[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-devel] [PATCH for-4.1 v2 12/13] tcg/ppc: Update vector support to
|
From: |
Richard Henderson |
|
Subject: |
[Qemu-devel] [PATCH for-4.1 v2 12/13] tcg/ppc: Update vector support to v2.07 |
|
Date: |
Sun, 17 Mar 2019 02:08:33 -0700 |
This includes single-word loads and stores, lots of double-word
arithmetic, and a few extra logical operations.
Signed-off-by: Richard Henderson <address@hidden>
---
tcg/ppc/tcg-target.h | 3 +-
tcg/ppc/tcg-target.inc.c | 155 +++++++++++++++++++++++++++++++++------
2 files changed, 134 insertions(+), 24 deletions(-)
diff --git a/tcg/ppc/tcg-target.h b/tcg/ppc/tcg-target.h
index 5797ad35d5..4bbb33df7e 100644
--- a/tcg/ppc/tcg-target.h
+++ b/tcg/ppc/tcg-target.h
@@ -60,6 +60,7 @@ typedef enum {
extern bool have_isa_altivec;
extern bool have_isa_2_06;
+extern bool have_isa_2_07_vsx;
extern bool have_isa_3_00;
/* optional instructions automatically implemented */
@@ -142,7 +143,7 @@ extern bool have_isa_3_00;
#endif
#define TCG_TARGET_HAS_andc_vec 1
-#define TCG_TARGET_HAS_orc_vec 0
+#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_shi_vec 0
diff --git a/tcg/ppc/tcg-target.inc.c b/tcg/ppc/tcg-target.inc.c
index e6f3dca394..b8df9b55cf 100644
--- a/tcg/ppc/tcg-target.inc.c
+++ b/tcg/ppc/tcg-target.inc.c
@@ -67,6 +67,7 @@ static tcg_insn_unit *tb_ret_addr;
bool have_isa_altivec;
bool have_isa_2_06;
bool have_isa_2_06_vsx;
+bool have_isa_2_07_vsx;
bool have_isa_3_00;
#define HAVE_ISA_2_06 have_isa_2_06
@@ -473,10 +474,12 @@ static int tcg_target_const_match(tcg_target_long val,
TCGType type,
#define LVEWX XO31(71)
#define LXSDX XO31(588) /* v2.06 */
#define LXVDSX XO31(332) /* v2.06 */
+#define LXSIWZX XO31(12) /* v2.07 */
#define STVX XO31(231)
#define STVEWX XO31(199)
#define STXSDX XO31(716) /* v2.06 */
+#define STXSIWX XO31(140) /* v2.07 */
#define VADDSBS VX4(768)
#define VADDUBS VX4(512)
@@ -487,6 +490,7 @@ static int tcg_target_const_match(tcg_target_long val,
TCGType type,
#define VADDSWS VX4(896)
#define VADDUWS VX4(640)
#define VADDUWM VX4(128)
+#define VADDUDM VX4(192) /* v2.07 */
#define VSUBSBS VX4(1792)
#define VSUBUBS VX4(1536)
@@ -497,47 +501,62 @@ static int tcg_target_const_match(tcg_target_long val,
TCGType type,
#define VSUBSWS VX4(1920)
#define VSUBUWS VX4(1664)
#define VSUBUWM VX4(1152)
+#define VSUBUDM VX4(1216) /* v2.07 */
#define VMAXSB VX4(258)
#define VMAXSH VX4(322)
#define VMAXSW VX4(386)
+#define VMAXSD VX4(450) /* v2.07 */
#define VMAXUB VX4(2)
#define VMAXUH VX4(66)
#define VMAXUW VX4(130)
+#define VMAXUD VX4(194) /* v2.07 */
#define VMINSB VX4(770)
#define VMINSH VX4(834)
#define VMINSW VX4(898)
+#define VMINSD VX4(962) /* v2.07 */
#define VMINUB VX4(514)
#define VMINUH VX4(578)
#define VMINUW VX4(642)
+#define VMINUD VX4(706) /* v2.07 */
#define VCMPEQUB VX4(6)
#define VCMPEQUH VX4(70)
#define VCMPEQUW VX4(134)
+#define VCMPEQUD VX4(199) /* v2.07 */
#define VCMPGTSB VX4(774)
#define VCMPGTSH VX4(838)
#define VCMPGTSW VX4(902)
+#define VCMPGTSD VX4(967) /* v2.07 */
#define VCMPGTUB VX4(518)
#define VCMPGTUH VX4(582)
#define VCMPGTUW VX4(646)
+#define VCMPGTUD VX4(711) /* v2.07 */
#define VSLB VX4(260)
#define VSLH VX4(324)
#define VSLW VX4(388)
+#define VSLD VX4(1476) /* v2.07 */
#define VSRB VX4(516)
#define VSRH VX4(580)
#define VSRW VX4(644)
+#define VSRD VX4(1732) /* v2.07 */
#define VSRAB VX4(772)
#define VSRAH VX4(836)
#define VSRAW VX4(900)
+#define VSRAD VX4(964) /* v2.07 */
#define VRLB VX4(4)
#define VRLH VX4(68)
#define VRLW VX4(132)
+#define VRLD VX4(196) /* v2.07 */
#define VMULEUB VX4(520)
#define VMULEUH VX4(584)
+#define VMULEUW VX4(648) /* v2.07 */
#define VMULOUB VX4(8)
#define VMULOUH VX4(72)
+#define VMULOUW VX4(136) /* v2.07 */
+#define VMULUWM VX4(137) /* v2.07 */
#define VMSUMUHM VX4(38)
#define VMRGHB VX4(12)
@@ -555,6 +574,9 @@ static int tcg_target_const_match(tcg_target_long val,
TCGType type,
#define VNOR VX4(1284)
#define VOR VX4(1156)
#define VXOR VX4(1220)
+#define VEQV VX4(1668) /* v2.07 */
+#define VNAND VX4(1412) /* v2.07 */
+#define VORC VX4(1348) /* v2.07 */
#define VSPLTB VX4(524)
#define VSPLTH VX4(588)
@@ -568,6 +590,11 @@ static int tcg_target_const_match(tcg_target_long val,
TCGType type,
#define XXPERMDI (OPCD(60) | (10 << 3)) /* 2.06 */
+#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 RT(r) ((r)<<21)
#define RS(r) ((r)<<21)
#define RA(r) ((r)<<16)
@@ -691,7 +718,15 @@ static bool tcg_out_mov(TCGContext *s, TCGType type,
TCGReg ret, TCGReg arg)
if (ret < 32 && arg < 32) {
tcg_out32(s, OR | SAB(arg, ret, arg));
break;
- } else if (ret < 32 || arg < 32) {
+ } else if (ret < 32 && have_isa_2_07_vsx) {
+ tcg_out32(s, (type == TCG_TYPE_I32 ? MFVSRWZ : MFVSRD)
+ | VRT(arg) | RA(ret) | 1);
+ break;
+ } else if (arg < 32 && have_isa_2_07_vsx) {
+ tcg_out32(s, (type == TCG_TYPE_I32 ? MTVSRWZ : MTVSRD)
+ | VRT(ret) | RA(arg) | 1);
+ break;
+ } else {
/* Altivec does not support vector/integer moves. */
return false;
}
@@ -1113,6 +1148,10 @@ static void tcg_out_ld(TCGContext *s, TCGType type,
TCGReg ret,
tcg_out_mem_long(s, LWZ, LWZX, ret, base, offset);
break;
}
+ if (have_isa_2_07_vsx) {
+ tcg_out_mem_long(s, 0, LXSIWZX | 1, ret & 31, base, offset);
+ break;
+ }
assert((offset & 3) == 0);
tcg_out_mem_long(s, 0, LVEWX, ret & 31, base, offset);
shift = (offset - 4) & 0xc;
@@ -1159,6 +1198,10 @@ static void tcg_out_st(TCGContext *s, TCGType type,
TCGReg arg,
tcg_out_mem_long(s, STW, STWX, arg, base, offset);
break;
}
+ if (have_isa_2_07_vsx) {
+ tcg_out_mem_long(s, 0, STXSIWX | 1, arg & 31, base, offset);
+ break;
+ }
assert((offset & 3) == 0);
shift = (offset - 4) & 0xc;
if (shift) {
@@ -2891,26 +2934,39 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type,
unsigned vece)
case INDEX_op_not_vec:
case INDEX_op_dupm_vec:
return 1;
+ case INDEX_op_orc_vec:
+ return have_isa_2_07_vsx;
case INDEX_op_add_vec:
case INDEX_op_sub_vec:
case INDEX_op_smax_vec:
case INDEX_op_smin_vec:
case INDEX_op_umax_vec:
case INDEX_op_umin_vec:
+ case INDEX_op_shlv_vec:
+ case INDEX_op_shrv_vec:
+ case INDEX_op_sarv_vec:
+ return vece <= MO_32 || have_isa_2_07_vsx;
case INDEX_op_ssadd_vec:
case INDEX_op_sssub_vec:
case INDEX_op_usadd_vec:
case INDEX_op_ussub_vec:
- case INDEX_op_shlv_vec:
- case INDEX_op_shrv_vec:
- case INDEX_op_sarv_vec:
return vece <= MO_32;
case INDEX_op_cmp_vec:
- case INDEX_op_mul_vec:
case INDEX_op_shli_vec:
case INDEX_op_shri_vec:
case INDEX_op_sari_vec:
- return vece <= MO_32 ? -1 : 0;
+ return vece <= MO_32 || have_isa_2_07_vsx ? -1 : 0;
+ case INDEX_op_mul_vec:
+ switch (vece) {
+ case MO_8:
+ case MO_16:
+ return -1;
+ case MO_32:
+ return have_isa_2_07_vsx ? 1 : -1;
+ case MO_64:
+ return have_isa_2_07_vsx ? -1 : 0;
+ }
+ return 0;
default:
return 0;
}
@@ -2974,28 +3030,28 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
const TCGArg *args, const int *const_args)
{
static const uint32_t
- add_op[4] = { VADDUBM, VADDUHM, VADDUWM, 0 },
- sub_op[4] = { VSUBUBM, VSUBUHM, VSUBUWM, 0 },
- eq_op[4] = { VCMPEQUB, VCMPEQUH, VCMPEQUW, 0 },
- gts_op[4] = { VCMPGTSB, VCMPGTSH, VCMPGTSW, 0 },
- gtu_op[4] = { VCMPGTUB, VCMPGTUH, VCMPGTUW, 0 },
+ add_op[4] = { VADDUBM, VADDUHM, VADDUWM, VADDUDM },
+ sub_op[4] = { VSUBUBM, VSUBUHM, VSUBUWM, VSUBUDM },
+ eq_op[4] = { VCMPEQUB, VCMPEQUH, VCMPEQUW, VCMPEQUD },
+ gts_op[4] = { VCMPGTSB, VCMPGTSH, VCMPGTSW, VCMPGTSD },
+ gtu_op[4] = { VCMPGTUB, VCMPGTUH, VCMPGTUW, VCMPGTUD },
ssadd_op[4] = { VADDSBS, VADDSHS, VADDSWS, 0 },
usadd_op[4] = { VADDUBS, VADDUHS, VADDUWS, 0 },
sssub_op[4] = { VSUBSBS, VSUBSHS, VSUBSWS, 0 },
ussub_op[4] = { VSUBUBS, VSUBUHS, VSUBUWS, 0 },
- umin_op[4] = { VMINUB, VMINUH, VMINUW, 0 },
- smin_op[4] = { VMINSB, VMINSH, VMINSW, 0 },
- umax_op[4] = { VMAXUB, VMAXUH, VMAXUW, 0 },
- smax_op[4] = { VMAXSB, VMAXSH, VMAXSW, 0 },
- shlv_op[4] = { VSLB, VSLH, VSLW, 0 },
- shrv_op[4] = { VSRB, VSRH, VSRW, 0 },
- sarv_op[4] = { VSRAB, VSRAH, VSRAW, 0 },
+ umin_op[4] = { VMINUB, VMINUH, VMINUW, VMINUD },
+ smin_op[4] = { VMINSB, VMINSH, VMINSW, VMINSD },
+ umax_op[4] = { VMAXUB, VMAXUH, VMAXUW, VMAXUD },
+ smax_op[4] = { VMAXSB, VMAXSH, VMAXSW, VMAXSD },
+ shlv_op[4] = { VSLB, VSLH, VSLW, VSLD },
+ shrv_op[4] = { VSRB, VSRH, VSRW, VSRD },
+ sarv_op[4] = { VSRAB, VSRAH, VSRAW, VSRAD },
mrgh_op[4] = { VMRGHB, VMRGHH, VMRGHW, 0 },
mrgl_op[4] = { VMRGLB, VMRGLH, VMRGLW, 0 },
- muleu_op[4] = { VMULEUB, VMULEUH, 0, 0 },
- mulou_op[4] = { VMULOUB, VMULOUH, 0, 0 },
+ muleu_op[4] = { VMULEUB, VMULEUH, VMULEUW, 0 },
+ mulou_op[4] = { VMULOUB, VMULOUH, VMULOUW, 0 },
pkum_op[4] = { VPKUHUM, VPKUWUM, 0, 0 },
- rotl_op[4] = { VRLB, VRLH, VRLW, 0 };
+ rotl_op[4] = { VRLB, VRLH, VRLW, VRLD };
TCGType type = vecl + TCG_TYPE_V64;
TCGArg a0 = args[0], a1 = args[1], a2 = args[2];
@@ -3017,6 +3073,10 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
case INDEX_op_sub_vec:
insn = sub_op[vece];
break;
+ case INDEX_op_mul_vec:
+ tcg_debug_assert(vece == MO_32 && have_isa_2_07_vsx);
+ insn = VMULUWM;
+ break;
case INDEX_op_ssadd_vec:
insn = ssadd_op[vece];
break;
@@ -3066,8 +3126,28 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
insn = VNOR;
a2 = a1;
break;
+ case INDEX_op_orc_vec:
+ insn = VORC;
+ break;
case INDEX_op_dup_vec:
+ if (a1 < 32) {
+ bool ok;
+ switch (vece) {
+ case MO_64:
+ ok = tcg_out_mov(s, TCG_TYPE_I64, a0, a1);
+ break;
+ case MO_32:
+ case MO_16:
+ case MO_8:
+ ok = tcg_out_mov(s, TCG_TYPE_I32, a0, a1);
+ break;
+ default:
+ g_assert_not_reached();
+ }
+ tcg_debug_assert(ok);
+ a1 = a0;
+ }
/* Recall we use VSX integer loads, so the integer is right
justified within the left (zero-index) double-word. */
switch (vece) {
@@ -3165,7 +3245,7 @@ static void expand_vec_cmp(TCGType type, unsigned vece,
TCGv_vec v0,
{
bool need_swap = false, need_inv = false;
- tcg_debug_assert(vece <= MO_32);
+ tcg_debug_assert(vece <= MO_32 || have_isa_2_07_vsx);
switch (cond) {
case TCG_COND_EQ:
@@ -3229,6 +3309,7 @@ static void expand_vec_mul(TCGType type, unsigned vece,
TCGv_vec v0,
break;
case MO_32:
+ tcg_debug_assert(!have_isa_2_07_vsx);
t3 = tcg_temp_new_vec(type);
t4 = tcg_temp_new_vec(type);
tcg_gen_dupi_vec(MO_8, t4, -16);
@@ -3246,6 +3327,27 @@ static void expand_vec_mul(TCGType type, unsigned vece,
TCGv_vec v0,
tcg_temp_free_vec(t4);
break;
+ case MO_64:
+ tcg_debug_assert(have_isa_2_07_vsx);
+ t3 = tcg_temp_new_vec(type);
+ t4 = tcg_temp_new_vec(type);
+ tcg_gen_dupi_vec(MO_8, t4, 32);
+ vec_gen_3(INDEX_op_ppc_rotl_vec, type, MO_64, tcgv_vec_arg(t2),
+ tcgv_vec_arg(v2), tcgv_vec_arg(t4));
+ vec_gen_3(INDEX_op_ppc_mulou_vec, type, MO_32, tcgv_vec_arg(t3),
+ tcgv_vec_arg(v1), tcgv_vec_arg(t2));
+ vec_gen_3(INDEX_op_ppc_muleu_vec, type, MO_32, tcgv_vec_arg(t2),
+ tcgv_vec_arg(v1), tcgv_vec_arg(t2));
+ vec_gen_3(INDEX_op_ppc_mulou_vec, type, MO_32, tcgv_vec_arg(t1),
+ tcgv_vec_arg(v1), tcgv_vec_arg(v2));
+ tcg_gen_add_vec(MO_64, t2, t2, t3);
+ vec_gen_3(INDEX_op_shlv_vec, type, MO_32, tcgv_vec_arg(t2),
+ tcgv_vec_arg(t2), tcgv_vec_arg(t4));
+ tcg_gen_add_vec(MO_64, v0, t1, t2);
+ tcg_temp_free_vec(t3);
+ tcg_temp_free_vec(t4);
+ break;
+
default:
g_assert_not_reached();
}
@@ -3327,6 +3429,7 @@ 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
@@ -3494,8 +3597,9 @@ 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:
return &v_v;
+ case INDEX_op_dup_vec:
+ return have_isa_2_07_vsx ? &v_vr : &v_v;
case INDEX_op_ld_vec:
case INDEX_op_st_vec:
case INDEX_op_dupm_vec:
@@ -3522,6 +3626,11 @@ static void tcg_target_init(TCGContext *s)
have_isa_2_06_vsx = true;
}
}
+ if (hwcap2 & PPC_FEATURE2_ARCH_2_07) {
+ if (hwcap & PPC_FEATURE_HAS_VSX) {
+ have_isa_2_07_vsx = true;
+ }
+ }
#ifdef PPC_FEATURE2_ARCH_3_00
if (hwcap2 & PPC_FEATURE2_ARCH_3_00) {
have_isa_3_00 = true;
--
2.17.2
- Re: [Qemu-devel] [PATCH for-4.1 v2 02/13] tcg: Return bool success from tcg_out_mov, (continued)
- [Qemu-devel] [PATCH for-4.1 v2 03/13] tcg: Support cross-class moves without instruction support, Richard Henderson, 2019/03/17
- [Qemu-devel] [PATCH for-4.1 v2 08/13] tcg/ppc: Implement INDEX_op_dupm_vec, Richard Henderson, 2019/03/17
- [Qemu-devel] [PATCH for-4.1 v2 07/13] tcg: Add INDEX_op_dup_mem_vec, Richard Henderson, 2019/03/17
- [Qemu-devel] [PATCH for-4.1 v2 09/13] tcg/ppc: Support vector shift by immediate, Richard Henderson, 2019/03/17
- [Qemu-devel] [PATCH for-4.1 v2 10/13] tcg/ppc: Support vector multiply, Richard Henderson, 2019/03/17
- [Qemu-devel] [PATCH for-4.1 v2 11/13] tcg/ppc: Update vector support to v2.06, Richard Henderson, 2019/03/17
- [Qemu-devel] [PATCH for-4.1 v2 06/13] tcg/ppc: Initial backend support for Altivec, Richard Henderson, 2019/03/17
- [Qemu-devel] [PATCH for-4.1 v2 12/13] tcg/ppc: Update vector support to v2.07,
Richard Henderson <=
- [Qemu-devel] [PATCH for-4.1 v2 13/13] tcg/ppc: Update vector support to v3.00, Richard Henderson, 2019/03/17
- Re: [Qemu-devel] [PATCH for-4.1 v2 00/13] tcg/ppc: Add vector opcodes, no-reply, 2019/03/17