tcg/ppc: Add support for vector maximum/minimum

Add support for vector maximum/minimum using Altivec instructions
VMAXSB, VMAXSH, VMAXSW, VMAXUB, VMAXUH, VMAXUW, and
VMINSB, VMINSH, VMINSW, VMINUB, VMINUH, VMINUW.

Tested-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
Reviewed-by: Aleksandar Markovic <amarkovic@wavecomp.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Aleksandar Markovic <amarkovic@wavecomp.com>
This commit is contained in:
Richard Henderson 2019-06-23 19:04:39 +02:00
parent 6ef14d7ebe
commit e238297282
2 changed files with 40 additions and 2 deletions

View File

@ -164,7 +164,7 @@ extern bool have_altivec;
#define TCG_TARGET_HAS_cmp_vec 1
#define TCG_TARGET_HAS_mul_vec 0
#define TCG_TARGET_HAS_sat_vec 0
#define TCG_TARGET_HAS_minmax_vec 0
#define TCG_TARGET_HAS_minmax_vec 1
#define TCG_TARGET_HAS_bitsel_vec 0
#define TCG_TARGET_HAS_cmpsel_vec 0

View File

@ -471,6 +471,19 @@ static int tcg_target_const_match(tcg_target_long val, TCGType type,
#define STVX XO31(231)
#define STVEWX XO31(199)
#define VMAXSB VX4(258)
#define VMAXSH VX4(322)
#define VMAXSW VX4(386)
#define VMAXUB VX4(2)
#define VMAXUH VX4(66)
#define VMAXUW VX4(130)
#define VMINSB VX4(770)
#define VMINSH VX4(834)
#define VMINSW VX4(898)
#define VMINUB VX4(514)
#define VMINUH VX4(578)
#define VMINUW VX4(642)
#define VCMPEQUB VX4(6)
#define VCMPEQUH VX4(70)
#define VCMPEQUW VX4(134)
@ -2817,6 +2830,11 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
case INDEX_op_andc_vec:
case INDEX_op_not_vec:
return 1;
case INDEX_op_smax_vec:
case INDEX_op_smin_vec:
case INDEX_op_umax_vec:
case INDEX_op_umin_vec:
return vece <= MO_32;
case INDEX_op_cmp_vec:
return vece <= MO_32 ? -1 : 0;
default:
@ -2914,7 +2932,11 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
static const uint32_t
eq_op[4] = { VCMPEQUB, VCMPEQUH, VCMPEQUW, 0 },
gts_op[4] = { VCMPGTSB, VCMPGTSH, VCMPGTSW, 0 },
gtu_op[4] = { VCMPGTUB, VCMPGTUH, VCMPGTUW, 0 };
gtu_op[4] = { VCMPGTUB, VCMPGTUH, VCMPGTUW, 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 };
TCGType type = vecl + TCG_TYPE_V64;
TCGArg a0 = args[0], a1 = args[1], a2 = args[2];
@ -2931,6 +2953,18 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
tcg_out_dupm_vec(s, type, vece, a0, a1, a2);
return;
case INDEX_op_smin_vec:
insn = smin_op[vece];
break;
case INDEX_op_umin_vec:
insn = umin_op[vece];
break;
case INDEX_op_smax_vec:
insn = smax_op[vece];
break;
case INDEX_op_umax_vec:
insn = umax_op[vece];
break;
case INDEX_op_and_vec:
insn = VAND;
break;
@ -3223,6 +3257,10 @@ static const TCGTargetOpDef *tcg_target_op_def(TCGOpcode op)
case INDEX_op_andc_vec:
case INDEX_op_orc_vec:
case INDEX_op_cmp_vec:
case INDEX_op_smax_vec:
case INDEX_op_smin_vec:
case INDEX_op_umax_vec:
case INDEX_op_umin_vec:
return &v_v_v;
case INDEX_op_not_vec:
case INDEX_op_dup_vec: