[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-devel] [PATCH 10/21] target-arm: A64: Implement remaining non-pair
From: |
Peter Maydell |
Subject: |
[Qemu-devel] [PATCH 10/21] target-arm: A64: Implement remaining non-pairwise int SIMD 3-reg-same insns |
Date: |
Sun, 26 Jan 2014 19:25:01 +0000 |
Implement the SIMD 3-reg-same instructions where the size == 3 case
is reserved: SHADD, UHADD, SRHADD, URHADD, SHSUB, UHSUB, SMAX,
UMAX, SMIN, UMIN, SABD, UABD, SABA, UABA, MLA, MLS, MUL, PMUL,
SQRDMULH, SQDMULH. (None of these have scalar-3-same versions.)
This completes the non-pairwise integer instructions in this category.
Signed-off-by: Peter Maydell <address@hidden>
---
target-arm/translate-a64.c | 134 +++++++++++++++++++++++++++++++++++++++------
1 file changed, 118 insertions(+), 16 deletions(-)
diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index 4a6886d..515c72b 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -6684,15 +6684,13 @@ static void disas_simd_3same_int(DisasContext *s,
uint32_t insn)
unallocated_encoding(s);
return;
}
- unsupported_encoding(s, insn);
- return;
+ break;
case 0x16: /* SQDMULH, SQRDMULH */
if (size == 0 || size == 3) {
unallocated_encoding(s);
return;
}
- unsupported_encoding(s, insn);
- return;
+ break;
default:
if (size == 3 && !is_q) {
unallocated_encoding(s);
@@ -6730,6 +6728,16 @@ static void disas_simd_3same_int(DisasContext *s,
uint32_t insn)
read_vec_element_i32(s, tcg_op2, rm, pass, MO_32);
switch (opcode) {
+ case 0x0: /* SHADD, UHADD */
+ {
+ static NeonGenTwoOpFn * const fns[3][2] = {
+ { gen_helper_neon_hadd_s8, gen_helper_neon_hadd_u8 },
+ { gen_helper_neon_hadd_s16, gen_helper_neon_hadd_u16 },
+ { gen_helper_neon_hadd_s32, gen_helper_neon_hadd_u32 },
+ };
+ genfn = fns[size][u];
+ break;
+ }
case 0x1: /* SQADD, UQADD */
{
static NeonGenTwoOpEnvFn * const fns[3][2] = {
@@ -6740,6 +6748,26 @@ static void disas_simd_3same_int(DisasContext *s,
uint32_t insn)
genenvfn = fns[size][u];
break;
}
+ case 0x2: /* SRHADD, URHADD */
+ {
+ static NeonGenTwoOpFn * const fns[3][2] = {
+ { gen_helper_neon_rhadd_s8, gen_helper_neon_rhadd_u8 },
+ { gen_helper_neon_rhadd_s16, gen_helper_neon_rhadd_u16 },
+ { gen_helper_neon_rhadd_s32, gen_helper_neon_rhadd_u32 },
+ };
+ genfn = fns[size][u];
+ break;
+ }
+ case 0x4: /* SHSUB, UHSUB */
+ {
+ static NeonGenTwoOpFn * const fns[3][2] = {
+ { gen_helper_neon_hsub_s8, gen_helper_neon_hsub_u8 },
+ { gen_helper_neon_hsub_s16, gen_helper_neon_hsub_u16 },
+ { gen_helper_neon_hsub_s32, gen_helper_neon_hsub_u32 },
+ };
+ genfn = fns[size][u];
+ break;
+ }
case 0x5: /* SQSUB, UQSUB */
{
static NeonGenTwoOpEnvFn * const fns[3][2] = {
@@ -6773,9 +6801,9 @@ static void disas_simd_3same_int(DisasContext *s,
uint32_t insn)
case 0x8: /* SSHL, USHL */
{
static NeonGenTwoOpFn * const fns[3][2] = {
- { gen_helper_neon_shl_u8, gen_helper_neon_shl_s8 },
- { gen_helper_neon_shl_u16, gen_helper_neon_shl_s16 },
- { gen_helper_neon_shl_u32, gen_helper_neon_shl_s32 },
+ { gen_helper_neon_shl_s8, gen_helper_neon_shl_u8 },
+ { gen_helper_neon_shl_s16, gen_helper_neon_shl_u16 },
+ { gen_helper_neon_shl_s32, gen_helper_neon_shl_u32 },
};
genfn = fns[size][u];
break;
@@ -6783,9 +6811,9 @@ static void disas_simd_3same_int(DisasContext *s,
uint32_t insn)
case 0x9: /* SQSHL, UQSHL */
{
static NeonGenTwoOpEnvFn * const fns[3][2] = {
- { gen_helper_neon_qshl_u8, gen_helper_neon_qshl_s8 },
- { gen_helper_neon_qshl_u16, gen_helper_neon_qshl_s16 },
- { gen_helper_neon_qshl_u32, gen_helper_neon_qshl_s32 },
+ { gen_helper_neon_qshl_s8, gen_helper_neon_qshl_u8 },
+ { gen_helper_neon_qshl_s16, gen_helper_neon_qshl_u16 },
+ { gen_helper_neon_qshl_s32, gen_helper_neon_qshl_u32 },
};
genenvfn = fns[size][u];
break;
@@ -6793,9 +6821,9 @@ static void disas_simd_3same_int(DisasContext *s,
uint32_t insn)
case 0xa: /* SRSHL, URSHL */
{
static NeonGenTwoOpFn * const fns[3][2] = {
- { gen_helper_neon_rshl_u8, gen_helper_neon_rshl_s8 },
- { gen_helper_neon_rshl_u16, gen_helper_neon_rshl_s16 },
- { gen_helper_neon_rshl_u32, gen_helper_neon_rshl_s32 },
+ { gen_helper_neon_rshl_s8, gen_helper_neon_rshl_u8 },
+ { gen_helper_neon_rshl_s16, gen_helper_neon_rshl_u16 },
+ { gen_helper_neon_rshl_s32, gen_helper_neon_rshl_u32 },
};
genfn = fns[size][u];
break;
@@ -6803,13 +6831,45 @@ static void disas_simd_3same_int(DisasContext *s,
uint32_t insn)
case 0xb: /* SQRSHL, UQRSHL */
{
static NeonGenTwoOpEnvFn * const fns[3][2] = {
- { gen_helper_neon_qrshl_u8, gen_helper_neon_qrshl_s8 },
- { gen_helper_neon_qrshl_u16, gen_helper_neon_qrshl_s16 },
- { gen_helper_neon_qrshl_u32, gen_helper_neon_qrshl_s32 },
+ { gen_helper_neon_qrshl_s8, gen_helper_neon_qrshl_u8 },
+ { gen_helper_neon_qrshl_s16, gen_helper_neon_qrshl_u16 },
+ { gen_helper_neon_qrshl_s32, gen_helper_neon_qrshl_u32 },
};
genenvfn = fns[size][u];
break;
}
+ case 0xc: /* SMAX, UMAX */
+ {
+ static NeonGenTwoOpFn * const fns[3][2] = {
+ { gen_helper_neon_max_s8, gen_helper_neon_max_u8 },
+ { gen_helper_neon_max_s16, gen_helper_neon_max_u16 },
+ { gen_helper_neon_max_s32, gen_helper_neon_max_u32 },
+ };
+ genfn = fns[size][u];
+ break;
+ }
+
+ case 0xd: /* SMIN, UMIN */
+ {
+ static NeonGenTwoOpFn * const fns[3][2] = {
+ { gen_helper_neon_min_s8, gen_helper_neon_min_u8 },
+ { gen_helper_neon_min_s16, gen_helper_neon_min_u16 },
+ { gen_helper_neon_min_s32, gen_helper_neon_min_u32 },
+ };
+ genfn = fns[size][u];
+ break;
+ }
+ case 0xe: /* SABD, UABD */
+ case 0xf: /* SABA, UABA */
+ {
+ static NeonGenTwoOpFn * const fns[3][2] = {
+ { gen_helper_neon_abd_s8, gen_helper_neon_abd_u8 },
+ { gen_helper_neon_abd_s16, gen_helper_neon_abd_u16 },
+ { gen_helper_neon_abd_s32, gen_helper_neon_abd_u32 },
+ };
+ genfn = fns[size][u];
+ break;
+ }
case 0x10: /* ADD, SUB */
{
static NeonGenTwoOpFn * const fns[3][2] = {
@@ -6830,6 +6890,34 @@ static void disas_simd_3same_int(DisasContext *s,
uint32_t insn)
genfn = fns[size][u];
break;
}
+ case 0x13: /* MUL, PMUL */
+ if (u) {
+ /* PMUL */
+ assert(size == 0);
+ genfn = gen_helper_neon_mul_p8;
+ break;
+ }
+ /* fall through : MUL */
+ case 0x12: /* MLA, MLS */
+ {
+ static NeonGenTwoOpFn * const fns[3] = {
+ gen_helper_neon_mul_u8,
+ gen_helper_neon_mul_u16,
+ tcg_gen_mul_i32,
+ };
+ genfn = fns[size];
+ break;
+ }
+ case 0x16: /* SQDMULH, SQRDMULH */
+ {
+ static NeonGenTwoOpEnvFn * const fns[2][2] = {
+ { gen_helper_neon_qdmulh_s16, gen_helper_neon_qrdmulh_s16
},
+ { gen_helper_neon_qdmulh_s32, gen_helper_neon_qrdmulh_s32
},
+ };
+ assert(size == 1 || size == 2);
+ genenvfn = fns[size - 1][u];
+ break;
+ }
default:
g_assert_not_reached();
}
@@ -6840,6 +6928,20 @@ static void disas_simd_3same_int(DisasContext *s,
uint32_t insn)
genfn(tcg_res, tcg_op1, tcg_op2);
}
+ if (opcode == 0xf || opcode == 0x12) {
+ /* SABA, UABA, MLA, MLS: accumulating ops */
+ static NeonGenTwoOpFn * const fns[3][2] = {
+ { gen_helper_neon_add_u8, gen_helper_neon_sub_u8 },
+ { gen_helper_neon_add_u16, gen_helper_neon_sub_u16 },
+ { tcg_gen_add_i32, tcg_gen_sub_i32 },
+ };
+ bool is_sub = (opcode == 0x12 && u); /* MLS */
+
+ genfn = fns[size][is_sub];
+ read_vec_element_i32(s, tcg_op1, rd, pass, MO_32);
+ genfn(tcg_res, tcg_res, tcg_op1);
+ }
+
write_vec_element_i32(s, tcg_res, rd, pass, MO_32);
tcg_temp_free_i32(tcg_res);
--
1.8.5
- [Qemu-devel] [PATCH 00/21] A64: Add Neon instructions, second and third sets, Peter Maydell, 2014/01/26
- [Qemu-devel] [PATCH 20/21] target-arm: A64: Add 2-reg-misc REV* instructions, Peter Maydell, 2014/01/26
- [Qemu-devel] [PATCH 19/21] target-arm: A64: Add narrowing 2-reg-misc instructions, Peter Maydell, 2014/01/26
- [Qemu-devel] [PATCH 17/21] target-arm: A64: Implement 2-register misc compares, ABS, NEG, Peter Maydell, 2014/01/26
- [Qemu-devel] [PATCH 18/21] target-arm: A64: Implement 2-reg-misc CNT, NOT and RBIT, Peter Maydell, 2014/01/26
- [Qemu-devel] [PATCH 10/21] target-arm: A64: Implement remaining non-pairwise int SIMD 3-reg-same insns,
Peter Maydell <=
- [Qemu-devel] [PATCH 01/21] target-arm: A64: Add SIMD three-different multiply accumulate insns, Peter Maydell, 2014/01/26
- [Qemu-devel] [PATCH 21/21] target-arm: A64: Add FNEG and FABS to the SIMD 2-reg-misc group, Peter Maydell, 2014/01/26
- [Qemu-devel] [PATCH 11/21] target-arm: A64: Implement pairwise integer ops from 3-reg-same SIMD, Peter Maydell, 2014/01/26
- [Qemu-devel] [PATCH 02/21] target-arm: A64: Add SIMD three-different ABDL instructions, Peter Maydell, 2014/01/26