From 39730420a24bbbfddb361e2a98335365a67a9e24 Mon Sep 17 00:00:00 2001 From: ceriel Date: Wed, 20 Jun 1990 10:05:22 +0000 Subject: [PATCH] Made to work with troff --- doc/ego/Makefile | 67 ++++++------- doc/ego/bo/bo1 | 101 +++++++++++--------- doc/ego/ca/ca1 | 10 -- doc/ego/cf/cf5 | 9 +- doc/ego/cj/cj1 | 100 +++++++++++--------- doc/ego/cs/cs1 | 13 ++- doc/ego/cs/cs2 | 11 ++- doc/ego/cs/cs3 | 13 ++- doc/ego/cs/cs4 | 60 ++++++------ doc/ego/ic/ic2 | 10 +- doc/ego/ic/ic3 | 229 ++++++++++++++++++++++++--------------------- doc/ego/ic/ic4 | 43 +++++---- doc/ego/ic/ic5 | 7 +- doc/ego/il/il3 | 8 +- doc/ego/il/il4 | 25 ++--- doc/ego/il/il5 | 36 ++++--- doc/ego/il/il6 | 2 +- doc/ego/intro/head | 11 ++- doc/ego/intro/tail | 14 +++ doc/ego/ov/ov1 | 13 ++- doc/ego/ra/ra3 | 9 +- doc/ego/sp/sp1 | 91 ++++++++++-------- doc/ego/sr/sr1 | 17 ++-- doc/ego/sr/sr2 | 36 ++++--- doc/ego/sr/sr3 | 104 +++++++++++--------- 25 files changed, 583 insertions(+), 456 deletions(-) diff --git a/doc/ego/Makefile b/doc/ego/Makefile index 7b5b067c8..f6aefa1ca 100644 --- a/doc/ego/Makefile +++ b/doc/ego/Makefile @@ -16,37 +16,40 @@ CA=ca/ca? EGO=$(INTRO) $(OV) $(IC) $(CF) $(IL) $(SR) $(CS) $(SP) $(CJ) $(BO) \ $(UD) $(LV) $(RA) $(CA) REFER=refer +TROFF=troff +TBL=tbl +TARGET=-Tlp -../ego.doc: $(EGO) - $(REFER) -sA+T -l4,2 $(REFS) intro/head $(EGO) intro/tail > ../ego.doc +../ego.doc: refs.opt refs.stat refs.gen intro/head intro/tail $(EGO) + $(REFER) -sA+T -l4,2 $(REFS) intro/head $(EGO) intro/tail | $(TBL) > ../ego.doc -ego.f: $(EGO) - $(REFER) -sA+T -l4,2 $(REFS) intro/head $(EGO) intro/tail | nroff -ms > ego.f -intro.f: $(INTRO) - $(REFER) -sA+T -l4,2 $(REFS) ov/head $(INTRO) intro/tail | nroff -ms > intro.f -ov.f: $(OV) - $(REFER) -sA+T -l4,2 $(REFS) ov/head $(OV) intro/tail | nroff -ms > ov.f -ic.f: $(IC) - $(REFER) -sA+T -l4,2 $(REFS) ic/head $(IC) intro/tail | nroff -ms > ic.f -cf.f: $(CF) - $(REFER) -sA+T -l4,2 $(REFS) cf/head $(CF) intro/tail | nroff -ms > cf.f -il.f: $(IL) - $(REFER) -sA+T -l4,2 $(REFS) il/head $(IL) intro/tail | nroff -ms > il.f -sr.f: $(SR) - $(REFER) -sA+T -l4,2 $(REFS) sr/head $(SR) intro/tail | nroff -ms > sr.f -cs.f: $(CS) - $(REFER) -sA+T -l4,2 $(REFS) cs/head $(CS) intro/tail | nroff -ms > cs.f -sp.f: $(SP) - $(REFER) -sA+T -l4,2 $(REFS) sp/head $(SP) intro/tail | nroff -ms > sp.f -cj.f: $(CJ) - $(REFER) -sA+T -l4,2 $(REFS) cj/head $(CJ) intro/tail | nroff -ms > cj.f -bo.f: $(BO) - $(REFER) -sA+T -l4,2 $(REFS) bo/head $(BO) intro/tail | nroff -ms > bo.f -ud.f: $(UD) - $(REFER) -sA+T -l4,2 $(REFS) ud/head $(UD) intro/tail | nroff -ms > ud.f -lv.f: $(LV) - $(REFER) -sA+T -l4,2 $(REFS) lv/head $(LV) intro/tail | nroff -ms > lv.f -ra.f: $(RA) - $(REFER) -sA+T -l4,2 $(REFS) ra/head $(RA) intro/tail | nroff -ms > ra.f -ca.f: $(CA) - $(REFER) -sA+T -l4,2 $(REFS) ca/head $(CA) intro/tail | nroff -ms > ca.f +ego.f: refs.opt refs.stat refs.gen intro/head intro/tail $(EGO) + $(REFER) -sA+T -l4,2 $(REFS) intro/head $(EGO) intro/tail | $(TBL) | $(TROFF) $(TARGET) -ms > ego.f +intro.f: refs.opt refs.stat refs.gen intro/head intro/tail $(INTRO) + $(REFER) -sA+T -l4,2 $(REFS) intro/head $(INTRO) intro/tail | $(TBL) | $(TROFF) $(TARGET) -ms > intro.f +ov.f: refs.opt refs.stat refs.gen intro/head intro/tail $(OV) + $(REFER) -sA+T -l4,2 $(REFS) intro/head $(OV) intro/tail | $(TBL) | $(TROFF) $(TARGET) -ms > ov.f +ic.f: refs.opt refs.stat refs.gen intro/head intro/tail $(IC) + $(REFER) -sA+T -l4,2 $(REFS) intro/head $(IC) intro/tail | $(TBL) | $(TROFF) $(TARGET) -ms > ic.f +cf.f: refs.opt refs.stat refs.gen intro/head intro/tail $(CF) + $(REFER) -sA+T -l4,2 $(REFS) intro/head $(CF) intro/tail | $(TBL) | $(TROFF) $(TARGET) -ms > cf.f +il.f: refs.opt refs.stat refs.gen intro/head intro/tail $(IL) + $(REFER) -sA+T -l4,2 $(REFS) intro/head $(IL) intro/tail | $(TBL) | $(TROFF) $(TARGET) -ms > il.f +sr.f: refs.opt refs.stat refs.gen intro/head intro/tail $(SR) + $(REFER) -sA+T -l4,2 $(REFS) intro/head $(SR) intro/tail | $(TBL) | $(TROFF) $(TARGET) -ms > sr.f +cs.f: refs.opt refs.stat refs.gen intro/head intro/tail $(CS) + $(REFER) -sA+T -l4,2 $(REFS) intro/head $(CS) intro/tail | $(TBL) | $(TROFF) $(TARGET) -ms > cs.f +sp.f: refs.opt refs.stat refs.gen intro/head intro/tail $(SP) + $(REFER) -sA+T -l4,2 $(REFS) intro/head $(SP) intro/tail | $(TBL) | $(TROFF) $(TARGET) -ms > sp.f +cj.f: refs.opt refs.stat refs.gen intro/head intro/tail $(CJ) + $(REFER) -sA+T -l4,2 $(REFS) intro/head $(CJ) intro/tail | $(TBL) | $(TROFF) $(TARGET) -ms > cj.f +bo.f: refs.opt refs.stat refs.gen intro/head intro/tail $(BO) + $(REFER) -sA+T -l4,2 $(REFS) intro/head $(BO) intro/tail | $(TBL) | $(TROFF) $(TARGET) -ms > bo.f +ud.f: refs.opt refs.stat refs.gen intro/head intro/tail $(UD) + $(REFER) -sA+T -l4,2 $(REFS) intro/head $(UD) intro/tail | $(TBL) | $(TROFF) $(TARGET) -ms > ud.f +lv.f: refs.opt refs.stat refs.gen intro/head intro/tail $(LV) + $(REFER) -sA+T -l4,2 $(REFS) intro/head $(LV) intro/tail | $(TBL) | $(TROFF) $(TARGET) -ms > lv.f +ra.f: refs.opt refs.stat refs.gen intro/head intro/tail $(RA) + $(REFER) -sA+T -l4,2 $(REFS) intro/head $(RA) intro/tail | $(TBL) | $(TROFF) $(TARGET) -ms > ra.f +ca.f: refs.opt refs.stat refs.gen intro/head intro/tail $(CA) + $(REFER) -sA+T -l4,2 $(REFS) intro/head $(CA) intro/tail | $(TBL) | $(TROFF) $(TARGET) -ms > ca.f diff --git a/doc/ego/bo/bo1 b/doc/ego/bo/bo1 index 23019605e..58c17c764 100644 --- a/doc/ego/bo/bo1 +++ b/doc/ego/bo/bo1 @@ -27,20 +27,23 @@ While-loop optimization The straightforward way to translate a while loop is to put the test for loop termination at the beginning of the loop. .DS -while cond loop LAB1: Test cond - body of the loop ---> Branch On False To LAB2 -end loop code for body of loop - Branch To LAB1 - LAB2: +while cond loop \kyLAB1: \kxTest cond + body of the loop --->\h'|\nxu'Branch On False To LAB2 +end loop\h'|\nxu'code for body of loop +\h'|\nxu'Branch To LAB1 +\h'|\nyu'LAB2: Fig. 10.1 Example of Branch Optimization .DE If the condition fails at the Nth iteration, the following code gets executed (dynamically): .DS -N * conditional branch (which fails N-1 times) -N-1 * unconditional branch -N-1 * body of the loop +.TS +l l l. +N * conditional branch (which fails N-1 times) +N-1 * unconditional branch +N-1 * body of the loop +.TE .DE An alternative translation is: .DS @@ -53,9 +56,12 @@ LAB2: .DE This translation results in the following profile: .DS -N * conditional branch (which succeeds N-1 times) -1 * unconditional branch -N-1 * body of the loop +.TS +l l l. +N * conditional branch (which succeeds N-1 times) +1 * unconditional branch +N-1 * body of the loop +.TE .DE So the second translation will be significantly faster if N >> 2. If N=2, execution time will be slightly increased. @@ -79,12 +85,15 @@ the basic block that comes textually next to S must stay in that position. So the transformation in Fig. 10.2 is illegal. .DS -LAB1: S1 LAB1: S1 - BRA LAB2 S2 - ... --> BEQ LAB3 -LAB2: S2 ... - BEQ LAB3 S3 - S3 +.TS +l l l l l. +LAB1: S1 LAB1: S1 + BRA LAB2 S2 + ... --> BEQ LAB3 +LAB2: S2 ... + BEQ LAB3 S3 + S3 +.TE Fig. 10.2 An illegal transformation of Branch Optimization .DE @@ -118,34 +127,36 @@ the last instruction of S is a conditional branch If such a block B is found, the control flow graph is changed as depicted in Fig. 10.3. .DS - | | - | v - v | - |-----<------| ----->-----| - ____|____ | | - | | | |-------| | - | S1 | | | v | - | Bcc | | | .... | -|--| | | | | -| --------- | | ----|---- | -| | | | | | -| .... ^ | | S2 | | -| | | | | | -| --------- | | | | | -v | | | ^ --------- | -| | S2 | | | | | -| | BRA | | | |-----<----- -| | | | | v -| --------- | | ____|____ -| | | | | | -| ------>------ | | S1 | -| | | Bnn | -|-------| | | | - | | ----|---- - v | | - |----<--| - | - v +.ft 5 + | | + | v + v | + |-----<------| ----->-----| + ____|____ | | + | | | |-------| | + | S1 | | | v | + | Bcc | | | .... | +|--| | | | | +| --------- | | ----|---- | +| | | | | | +| .... ^ | | S2 | | +| | | | | | +| --------- | | | | | +v | | | ^ --------- | +| | S2 | | | | | +| | BRA | | | |-----<----- +| | | | | v +| --------- | | ____|____ +| | | | | | +| ------>------ | | S1 | +| | | Bnn | +|-------| | | | + | | ----|---- + v | | + |----<--| + | + v +.ft R Fig. 10.3 Transformation of the CFG by Branch Optimization .DE diff --git a/doc/ego/ca/ca1 b/doc/ego/ca/ca1 index 781710ea7..ab06af430 100644 --- a/doc/ego/ca/ca1 +++ b/doc/ego/ca/ca1 @@ -63,13 +63,3 @@ present in the input program). On the other hand, an identifier may be only internally visible. If such an identifier is referenced before being defined, an INA or INP pseudo must be emitted prior to its first reference. -.UH -Acknowledgements -.PP -The author would like to thank Andy Tanenbaum for his guidance, -Duk Bekema for implementing the Common Subexpression Elimination phase -and writing the initial documentation of that phase, -Dick Grune for reading the manuscript of this report -and Ceriel Jacobs, Ed Keizer, Martin Kersten, Hans van Staveren -and the members of the S.T.W. user's group for their -interest and assistance. diff --git a/doc/ego/cf/cf5 b/doc/ego/cf/cf5 index 8ef4d11c3..1926c450c 100644 --- a/doc/ego/cf/cf5 +++ b/doc/ego/cf/cf5 @@ -7,9 +7,12 @@ The optimization below is only possible if we know for sure that the call to P cannot change A. .DS -A := 10; A:= 10; -P; -- procedure call --> P; -B := A + 2; B := 12; +.TS +l l. +A := 10; A:= 10; +P; -- procedure call --> P; +B := A + 2; B := 12; +.TE .DE Although it is not possible to predict exactly all the effects a procedure call has, we may diff --git a/doc/ego/cj/cj1 b/doc/ego/cj/cj1 index c725a7861..e7174af61 100644 --- a/doc/ego/cj/cj1 +++ b/doc/ego/cj/cj1 @@ -27,16 +27,18 @@ else S3 (pseudo) EM: - -TEST COND TEST COND -BNE *1 BNE *1 -S1 S1 -S3 ---> BRA *2 -BRA *2 1: -1: S2 -S2 2: -S3 S3 +.TS +l l l. + TEST COND TEST COND + BNE *1 BNE *1 + S1 S1 + S3 ---> BRA *2 + BRA *2 1: +1: S2 + S2 2: + S3 S3 2: +.TE Fig. 9.1 An example of Cross Jumping .DE @@ -54,20 +56,23 @@ as demonstrated by the Fig. 8.2. .DS Pascal: - if cond then - x := f(4) - else - x := g(5) +if cond then + x := f(4) +else + x := g(5) - EM: +EM: - ... ... - LOC 4 LOC 5 - CAL F CAL G - ASP 2 ASP 2 - LFR 2 LFR 2 - STL X STL X +.TS +l l. +... ... +LOC 4 LOC 5 +CAL F CAL G +ASP 2 ASP 2 +LFR 2 LFR 2 +STL X STL X +.TE Fig. 9.2 Effectiveness of Cross Jumping .DE @@ -92,37 +97,40 @@ blocks must be split into two. The control flow graphs before and after the optimization are shown in Fig. 9.3 and Fig. 9.4. .DS +.ft 5 - -------- -------- - | | | | - | S1 | | S2 | - | S3 | | S3 | - | | | | - -------- -------- - | | - |------------------|--------------------| - | - v + -------- -------- + | | | | + | S1 | | S2 | + | S3 | | S3 | + | | | | + -------- -------- + | | + |------------------|--------------------| + | + v +.ft R Fig. 9.3 CFG before optimization .DE .DS - - -------- -------- - | | | | - | S1 | | S2 | - | | | | - -------- -------- - | | - |--------------------<------------------| - v - -------- - | | - | S3 | - | | - -------- - | - v +.ft 5 + -------- -------- + | | | | + | S1 | | S2 | + | | | | + -------- -------- + | | + |--------------------<------------------| + v + -------- + | | + | S3 | + | | + -------- + | + v +.ft R Fig. 9.4 CFG after optimization .DE diff --git a/doc/ego/cs/cs1 b/doc/ego/cs/cs1 index d1cc8cebe..842e514a4 100644 --- a/doc/ego/cs/cs1 +++ b/doc/ego/cs/cs1 @@ -18,12 +18,15 @@ but in general it will save space too. As an example of the application of Common Subexpression Elimination, consider the piece of program in Fig. 7.1(a). .DS -x := a * b; TMP := a * b; x := a * b; -CODE; x := TMP; CODE -y := c + a * b; CODE y := x; - y := c + TMP; +.TS +l l l. +x := a * b; TMP := a * b; x := a * b; +CODE; x := TMP; CODE +y := c + a * b; CODE y := x; + y := c + TMP; - (a) (b) (c) + (a) (b) (c) +.TE Fig. 7.1 Examples of Common Subexpression Elimination .DE diff --git a/doc/ego/cs/cs2 b/doc/ego/cs/cs2 index 90877aa96..0fe4dfc16 100644 --- a/doc/ego/cs/cs2 +++ b/doc/ego/cs/cs2 @@ -70,10 +70,13 @@ a common subexpression, references to the element itself are replaced by indirect references through TMP (see Fig. 7.4). .DS -x := A[i]; TMP := &A[i]; - . . . --> x := *TMP; -A[i] := y; . . . - *TMP := y; +.TS +l l l. +x := A[i]; TMP := &A[i]; + . . . --> x := *TMP; +A[i] := y; . . . + *TMP := y; +.TE Fig. 7.4 Elimination of an array address computation .DE diff --git a/doc/ego/cs/cs3 b/doc/ego/cs/cs3 index 2d84a83eb..416d9e4bc 100644 --- a/doc/ego/cs/cs3 +++ b/doc/ego/cs/cs3 @@ -27,10 +27,13 @@ The value number of the result of an expression depends only on the kind of operator and the value number(s) of the operand(s). The expressions need not be textually equal, as shown in Fig. 7.5. .DS -a := c; (1) +.TS +l l. +a := c; (1) use(a * b); (2) -d := b; (3) +d := b; (3) use(c * d); (4) +.TE Fig. 7.5 Different expressions with the same value number .DE @@ -43,9 +46,12 @@ and the operator (*) is the same. .PP As another example of the value number method, consider Fig. 7.6. .DS +.TS +l l. use(a * b); (1) a := 123; (2) use(a * b); (3) +.TE Fig. 7.6 Identical expressions with the different value numbers .DE @@ -64,7 +70,7 @@ of its operands. A table of "available expressions" is used to do this mapping. .PP CS recognizes the following kinds of EM operands, called \fIentities\fR: -.IP +.DS - constant - local variable - external variable @@ -81,6 +87,7 @@ CS recognizes the following kinds of EM operands, called \fIentities\fR: - local base - heap pointer - ignore mask +.DE .LP Whenever a new entity is encountered in the working window, it is entered in the symbol table and given a brand new value number. diff --git a/doc/ego/cs/cs4 b/doc/ego/cs/cs4 index 543621833..c8eef93f5 100644 --- a/doc/ego/cs/cs4 +++ b/doc/ego/cs/cs4 @@ -26,26 +26,26 @@ There are groups for all sorts of operators: unary, binary, and ternary. The groups of operators are further partitioned according to the size of their operand(s) and result. -\" .PP -\" The distinction between operators and expensive loads is not always clear. -\" The ADP instruction for example, -\" might seem a unary operator because it pops one item -\" (a pointer) from the stack. -\" However, two ADP-instructions which pop an item with the same value number -\" need not have the same result, -\" because the attributes (an offset, to be added to the pointer) -\" can be different. -\" Is it then a binary operator? -\" That would give rise to the strange, and undesirable, -\" situation that some binary operators pop two operands -\" and others pop one. -\" The conclusion is inevitable: -\" we have been fooled by the name (ADd Pointer). -\" The ADP-instruction is an expensive load. -\" In this context LAF, meaning Load Address of oFfsetted, -\" would have been a better name, -\" corresponding to LOF, like LAL, -\" Load Address of Local, corresponds to LOL. +.\" .PP +.\" The distinction between operators and expensive loads is not always clear. +.\" The ADP instruction for example, +.\" might seem a unary operator because it pops one item +.\" (a pointer) from the stack. +.\" However, two ADP-instructions which pop an item with the same value number +.\" need not have the same result, +.\" because the attributes (an offset, to be added to the pointer) +.\" can be different. +.\" Is it then a binary operator? +.\" That would give rise to the strange, and undesirable, +.\" situation that some binary operators pop two operands +.\" and others pop one. +.\" The conclusion is inevitable: +.\" we have been fooled by the name (ADd Pointer). +.\" The ADP-instruction is an expensive load. +.\" In this context LAF, meaning Load Address of oFfsetted, +.\" would have been a better name, +.\" corresponding to LOF, like LAL, +.\" Load Address of Local, corresponds to LOL. .PP There are groups for all sorts of stores: direct, indirect, array element. @@ -91,10 +91,13 @@ because EM expressions are postfix. When we find an instruction to load an operand, we load on the fake-stack a struct with the following information: .DS -(1) the value number of the operand -(2) the size of the operand -(3) a pointer to the first line of EM-code - that constitutes the operand +.TS +l l. +(1) the value number of the operand +(2) the size of the operand +(3) a pointer to the first line of EM-code + that constitutes the operand +.TE .DE In most cases, (3) will point to the line that loaded the operand (e.g. LOL, LOC), @@ -121,9 +124,12 @@ a recurrence of this expression. Not only will the operand(s) be popped from the fake-stack, but the following will be pushed: .DS -(1) the value number of the result -(2) the size of the result -(3) a pointer to the first line of the expression +.TS +l l. +(1) the value number of the result +(2) the size of the result +(3) a pointer to the first line of the expression +.TE .DE In this way an item on the fake-stack always contains the necessary information. diff --git a/doc/ego/ic/ic2 b/doc/ego/ic/ic2 index 13715626a..f55e69927 100644 --- a/doc/ego/ic/ic2 +++ b/doc/ego/ic/ic2 @@ -90,18 +90,22 @@ and let the null item be 0. Then the tree of fig. 3.1(a) can be represented as in fig. 3.1(b). .DS +.ft 5 4 - + / \e 9 12 - + / \e / \e 12 3 4 6 - + / \e \e / 8 1 5 1 +.ft R Fig. 3.1(a) A binary tree +.ft 5 4 9 12 0 0 3 8 0 0 1 0 0 12 4 0 5 0 0 6 1 0 0 0 +.ft R Fig. 3.1(b) Its sequential representation .DE diff --git a/doc/ego/ic/ic3 b/doc/ego/ic/ic3 index d98e8233f..d140160b7 100644 --- a/doc/ego/ic/ic3 +++ b/doc/ego/ic/ic3 @@ -21,12 +21,15 @@ The syntactic structure of every component is described by a set of context free syntax rules, with the following conventions: .DS -x a non-terminal symbol -A a terminal symbol (in capitals) -x: a b c; a grammar rule -a | b a or b -(a)+ 1 or more occurrences of a -{a} 0 or more occurrences of a +.TS +l l. +x a non-terminal symbol +A a terminal symbol (in capitals) +x: a b c; a grammar rule +a | b a or b +(a)+ 1 or more occurrences of a +{a} 0 or more occurrences of a +.TE .DE .NH 3 The object table @@ -70,21 +73,24 @@ identifying number (see previous section for their use). .DS .UL syntax - object_table: - {datablock} ; - datablock: - D_ID -- unique identifying number - PSEUDO -- one of ROM,CON,BSS,HOL,UNKNOWN - SIZE -- # bytes declared - FLAGS - {value} -- contents of rom - {object} ; -- objects of the datablock - object: - O_ID -- unique identifying number - OFFSET -- offset within the datablock - SIZE ; -- size of the object in bytes - value: - argument ; +.TS +lw(1i) l l. +object_table: + {datablock} ; +datablock: + D_ID -- unique identifying number + PSEUDO -- one of ROM,CON,BSS,HOL,UNKNOWN + SIZE -- # bytes declared + FLAGS + {value} -- contents of rom + {object} ; -- objects of the datablock +object: + O_ID -- unique identifying number + OFFSET -- offset within the datablock + SIZE ; -- size of the object in bytes +value: + argument ; +.TE .DE A data block has only one flag: "external", indicating whether the data label is externally visible. @@ -102,26 +108,29 @@ The table has one entry for every procedure. .DS .UL syntax - procedure_table: - {procedure} - procedure: - P_ID -- unique identifying number - #LABELS -- number of instruction labels - #LOCALS -- number of bytes for locals - #FORMALS -- number of bytes for formals - FLAGS -- flag bits - calling -- procedures called by this one - change -- info about global variables changed - use ; -- info about global variables used - calling: - {P_ID} ; -- procedures called - change: - ext -- external variables changed - FLAGS ; - use: - FLAGS ; - ext: - {O_ID} ; -- a set of objects +.TS +lw(1i) l l. +procedure_table: + {procedure} +procedure: + P_ID -- unique identifying number + #LABELS -- number of instruction labels + #LOCALS -- number of bytes for locals + #FORMALS -- number of bytes for formals + FLAGS -- flag bits + calling -- procedures called by this one + change -- info about global variables changed + use ; -- info about global variables used +calling: + {P_ID} ; -- procedures called +change: + ext -- external variables changed + FLAGS ; +use: + FLAGS ; +ext: + {O_ID} ; -- a set of objects +.TE .DE .PP The number of bytes of formal parameters accessed by @@ -231,38 +240,41 @@ of arguments), then the list is terminated by a special argument of type CEND. .DS .UL syntax - em_text: - {line} ; - line: - INSTR -- opcode - OPTYPE -- operand type - operand ; - operand: - empty | -- OPTYPE = NO - SHORT | -- OPTYPE = SHORT - OFFSET | -- OPTYPE = OFFSET - LAB_ID | -- OPTYPE = INSTRLAB - O_ID | -- OPTYPE = OBJECT - P_ID | -- OPTYPE = PROCEDURE - {argument} ; -- OPTYPE = LIST - argument: - ARGTYPE - arg ; - arg: - empty | -- ARGTYPE = CEND - OFFSET | - LAB_ID | - O_ID | - P_ID | - string | -- ARGTYPE = STRING - const ; -- ARGTYPE = ICON,UCON or FCON - string: - LENGTH -- number of characters - {CHARACTER} ; - const: - SIZE -- number of bytes - string ; -- string representation of (un)signed - -- or floating point constant +.TS +lw(1i) l l. +em_text: + {line} ; +line: + INSTR -- opcode + OPTYPE -- operand type + operand ; +operand: + empty | -- OPTYPE = NO + SHORT | -- OPTYPE = SHORT + OFFSET | -- OPTYPE = OFFSET + LAB_ID | -- OPTYPE = INSTRLAB + O_ID | -- OPTYPE = OBJECT + P_ID | -- OPTYPE = PROCEDURE + {argument} ; -- OPTYPE = LIST +argument: + ARGTYPE + arg ; +arg: + empty | -- ARGTYPE = CEND + OFFSET | + LAB_ID | + O_ID | + P_ID | + string | -- ARGTYPE = STRING + const ; -- ARGTYPE = ICON,UCON or FCON +string: + LENGTH -- number of characters + {CHARACTER} ; +const: + SIZE -- number of bytes + string ; -- string representation of (un)signed + -- or floating point constant +.TE .DE .NH 3 The control flow graphs @@ -306,24 +318,27 @@ the identifiers of every that the block belongs to (see next section for loops). .DS .UL syntax - control_flow_graph: - {basic_block} ; - basic_block: - B_ID -- unique identifying number - #INSTR -- number of EM instructions - succ - pred - idom -- immediate dominator - loops -- set of loops - FLAGS ; -- flag bits - succ: - {B_ID} ; - pred: - {B_ID} ; - idom: - B_ID ; - loops: - {LP_ID} ; +.TS +lw(1i) l l. +control_flow_graph: + {basic_block} ; +basic_block: + B_ID -- unique identifying number + #INSTR -- number of EM instructions + succ + pred + idom -- immediate dominator + loops -- set of loops + FLAGS ; -- flag bits +succ: + {B_ID} ; +pred: + {B_ID} ; +idom: + B_ID ; +loops: + {LP_ID} ; +.TE .DE The flag bits can have the values 'firm' and 'strong', which are explained below. @@ -387,28 +402,30 @@ strong nor firm, as it may be skipped during some iterations .DS loop if cond1 then - ... -- this code will not - -- result in a firm or strong block + ... \kx-- this code will not + \h'|\nxu'-- result in a firm or strong block end if; ... -- strong (always executed) exit when cond2; - ... -- firm (not executed on - -- last iteration). + ... \kx-- firm (not executed on last iteration). end loop; Fig. 3.2 Example of firm and strong block .DE .DS .UL syntax - looptable: - {loop} ; - loop: - LP_ID -- unique identifying number - LEVEL -- loop nesting level - entry -- loop entry block - end ; - entry: - B_ID ; - end: - B_ID ; +.TS +lw(1i) l l. +looptable: + {loop} ; +loop: + LP_ID -- unique identifying number + LEVEL -- loop nesting level + entry -- loop entry block + end ; +entry: + B_ID ; +end: + B_ID ; +.TE .DE diff --git a/doc/ego/ic/ic4 b/doc/ego/ic/ic4 index 950a660ed..b75f13f88 100644 --- a/doc/ego/ic/ic4 +++ b/doc/ego/ic/ic4 @@ -57,24 +57,27 @@ indicating which part of the EM text belongs to that block. .DS .UL syntax - intermediate_code: - object_table_file - proctable_file - em_text_file - cfg_file ; - object_table_file: - LENGTH -- number of objects - object_table ; - proctable_file: - LENGTH -- number of procedures - procedure_table ; - em_text_file: - em_text ; - cfg_file: - {per_proc} ; -- one for every procedure - per_proc: - BLENGTH -- number of basic blocks - LLENGTH -- number of loops - control_flow_graph - looptable ; +.TS +lw(1i) l l. +intermediate_code: + object_table_file + proctable_file + em_text_file + cfg_file ; +object_table_file: + LENGTH -- number of objects + object_table ; +proctable_file: + LENGTH -- number of procedures + procedure_table ; +em_text_file: + em_text ; +cfg_file: + {per_proc} ; -- one for every procedure +per_proc: + BLENGTH -- number of basic blocks + LLENGTH -- number of loops + control_flow_graph + looptable ; +.TE .DE diff --git a/doc/ego/ic/ic5 b/doc/ego/ic/ic5 index 9dd5daae2..eb91bd5d9 100644 --- a/doc/ego/ic/ic5 +++ b/doc/ego/ic/ic5 @@ -93,8 +93,11 @@ Objects are recognized by looking at the operands of instructions that reference global data. If we come across the instructions: .DS -LDE X+6 -- Load Double External -LAE X+20 -- Load Address External +.TS +l l. +LDE X+6 -- Load Double External +LAE X+20 -- Load Address External +.TE .DE we conclude that the data block preceded by the data label X contains an object diff --git a/doc/ego/il/il3 b/doc/ego/il/il3 index e8ec7ee85..398b4c8bf 100644 --- a/doc/ego/il/il3 +++ b/doc/ego/il/il3 @@ -139,10 +139,10 @@ procedure p (x:integer); begin x := 20; end; -... -a := 10; a := 10; -p(a); ---> a := 20; -write(a); write(a); +\&... +a := 10; \kxa := 10; +p(a); ---> \h'|\nxu'a := 20; +write(a); \h'|\nxu'write(a); .DE .IP 2. P changes any of the operands of the diff --git a/doc/ego/il/il4 b/doc/ego/il/il4 index fdc664b1b..8ef685829 100644 --- a/doc/ego/il/il4 +++ b/doc/ego/il/il4 @@ -104,18 +104,21 @@ The following model was developed empirically. Assume procedure P calls procedure Q. The call takes place in basic block B. .DS -ZP = # zero parameters -CP = # constant parameters - ZP -LN = Loop Nesting level (0 if outside any loop) -F = \fIif\fR # formal parameters of Q > 0 \fIthen\fR 1 \fIelse\fR 0 -FT = \fIif\fR Q falls through \fIthen\fR 1 \fIelse\fR 0 -S = size(Q) - 1 - # inline_parameters - F -L = \fIif\fR # local variables of P > 0 \fIthen\fR 0 \fIelse\fR -1 -A = CP + 2 * ZP -N = \fIif\fR LN=0 and P is never called from a loop \fIthen\fR 0 \fIelse\fR (LN+1)**2 -FM = \fIif\fR B is a firm block \fIthen\fR 2 \fIelse\fR 1 +.TS +l l l. +ZP \&= # zero parameters +CP \&= # constant parameters - ZP +LN \&= Loop Nesting level (0 if outside any loop) +F \&= \fIif\fR # formal parameters of Q > 0 \fIthen\fR 1 \fIelse\fR 0 +FT \&= \fIif\fR Q falls through \fIthen\fR 1 \fIelse\fR 0 +S \&= size(Q) - 1 - # inline_parameters - F +L \&= \fIif\fR # local variables of P > 0 \fIthen\fR 0 \fIelse\fR -1 +A \&= CP + 2 * ZP +N \&= \fIif\fR LN=0 and P is never called from a loop \fIthen\fR 0 \fIelse\fR (LN+1)**2 +FM \&= \fIif\fR B is a firm block \fIthen\fR 2 \fIelse\fR 1 -pay_off = (100/S + FT + F + L + A) * N * FM +pay_off \&= (100/S + FT + F + L + A) * N * FM +.TE .DE S stands for the size increase of the program, which is slightly less than the size of Q. diff --git a/doc/ego/il/il5 b/doc/ego/il/il5 index 6445ba7df..2c434de69 100644 --- a/doc/ego/il/il5 +++ b/doc/ego/il/il5 @@ -165,19 +165,25 @@ These calls are inherited from the called procedure. We will refer to these invocations as \fInested calls\fR (see Fig. 5.1). .DS +.TS +lw(2.5i) l. procedure p is -begin . - a(); . - b(); . +begin . + a(); . + b(); . end; +.TE -procedure r is procedure r is -begin begin - x(); x(); - p(); -- in line a(); -- nested call - y(); b(); -- nested call -end; y(); - end; +.TS +lw(2.5i) l. +procedure r is procedure r is +begin begin + x(); x(); + p(); -- in line a(); -- nested call + y(); b(); -- nested call +end; y(); + end; +.TE Fig. 5.1 Example of nested procedure calls .DE @@ -224,11 +230,11 @@ All list traversals look like: traverse(list) { for (c = first(list); c != 0; c = CDR(c)) { - if (c is marked) { - traverse(CAR(c)); - } else { - do something with c - } + if (c is marked) { + traverse(CAR(c)); + } else { + do something with c + } } } .DE diff --git a/doc/ego/il/il6 b/doc/ego/il/il6 index bf61cad5c..a7e37a4a9 100644 --- a/doc/ego/il/il6 +++ b/doc/ego/il/il6 @@ -22,6 +22,6 @@ the driving routine for doing the substitution lower level routines that do certain modifications .IP 3_aux: implements auxiliary procedures used by subphase 3 -.IP aux +.IP aux: implements auxiliary procedures used by several subphases. .LP diff --git a/doc/ego/intro/head b/doc/ego/intro/head index 0d015a9d8..ccc710bd3 100644 --- a/doc/ego/intro/head +++ b/doc/ego/intro/head @@ -1,7 +1,10 @@ .ND -.ll 80m -.nr LL 80m -.nr tl 78m +.\".ll 80m +.\".nr LL 80m +.\".nr tl 78m .tr ~ .ds >. . -.ds [. " \[ +.ds >, , +.ds [. " [ +.ds .] ] +.cs 5 22 diff --git a/doc/ego/intro/tail b/doc/ego/intro/tail index 6cd2d4867..46cced8ac 100644 --- a/doc/ego/intro/tail +++ b/doc/ego/intro/tail @@ -1,3 +1,17 @@ +.SH +Acknowledgements +.PP +The author would like to thank Andy Tanenbaum for his guidance, +Duk Bekema for implementing the Common Subexpression Elimination phase +and writing the initial documentation of that phase, +Dick Grune for reading the manuscript of this report +and Ceriel Jacobs, Ed Keizer, Martin Kersten, Hans van Staveren +and the members of the S.T.W. user's group for their +interest and assistance. +.bp +.SH +References +.LP .[ $LIST$ .] diff --git a/doc/ego/ov/ov1 b/doc/ego/ov/ov1 index 5ab3d5d01..78d4326e6 100644 --- a/doc/ego/ov/ov1 +++ b/doc/ego/ov/ov1 @@ -76,11 +76,14 @@ EM is the assembly code of a virtual \fIstack machine\fR. All operations are performed on the top of the stack. For example, the statement "A := B + 3" may be expressed in EM as: .DS -LOL -4 -- push local variable B -LOC 3 -- push constant 3 -ADI 2 -- add two 2-byte items on top of - -- the stack and push the result -STL -2 -- pop A +.TS +l l. +LOL -4 -- push local variable B +LOC 3 -- push constant 3 +ADI 2 -- add two 2-byte items on top of + -- the stack and push the result +STL -2 -- pop A +.TE .DE So EM is essentially a \fIpostfix\fR code. .PP diff --git a/doc/ego/ra/ra3 b/doc/ego/ra/ra3 index 6ba296bd3..d02ed3bc9 100644 --- a/doc/ego/ra/ra3 +++ b/doc/ego/ra/ra3 @@ -225,9 +225,12 @@ allocation. To summarize, the number of bytes a certain allocation would save is computed as follows: .DS -net_bytes_saved = bytes_saved - init_cost -bytes_saved = #occurrences * gains_per_occ -init_cost = #initializations * costs_per_init +.TS +l l. +net_bytes_saved = bytes_saved - init_cost +bytes_saved = #occurrences * gains_per_occ +init_cost = #initializations * costs_per_init +.TE .DE .PP It is inherently more difficult to estimate the execution diff --git a/doc/ego/sp/sp1 b/doc/ego/sp/sp1 index 20c633f8a..86df413fd 100644 --- a/doc/ego/sp/sp1 +++ b/doc/ego/sp/sp1 @@ -11,12 +11,15 @@ the stack by the \fIcalling\fR procedure. The ASP (Adjust Stack Pointer) instruction is used for this purpose. A call in EM is shown in Fig. 8.1 .DS -Pascal: EM: +.TS +l l. +Pascal: EM: -f(a,2) LOC 2 - LOE A - CAL F - ASP 4 -- pop 4 bytes +f(a,2) LOC 2 + LOE A + CAL F + ASP 4 -- pop 4 bytes +.TE Fig. 8.1 An example procedure call in Pascal and EM .DE @@ -35,17 +38,20 @@ A stack adjustment may be delayed if there is some other stack adjustment later on in the same basic block. The two ASPs can be combined into one. .DS -Pascal: EM: optimized EM: +.TS +l l l. +Pascal: EM: optimized EM: -f(a,2) LOC 2 LOC 2 -g(3,b,c) LOE A LOE A - CAL F CAL F - ASP 4 LOE C - LOE C LOE B - LOE B LOC 3 - LOC 3 CAL G - CAL G ASP 10 - ASP 6 +f(a,2) LOC 2 LOC 2 +g(3,b,c) LOE A LOE A + CAL F CAL F + ASP 4 LOE C + LOE C LOE B + LOE B LOC 3 + LOC 3 CAL G + CAL G ASP 10 + ASP 6 +.TE Fig. 8.2 An example of local Stack Pollution .DE @@ -85,19 +91,23 @@ the number of bytes pushed since the first ASP. .LP Condition 1. is not satisfied in Fig. 8.3. .DS -Pascal: EM: +.TS +l l. +Pascal: EM: + +5 + f(10) + g(30) LOC 5 + LOC 10 + CAL F + ASP 2 -- cannot be removed + LFR 2 -- push function result + ADI 2 + LOC 30 + CAL G + ASP 2 + LFR 2 + ADI 2 +.TE -5 + f(10) + g(30) LOC 5 - LOC 10 - CAL F - ASP 2 -- cannot be removed - LFR 2 -- push function result - ADI 2 - LOC 30 - CAL G - ASP 2 - LFR 2 - ADI 2 Fig. 8.3 An illegal transformation .DE If the first ASP were removed (delayed), the first ADI would add @@ -105,19 +115,22 @@ If the first ASP were removed (delayed), the first ADI would add .sp Condition 2. is not satisfied in Fig. 8.4. .DS -Pascal: EM: +.TS +l l. +Pascal: EM: -f(10) + 5 * g(30) LOC 10 - CAL F - ASP 2 - LFR 2 - LOC 5 - LOC 30 - CAL G - ASP 2 - LFR 2 - MLI 2 -- 5 * g(30) - ADI 2 +f(10) + 5 * g(30) LOC 10 + CAL F + ASP 2 + LFR 2 + LOC 5 + LOC 30 + CAL G + ASP 2 + LFR 2 + MLI 2 -- 5 * g(30) + ADI 2 +.TE Fig. 8.4 A second illegal transformation .DE diff --git a/doc/ego/sr/sr1 b/doc/ego/sr/sr1 index cc8f660e4..7273d8ffa 100644 --- a/doc/ego/sr/sr1 +++ b/doc/ego/sr/sr1 @@ -16,13 +16,16 @@ done by the EM Peephole Optimizer. Strength reduction can also be applied more generally to operators used in a loop. .DS -i := 1; i := 1; -while i < 100 loop --> TMP := i * 118; - put(i * 118); while i < 100 loop - i := i + 1; put(TMP); -end loop; i := i + 1; - TMP := TMP + 118; - end loop; +.TS +l l. +i := 1; i := 1; +while i < 100 loop\ \ \ \ \ \ \ --> TMP := i * 118; + put(i * 118); while i < 100 loop + i := i + 1; put(TMP); +end loop; i := i + 1; + TMP := TMP + 118; + end loop; +.TE Fig. 6.1 An example of Strenght Reduction .DE diff --git a/doc/ego/sr/sr2 b/doc/ego/sr/sr2 index c3000f93e..9f7f01e88 100644 --- a/doc/ego/sr/sr2 +++ b/doc/ego/sr/sr2 @@ -105,11 +105,11 @@ iv_expression * constant .IP (2) constant * iv_expression .IP (3) -A[iv-expression] := (assign to array element) +A[iv-expression] := \kx(assign to array element) .IP (4) -A[iv-expression] (use array element) +A[iv-expression] \h'|\nxu'(use array element) .IP (5) -& A[iv-expression] (take address of array element) +& A[iv-expression] \h'|\nxu'(take address of array element) .LP (Note that EM has different instructions to use an array element, store into one, or take the address of one, resp. LAR, SAR, and AAR). @@ -171,10 +171,13 @@ replaced by TMP. For array optimizations, the replacement depends on the form: .DS -\fIform\fR \fIreplacement\fR -(3) A[iv-expr] := *TMP := (assign indirect) -(4) A[iv-expr] *TMP (use indirect) -(5) &A[iv-expr] TMP +.TS +l l l. +\fIform\fR \fIreplacement\fR +(3) A[iv-expr] := *TMP := (assign indirect) +(4) A[iv-expr] *TMP (use indirect) +(5) &A[iv-expr] TMP +.TE .DE The '*' denotes the indirect operator. (Note that EM has different instructions to do @@ -199,14 +202,17 @@ must be negated. .PP The transformations are demonstrated by an example. .DS -i := 100; i := 100; -while i > 1 loop TMP := (6-i) * 5; - X := (6-i) * 5 + 2; while i > 1 loop - Y := (6-i) * 5 - 8; --> X := TMP + 2; - i := i - 3; Y := TMP - 8; -end loop; i := i - 3; - TMP := TMP + 15; - end loop; +.TS +l l. +i := 100; i := 100; +while i > 1 loop TMP := (6-i) * 5; + X := (6-i) * 5 + 2; while i > 1 loop + Y := (6-i) * 5 - 8;\ \ \ \ \ \ \ --> X := TMP + 2; + i := i - 3; Y := TMP - 8; +end loop; i := i - 3; + TMP := TMP + 15; + end loop; +.TE Fig. 6.2 Example of complex Strength Reduction transformations .DE diff --git a/doc/ego/sr/sr3 b/doc/ego/sr/sr3 index 12dbcff7a..10dbf64a7 100644 --- a/doc/ego/sr/sr3 +++ b/doc/ego/sr/sr3 @@ -64,12 +64,15 @@ The assignment must match one of the EM patterns below. ('x' is the candidate. 'ws' is the word size of the target machine. 'n' is any number.) .DS -\fIpattern\fR \fIstep size\fR -INL x | +1 -DEL x | -1 -LOL x ; (INC | DEC) ; STL x | +1 | -1 -LOL x ; LOC n ; (ADI ws | SBI ws) ; STL x | +n | -n -LOC n ; LOL x ; ADI ws ; STL x. +n +.TS +l l. +\fIpattern\fR \fIstep size\fR +INL x | +1 +DEL x | -1 +LOL x ; (INC | DEC) ; STL x | +1 | -1 +LOL x ; LOC n ; (ADI ws | SBI ws) ; STL x | +n | -n +LOC n ; LOL x ; ADI ws ; STL x +n +.TE .DE From the patterns the step size of the induction variable can also be determined. @@ -95,19 +98,22 @@ code in front of it. If an expression is to be optimized, it must be generated by the following syntax rules. .DS - optimizable_expr: - iv_expr const mult | - const iv_expr mult | - address iv_expr address array_instr; - mult: - MLI ws | - MLU ws ; - array_instr: - LAR ws | - SAR ws | - AAR ws ; - const: - LOC n ; +.TS +l l. +optimizable_expr: + iv_expr const mult | + const iv_expr mult | + address iv_expr address array_instr; +mult: + MLI ws | + MLU ws ; +array_instr: + LAR ws | + SAR ws | + AAR ws ; +const: + LOC n ; +.TE .DE An 'address' is an EM instruction that loads an address on the stack. @@ -120,36 +126,42 @@ instructions like LDL are an 'address'. denote resp. the array address and the array descriptor address). .DS - address: - LAE | - LAL | - LOL if ps=ws | - LOE ,, | - LIL ,, | - LDL if ps=2*ws | - LDE ,, ; +.TS +l l. +address: + LAE | + LAL | + LOL if ps=ws | + LOE ,, | + LIL ,, | + LDL if ps=2*ws | + LDE ,, ; +.TE .DE The notion of an iv-expression was introduced earlier. .DS - iv_expr: - iv_expr unair_op | - iv_expr iv_expr binary_op | - loopconst | - iv ; - unair_op: - NGI ws | - INC | - DEC ; - binary_op: - ADI ws | - ADU ws | - SBI ws | - SBU ws ; - loopconst: - const | - LOL x if x is not changed in loop ; - iv: - LOL x if x is an induction variable ; +.TS +l l. +iv_expr: + iv_expr unair_op | + iv_expr iv_expr binary_op | + loopconst | + iv ; +unair_op: + NGI ws | + INC | + DEC ; +binary_op: + ADI ws | + ADU ws | + SBI ws | + SBU ws ; +loopconst: + const | + LOL x if x is not changed in loop ; +iv: + LOL x if x is an induction variable ; +.TE .DE An iv_expression must satisfy one additional constraint: it must use exactly one operand that is an induction