2016-02-14  Iain Buclaw  <ibuclaw@gdcproject.org>

	* d-elem.cc: Remove redundant IRState parameter from all lowering
	routines for expressions, update all callers.

2016-02-07  Iain Buclaw  <ibuclaw@gdcproject.org>

	* d-codegen.cc (build_array_set): Use POSTINCREMENT_EXPR to adjust
	array pointer.
	(identity_compare_p): New function.
	(build_struct_memcmp): Refactor into ...
	(lower_struct_comparison): ... New function.
	(build_struct_comparison): New function.
	(build_array_struct_comparison): New function.
	* d-elem.cc (IdentityExp::toElem): Use build_struct_comparison for
	RECORD_TYPE values.
	(EqualExp::toElem): Likewise.
	Use memcmp for array of structs that pass test for identity_compare_p,
	or fallback to build_array_struct_comparison.
	(NewExp::toElem): Remove setting of StructLiteralExp::fillHoles.
	(StructLiteralExp::toElem): Ignore StructLiteralExp::fillHoles, unless
	building a union literal.

2016-02-03  Iain Buclaw  <ibuclaw@gdcproject.org>

	* d-elem.cc (AssignExp::toElem): Pass parameters for arraycopy and
	arrayassign in the correct order.

2016-01-31  Iain Buclaw  <ibuclaw@gdcproject.org>

	* longdouble.h (longdouble): Use one contiguous array for the
	real_value data payload.

2016-01-23  Iain Buclaw  <ibuclaw@gdcproject.org>

	* toir.cc (IRVisitor::visit (ExtAsmStatement): Do validation of input
	and output constraints, marking operands as addressable if requested.

2016-01-10  Iain Buclaw  <ibuclaw@gdcproject.org>

	* d-codegen.cc (empty_aggregate_p): New function.
	(d_build_call): Don't pass empty aggregates by value.
	(build_struct_memcmp): Don't compare empty aggregates by value.
	* d-elem.cc (IdentityExp::toElem): Likewise.
	(EqualExp::toElem): Likewise.
	* (StructLiteralExp::toElem): Don't create temporaries or initialize
	holes for empty	aggregates.
	* d-lang.cc (empty_modify_p): New function.
	(d_gimplify_expr): Remove assignments that involve empty aggregates.

2016-01-09  Iain Buclaw  <ibuclaw@gdcproject.org>

	* d-builtins.cc (d_builtin_type): Define DEF_FUNCTION_TYPE_9,
	DEF_FUNCTION_TYPE_10, and DEF_FUNCTION_TYPE_11.
	(d_init_builtins): Likewise.
	* d-longdouble.cc (machineMode): Remove function.
	(longdouble::init): Don't use initialize real format by reference.
	(longdouble::operator+): Use real_arithmetic instead of
	REAL_ARITHMETIC.
	(longdouble::operator-): Likewise.
	(longdouble::operator*): Likewise.
	(longdouble::operator/): Likewise.
	(longdouble::operator%): Likewise.
	* d-port.cc (Port::isSignallingNan): Use REAL_VALUE_ISSIGNALING_NAN.
	(Port::fequal): Use real_identical instead of REAL_VALUES_IDENTICAL.
	* d-target.cc: Include stor-layout.h header.
	* lang.opt: Remove documentation for switches defined elsewhere.

2016-01-09  Iain Buclaw  <ibuclaw@gdcproject.org>

	* d-codegen.cc (get_libcall): Use set_call_expr_flags to apply runtime
	function attributes.
	* d-codegen.h (LibCallFlag): Remove type.
	* runtime.def: Replace LibCallFlag with ECF everywhere.


Copyright (C) 2016 Free Software Foundation, Inc.

Copying and distribution of this file, with or without modification,
are permitted in any medium without royalty provided the copyright
notice and this notice are preserved.
