntries) const {
NumEntries = 0;
return nullptr;
}
/// targetHandlesStackFrameRounding - Returns true if the target is
/// responsible for rounding up the stack frame (probably at emitPrologue
/// time).
virtual bool targetHandlesStackFrameRounding() const {
return false;
}
/// Returns true if the target will correctly handle shrink wrapping.
virtual bool enableShrinkWrapping(const MachineFunction &MF) const {
return false;
}
2015-10-05 06:43:48 +02:00
/// emitProlog/emitEpilog - These methods insert prolog and epilog code into
/// the function.
[ShrinkWrap] Add (a simplified version) of shrink-wrapping. This patch introduces a new pass that computes the safe point to insert the prologue and epilogue of the function. The interest is to find safe points that are cheaper than the entry and exits blocks. As an example and to avoid regressions to be introduce, this patch also implements the required bits to enable the shrink-wrapping pass for AArch64. ** Context ** Currently we insert the prologue and epilogue of the method/function in the entry and exits blocks. Although this is correct, we can do a better job when those are not immediately required and insert them at less frequently executed places. The job of the shrink-wrapping pass is to identify such places. ** Motivating example ** Let us consider the following function that perform a call only in one branch of a if: define i32 @f(i32 %a, i32 %b) { %tmp = alloca i32, align 4 %tmp2 = icmp slt i32 %a, %b br i1 %tmp2, label %true, label %false true: store i32 %a, i32* %tmp, align 4 %tmp4 = call i32 @doSomething(i32 0, i32* %tmp) br label %false false: %tmp.0 = phi i32 [ %tmp4, %true ], [ %a, %0 ] ret i32 %tmp.0 } On AArch64 this code generates (removing the cfi directives to ease readabilities): _f: ; @f ; BB#0: stp x29, x30, [sp, #-16]! mov x29, sp sub sp, sp, #16 ; =16 cmp w0, w1 b.ge LBB0_2 ; BB#1: ; %true stur w0, [x29, #-4] sub x1, x29, #4 ; =4 mov w0, wzr bl _doSomething LBB0_2: ; %false mov sp, x29 ldp x29, x30, [sp], #16 ret With shrink-wrapping we could generate: _f: ; @f ; BB#0: cmp w0, w1 b.ge LBB0_2 ; BB#1: ; %true stp x29, x30, [sp, #-16]! mov x29, sp sub sp, sp, #16 ; =16 stur w0, [x29, #-4] sub x1, x29, #4 ; =4 mov w0, wzr bl _doSomething add sp, x29, #16 ; =16 ldp x29, x30, [sp], #16 LBB0_2: ; %false ret Therefore, we would pay the overhead of setting up/destroying the frame only if we actually do the call. ** Proposed Solution ** This patch introduces a new machine pass that perform the shrink-wrapping analysis (See the comments at the beginning of ShrinkWrap.cpp for more details). It then stores the safe save and restore point into the MachineFrameInfo attached to the MachineFunction. This information is then used by the PrologEpilogInserter (PEI) to place the related code at the right place. This pass runs right before the PEI. Unlike the original paper of Chow from PLDI’88, this implementation of shrink-wrapping does not use expensive data-flow analysis and does not need hack to properly avoid frequently executed point. Instead, it relies on dominance and loop properties. The pass is off by default and each target can opt-in by setting the EnableShrinkWrap boolean to true in their derived class of TargetPassConfig. This setting can also be overwritten on the command line by using -enable-shrink-wrap. Before you try out the pass for your target, make sure you properly fix your emitProlog/emitEpilog/adjustForXXX method to cope with basic blocks that are not necessarily the entry block. ** Design Decisions ** 1. ShrinkWrap is its own pass right now. It could frankly be merged into PEI but for debugging and clarity I thought it was best to have its own file. 2. Right now, we only support one save point and one restore point. At some point we can expand this to several save point and restore point, the impacted component would then be: - The pass itself: New algorithm needed. - MachineFrameInfo: Hold a list or set of Save/Restore point instead of one pointer. - PEI: Should loop over the save point and restore point. Anyhow, at least for this first iteration, I do not believe this is interesting to support the complex cases. We should revisit that when we motivating examples. Differential Revision: http://reviews.llvm.org/D9210 <rdar://problem/3201744> llvm-svn: 236507
2015-05-05 19:38:16 +02:00
virtual void emitPrologue(MachineFunction &MF,
MachineBasicBlock &MBB) const = 0;
virtual void emitEpilogue(MachineFunction &MF,
MachineBasicBlock &MBB) const = 0;
/// Replace a StackProbe stub (if any) with the actual probe code inline
virtual void inlineStackProbe(MachineFunction &MF,
MachineBasicBlock &PrologueMBB) const {}
/// Adjust the prologue to have the function use segmented stacks. This works
/// by adding a check even before the "normal" function prologue.
[ShrinkWrap] Add (a simplified version) of shrink-wrapping. This patch introduces a new pass that computes the safe point to insert the prologue and epilogue of the function. The interest is to find safe points that are cheaper than the entry and exits blocks. As an example and to avoid regressions to be introduce, this patch also implements the required bits to enable the shrink-wrapping pass for AArch64. ** Context ** Currently we insert the prologue and epilogue of the method/function in the entry and exits blocks. Although this is correct, we can do a better job when those are not immediately required and insert them at less frequently executed places. The job of the shrink-wrapping pass is to identify such places. ** Motivating example ** Let us consider the following function that perform a call only in one branch of a if: define i32 @f(i32 %a, i32 %b) { %tmp = alloca i32, align 4 %tmp2 = icmp slt i32 %a, %b br i1 %tmp2, label %true, label %false true: store i32 %a, i32* %tmp, align 4 %tmp4 = call i32 @doSomething(i32 0, i32* %tmp) br label %false false: %tmp.0 = phi i32 [ %tmp4, %true ], [ %a, %0 ] ret i32 %tmp.0 } On AArch64 this code generates (removing the cfi directives to ease readabilities): _f: ; @f ; BB#0: stp x29, x30, [sp, #-16]! mov x29, sp sub sp, sp, #16 ; =16 cmp w0, w1 b.ge LBB0_2 ; BB#1: ; %true stur w0, [x29, #-4] sub x1, x29, #4 ; =4 mov w0, wzr bl _doSomething LBB0_2: ; %false mov sp, x29 ldp x29, x30, [sp], #16 ret With shrink-wrapping we could generate: _f: ; @f ; BB#0: cmp w0, w1 b.ge LBB0_2 ; BB#1: ; %true stp x29, x30, [sp, #-16]! mov x29, sp sub sp, sp, #16 ; =16 stur w0, [x29, #-4] sub x1, x29, #4 ; =4 mov w0, wzr bl _doSomething add sp, x29, #16 ; =16 ldp x29, x30, [sp], #16 LBB0_2: ; %false ret Therefore, we would pay the overhead of setting up/destroying the frame only if we actually do the call. ** Proposed Solution ** This patch introduces a new machine pass that perform the shrink-wrapping analysis (See the comments at the beginning of ShrinkWrap.cpp for more details). It then stores the safe save and restore point into the MachineFrameInfo attached to the MachineFunction. This information is then used by the PrologEpilogInserter (PEI) to place the related code at the right place. This pass runs right before the PEI. Unlike the original paper of Chow from PLDI’88, this implementation of shrink-wrapping does not use expensive data-flow analysis and does not need hack to properly avoid frequently executed point. Instead, it relies on dominance and loop properties. The pass is off by default and each target can opt-in by setting the EnableShrinkWrap boolean to true in their derived class of TargetPassConfig. This setting can also be overwritten on the command line by using -enable-shrink-wrap. Before you try out the pass for your target, make sure you properly fix your emitProlog/emitEpilog/adjustForXXX method to cope with basic blocks that are not necessarily the entry block. ** Design Decisions ** 1. ShrinkWrap is its own pass right now. It could frankly be merged into PEI but for debugging and clarity I thought it was best to have its own file. 2. Right now, we only support one save point and one restore point. At some point we can expand this to several save point and restore point, the impacted component would then be: - The pass itself: New algorithm needed. - MachineFrameInfo: Hold a list or set of Save/Restore point instead of one pointer. - PEI: Should loop over the save point and restore point. Anyhow, at least for this first iteration, I do not believe this is interesting to support the complex cases. We should revisit that when we motivating examples. Differential Revision: http://reviews.llvm.org/D9210 <rdar://problem/3201744> llvm-svn: 236507
2015-05-05 19:38:16 +02:00
virtual void adjustForSegmentedStacks(MachineFunction &MF,
MachineBasicBlock &PrologueMBB) const {}
/// Adjust the prologue to add Erlang Run-Time System (ERTS) specific code in
/// the assembly prologue to explicitly handle the stack.
[ShrinkWrap] Add (a simplified version) of shrink-wrapping. This patch introduces a new pass that computes the safe point to insert the prologue and epilogue of the function. The interest is to find safe points that are cheaper than the entry and exits blocks. As an example and to avoid regressions to be introduce, this patch also implements the required bits to enable the shrink-wrapping pass for AArch64. ** Context ** Currently we insert the prologue and epilogue of the method/function in the entry and exits blocks. Although this is correct, we can do a better job when those are not immediately required and insert them at less frequently executed places. The job of the shrink-wrapping pass is to identify such places. ** Motivating example ** Let us consider the following function that perform a call only in one branch of a if: define i32 @f(i32 %a, i32 %b) { %tmp = alloca i32, align 4 %tmp2 = icmp slt i32 %a, %b br i1 %tmp2, label %true, label %false true: store i32 %a, i32* %tmp, align 4 %tmp4 = call i32 @doSomething(i32 0, i32* %tmp) br label %false false: %tmp.0 = phi i32 [ %tmp4, %true ], [ %a, %0 ] ret i32 %tmp.0 } On AArch64 this code generates (removing the cfi directives to ease readabilities): _f: ; @f ; BB#0: stp x29, x30, [sp, #-16]! mov x29, sp sub sp, sp, #16 ; =16 cmp w0, w1 b.ge LBB0_2 ; BB#1: ; %true stur w0, [x29, #-4] sub x1, x29, #4 ; =4 mov w0, wzr bl _doSomething LBB0_2: ; %false mov sp, x29 ldp x29, x30, [sp], #16 ret With shrink-wrapping we could generate: _f: ; @f ; BB#0: cmp w0, w1 b.ge LBB0_2 ; BB#1: ; %true stp x29, x30, [sp, #-16]! mov x29, sp sub sp, sp, #16 ; =16 stur w0, [x29, #-4] sub x1, x29, #4 ; =4 mov w0, wzr bl _doSomething add sp, x29, #16 ; =16 ldp x29, x30, [sp], #16 LBB0_2: ; %false ret Therefore, we would pay the overhead of setting up/destroying the frame only if we actually do the call. ** Proposed Solution ** This patch introduces a new machine pass that perform the shrink-wrapping analysis (See the comments at the beginning of ShrinkWrap.cpp for more details). It then stores the safe save and restore point into the MachineFrameInfo attached to the MachineFunction. This information is then used by the PrologEpilogInserter (PEI) to place the related code at the right place. This pass runs right before the PEI. Unlike the original paper of Chow from PLDI’88, this implementation of shrink-wrapping does not use expensive data-flow analysis and does not need hack to properly avoid frequently executed point. Instead, it relies on dominance and loop properties. The pass is off by default and each target can opt-in by setting the EnableShrinkWrap boolean to true in their derived class of TargetPassConfig. This setting can also be overwritten on the command line by using -enable-shrink-wrap. Before you try out the pass for your target, make sure you properly fix your emitProlog/emitEpilog/adjustForXXX method to cope with basic blocks that are not necessarily the entry block. ** Design Decisions ** 1. ShrinkWrap is its own pass right now. It could frankly be merged into PEI but for debugging and clarity I thought it was best to have its own file. 2. Right now, we only support one save point and one restore point. At some point we can expand this to several save point and restore point, the impacted component would then be: - The pass itself: New algorithm needed. - MachineFrameInfo: Hold a list or set of Save/Restore point instead of one pointer. - PEI: Should loop over the save point and restore point. Anyhow, at least for this first iteration, I do not believe this is interesting to support the complex cases. We should revisit that when we motivating examples. Differential Revision: http://reviews.llvm.org/D9210 <rdar://problem/3201744> llvm-svn: 236507
2015-05-05 19:38:16 +02:00
virtual void adjustForHiPEPrologue(MachineFunction &MF,
MachineBasicBlock &PrologueMBB) const {}
/// Adjust the prologue to add an allocation at a fixed offset from the frame
/// pointer.
[ShrinkWrap] Add (a simplified version) of shrink-wrapping. This patch introduces a new pass that computes the safe point to insert the prologue and epilogue of the function. The interest is to find safe points that are cheaper than the entry and exits blocks. As an example and to avoid regressions to be introduce, this patch also implements the required bits to enable the shrink-wrapping pass for AArch64. ** Context ** Currently we insert the prologue and epilogue of the method/function in the entry and exits blocks. Although this is correct, we can do a better job when those are not immediately required and insert them at less frequently executed places. The job of the shrink-wrapping pass is to identify such places. ** Motivating example ** Let us consider the following function that perform a call only in one branch of a if: define i32 @f(i32 %a, i32 %b) { %tmp = alloca i32, align 4 %tmp2 = icmp slt i32 %a, %b br i1 %tmp2, label %true, label %false true: store i32 %a, i32* %tmp, align 4 %tmp4 = call i32 @doSomething(i32 0, i32* %tmp) br label %false false: %tmp.0 = phi i32 [ %tmp4, %true ], [ %a, %0 ] ret i32 %tmp.0 } On AArch64 this code generates (removing the cfi directives to ease readabilities): _f: ; @f ; BB#0: stp x29, x30, [sp, #-16]! mov x29, sp sub sp, sp, #16 ; =16 cmp w0, w1 b.ge LBB0_2 ; BB#1: ; %true stur w0, [x29, #-4] sub x1, x29, #4 ; =4 mov w0, wzr bl _doSomething LBB0_2: ; %false mov sp, x29 ldp x29, x30, [sp], #16 ret With shrink-wrapping we could generate: _f: ; @f ; BB#0: cmp w0, w1 b.ge LBB0_2 ; BB#1: ; %true stp x29, x30, [sp, #-16]! mov x29, sp sub sp, sp, #16 ; =16 stur w0, [x29, #-4] sub x1, x29, #4 ; =4 mov w0, wzr bl _doSomething add sp, x29, #16 ; =16 ldp x29, x30, [sp], #16 LBB0_2: ; %false ret Therefore, we would pay the overhead of setting up/destroying the frame only if we actually do the call. ** Proposed Solution ** This patch introduces a new machine pass that perform the shrink-wrapping analysis (See the comments at the beginning of ShrinkWrap.cpp for more details). It then stores the safe save and restore point into the MachineFrameInfo attached to the MachineFunction. This information is then used by the PrologEpilogInserter (PEI) to place the related code at the right place. This pass runs right before the PEI. Unlike the original paper of Chow from PLDI’88, this implementation of shrink-wrapping does not use expensive data-flow analysis and does not need hack to properly avoid frequently executed point. Instead, it relies on dominance and loop properties. The pass is off by default and each target can opt-in by setting the EnableShrinkWrap boolean to true in their derived class of TargetPassConfig. This setting can also be overwritten on the command line by using -enable-shrink-wrap. Before you try out the pass for your target, make sure you properly fix your emitProlog/emitEpilog/adjustForXXX method to cope with basic blocks that are not necessarily the entry block. ** Design Decisions ** 1. ShrinkWrap is its own pass right now. It could frankly be merged into PEI but for debugging and clarity I thought it was best to have its own file. 2. Right now, we only support one save point and one restore point. At some point we can expand this to several save point and restore point, the impacted component would then be: - The pass itself: New algorithm needed. - MachineFrameInfo: Hold a list or set of Save/Restore point instead of one pointer. - PEI: Should loop over the save point and restore point. Anyhow, at least for this first iteration, I do not believe this is interesting to support the complex cases. We should revisit that when we motivating examples. Differential Revision: http://reviews.llvm.org/D9210 <rdar://problem/3201744> llvm-svn: 236507
2015-05-05 19:38:16 +02:00
virtual void
adjustForFrameAllocatePrologue(MachineFunction &MF,
MachineBasicBlock &PrologueMBB) const {}
/// spillCalleeSavedRegisters - Issues instruction(s) to spill all callee
/// saved registers and returns true if it isn't possible / profitable to do
/// so by issuing a series of store instructions via
/// storeRegToStackSlot(). Returns false otherwise.
virtual bool spillCalleeSavedRegisters(MachineBasicBlock &MBB,
MachineBasicBlock::iterator MI,
const std::vector<CalleeSavedInfo> &CSI,
const TargetRegisterInfo *TRI) const {
return false;
}
/// restoreCalleeSavedRegisters - Issues instruction(s) to restore all callee
/// saved registers and returns true if it isn't possible / profitable to do
/// so by issuing a series of load instructions via loadRegToStackSlot().
/// Returns false otherwise.
virtual bool restoreCalleeSavedRegisters(MachineBasicBlock &MBB,
MachineBasicBlock::iterator MI,
const std::vector<CalleeSavedInfo> &CSI,
const TargetRegisterInfo *TRI) const {
return false;
}
/// Return true if the target needs to disable frame pointer elimination.
virtual bool noFramePointerElim(const MachineFunction &MF) const;
/// hasFP - Return true if the specified function should have a dedicated
/// frame pointer register. For most targets this is true only if the function
/// has variable sized allocas or if frame pointer elimination is disabled.
virtual bool hasFP(const MachineFunction &MF) const = 0;
/// hasReservedCallFrame - Under normal circumstances, when a frame pointer is
/// not required, we reserve argument space for call sites in the function
/// immediately on entry to the current function. This eliminates the need for
/// add/sub sp brackets around call sites. Returns true if the call frame is
/// included as part of the stack frame.
virtual bool hasReservedCallFrame(const MachineFunction &MF) const {
return !hasFP(MF);
}
/// canSimplifyCallFramePseudos - When possible, it's best to simplify the
/// call frame pseudo ops before doing frame index elimination. This is
/// possible only when frame index references between the pseudos won't
/// need adjusting for the call frame adjustments. Normally, that's true
/// if the function has a reserved call frame or a frame pointer. Some
/// targets (Thumb2, for example) may have more complicated criteria,
/// however, and can override this behavior.
virtual bool canSimplifyCallFramePseudos(const MachineFunction &MF) const {
return hasReservedCallFrame(MF) || hasFP(MF);
}
// needsFrameIndexResolution - Do we need to perform FI resolution for
// this function. Normally, this is required only when the function
// has any stack objects. However, targets may want to override this.
virtual bool needsFrameIndexResolution(const MachineFunction &MF) const;
/// getFrameIndexReference - This method should return the base register
/// and offset used to reference a frame index location. The offset is
/// returned directly, and the base register is returned via FrameReg.
virtual int getFrameIndexReference(const MachineFunction &MF, int FI,
unsigned &FrameReg) const;
[Statepoints 2/4] Statepoint infrastructure for garbage collection: MI & x86-64 Backend This is the second patch in a small series. This patch contains the MachineInstruction and x86-64 backend pieces required to lower Statepoints. It does not include the code to actually generate the STATEPOINT machine instruction and as a result, the entire patch is currently dead code. I will be submitting the SelectionDAG parts within the next 24-48 hours. Since those pieces are by far the most complicated, I wanted to minimize the size of that patch. That patch will include the tests which exercise the functionality in this patch. The entire series can be seen as one combined whole in http://reviews.llvm.org/D5683. The STATEPOINT psuedo node is generated after all gc values are explicitly spilled to stack slots. The purpose of this node is to wrap an actual call instruction while recording the spill locations of the meta arguments used for garbage collection and other purposes. The STATEPOINT is modeled as modifing all of those locations to prevent backend optimizations from forwarding the value from before the STATEPOINT to after the STATEPOINT. (Doing so would break relocation semantics for collectors which wish to relocate roots.) The implementation of STATEPOINT is closely modeled on PATCHPOINT. Eventually, much of the code in this patch will be removed. The long term plan is to merge the functionality provided by statepoints and patchpoints. Merging their implementations in the backend is likely to be a good starting point. Reviewed by: atrick, ributzka llvm-svn: 223085
2014-12-01 23:52:56 +01:00
/// Same as above, except that the 'base register' will always be RSP, not
/// RBP on x86. This is generally used for emitting statepoint or EH tables
/// that use offsets from RSP.
[Statepoints 2/4] Statepoint infrastructure for garbage collection: MI & x86-64 Backend This is the second patch in a small series. This patch contains the MachineInstruction and x86-64 backend pieces required to lower Statepoints. It does not include the code to actually generate the STATEPOINT machine instruction and as a result, the entire patch is currently dead code. I will be submitting the SelectionDAG parts within the next 24-48 hours. Since those pieces are by far the most complicated, I wanted to minimize the size of that patch. That patch will include the tests which exercise the functionality in this patch. The entire series can be seen as one combined whole in http://reviews.llvm.org/D5683. The STATEPOINT psuedo node is generated after all gc values are explicitly spilled to stack slots. The purpose of this node is to wrap an actual call instruction while recording the spill locations of the meta arguments used for garbage collection and other purposes. The STATEPOINT is modeled as modifing all of those locations to prevent backend optimizations from forwarding the value from before the STATEPOINT to after the STATEPOINT. (Doing so would break relocation semantics for collectors which wish to relocate roots.) The implementation of STATEPOINT is closely modeled on PATCHPOINT. Eventually, much of the code in this patch will be removed. The long term plan is to merge the functionality provided by statepoints and patchpoints. Merging their implementations in the backend is likely to be a good starting point. Reviewed by: atrick, ributzka llvm-svn: 223085
2014-12-01 23:52:56 +01:00
/// TODO: This should really be a parameterizable choice.
virtual int getFrameIndexReferenceFromSP(const MachineFunction &MF, int FI,
unsigned &FrameReg) const {
[Statepoints 2/4] Statepoint infrastructure for garbage collection: MI & x86-64 Backend This is the second patch in a small series. This patch contains the MachineInstruction and x86-64 backend pieces required to lower Statepoints. It does not include the code to actually generate the STATEPOINT machine instruction and as a result, the entire patch is currently dead code. I will be submitting the SelectionDAG parts within the next 24-48 hours. Since those pieces are by far the most complicated, I wanted to minimize the size of that patch. That patch will include the tests which exercise the functionality in this patch. The entire series can be seen as one combined whole in http://reviews.llvm.org/D5683. The STATEPOINT psuedo node is generated after all gc values are explicitly spilled to stack slots. The purpose of this node is to wrap an actual call instruction while recording the spill locations of the meta arguments used for garbage collection and other purposes. The STATEPOINT is modeled as modifing all of those locations to prevent backend optimizations from forwarding the value from before the STATEPOINT to after the STATEPOINT. (Doing so would break relocation semantics for collectors which wish to relocate roots.) The implementation of STATEPOINT is closely modeled on PATCHPOINT. Eventually, much of the code in this patch will be removed. The long term plan is to merge the functionality provided by statepoints and patchpoints. Merging their implementations in the backend is likely to be a good starting point. Reviewed by: atrick, ributzka llvm-svn: 223085
2014-12-01 23:52:56 +01:00
// default to calling normal version, we override this on x86 only
llvm_unreachable("unimplemented for non-x86");
return 0;
}
/// This method determines which of the registers reported by
/// TargetRegisterInfo::getCalleeSavedRegs() should actually get saved.
/// The default implementation checks populates the \p SavedRegs bitset with
/// all registers which are modified in the function, targets may override
/// this function to save additional registers.
/// This method also sets up the register scavenger ensuring there is a free
/// register or a frameindex available.
virtual void determineCalleeSaves(MachineFunction &MF, BitVector &SavedRegs,
RegScavenger *RS = nullptr) const;
/// processFunctionBeforeFrameFinalized - This method is called immediately
/// before the specified function's frame layout (MF.getFrameInfo()) is
/// finalized. Once the frame is finalized, MO_FrameIndex operands are
/// replaced with direct constants. This method is optional.
///
virtual void processFunctionBeforeFrameFinalized(MachineFunction &MF,
RegScavenger *RS = nullptr) const {
}
virtual unsigned getWinEHParentFrameOffset(const MachineFunction &MF) const {
report_fatal_error("WinEH not implemented for this target");
}
/// eliminateCallFramePseudoInstr - This method is called during prolog/epilog
/// code insertion to eliminate call frame setup and destroy pseudo
/// instructions (but only if the Target is using them). It is responsible
/// for eliminating these instructions, replacing them with concrete
/// instructions. This method need only be implemented if using call frame
/// setup/destroy pseudo instructions.
///
virtual void
eliminateCallFramePseudoInstr(MachineFunction &MF,
MachineBasicBlock &MBB,
MachineBasicBlock::iterator MI) const {
llvm_unreachable("Call Frame Pseudo Instructions do not exist on this "
"target!");
}
/// Order the symbols in the local stack frame.
/// The list of objects that we want to order is in \p objectsToAllocate as
/// indices into the MachineFrameInfo. The array can be reordered in any way
/// upon return. The contents of the array, however, may not be modified (i.e.
/// only their order may be changed).
/// By default, just maintain the original order.
virtual void
orderFrameObjects(const MachineFunction &MF,
SmallVectorImpl<int> &objectsToAllocate) const {
}
/// Check whether or not the given \p MBB can be used as a prologue
/// for the target.
/// The prologue will be inserted first in this basic block.
/// This method is used by the shrink-wrapping pass to decide if
/// \p MBB will be correctly handled by the target.
/// As soon as the target enable shrink-wrapping without overriding
/// this method, we assume that each basic block is a valid
/// prologue.
virtual bool canUseAsPrologue(const MachineBasicBlock &MBB) const {
return true;
}
/// Check whether or not the given \p MBB can be used as a epilogue
/// for the target.
/// The epilogue will be inserted before the first terminator of that block.
/// This method is used by the shrink-wrapping pass to decide if
/// \p MBB will be correctly handled by the target.
/// As soon as the target enable shrink-wrapping without overriding
/// this method, we assume that each basic block is a valid
/// epilogue.
virtual bool canUseAsEpilogue(const MachineBasicBlock &MBB) const {
return true;
}
};
} // End llvm namespace
#endif