output.hpp revision 1879
1879N/A * Copyright (c) 2000, 2010, Oracle and/or its affiliates. All rights reserved. 0N/A * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. 0N/A * This code is free software; you can redistribute it and/or modify it 0N/A * under the terms of the GNU General Public License version 2 only, as 0N/A * published by the Free Software Foundation. 0N/A * This code is distributed in the hope that it will be useful, but WITHOUT 0N/A * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or 0N/A * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License 0N/A * version 2 for more details (a copy is included in the LICENSE file that 0N/A * accompanied this code). 0N/A * You should have received a copy of the GNU General Public License version 0N/A * 2 along with this work; if not, write to the Free Software Foundation, 0N/A * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. 1472N/A * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA 0N/A// Define the initial sizes for allocation of the resizable code buffer 0N/A//------------------------------Scheduling---------------------------------- 0N/A// This class contains all the information necessary to implement instruction 0N/A// scheduling and bundling. 0N/A // Control-Flow Graph info 0N/A // Register Allocation info 0N/A // Number of nodes in the method 0N/A // List of scheduled nodes. Generated in reverse order 0N/A // List of nodes currently available for choosing for scheduling 0N/A // Mapping from node (index) to basic block 0N/A // For each instruction beginning a bundle, the number of following 0N/A // nodes to be bundled with it. 0N/A // Mapping from register to Node 0N/A // Free list for pinch nodes. 0N/A // Latency from the beginning of the containing basic block (base 1) 0N/A // Number of uses of this node within the containing basic block. 0N/A // branch-at-end), plus just-prior exception-throwing call. 0N/A // Latency from the end of the basic block as scheduled 0N/A // Remember the next node 0N/A // Use this for an unconditional branch delay slot 0N/A // Length of the current bundle, in instructions 0N/A // Current Cycle number, for computing latencies and bundling 0N/A // Bundle information 0N/A // Dump the available list 0N/A // Step ahead "i" cycles 0N/A // Step ahead 1 cycle, and clear the bundle state (for example, 0N/A // at a branch target) 0N/A // Do the scheduling 0N/A // Compute the local latencies walking forward over the list of 0N/A // nodes for a basic block 0N/A // Compute the register antidependencies within a basic block 0N/A // Add a node to the current bundle 0N/A // Add a node to the list of available nodes 0N/A // Compute the local use count for the nodes in a block, and compute 0N/A // the list of instructions with no uses in the block as available 0N/A // Choose an instruction from the available list to add to the bundle 0N/A // See if this Node fits into the currently accumulating bundle 0N/A // Decrement the use count for a node 0N/A // Garbage collect pinch nodes for reuse by other blocks. 0N/A // Clean up a pinch node for reuse (helper for above). 0N/A // Information for statistics gathering 0N/A // Gather information on size of nops relative to total 1879N/A#
endif // SHARE_VM_OPTO_OUTPUT_HPP