x86-64 jit: inline enhancements (micro-ops lowered to registers, literal specialization, ZYNOENH=1 to call xrun); enh_ops test; jit_x64_test in test.sh

1 files changed, 148 insertions, 0 deletions

diff --git a/tests/programs/enh_ops.zc b/tests/programs/enh_ops.zc
new file mode 100644
index 0000000..da3cc09
--- /dev/null
+++ b/tests/programs/enh_ops.zc
@@ -0,0 +1,148 @@
+namespace;
+include rt;
+
+// every micro-op the x86-64 jit lowers inline, on edge values (0, -1, the
+// minimum, shift counts past 63, out-of-range loads), called with variables
+// and with literals (which specialize the enhancement on them). the output must
+// be the same on every backend; tests/drivers/jit_x64_test.sh compares it
+// against the interpreter.
+enhance e_add(a, b) micro "r0 = add a b";
+enhance e_sub(a, b) micro "r0 = sub a b";
+enhance e_mul(a, b) micro "r0 = mul a b";
+enhance e_sdiv(a, b) micro "r0 = sdiv a b";
+enhance e_udiv(a, b) micro "r0 = udiv a b";
+enhance e_srem(a, b) micro "r0 = srem a b";
+enhance e_urem(a, b) micro "r0 = urem a b";
+enhance e_and(a, b) micro "r0 = and a b";
+enhance e_or(a, b) micro "r0 = or a b";
+enhance e_xor(a, b) micro "r0 = xor a b";
+enhance e_shl(a, b) micro "r0 = shl a b";
+enhance e_shr(a, b) micro "r0 = shr a b";
+enhance e_sar(a, b) micro "r0 = sar a b";
+enhance e_lt(a, b) micro "r0 = lt a b";
+enhance e_ltu(a, b) micro "r0 = ltu a b";
+enhance e_eq(a, b) micro "r0 = eq a b";
+enhance e_ne(a, b) micro "r0 = ne a b";
+enhance e_min(a, b) micro "r0 = min a b";
+enhance e_max(a, b) micro "r0 = max a b";
+enhance e_minu(a, b) micro "r0 = minu a b";
+enhance e_maxu(a, b) micro "r0 = maxu a b";
+enhance e_mulhs(a, b) micro "r0 = mulhs a b";
+enhance e_mulhu(a, b) micro "r0 = mulhu a b";
+enhance e_rotl(a, b) micro "r0 = rotl a b";
+enhance e_rotr(a, b) micro "r0 = rotr a b";
+enhance u_neg(a) micro "r0 = neg a";
+enhance u_not(a) micro "r0 = not a";
+enhance u_clz(a) micro "r0 = clz a";
+enhance u_ctz(a) micro "r0 = ctz a";
+enhance u_abs(a) micro "r0 = abs a";
+enhance u_bswap(a) micro "r0 = bswap a";
+enhance e_sel(a, b, c) micro "r0 = sel a b c";
+enhance e_ld(a) micro "r0 = ld a";
+enhance e_st(a, b) micro "st a b; r0 = ld a";
+enhance e_mix(a, b) micro "r2 = mul a 3; r3 = add r2 b; r4 = sdiv r3 7; r5 = minu r4 b; r0 = xor r5 r2";
+
+int[12] v;
+int h;
+int mix(int r) { h = h * 31 + r; return 0; }
+int show(char* name) { rt.put_s(name); rt.put_c(32); rt.put_n(h); rt.put_c(10); h = 0; return 0; }
+
+unchecked int main() {
+	int i, j, a, b; word g = rt.new(4);
+	v[0] = 0; v[1] = 1; v[2] = 0 - 1; v[3] = 1 << 63; v[4] = (1 << 63) - 1; v[5] = 7; v[6] = 0 - 7; v[7] = 63; v[8] = 64; v[9] = 65; v[10] = 100; v[11] = 0x123456789;
+	for (i = 0; i < 12; i++) for (j = 0; j < 12; j++) { a = v[i]; b = v[j]; mix(e_add(a, b)); }
+	for (i = 0; i < 12; i++) { a = v[i]; mix(e_add(a, 0)); mix(e_add(a, 0 - 1)); mix(e_add(a, 3)); mix(e_add(a, 64)); mix(e_add(a, 0x7fffffff)); }
+	show("add");
+	for (i = 0; i < 12; i++) for (j = 0; j < 12; j++) { a = v[i]; b = v[j]; mix(e_sub(a, b)); }
+	for (i = 0; i < 12; i++) { a = v[i]; mix(e_sub(a, 0)); mix(e_sub(a, 0 - 1)); mix(e_sub(a, 3)); mix(e_sub(a, 64)); mix(e_sub(a, 0x7fffffff)); }
+	show("sub");
+	for (i = 0; i < 12; i++) for (j = 0; j < 12; j++) { a = v[i]; b = v[j]; mix(e_mul(a, b)); }
+	for (i = 0; i < 12; i++) { a = v[i]; mix(e_mul(a, 0)); mix(e_mul(a, 0 - 1)); mix(e_mul(a, 3)); mix(e_mul(a, 64)); mix(e_mul(a, 0x7fffffff)); }
+	show("mul");
+	for (i = 0; i < 12; i++) for (j = 0; j < 12; j++) { a = v[i]; b = v[j]; mix(e_sdiv(a, b)); }
+	for (i = 0; i < 12; i++) { a = v[i]; mix(e_sdiv(a, 0)); mix(e_sdiv(a, 0 - 1)); mix(e_sdiv(a, 3)); mix(e_sdiv(a, 64)); mix(e_sdiv(a, 0x7fffffff)); }
+	show("sdiv");
+	for (i = 0; i < 12; i++) for (j = 0; j < 12; j++) { a = v[i]; b = v[j]; mix(e_udiv(a, b)); }
+	for (i = 0; i < 12; i++) { a = v[i]; mix(e_udiv(a, 0)); mix(e_udiv(a, 0 - 1)); mix(e_udiv(a, 3)); mix(e_udiv(a, 64)); mix(e_udiv(a, 0x7fffffff)); }
+	show("udiv");
+	for (i = 0; i < 12; i++) for (j = 0; j < 12; j++) { a = v[i]; b = v[j]; mix(e_srem(a, b)); }
+	for (i = 0; i < 12; i++) { a = v[i]; mix(e_srem(a, 0)); mix(e_srem(a, 0 - 1)); mix(e_srem(a, 3)); mix(e_srem(a, 64)); mix(e_srem(a, 0x7fffffff)); }
+	show("srem");
+	for (i = 0; i < 12; i++) for (j = 0; j < 12; j++) { a = v[i]; b = v[j]; mix(e_urem(a, b)); }
+	for (i = 0; i < 12; i++) { a = v[i]; mix(e_urem(a, 0)); mix(e_urem(a, 0 - 1)); mix(e_urem(a, 3)); mix(e_urem(a, 64)); mix(e_urem(a, 0x7fffffff)); }
+	show("urem");
+	for (i = 0; i < 12; i++) for (j = 0; j < 12; j++) { a = v[i]; b = v[j]; mix(e_and(a, b)); }
+	for (i = 0; i < 12; i++) { a = v[i]; mix(e_and(a, 0)); mix(e_and(a, 0 - 1)); mix(e_and(a, 3)); mix(e_and(a, 64)); mix(e_and(a, 0x7fffffff)); }
+	show("and");
+	for (i = 0; i < 12; i++) for (j = 0; j < 12; j++) { a = v[i]; b = v[j]; mix(e_or(a, b)); }
+	for (i = 0; i < 12; i++) { a = v[i]; mix(e_or(a, 0)); mix(e_or(a, 0 - 1)); mix(e_or(a, 3)); mix(e_or(a, 64)); mix(e_or(a, 0x7fffffff)); }
+	show("or");
+	for (i = 0; i < 12; i++) for (j = 0; j < 12; j++) { a = v[i]; b = v[j]; mix(e_xor(a, b)); }
+	for (i = 0; i < 12; i++) { a = v[i]; mix(e_xor(a, 0)); mix(e_xor(a, 0 - 1)); mix(e_xor(a, 3)); mix(e_xor(a, 64)); mix(e_xor(a, 0x7fffffff)); }
+	show("xor");
+	for (i = 0; i < 12; i++) for (j = 0; j < 12; j++) { a = v[i]; b = v[j]; mix(e_shl(a, b)); }
+	for (i = 0; i < 12; i++) { a = v[i]; mix(e_shl(a, 0)); mix(e_shl(a, 0 - 1)); mix(e_shl(a, 3)); mix(e_shl(a, 64)); mix(e_shl(a, 0x7fffffff)); }
+	show("shl");
+	for (i = 0; i < 12; i++) for (j = 0; j < 12; j++) { a = v[i]; b = v[j]; mix(e_shr(a, b)); }
+	for (i = 0; i < 12; i++) { a = v[i]; mix(e_shr(a, 0)); mix(e_shr(a, 0 - 1)); mix(e_shr(a, 3)); mix(e_shr(a, 64)); mix(e_shr(a, 0x7fffffff)); }
+	show("shr");
+	for (i = 0; i < 12; i++) for (j = 0; j < 12; j++) { a = v[i]; b = v[j]; mix(e_sar(a, b)); }
+	for (i = 0; i < 12; i++) { a = v[i]; mix(e_sar(a, 0)); mix(e_sar(a, 0 - 1)); mix(e_sar(a, 3)); mix(e_sar(a, 64)); mix(e_sar(a, 0x7fffffff)); }
+	show("sar");
+	for (i = 0; i < 12; i++) for (j = 0; j < 12; j++) { a = v[i]; b = v[j]; mix(e_lt(a, b)); }
+	for (i = 0; i < 12; i++) { a = v[i]; mix(e_lt(a, 0)); mix(e_lt(a, 0 - 1)); mix(e_lt(a, 3)); mix(e_lt(a, 64)); mix(e_lt(a, 0x7fffffff)); }
+	show("lt");
+	for (i = 0; i < 12; i++) for (j = 0; j < 12; j++) { a = v[i]; b = v[j]; mix(e_ltu(a, b)); }
+	for (i = 0; i < 12; i++) { a = v[i]; mix(e_ltu(a, 0)); mix(e_ltu(a, 0 - 1)); mix(e_ltu(a, 3)); mix(e_ltu(a, 64)); mix(e_ltu(a, 0x7fffffff)); }
+	show("ltu");
+	for (i = 0; i < 12; i++) for (j = 0; j < 12; j++) { a = v[i]; b = v[j]; mix(e_eq(a, b)); }
+	for (i = 0; i < 12; i++) { a = v[i]; mix(e_eq(a, 0)); mix(e_eq(a, 0 - 1)); mix(e_eq(a, 3)); mix(e_eq(a, 64)); mix(e_eq(a, 0x7fffffff)); }
+	show("eq");
+	for (i = 0; i < 12; i++) for (j = 0; j < 12; j++) { a = v[i]; b = v[j]; mix(e_ne(a, b)); }
+	for (i = 0; i < 12; i++) { a = v[i]; mix(e_ne(a, 0)); mix(e_ne(a, 0 - 1)); mix(e_ne(a, 3)); mix(e_ne(a, 64)); mix(e_ne(a, 0x7fffffff)); }
+	show("ne");
+	for (i = 0; i < 12; i++) for (j = 0; j < 12; j++) { a = v[i]; b = v[j]; mix(e_min(a, b)); }
+	for (i = 0; i < 12; i++) { a = v[i]; mix(e_min(a, 0)); mix(e_min(a, 0 - 1)); mix(e_min(a, 3)); mix(e_min(a, 64)); mix(e_min(a, 0x7fffffff)); }
+	show("min");
+	for (i = 0; i < 12; i++) for (j = 0; j < 12; j++) { a = v[i]; b = v[j]; mix(e_max(a, b)); }
+	for (i = 0; i < 12; i++) { a = v[i]; mix(e_max(a, 0)); mix(e_max(a, 0 - 1)); mix(e_max(a, 3)); mix(e_max(a, 64)); mix(e_max(a, 0x7fffffff)); }
+	show("max");
+	for (i = 0; i < 12; i++) for (j = 0; j < 12; j++) { a = v[i]; b = v[j]; mix(e_minu(a, b)); }
+	for (i = 0; i < 12; i++) { a = v[i]; mix(e_minu(a, 0)); mix(e_minu(a, 0 - 1)); mix(e_minu(a, 3)); mix(e_minu(a, 64)); mix(e_minu(a, 0x7fffffff)); }
+	show("minu");
+	for (i = 0; i < 12; i++) for (j = 0; j < 12; j++) { a = v[i]; b = v[j]; mix(e_maxu(a, b)); }
+	for (i = 0; i < 12; i++) { a = v[i]; mix(e_maxu(a, 0)); mix(e_maxu(a, 0 - 1)); mix(e_maxu(a, 3)); mix(e_maxu(a, 64)); mix(e_maxu(a, 0x7fffffff)); }
+	show("maxu");
+	for (i = 0; i < 12; i++) for (j = 0; j < 12; j++) { a = v[i]; b = v[j]; mix(e_mulhs(a, b)); }
+	for (i = 0; i < 12; i++) { a = v[i]; mix(e_mulhs(a, 0)); mix(e_mulhs(a, 0 - 1)); mix(e_mulhs(a, 3)); mix(e_mulhs(a, 64)); mix(e_mulhs(a, 0x7fffffff)); }
+	show("mulhs");
+	for (i = 0; i < 12; i++) for (j = 0; j < 12; j++) { a = v[i]; b = v[j]; mix(e_mulhu(a, b)); }
+	for (i = 0; i < 12; i++) { a = v[i]; mix(e_mulhu(a, 0)); mix(e_mulhu(a, 0 - 1)); mix(e_mulhu(a, 3)); mix(e_mulhu(a, 64)); mix(e_mulhu(a, 0x7fffffff)); }
+	show("mulhu");
+	for (i = 0; i < 12; i++) for (j = 0; j < 12; j++) { a = v[i]; b = v[j]; mix(e_rotl(a, b)); }
+	for (i = 0; i < 12; i++) { a = v[i]; mix(e_rotl(a, 0)); mix(e_rotl(a, 0 - 1)); mix(e_rotl(a, 3)); mix(e_rotl(a, 64)); mix(e_rotl(a, 0x7fffffff)); }
+	show("rotl");
+	for (i = 0; i < 12; i++) for (j = 0; j < 12; j++) { a = v[i]; b = v[j]; mix(e_rotr(a, b)); }
+	for (i = 0; i < 12; i++) { a = v[i]; mix(e_rotr(a, 0)); mix(e_rotr(a, 0 - 1)); mix(e_rotr(a, 3)); mix(e_rotr(a, 64)); mix(e_rotr(a, 0x7fffffff)); }
+	show("rotr");
+	for (i = 0; i < 12; i++) { a = v[i]; mix(u_neg(a)); } mix(u_neg(0)); mix(u_neg(0 - 1)); mix(u_neg(8));
+	show("neg");
+	for (i = 0; i < 12; i++) { a = v[i]; mix(u_not(a)); } mix(u_not(0)); mix(u_not(0 - 1)); mix(u_not(8));
+	show("not");
+	for (i = 0; i < 12; i++) { a = v[i]; mix(u_clz(a)); } mix(u_clz(0)); mix(u_clz(0 - 1)); mix(u_clz(8));
+	show("clz");
+	for (i = 0; i < 12; i++) { a = v[i]; mix(u_ctz(a)); } mix(u_ctz(0)); mix(u_ctz(0 - 1)); mix(u_ctz(8));
+	show("ctz");
+	for (i = 0; i < 12; i++) { a = v[i]; mix(u_abs(a)); } mix(u_abs(0)); mix(u_abs(0 - 1)); mix(u_abs(8));
+	show("abs");
+	for (i = 0; i < 12; i++) { a = v[i]; mix(u_bswap(a)); } mix(u_bswap(0)); mix(u_bswap(0 - 1)); mix(u_bswap(8));
+	show("bswap");
+	for (i = 0; i < 12; i++) { a = v[i]; mix(e_sel(a, 5, 9)); mix(e_sel(a, a, 0 - a)); mix(e_sel(0, a, 2)); }
+	show("sel");
+	mix(e_ld(0 - 1)); mix(e_ld(1 << 62)); a = g; mix(e_ld(a) == g[0]); mix(e_st(a, 42)); mix(g[0]); mix(e_st(0 - 5, 1));
+	show("ld st");
+	for (i = 0; i < 12; i++) for (j = 0; j < 12; j++) { a = v[i]; b = v[j]; mix(e_mix(a, b)); mix(e_mix(a, 5)); }
+	show("mix");
+	rt.free(g);
+	return 0;
+}