postaloc.cpp revision 0
/*
* Copyright 1998-2007 Sun Microsystems, Inc. All Rights Reserved.
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
*
* under the terms of the GNU General Public License version 2 only, as
* published by the Free Software Foundation.
*
* This code is distributed in the hope that it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
* version 2 for more details (a copy is included in the LICENSE file that
* accompanied this code).
*
* You should have received a copy of the GNU General Public License version
* 2 along with this work; if not, write to the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
*
* Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa Clara,
* CA 95054 USA or visit www.sun.com if you need additional information or
* have any questions.
*
*/
#include "incls/_precompiled.incl"
#include "incls/_postaloc.cpp.incl"
// see if this register kind does not requires two registers
static bool is_single_register(uint x) {
#ifdef _LP64
#else
#endif
}
//------------------------------may_be_copy_of_callee-----------------------------
// Check to see if we can possibly be a copy of a callee-save value.
// Short circuit if there are no callee save registers
if (_matcher.number_of_saved_registers() == 0) return false;
// Expect only a spill-down and reload on exit for callee-save spills.
// Chains of copies cannot be deep.
// 5008997 - This is wishful thinking. Register allocator seems to
// be splitting live ranges for callee save registers to such
// an extent that in large methods the chains can be very long
// (50+). The conservative answer is to return true if we don't
// know as this prevents optimizations from occuring.
const int limit = 60;
int i;
for( i=0; i < limit; i++ ) {
return true; // Direct use of callee-save proj
else
break;
}
// If we reached the end and didn't find a callee save proj
// then this may be a callee save proj so we return true
// as the conservative answer. If we didn't reach then end
// we must have discovered that it was not a callee save
// else we would have returned.
return i == limit;
}
//------------------------------yank_if_dead-----------------------------------
// Removed an edge from 'old'. Yank if dead. Return adjustment counts to
// iterators in the current block.
int PhaseChaitin::yank_if_dead( Node *old, Block *current_block, Node_List *value, Node_List *regnd ) {
int blk_adjust=0;
// Count 1 if deleting an instruction from the current block
}
if( !tmp ) break;
}
return blk_adjust;
}
//------------------------------use_prior_register-----------------------------
// Use the prior value instead of the current value, in an effort to make
// the current value go dead. Return block iterator adjustment, in case
// we yank some instructions from this block.
int PhaseChaitin::use_prior_register( Node *n, uint idx, Node *def, Block *current_block, Node_List &value, Node_List ®nd ) {
// No effect?
// Def is currently dead and can be removed? Do not resurrect
// Not every pair of physical registers are assignment compatible,
// e.g. on sparc floating point registers are not assignable to integer
// registers.
: (use_mask.is_AllStack() != 0));
// Check for a copy to or from a misaligned pair.
if (!can_use)
return 0;
// Capture the old def in case it goes dead...
// Save-on-call copies can only be elided if the entire copy chain can go
// away, lest we get the same callee-save value alive in 2 locations at
// once. We check for the obvious trivial case here. Although it can
// sometimes be elided with cooperation outside our scope, here we will just
// miss the opportunity. :-(
if( may_be_copy_of_callee(def) ) {
if( !idx2 ) return 0; // Not a chain of 2 copies
}
// Use the new def
_post_alloc++;
// Is old def now dead? We successfully yanked a copy?
}
//------------------------------skip_copies------------------------------------
// Skip through any number of copies (that don't mod oop-i-ness)
while (idx != 0) {
break; // casting copy, not the same value
}
return c;
}
//------------------------------elide_copy-------------------------------------
// Remove (bypass) copies along Node n, edge k.
int PhaseChaitin::elide_copy( Node *n, int k, Block *current_block, Node_List &value, Node_List ®nd, bool can_change_regs ) {
int blk_adjust = 0;
// Remove obvious same-register copies
int idx;
x = copy; // Progress, try again
}
// Phis and 2-address instructions cannot change registers so easily - their
// outputs must match their input.
if( !can_change_regs )
return blk_adjust; // Only check stupid copies!
// Loop backedges won't have a value-mapping yet
// Skip through all copies to the _value_ being used. Do not change from
// int to pointer. This attempts to jump through a chain of copies, where
// intermediate copies might be illegal, i.e., value is stored down to stack
// then reloaded BUT survives in a register the whole way.
// See if it happens to already be in the correct register!
// (either Phi's direct register, or the common case of the name
// never-clobbered original-def register)
// Doubles check both halves
return blk_adjust;
}
// See if we can skip the copy by changing registers. Don't change from
// using a register to using the stack unless we know we can remove a
// copy-load. Otherwise we might end up making a pile of Intel cisc-spill
// ops reading from memory instead of just loading once and using the
// register.
// Also handle duplicate copies here.
// Scan all registers to see if this value is around already
if( !single ) { // Doubles check for aligned-adjacent pair
}
return blk_adjust;
} // End of if not degrading to a stack
} // End of if found value in another register
} // End of scan all machine registers
return blk_adjust;
}
//
// Check if nreg already contains the constant value val. Normal copy
// elimination doesn't doesn't work on constants because multiple
// nodes can represent the same constant so the type and rule of the
// MachNode must be checked to ensure equivalence.
//
// This code assumes that two MachNodes representing constants
// which have the same rule and the same bottom type will produce
// identical effects into a register. This seems like it must be
// objectively true unless there are hidden inputs to the nodes
// but if that were to change this code would need to updated.
// Since they are equivalent the second one if redundant and can
// be removed.
//
// val will be replaced with the old value but val might have
// kills projections associated with it so remove them now so that
// yank_if_dead will be able to elminate the copy once the uses
// have been transferred to the old[value].
// Kill projections have no users and one input
--i; --imax;
}
}
_post_alloc++;
return true;
}
return false;
}
//------------------------------post_allocate_copy_removal---------------------
// Post-Allocation peephole copy removal. We do this in 1 pass over the
// basic blocks. We maintain a mapping of registers to Nodes (an array of
// Nodes indexed by machine register or stack slot number). NULL means that a
// register is not mapped to any Node. We can (want to have!) have several
// registers map to the same Node. We walk forward over the instructions
// updating the mapping as we go. At merge points we force a NULL if we have
// to merge 2 different Nodes into the same register. Phi functions will give
// us a new Node if there is a proper value merging. Since the blocks are
// arranged in some RPO, we will visit all parent blocks before visiting any
// successor blocks (except at loops).
//
// If we find a Copy we look to see if the Copy's source register is a stack
// slot and that value has already been loaded into some machine register; if
// so we use machine register directly. This turns a Load into a reg-reg
// Move. We also look for reloads of identical constants.
//
// When we see a use from a reg-reg Copy, we will attempt to use the copy's
// source directly and make the copy go dead.
void PhaseChaitin::post_allocate_copy_removal() {
NOT_PRODUCT( Compile::TracePhase t3("postAllocCopyRemoval", &_t_postAllocCopyRemoval, TimeCompiler); )
// Need a mapping from basic block Node_Lists. We need a Node_List to
// map from register number to value-producing Node.
// Need a mapping from basic block Node_Lists. We need a Node_List to
// map from register number to register-defining Node.
// We keep unused Node_Lists on a free_list to avoid wasting
// memory.
// For all blocks
uint j;
// Count of Phis in block
break;
}
// If any predecessor has not been visited, we do not know the state
// of registers at the start. Check for this, while updating copies
// along Phi input edges
bool missing_some_inputs = false;
for( j = 1; j < b->num_preds(); j++ ) {
// Remove copies along phi edges
// See if this predecessor's mappings have been used by everybody
// who wants them. If so, free 'em.
uint k;
for( k=0; k<pb->_num_succs; k++ ) {
break; // Found a future user
}
}
} else { // This block has unvisited (loopback) inputs
missing_some_inputs = true;
}
}
// Extract Node_List mappings. If 'freed' is non-zero, we just popped
// 'freed's blocks off the list
// Set mappings as OUR mappings
// Initialize value & regnd for this block
if( missing_some_inputs ) {
// Some predecessor has not yet been visited; zap map to empty
}
} else {
if( !freed ) { // Didn't get a freebie prior block
// Must clone some data
}
}
// Merge all inputs together, setting to NULL any conflicts.
for( j = 1; j < b->num_preds(); j++ ) {
}
}
}
}
// For all Phi's
for( j = 1; j < phi_dex; j++ ) {
uint k;
// Remove copies remaining on edges. Check for junk phi.
if( phi != x && u != x ) // Found a different input
u = u ? NodeSentinel : x; // Capture unique input, or NodeSentinel for 2nd input
}
if( u != NodeSentinel ) { // Junk Phi. Remove
phi->replace_by(u);
continue;
}
// Note that if value[pidx] exists, then we merged no new values here
// and the phi is useless. This can happen even with the above phi
// removal for complex flows. I cannot keep the better known value here
// because locally the phi appears to define a new merged value. If I
// keep the better value then a copy of the phi, being unable to use the
// global flow analysis, can't "peek through" the phi to the original
// reaching value and so will act like it's defining a new value. This
// can lead to situations where some uses are from the old and some from
// the new values. Not illegal by itself but throws the over-strong
// assert in scheduling.
if( pidx ) {
}
}
}
// For all remaining instructions
if( n->outcnt() == 0 && // Dead?
n != C->top() && // (ignore TOP, it has no du info)
!n->is_Proj() ) { // fat-proj kills
continue;
}
// Improve reaching-def info. Occasionally post-alloc's liveness gives
// up (at loop backedges, because we aren't doing a full flow pass).
// The presence of a live use essentially asserts that the use's def is
// alive and well at the use (or else the allocator fubar'd). Take
// advantage of this info to set a reaching def for the use-reg.
uint k;
for( k = 1; k < n->req(); k++ ) {
if( useidx ) {
int idx; // Skip occasional useless copy
// Record other half of doubles
}
}
}
}
// Remove copies along input edges
for( k = 1; k < n->req(); k++ )
// Unallocated Nodes define no registers
if( !lidx ) continue;
// Update the register defined by this instruction
// Skip through all copies to the _value_ being defined.
// Do not change from int to pointer
if( is_single_register(n_ideal_reg) ) {
// If Node 'n' does not change the value mapped by the register,
// then 'n' is a useless copy. Do not update the register->node
// mapping so 'n' will go dead.
} else {
// Update the mapping: record new Node defined by the register
// Update mapping for defined *value*, which is the defined
// Node after skipping all copies.
}
}
} else {
// If the value occupies a register pair, record same info
// in both registers.
// Sparc occasionally has non-adjacent pairs.
// Find the actual other value
}
} else {
}
}
}
// Fat projections kill many registers
// wow, what an expensive iterator...
}
}
} // End of for all instructions in the block
} // End for all blocks
}