summaryrefslogtreecommitdiff
path: root/module/language
diff options
context:
space:
mode:
authorAndy Wingo <wingo@oblong.net>2009-08-12 16:33:49 +0200
committerAndy Wingo <wingo@oblong.net>2009-08-12 16:34:05 +0200
commit94ff26b96b555f0263fab2221cd55801119ffddd (patch)
tree6911dde6ef41d2b87eb9cfa6b857e7692bc21ac1 /module/language
parent6cf48307989d2552f2215ef8406ea92745d2d3e9 (diff)
downloadguile-94ff26b96b555f0263fab2221cd55801119ffddd.tar.gz
rework the vm support for wide strings
* libguile/_scm.h (SCM_OBJCODE_MINOR_VERSION): Bump. * libguile/vm-engine.c (vm_error_bad_wide_string_length): New error case. * libguile/vm-i-loader.c (load-unsigned-integer, load-integer) (load-keyword): Remove these instructions. The former two are obsoleted by make-int64/make-uint64, the latter via make-keyword. (load-string): Only handle narrow strings. (load-symbol): Only handle narrow symbols. The wide case is handled via make-symbol. (load-wide-string): New instruction, for wide strings. * libguile/vm-i-system.c (define): Move here from loaders.c, as now it just takes a sym on the stack. (make-keyword, make-symbol): New instructions. * module/language/assembly.scm: Remove removed instructions. No more width byte in load-string etc. * module/language/assembly/compile-bytecode.scm (write-bytecode): Adapt to change in instruction set. * module/language/glil/compile-assembly.scm (glil->assembly): Compile define by pushing the sym then emitting (define). (dump-object): Dump narrow and wide strings differently. Use make-keyword and make-symbol as appropriate. * module/language/tree-il/compile-glil.scm (flatten): When compiling a ref to a primitive (not a call), first see if the primitive is actually bound in the root module. (That's not the case with e.g. bytevector-u8-ref). * module/system/xref.scm (program-callee-rev-vars): Don't parse out "nexts". * test-suite/tests/asm-to-bytecode.test ("compiler"): Adapt to bytecode format change.
Diffstat (limited to 'module/language')
-rw-r--r--module/language/assembly.scm18
-rw-r--r--module/language/assembly/compile-bytecode.scm19
-rw-r--r--module/language/assembly/decompile-bytecode.scm27
-rw-r--r--module/language/glil/compile-assembly.scm19
-rw-r--r--module/language/tree-il/compile-glil.scm9
5 files changed, 40 insertions, 52 deletions
diff --git a/module/language/assembly.scm b/module/language/assembly.scm
index 5571bee61..683da6cc1 100644
--- a/module/language/assembly.scm
+++ b/module/language/assembly.scm
@@ -34,30 +34,21 @@
;; lengths are encoded in 3 bytes
(define *len-len* 3)
-;; the number of bytes per string character is encoded in 1 byte
-(define *width-len* 1)
-
(define (byte-length assembly)
(pmatch assembly
(,label (guard (not (pair? label)))
0)
- ((load-unsigned-integer ,str)
- (+ 1 *len-len* (string-length str)))
- ((load-integer ,str)
- (+ 1 *len-len* (string-length str)))
((load-number ,str)
(+ 1 *len-len* (string-length str)))
((load-string ,str)
- (+ 1 *len-len* *width-len* (* (string-width str) (string-length str))))
+ (+ 1 *len-len* (string-length str)))
+ ((load-wide-string ,str)
+ (+ 1 *len-len* (* 4 (string-length str))))
((load-symbol ,str)
- (+ 1 *len-len* *width-len* (* (string-width str) (string-length str))))
- ((load-keyword ,str)
- (+ 1 *len-len* *width-len* (* (string-width str) (string-length str))))
+ (+ 1 *len-len* (string-length str)))
((load-array ,bv)
(+ 1 *len-len* (bytevector-length bv)))
- ((define ,str)
- (+ 1 *len-len* *width-len* (* (string-width str) (string-length str))))
((load-program ,nargs ,nrest ,nlocs ,labels ,len ,meta . ,code)
(+ 1 *program-header-len* len (if meta (1- (byte-length meta)) 0)))
((,inst . _) (guard (>= (instruction-length inst) 0))
@@ -171,5 +162,4 @@
n4)))
((load-string ,s) s)
((load-symbol ,s) (string->symbol s))
- ((load-keyword ,s) (symbol->keyword (string->symbol s)))
(else #f)))
diff --git a/module/language/assembly/compile-bytecode.scm b/module/language/assembly/compile-bytecode.scm
index 840c73b3a..c49c20081 100644
--- a/module/language/assembly/compile-bytecode.scm
+++ b/module/language/assembly/compile-bytecode.scm
@@ -65,11 +65,13 @@
(write-byte (logand (ash x -8) 255))
(write-byte (logand (ash x -16) 255))
(write-byte (logand (ash x -24) 255)))
- (define (write-uint32 x) (case byte-order
- ((1234) (write-uint32-le x))
- ((4321) (write-uint32-be x))
- (else (error "unknown endianness" byte-order))))
+ (define (write-uint32 x)
+ (case byte-order
+ ((1234) (write-uint32-le x))
+ ((4321) (write-uint32-be x))
+ (else (error "unknown endianness" byte-order))))
(define (write-wide-string s)
+ (write-loader-len (* 4 (string-length s)))
(string-for-each (lambda (c) (write-uint32 (char->integer c))) s))
(define (write-loader-len len)
(write-byte (ash len -16))
@@ -133,14 +135,11 @@
;; `scm_c_make_objcode_slice ()'.
(write-bytecode meta write get-addr '()))))
((make-char32 ,x) (write-uint32-be x))
- ((load-unsigned-integer ,str) (write-loader str))
- ((load-integer ,str) (write-loader str))
((load-number ,str) (write-loader str))
- ((load-string ,str) (write-sized-loader str))
- ((load-symbol ,str) (write-sized-loader str))
- ((load-keyword ,str) (write-sized-loader str))
+ ((load-string ,str) (write-loader str))
+ ((load-wide-string ,str) (write-wide-string str))
+ ((load-symbol ,str) (write-loader str))
((load-array ,bv) (write-bytevector bv))
- ((define ,str) (write-sized-loader str))
((br ,l) (write-break l))
((br-if ,l) (write-break l))
((br-if-not ,l) (write-break l))
diff --git a/module/language/assembly/decompile-bytecode.scm b/module/language/assembly/decompile-bytecode.scm
index a05db537d..8cdebcfd0 100644
--- a/module/language/assembly/decompile-bytecode.scm
+++ b/module/language/assembly/decompile-bytecode.scm
@@ -96,16 +96,6 @@
(lp (cons exp out))))))))))
(define (decode-bytecode pop)
- (define (get1 bytes-per-char)
- (if (= bytes-per-char 1)
- (pop)
- (let* ((a (pop))
- (b (pop))
- (c (pop))
- (d (pop)))
- (if (= byte-order 1234)
- (+ (ash d 24) (ash c 16) (ash b 8) a)
- (+ (ash a 24) (ash b 16) (ash c 8) d)))))
(and=> (pop)
(lambda (opcode)
(let ((inst (opcode->instruction opcode)))
@@ -117,29 +107,24 @@
;; the negative length indicates a variable length
;; instruction
(let* ((make-sequence
- (if (eq? inst 'load-array)
+ (if (or (memq inst '(load-array load-wide-string)))
make-bytevector
make-string))
(sequence-set!
- (if (eq? inst 'load-array)
+ (if (or (memq inst '(load-array load-wide-string)))
bytevector-u8-set!
(lambda (str pos value)
(string-set! str pos (integer->char value)))))
(len (let* ((a (pop)) (b (pop)) (c (pop)))
(+ (ash a 16) (ash b 8) c)))
- (bytes-per-count
- (if (or (eq? inst 'load-string)
- (eq? inst 'load-symbol)
- (eq? inst 'load-keyword)
- (eq? inst 'define))
- (pop)
- 1))
(seq (make-sequence len)))
(let lp ((i 0))
(if (= i len)
- `(,inst ,seq)
+ `(,inst ,(if (eq? inst 'load-wide-string)
+ (utf32->string seq)
+ seq))
(begin
- (sequence-set! seq i (get1 bytes-per-count))
+ (sequence-set! seq i (pop))
(lp (1+ i)))))))
(else
;; fixed length
diff --git a/module/language/glil/compile-assembly.scm b/module/language/glil/compile-assembly.scm
index 4bd6c4f04..c67ef694b 100644
--- a/module/language/glil/compile-assembly.scm
+++ b/module/language/glil/compile-assembly.scm
@@ -318,8 +318,8 @@
,(modulo i 256))))
object-alist)))))
((define)
- (emit-code `((define ,(symbol->string name))
- (variable-set))))
+ (emit-code `(,@(dump-object name addr)
+ (define))))
(else
(error "unknown toplevel var kind" op name))))
@@ -391,11 +391,20 @@
((number? x)
`((load-number ,(number->string x))))
((string? x)
- `((load-string ,x)))
+ (case (string-width x)
+ ((1) `((load-string ,x)))
+ ((4) (align-code `(load-wide-string ,x) addr 4 4))
+ (else (error "bad string width" x))))
((symbol? x)
- `((load-symbol ,(symbol->string x))))
+ (let ((str (symbol->string x)))
+ (case (string-width str)
+ ((1) `((load-symbol ,str)))
+ ((4) `(,@(dump-object str addr)
+ (make-symbol)))
+ (else (error "bad string width" str)))))
((keyword? x)
- `((load-keyword ,(symbol->string (keyword->symbol x)))))
+ `(,@(dump-object (keyword->symbol x) addr)
+ (make-keyword)))
((list? x)
(let ((tail (let ((len (length x)))
(if (>= len 65536) (too-long "list"))
diff --git a/module/language/tree-il/compile-glil.scm b/module/language/tree-il/compile-glil.scm
index 48db6f6c4..503e0a44f 100644
--- a/module/language/tree-il/compile-glil.scm
+++ b/module/language/tree-il/compile-glil.scm
@@ -492,11 +492,16 @@
((tail push vals)
(emit-code src (make-glil-toplevel 'ref name))))
(maybe-emit-return))
- (else
- (pk 'ew-the-badness x (current-module) (fluid-ref *comp-module*))
+ ((module-variable the-root-module name)
(case context
((tail push vals)
(emit-code src (make-glil-module 'ref '(guile) name #f))))
+ (maybe-emit-return))
+ (else
+ (case context
+ ((tail push vals)
+ (emit-code src (make-glil-module
+ 'ref (module-name (fluid-ref *comp-module*)) name #f))))
(maybe-emit-return))))
((<lexical-ref> src name gensym)