@@ -63,6 +63,7 @@ extern bool have_isa_2_06;
extern bool have_isa_2_06_vsx;
extern bool have_isa_2_07_vsx;
extern bool have_isa_3_00;
+extern bool have_isa_3_00_vsx;
/* optional instructions automatically implemented */
#define TCG_TARGET_HAS_ext8u_i32 0 /* andi */
@@ -147,7 +148,7 @@ extern bool have_isa_3_00;
#define TCG_TARGET_HAS_andc_vec 1
#define TCG_TARGET_HAS_orc_vec have_isa_2_07_vsx
#define TCG_TARGET_HAS_not_vec 1
-#define TCG_TARGET_HAS_neg_vec 0
+#define TCG_TARGET_HAS_neg_vec have_isa_3_00_vsx
#define TCG_TARGET_HAS_shi_vec 0
#define TCG_TARGET_HAS_shs_vec 0
#define TCG_TARGET_HAS_shv_vec 1
@@ -69,6 +69,7 @@ bool have_isa_2_06;
bool have_isa_2_06_vsx;
bool have_isa_2_07_vsx;
bool have_isa_3_00;
+bool have_isa_3_00_vsx;
#define HAVE_ISA_2_06 have_isa_2_06
#define HAVE_ISEL have_isa_2_06
@@ -475,11 +476,16 @@ static int tcg_target_const_match(tcg_target_long val, TCGType type,
#define LXSDX XO31(588) /* v2.06 */
#define LXVDSX XO31(332) /* v2.06 */
#define LXSIWZX XO31(12) /* v2.07 */
+#define LXV (OPCD(61) | 1) /* v3.00 */
+#define LXSD (OPCD(57) | 2) /* v3.00 */
+#define LXVWSX XO31(364) /* v3.00 */
#define STVX XO31(231)
#define STVEWX XO31(199)
#define STXSDX XO31(716) /* v2.06 */
#define STXSIWX XO31(140) /* v2.07 */
+#define STXV (OPCD(61) | 5) /* v3.00 */
+#define STXSD (OPCD(61) | 2) /* v3.00 */
#define VADDSBS VX4(768)
#define VADDUBS VX4(512)
@@ -503,6 +509,9 @@ static int tcg_target_const_match(tcg_target_long val, TCGType type,
#define VSUBUWM VX4(1152)
#define VSUBUDM VX4(1216) /* v2.07 */
+#define VNEGW (VX4(1538) | (6 << 16)) /* v3.00 */
+#define VNEGD (VX4(1538) | (7 << 16)) /* v3.00 */
+
#define VMAXSB VX4(258)
#define VMAXSH VX4(322)
#define VMAXSW VX4(386)
@@ -532,6 +541,9 @@ static int tcg_target_const_match(tcg_target_long val, TCGType type,
#define VCMPGTUH VX4(582)
#define VCMPGTUW VX4(646)
#define VCMPGTUD VX4(711) /* v2.07 */
+#define VCMPNEB VX4(7) /* v3.00 */
+#define VCMPNEH VX4(71) /* v3.00 */
+#define VCMPNEW VX4(135) /* v3.00 */
#define VSLB VX4(260)
#define VSLH VX4(324)
@@ -588,11 +600,14 @@ static int tcg_target_const_match(tcg_target_long val, TCGType type,
#define VSLDOI VX4(44)
#define XXPERMDI (OPCD(60) | (10 << 3)) /* v2.06 */
+#define XXSPLTIB (OPCD(60) | (360 << 1)) /* v3.00 */
#define MFVSRD XO31(51) /* v2.07 */
#define MFVSRWZ XO31(115) /* v2.07 */
#define MTVSRD XO31(179) /* v2.07 */
#define MTVSRWZ XO31(179) /* v2.07 */
+#define MTVSRDD XO31(435) /* v3.00 */
+#define MTVSRWS XO31(403) /* v3.00 */
#define RT(r) ((r)<<21)
#define RS(r) ((r)<<21)
@@ -919,6 +934,10 @@ static void tcg_out_dupi_vec(TCGContext *s, TCGType type, TCGReg ret,
return;
}
}
+ if (have_isa_3_00_vsx && val == (tcg_target_long)dup_const(MO_8, val)) {
+ tcg_out32(s, XXSPLTIB | VRT(ret) | ((val & 0xff) << 11) | 1);
+ return;
+ }
/*
* Otherwise we must load the value from the constant pool.
@@ -1104,7 +1123,7 @@ static void tcg_out_mem_long(TCGContext *s, int opi, int opx, TCGReg rt,
TCGReg base, tcg_target_long offset)
{
tcg_target_long orig = offset, l0, l1, extra = 0, align = 0;
- bool is_store = false;
+ bool is_int_store = false;
TCGReg rs = TCG_REG_TMP1;
switch (opi) {
@@ -1117,11 +1136,20 @@ static void tcg_out_mem_long(TCGContext *s, int opi, int opx, TCGReg rt,
break;
}
break;
+ case LXSD:
+ case STXSD:
+ align = 3;
+ break;
+ case LXV: case LXV | 8:
+ case STXV: case STXV | 8:
+ /* The |8 cases force altivec registers. */
+ align = 15;
+ break;
case STD:
align = 3;
/* FALLTHRU */
case STB: case STH: case STW:
- is_store = true;
+ is_int_store = true;
break;
}
@@ -1130,7 +1158,7 @@ static void tcg_out_mem_long(TCGContext *s, int opi, int opx, TCGReg rt,
if (rs == base) {
rs = TCG_REG_R0;
}
- tcg_debug_assert(!is_store || rs != rt);
+ tcg_debug_assert(!is_int_store || rs != rt);
tcg_out_movi(s, TCG_TYPE_PTR, rs, orig);
tcg_out32(s, opx | TAB(rt, base, rs));
return;
@@ -1194,7 +1222,8 @@ static void tcg_out_ld(TCGContext *s, TCGType type, TCGReg ret,
case TCG_TYPE_V64:
tcg_debug_assert(ret >= 32);
if (have_isa_2_06_vsx) {
- tcg_out_mem_long(s, 0, LXSDX | 1, ret & 31, base, offset);
+ tcg_out_mem_long(s, have_isa_3_00_vsx ? LXSD : 0, LXSDX | 1,
+ ret & 31, base, offset);
break;
}
assert((offset & 7) == 0);
@@ -1206,7 +1235,8 @@ static void tcg_out_ld(TCGContext *s, TCGType type, TCGReg ret,
case TCG_TYPE_V128:
tcg_debug_assert(ret >= 32);
assert((offset & 15) == 0);
- tcg_out_mem_long(s, 0, LVX, ret & 31, base, offset);
+ tcg_out_mem_long(s, have_isa_3_00_vsx ? LXV | 8 : 0, LVX,
+ ret & 31, base, offset);
break;
default:
g_assert_not_reached();
@@ -1245,7 +1275,8 @@ static void tcg_out_st(TCGContext *s, TCGType type, TCGReg arg,
case TCG_TYPE_V64:
tcg_debug_assert(arg >= 32);
if (have_isa_2_06_vsx) {
- tcg_out_mem_long(s, 0, STXSDX | 1, arg & 31, base, offset);
+ tcg_out_mem_long(s, have_isa_3_00_vsx ? STXSD : 0,
+ STXSDX | 1, arg & 31, base, offset);
break;
}
assert((offset & 7) == 0);
@@ -1258,7 +1289,8 @@ static void tcg_out_st(TCGContext *s, TCGType type, TCGReg arg,
break;
case TCG_TYPE_V128:
tcg_debug_assert(arg >= 32);
- tcg_out_mem_long(s, 0, STVX, arg & 31, base, offset);
+ tcg_out_mem_long(s, have_isa_3_00_vsx ? STXV | 8 : 0, STVX,
+ arg & 31, base, offset);
break;
default:
g_assert_not_reached();
@@ -2979,6 +3011,8 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
case INDEX_op_shri_vec:
case INDEX_op_sari_vec:
return vece <= MO_32 || have_isa_2_07_vsx ? -1 : 0;
+ case INDEX_op_neg_vec:
+ return vece >= MO_32 && have_isa_3_00_vsx;
case INDEX_op_mul_vec:
switch (vece) {
case MO_8:
@@ -2997,7 +3031,22 @@ static bool tcg_out_dup_vec(TCGContext *s, TCGType type, unsigned vece,
TCGReg dst, TCGReg src)
{
tcg_debug_assert(dst >= 32);
- tcg_debug_assert(src >= 32);
+
+ /* Splat from integer reg allowed via constraints for v3.00. */
+ if (src < 32) {
+ tcg_debug_assert(have_isa_3_00_vsx);
+ switch (vece) {
+ case MO_64:
+ tcg_out32(s, MTVSRDD | 1 | VRT(dst) | RA(src) | RB(src));
+ return true;
+ case MO_32:
+ tcg_out32(s, MTVSRWS | 1 | VRT(dst) | RA(src));
+ return true;
+ default:
+ /* Fail, so that we fall back on either dupm or mov+dup. */
+ return false;
+ }
+ }
/*
* Recall we use (or emulate) VSX integer loads, so the integer is
@@ -3036,7 +3085,11 @@ static bool tcg_out_dupm_vec(TCGContext *s, TCGType type, unsigned vece,
out &= 31;
switch (vece) {
case MO_8:
- tcg_out_mem_long(s, 0, LVEBX, out, base, offset);
+ if (have_isa_3_00_vsx) {
+ tcg_out_mem_long(s, LXV | 8, LVX, out, base, offset & -16);
+ } else {
+ tcg_out_mem_long(s, 0, LVEBX, out, base, offset);
+ }
elt = extract32(offset, 0, 4);
#ifndef HOST_WORDS_BIGENDIAN
elt ^= 15;
@@ -3045,7 +3098,11 @@ static bool tcg_out_dupm_vec(TCGContext *s, TCGType type, unsigned vece,
break;
case MO_16:
assert((offset & 1) == 0);
- tcg_out_mem_long(s, 0, LVEHX, out, base, offset);
+ if (have_isa_3_00_vsx) {
+ tcg_out_mem_long(s, LXV | 8, LVX, out, base, offset & -16);
+ } else {
+ tcg_out_mem_long(s, 0, LVEHX, out, base, offset);
+ }
elt = extract32(offset, 1, 3);
#ifndef HOST_WORDS_BIGENDIAN
elt ^= 7;
@@ -3053,6 +3110,10 @@ static bool tcg_out_dupm_vec(TCGContext *s, TCGType type, unsigned vece,
tcg_out32(s, VSPLTH | VRT(out) | VRB(out) | (elt << 16));
break;
case MO_32:
+ if (have_isa_3_00_vsx) {
+ tcg_out_mem_long(s, 0, LXVWSX | 1, out, base, offset);
+ break;
+ }
assert((offset & 3) == 0);
tcg_out_mem_long(s, 0, LVEWX, out, base, offset);
elt = extract32(offset, 2, 2);
@@ -3092,7 +3153,9 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
static const uint32_t
add_op[4] = { VADDUBM, VADDUHM, VADDUWM, VADDUDM },
sub_op[4] = { VSUBUBM, VSUBUHM, VSUBUWM, VSUBUDM },
+ neg_op[4] = { 0, 0, VNEGW, VNEGD },
eq_op[4] = { VCMPEQUB, VCMPEQUH, VCMPEQUW, VCMPEQUD },
+ ne_op[4] = { VCMPNEB, VCMPNEH, VCMPNEW, 0 },
gts_op[4] = { VCMPGTSB, VCMPGTSH, VCMPGTSW, VCMPGTSD },
gtu_op[4] = { VCMPGTUB, VCMPGTUH, VCMPGTUW, VCMPGTUD },
ssadd_op[4] = { VADDSBS, VADDSHS, VADDSWS, 0 },
@@ -3134,6 +3197,11 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
case INDEX_op_sub_vec:
insn = sub_op[vece];
break;
+ case INDEX_op_neg_vec:
+ insn = neg_op[vece];
+ a2 = a1;
+ a1 = 0;
+ break;
case INDEX_op_mul_vec:
tcg_debug_assert(vece == MO_32 && have_isa_2_07_vsx);
insn = VMULUWM;
@@ -3196,6 +3264,9 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
case TCG_COND_EQ:
insn = eq_op[vece];
break;
+ case TCG_COND_NE:
+ insn = ne_op[vece];
+ break;
case TCG_COND_GT:
insn = gts_op[vece];
break;
@@ -3266,6 +3337,10 @@ static void expand_vec_cmp(TCGType type, unsigned vece, TCGv_vec v0,
case TCG_COND_GTU:
break;
case TCG_COND_NE:
+ if (have_isa_3_00_vsx && vece <= MO_32) {
+ break;
+ }
+ /* fall through */
case TCG_COND_LE:
case TCG_COND_LEU:
need_inv = true;
@@ -3421,6 +3496,7 @@ static const TCGTargetOpDef *tcg_target_op_def(TCGOpcode op)
static const TCGTargetOpDef sub2
= { .args_ct_str = { "r", "r", "rI", "rZM", "r", "r" } };
static const TCGTargetOpDef v_r = { .args_ct_str = { "v", "r" } };
+ static const TCGTargetOpDef v_vr = { .args_ct_str = { "v", "vr" } };
static const TCGTargetOpDef v_v = { .args_ct_str = { "v", "v" } };
static const TCGTargetOpDef v_v_v = { .args_ct_str = { "v", "v", "v" } };
static const TCGTargetOpDef v_v_v_v
@@ -3588,8 +3664,10 @@ static const TCGTargetOpDef *tcg_target_op_def(TCGOpcode op)
case INDEX_op_ppc_rotl_vec:
return &v_v_v;
case INDEX_op_not_vec:
- case INDEX_op_dup_vec:
+ case INDEX_op_neg_vec:
return &v_v;
+ case INDEX_op_dup_vec:
+ return have_isa_3_00_vsx ? &v_vr : &v_v;
case INDEX_op_ld_vec:
case INDEX_op_st_vec:
case INDEX_op_dupm_vec:
@@ -3624,6 +3702,9 @@ static void tcg_target_init(TCGContext *s)
#ifdef PPC_FEATURE2_ARCH_3_00
if (hwcap2 & PPC_FEATURE2_ARCH_3_00) {
have_isa_3_00 = true;
+ if (hwcap & PPC_FEATURE_HAS_VSX) {
+ have_isa_3_00_vsx = true;
+ }
}
#endif
This includes vector load/store with immediate offset, some extra move and splat insns, compare ne, and negate. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/ppc/tcg-target.h | 3 +- tcg/ppc/tcg-target.inc.c | 103 ++++++++++++++++++++++++++++++++++----- 2 files changed, 94 insertions(+), 12 deletions(-) -- 2.17.2