x86-64 jit: zyi target, ZYNOO3, bench and test timeouts, docs; drop a stray file

1 files changed, 12 insertions, 9 deletions

diff --git a/src/core/core.c b/src/core/core.c
index 51d6b4f..b571981 100644
--- a/src/core/core.c
+++ b/src/core/core.c
@@ -1,10 +1,12 @@
 /* zygote core: puts the genome (the zc compiler and its runtime, both vm code)
-   into memory and runs it. on arm64, every block of vm code is translated to
-   arm64 the first time it is reached, straight from live memory. stores that
-   land on translated words throw those translations away, so code that
-   rewrites itself, including the resident compiler, just gets retranslated
-   on the next visit. on other hosts (or with -DZYINTERP) a plain interpreter
-   with the same semantics runs instead. ZYTRACE=1 logs translations on stderr. */
+   into memory and runs it. on arm64 and on x86-64 linux, every block of vm code
+   is translated to native code the first time it is reached, straight from live
+   memory. stores that land on translated words throw those translations away,
+   so code that rewrites itself, including the resident compiler, just gets
+   retranslated on the next visit. the arm64 jit also compiles o3 regions; on
+   x86-64 they run on the region interpreter, and enhancements are called, not
+   inlined. on other hosts (or with -DZYINTERP) a plain interpreter with the same
+   semantics runs instead. ZYTRACE=1 logs translations on stderr. */
 #include <stdio.h>
 #include <stdlib.h>
 #include <stdint.h>
@@ -5895,11 +5897,11 @@ static void rcompile(Rg *R, int eager)
    c and every exit. o3 regions are not compiled here: a region entry is never
    translated (the c loop sees it first), and the region interpreter runs it. */
 static VM_TLS int vd;
+static VM_TLS int x64_noo3;	/* ZYNOO3=1: leave o3 regions alone and run their vm code through the jit (what the microcore does) */
 #define SL(k) (8 * (vd + (k)))
 static void ldv(int r, int k) { mov_rm(r, rSP, SL(k)); }
 static void stv(int k, int r) { mov_mr(rSP, SL(k), r); }
 static void sp_keep(void) { if (vd) lea(rSP, rSP, -1, 1, 8 * vd); }	/* r13 up to date; vd stays for the other path */
-static void sp_sync(void) { sp_keep(); vd = 0; }
 static void exit_with(int v) { sp_keep(); mov_r32i(r_ax, (unsigned)v); jmp_to(x_exit); }
 static void disp_imm(Cell t) { sp_keep(); mov_r32i(r_ax, (unsigned)(int)t); jmp_to(x_disp); }	/* a constant target: the low 32 bits, like the interpreter's int pc */
 static void disp_ax(void) { sp_keep(); jmp_to(x_disp); }
@@ -6015,7 +6017,7 @@ static void *translate(int p)
 {
 	JW *start;
 	int i = p, n = 0, k, t, used[64], nused = 0, j2, ju;
-	Cell w, x;
+	Cell w;
 	if (cp - code > CODEW * 4 - (1 << 19) || !ix_room()) flush();
 	start = cp;
 	vd = 0;
@@ -6199,7 +6201,7 @@ static int vm_until(int pc, int stop_eq, int stop_ge, Rg *re, Cell *ps, Cell *pr
 		if (stop_eq >= 0 && pc == stop_eq && S[2] - (stack_control ? stack_get(SC_RETURN_LOW) : RS0) == return_depth) break;
 		if (stop_ge >= 0 && pc >= stop_ge) break;
 		if (re && pc >= re->lo && pc < re->hi && o3ent[pc] == re->idx + 1) break;
-		if (o3ent[pc]) {	/* an o3 region: the region interpreter runs it */
+		if (o3ent[pc] && !x64_noo3) {	/* an o3 region: the region interpreter runs it */
 			Rg *R = rat(pc);
 			if (R) {
 				int s = (int)S[1], r = (int)S[2];
@@ -6239,6 +6241,7 @@ static int x64_boot(Cell sp, Cell rp, void *stop)
 {
 	code = mmap(0, CODEW * 4, PROT_READ | PROT_WRITE | PROT_EXEC, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
 	if (code == MAP_FAILED) { perror("mmap"); return 1; }
+	x64_noo3 = getenv("ZYNOO3") != 0;
 	jitwrite(1); build_stubs(); jitwrite(0); syncicache(code, cp);
 	S[0] = (long)m; S[1] = sp; S[2] = rp; S[3] = (long)tab; S[4] = (long)cov;
 	S[5] = (long)Q; S[6] = (long)G; S[7] = (long)&J; S[8] = (long)hook;