📄 d30v.md
字号:
(define_attr "predicable" "no,yes" (const_string "yes"));; ::::::::::::::::::::;; ::;; :: Function Units;; ::;; ::::::::::::::::::::;; On most RISC machines, there are instructions whose results are not;; available for a specific number of cycles. Common cases are instructions;; that load data from memory. On many machines, a pipeline stall will result;; if the data is referenced too soon after the load instruction.;; In addition, many newer microprocessors have multiple function units,;; usually one for integer and one for floating point, and often will incur;; pipeline stalls when a result that is needed is not yet ready.;; The descriptions in this section allow the specification of how much time;; must elapse between the execution of an instruction and the time when its;; result is used. It also allows specification of when the execution of an;; instruction will delay execution of similar instructions due to function;; unit conflicts.;; For the purposes of the specifications in this section, a machine is divided;; into "function units", each of which execute a specific class of;; instructions in first-in-first-out order. Function units that accept one;; instruction each cycle and allow a result to be used in the succeeding;; instruction (usually via forwarding) need not be specified. Classic RISC;; microprocessors will normally have a single function unit, which we can call;; `memory'. The newer "superscalar" processors will often have function units;; for floating point operations, usually at least a floating point adder and;; multiplier.;; Each usage of a function units by a class of insns is specified with a;; `define_function_unit' expression, which looks like this:;; (define_function_unit NAME MULTIPLICITY SIMULTANEITY TEST READY-DELAY;; ISSUE-DELAY [CONFLICT-LIST]);; NAME is a string giving the name of the function unit.;; MULTIPLICITY is an integer specifying the number of identical units in the;; processor. If more than one unit is specified, they will be scheduled;; independently. Only truly independent units should be counted; a pipelined;; unit should be specified as a single unit. (The only common example of a;; machine that has multiple function units for a single instruction class that;; are truly independent and not pipelined are the two multiply and two;; increment units of the CDC 6600.);; SIMULTANEITY specifies the maximum number of insns that can be executing in;; each instance of the function unit simultaneously or zero if the unit is;; pipelined and has no limit.;; All `define_function_unit' definitions referring to function unit NAME must;; have the same name and values for MULTIPLICITY and SIMULTANEITY.;; TEST is an attribute test that selects the insns we are describing in this;; definition. Note that an insn may use more than one function unit and a;; function unit may be specified in more than one `define_function_unit'.;; READY-DELAY is an integer that specifies the number of cycles after which;; the result of the instruction can be used without introducing any stalls.;; ISSUE-DELAY is an integer that specifies the number of cycles after the;; instruction matching the TEST expression begins using this unit until a;; subsequent instruction can begin. A cost of N indicates an N-1 cycle delay.;; A subsequent instruction may also be delayed if an earlier instruction has a;; longer READY-DELAY value. This blocking effect is computed using the;; SIMULTANEITY, READY-DELAY, ISSUE-DELAY, and CONFLICT-LIST terms. For a;; normal non-pipelined function unit, SIMULTANEITY is one, the unit is taken;; to block for the READY-DELAY cycles of the executing insn, and smaller;; values of ISSUE-DELAY are ignored.;; CONFLICT-LIST is an optional list giving detailed conflict costs for this;; unit. If specified, it is a list of condition test expressions to be;; applied to insns chosen to execute in NAME following the particular insn;; matching TEST that is already executing in NAME. For each insn in the list,;; ISSUE-DELAY specifies the conflict cost; for insns not in the list, the cost;; is zero. If not specified, CONFLICT-LIST defaults to all instructions that;; use the function unit.;; Typical uses of this vector are where a floating point function unit can;; pipeline either single- or double-precision operations, but not both, or;; where a memory unit can pipeline loads, but not stores, etc.;; As an example, consider a classic RISC machine where the result of a load;; instruction is not available for two cycles (a single "delay" instruction is;; required) and where only one load instruction can be executed;; simultaneously. This would be specified as:;; (define_function_unit "memory" 1 1 (eq_attr "type" "load") 2 0);; For the case of a floating point function unit that can pipeline;; either single or double precision, but not both, the following could be;; specified:;;;; (define_function_unit "fp" 1 0;; (eq_attr "type" "sp_fp") 4 4;; [(eq_attr "type" "dp_fp")]);;;; (define_function_unit "fp" 1 0;; (eq_attr "type" "dp_fp") 4 4;; [(eq_attr "type" "sp_fp")]);; Note: The scheduler attempts to avoid function unit conflicts and uses all;; the specifications in the `define_function_unit' expression. It has;; recently come to our attention that these specifications may not allow;; modeling of some of the newer "superscalar" processors that have insns using;; multiple pipelined units. These insns will cause a potential conflict for;; the second unit used during their execution and there is no way of;; representing that conflict. We welcome any examples of how function unit;; conflicts work in such processors and suggestions for their representation.(define_function_unit "iu" 1 0 (eq_attr "type" "iu,either") 1 1 [(eq_attr "type" "long,lcmp,lload,multi,unknown")])(define_function_unit "iu" 1 0 (eq_attr "type" "scmp,mul,scarry") 2 1 [(eq_attr "type" "long,lcmp,lload,multi,unknown")])(define_function_unit "mu" 1 0 (eq_attr "type" "mu,br,br2,either") 1 1 [(eq_attr "type" "long,lcmp,lload,multi,unknown")])(define_function_unit "mu" 1 0 (eq_attr "type" "scarry,scmp,sload") 2 1 [(eq_attr "type" "long,lcmp,lload,multi,unknown")])(define_function_unit "long" 1 0 (eq_attr "type" "long,multi,unknown") 1 1 [(eq_attr "type" "iu,mu,scarry,scmp,sload,mul,br,br2,either")])(define_function_unit "long" 1 0 (eq_attr "type" "lcmp,lload,lcarry") 2 1 [(eq_attr "type" "iu,mu,scarry,scmp,sload,mul,br,br2,either")]);; ::::::::::::::::::::;; ::;; :: Delay Slots;; ::;; ::::::::::::::::::::;; The insn attribute mechanism can be used to specify the requirements for;; delay slots, if any, on a target machine. An instruction is said to require;; a "delay slot" if some instructions that are physically after the;; instruction are executed as if they were located before it. Classic;; examples are branch and call instructions, which often execute the following;; instruction before the branch or call is performed.;; On some machines, conditional branch instructions can optionally "annul";; instructions in the delay slot. This means that the instruction will not be;; executed for certain branch outcomes. Both instructions that annul if the;; branch is true and instructions that annul if the branch is false are;; supported.;; Delay slot scheduling differs from instruction scheduling in that;; determining whether an instruction needs a delay slot is dependent only;; on the type of instruction being generated, not on data flow between the;; instructions. See the next section for a discussion of data-dependent;; instruction scheduling.;; The requirement of an insn needing one or more delay slots is indicated via;; the `define_delay' expression. It has the following form:;;;; (define_delay TEST;; [DELAY-1 ANNUL-TRUE-1 ANNUL-FALSE-1;; DELAY-2 ANNUL-TRUE-2 ANNUL-FALSE-2;; ...]);; TEST is an attribute test that indicates whether this `define_delay' applies;; to a particular insn. If so, the number of required delay slots is;; determined by the length of the vector specified as the second argument. An;; insn placed in delay slot N must satisfy attribute test DELAY-N.;; ANNUL-TRUE-N is an attribute test that specifies which insns may be annulled;; if the branch is true. Similarly, ANNUL-FALSE-N specifies which insns in;; the delay slot may be annulled if the branch is false. If annulling is not;; supported for that delay slot, `(nil)' should be coded.;; For example, in the common case where branch and call insns require a single;; delay slot, which may contain any insn other than a branch or call, the;; following would be placed in the `md' file:;; (define_delay (eq_attr "type" "branch,call");; [(eq_attr "type" "!branch,call") (nil) (nil)]);; Multiple `define_delay' expressions may be specified. In this case, each;; such expression specifies different delay slot requirements and there must;; be no insn for which tests in two `define_delay' expressions are both true.;; For example, if we have a machine that requires one delay slot for branches;; but two for calls, no delay slot can contain a branch or call insn, and any;; valid insn in the delay slot for the branch can be annulled if the branch is;; true, we might represent this as follows:;; (define_delay (eq_attr "type" "branch");; [(eq_attr "type" "!branch,call");; (eq_attr "type" "!branch,call");; (nil)]);;;; (define_delay (eq_attr "type" "call");; [(eq_attr "type" "!branch,call") (nil) (nil);; (eq_attr "type" "!branch,call") (nil) (nil)]);; ::::::::::::::::::::;; ::;; :: Moves;; ::;; ::::::::::::::::::::;; Wrap moves in define_expand to prevent memory->memory moves from being;; generated at the RTL level, which generates better code for most machines;; which can't do mem->mem moves.;; If operand 0 is a `subreg' with mode M of a register whose own mode is wider;; than M, the effect of this instruction is to store the specified value in;; the part of the register that corresponds to mode M. The effect on the rest;; of the register is undefined.;; This class of patterns is special in several ways. First of all, each of;; these names *must* be defined, because there is no other way to copy a datum;; from one place to another.;; Second, these patterns are not used solely in the RTL generation pass. Even;; the reload pass can generate move insns to copy values from stack slots into;; temporary registers. When it does so, one of the operands is a hard;; register and the other is an operand that can need to be reloaded into a;; register.;; Therefore, when given such a pair of operands, the pattern must;; generate RTL which needs no reloading and needs no temporary;; registers--no registers other than the operands. For example, if;; you support the pattern with a `define_expand', then in such a;; case the `define_expand' mustn't call `force_reg' or any other such;; function which might generate new pseudo registers.;; This requirement exists even for subword modes on a RISC machine;; where fetching those modes from memory normally requires several;; insns and some temporary registers. Look in `spur.md' to see how;; the requirement can be satisfied.;; During reload a memory reference with an invalid address may be passed as an;; operand. Such an address will be replaced with a valid address later in the;; reload pass. In this case, nothing may be done with the address except to;; use it as it stands. If it is copied, it will not be replaced with a valid;; address. No attempt should be made to make such an address into a valid;; address and no routine (such as `change_address') that will do so may be;; called. Note that `general_operand' will fail when applied to such an;; address.;;;; The global variable `reload_in_progress' (which must be explicitly declared;; if required) can be used to determine whether such special handling is;; required.;;;; The variety of operands that have reloads depends on the rest of;; the machine description, but typically on a RISC machine these can;; only be pseudo registers that did not get hard registers, while on;; other machines explicit memory references will get optional;; reloads.;;;; If a scratch register is required to move an object to or from memory, it;; can be allocated using `gen_reg_rtx' prior to reload. But this is;; impossible during and after reload. If there are cases needing scratch;; registers after reload, you must define `SECONDARY_INPUT_RELOAD_CLASS' and;; perhaps also `SECONDARY_OUTPUT_RELOAD_CLASS' to detect them, and provide;; patterns `reload_inM' or `reload_outM' to handle them. *Note Register;; Classes::.;; The constraints on a `moveM' must permit moving any hard register to any;; other hard register provided that `HARD_REGNO_MODE_OK' permits mode M in;; both registers and `REGISTER_MOVE_COST' applied to their classes returns a;; value of 2.;; It is obligatory to support floating point `moveM' instructions;; into and out of any registers that can hold fixed point values,;; because unions and structures (which have modes `SImode' or;; `DImode') can be in those registers and they may have floating;; point members.;; There may also be a need to support fixed point `moveM' instructions in and;; out of floating point registers. Unfortunately, I have forgotten why this;; was so, and I don't know whether it is still true. If `HARD_REGNO_MODE_OK';; rejects fixed point values in floating point registers, then the constraints;; of the fixed point `moveM' instructions must be designed to avoid ever;; trying to reload into a floating point register.(define_expand "movqi" [(set (match_operand:QI 0 "general_operand" "") (match_operand:QI 1 "general_operand" ""))] "" "{ if (!reload_in_progress && !reload_completed && !register_operand (operands[0], QImode) && !reg_or_0_operand (operands[1], QImode)) operands[1] = copy_to_mode_reg (QImode, operands[1]);}")(define_insn "*movqi_internal" [(set (match_operand:QI 0 "move_output_operand" "=d,d,d,d,Q,m,Q,m,d,c") (match_operand:QI 1 "move_input_operand" "dI,i,Q,m,d,d,O,O,c,d"))] "register_operand (operands[0], QImode) || reg_or_0_operand (operands[1], QImode)" "@ or%: %0,%.,%1 or%: %0,%.,%1 ldb%: %0,%M1 ldb%: %0,%M1 stb%: %1,%M0 stb%: %1,%M0 stb%: %.,%M0 stb%: %.,%M0 mvfsys%: %0,%1 mvtsys%: %0,%1" [(set_attr "length" "4,8,4,8,4,8,4,8,4,4") (set_attr "type" "either,long,sload,lload,mu,long,mu,long,mu,mu")])(define_expand "movhi" [(set (match_operand:HI 0 "general_operand" "") (match_operand:HI 1 "general_operand" ""))] "" "{ if (!reload_in_progress && !reload_completed && !register_operand (operands[0], HImode) && !reg_or_0_operand (operands[1], HImode)) operands[1] = copy_to_mode_reg (HImode, operands[1]);}")(define_insn "*movhi_internal" [(set (match_operand:HI 0 "move_output_operand" "=d,d,d,d,Q,m,Q,m,d,c") (match_operand:HI 1 "move_input_operand" "dI,i,Q,m,d,d,O,O,c,d"))] "register_operand (operands[0], HImode) || reg_or_0_operand (operands[1], HImode)" "@ or%: %0,%.,%1 or%: %0,%.,%1 ldh%: %0,%M1 ldh%: %0,%M1 sth%: %1,%M0 sth%: %1,%M0 sth%: %.,%M0 sth%: %.,%M0 mvfsys%: %0,%1 mvtsys%: %0,%1" [(set_attr "length" "4,8,4,8,4,8,4,8,4,4") (set_attr "type" "either,long,sload,lload,mu,long,mu,long,mu,mu")])(define_expand "movsi" [(set (match_operand:SI 0 "general_operand" "") (match_operand:SI 1 "general_operand" ""))] "" "{ if (!reload_in_progress && !reload_completed && !register_operand (operands[0], SImode) && !reg_or_0_operand (operands[1], SImode)) operands[1] = copy_to_mode_reg (SImode, operands[1]); /* Convert addressing modes into the appropriate add/sub with the clobbers needed. This is generated by builtin_setjmp in the exception handling. */ if (GET_CODE (operands[1]) == PLUS) { emit_insn (gen_addsi3 (operands[0], XEXP (operands[1], 0), XEXP (operands[1], 1))); DONE; }
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -