[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-devel] [PATCH 09/21] target-arm: A64: Implement SIMD 3-reg-same sh
From: |
Peter Maydell |
Subject: |
[Qemu-devel] [PATCH 09/21] target-arm: A64: Implement SIMD 3-reg-same shift and saturate insns |
Date: |
Sun, 26 Jan 2014 19:25:00 +0000 |
Implement the SIMD 3-reg-same instructions SQADD, UQADD,
SQSUB, UQSUB, SSHL, USHL, SQSHl, UQSHL, SRSHL, URSHL,
SQRSHL, UQRSHL; these are all simple calls to existing
Neon helpers. We also enable SSHL, USHL, SRSHL and URSHL
for the 3-reg-same-scalar category (but not the others
because they can have non-size-64 operands and the
scalar_3reg_same function doesn't support that yet.)
Signed-off-by: Peter Maydell <address@hidden>
---
target-arm/translate-a64.c | 134 +++++++++++++++++++++++++++++++++++++--------
1 file changed, 112 insertions(+), 22 deletions(-)
diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index 6cdb8fc..4a6886d 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -74,6 +74,7 @@ typedef struct AArch64DecodeTable {
/* Function prototype for gen_ functions for calling Neon helpers */
typedef void NeonGenTwoOpFn(TCGv_i32, TCGv_i32, TCGv_i32);
+typedef void NeonGenTwoOpEnvFn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32);
/* initialize TCG globals. */
void a64_translate_init(void)
@@ -5766,6 +5767,20 @@ static void handle_3same_64(DisasContext *s, int opcode,
bool u,
TCGCond cond;
switch (opcode) {
+ case 0x1: /* SQADD */
+ if (u) {
+ gen_helper_neon_qadd_u64(tcg_rd, cpu_env, tcg_rn, tcg_rm);
+ } else {
+ gen_helper_neon_qadd_s64(tcg_rd, cpu_env, tcg_rn, tcg_rm);
+ }
+ break;
+ case 0x5: /* SQSUB */
+ if (u) {
+ gen_helper_neon_qsub_u64(tcg_rd, cpu_env, tcg_rn, tcg_rm);
+ } else {
+ gen_helper_neon_qsub_s64(tcg_rd, cpu_env, tcg_rn, tcg_rm);
+ }
+ break;
case 0x6: /* CMGT, CMHI */
/* 64 bit integer comparison, result = test ? (2^64 - 1) : 0.
* We implement this using setcond (test) and then negating.
@@ -5788,19 +5803,41 @@ static void handle_3same_64(DisasContext *s, int
opcode, bool u,
tcg_gen_setcondi_i64(TCG_COND_NE, tcg_rd, tcg_rd, 0);
tcg_gen_neg_i64(tcg_rd, tcg_rd);
break;
- case 0x10: /* ADD, SUB */
+ case 0x8: /* SSHL, USHL */
if (u) {
- tcg_gen_sub_i64(tcg_rd, tcg_rn, tcg_rm);
+ gen_helper_neon_shl_u64(tcg_rd, tcg_rn, tcg_rm);
} else {
- tcg_gen_add_i64(tcg_rd, tcg_rn, tcg_rm);
+ gen_helper_neon_shl_s64(tcg_rd, tcg_rn, tcg_rm);
}
break;
- case 0x1: /* SQADD */
- case 0x5: /* SQSUB */
- case 0x8: /* SSHL, USHL */
case 0x9: /* SQSHL, UQSHL */
+ if (u) {
+ gen_helper_neon_qshl_u64(tcg_rd, cpu_env, tcg_rn, tcg_rm);
+ } else {
+ gen_helper_neon_qshl_s64(tcg_rd, cpu_env, tcg_rn, tcg_rm);
+ }
+ break;
case 0xa: /* SRSHL, URSHL */
+ if (u) {
+ gen_helper_neon_rshl_u64(tcg_rd, tcg_rn, tcg_rm);
+ } else {
+ gen_helper_neon_rshl_s64(tcg_rd, tcg_rn, tcg_rm);
+ }
+ break;
case 0xb: /* SQRSHL, UQRSHL */
+ if (u) {
+ gen_helper_neon_qrshl_u64(tcg_rd, cpu_env, tcg_rn, tcg_rm);
+ } else {
+ gen_helper_neon_qrshl_s64(tcg_rd, cpu_env, tcg_rn, tcg_rm);
+ }
+ break;
+ case 0x10: /* ADD, SUB */
+ if (u) {
+ tcg_gen_sub_i64(tcg_rd, tcg_rn, tcg_rm);
+ } else {
+ tcg_gen_add_i64(tcg_rd, tcg_rn, tcg_rm);
+ }
+ break;
default:
g_assert_not_reached();
}
@@ -5977,10 +6014,10 @@ static void
disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn)
switch (opcode) {
case 0x1: /* SQADD, UQADD */
case 0x5: /* SQSUB, UQSUB */
- case 0x8: /* SSHL, USHL */
- case 0xa: /* SRSHL, URSHL */
unsupported_encoding(s, insn);
return;
+ case 0x8: /* SSHL, USHL */
+ case 0xa: /* SRSHL, URSHL */
case 0x6: /* CMGT, CMHI */
case 0x7: /* CMGE, CMHS */
case 0x11: /* CMTST, CMEQ */
@@ -6649,18 +6686,6 @@ static void disas_simd_3same_int(DisasContext *s,
uint32_t insn)
}
unsupported_encoding(s, insn);
return;
- case 0x1: /* SQADD */
- case 0x5: /* SQSUB */
- case 0x8: /* SSHL, USHL */
- case 0x9: /* SQSHL, UQSHL */
- case 0xa: /* SRSHL, URSHL */
- case 0xb: /* SQRSHL, UQRSHL */
- if (size == 3 && !is_q) {
- unallocated_encoding(s);
- return;
- }
- unsupported_encoding(s, insn);
- return;
case 0x16: /* SQDMULH, SQRDMULH */
if (size == 0 || size == 3) {
unallocated_encoding(s);
@@ -6698,12 +6723,33 @@ static void disas_simd_3same_int(DisasContext *s,
uint32_t insn)
TCGv_i32 tcg_op1 = tcg_temp_new_i32();
TCGv_i32 tcg_op2 = tcg_temp_new_i32();
TCGv_i32 tcg_res = tcg_temp_new_i32();
- NeonGenTwoOpFn *genfn;
+ NeonGenTwoOpFn *genfn = NULL;
+ NeonGenTwoOpEnvFn *genenvfn = NULL;
read_vec_element_i32(s, tcg_op1, rn, pass, MO_32);
read_vec_element_i32(s, tcg_op2, rm, pass, MO_32);
switch (opcode) {
+ case 0x1: /* SQADD, UQADD */
+ {
+ static NeonGenTwoOpEnvFn * const fns[3][2] = {
+ { gen_helper_neon_qadd_s8, gen_helper_neon_qadd_u8 },
+ { gen_helper_neon_qadd_s16, gen_helper_neon_qadd_u16 },
+ { gen_helper_neon_qadd_s32, gen_helper_neon_qadd_u32 },
+ };
+ genenvfn = fns[size][u];
+ break;
+ }
+ case 0x5: /* SQSUB, UQSUB */
+ {
+ static NeonGenTwoOpEnvFn * const fns[3][2] = {
+ { gen_helper_neon_qsub_s8, gen_helper_neon_qsub_u8 },
+ { gen_helper_neon_qsub_s16, gen_helper_neon_qsub_u16 },
+ { gen_helper_neon_qsub_s32, gen_helper_neon_qsub_u32 },
+ };
+ genenvfn = fns[size][u];
+ break;
+ }
case 0x6: /* CMGT, CMHI */
{
static NeonGenTwoOpFn * const fns[3][2] = {
@@ -6724,6 +6770,46 @@ static void disas_simd_3same_int(DisasContext *s,
uint32_t insn)
genfn = fns[size][u];
break;
}
+ 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 },
+ };
+ genfn = fns[size][u];
+ break;
+ }
+ 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 },
+ };
+ genenvfn = fns[size][u];
+ break;
+ }
+ 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 },
+ };
+ genfn = fns[size][u];
+ break;
+ }
+ 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 },
+ };
+ genenvfn = fns[size][u];
+ break;
+ }
case 0x10: /* ADD, SUB */
{
static NeonGenTwoOpFn * const fns[3][2] = {
@@ -6748,7 +6834,11 @@ static void disas_simd_3same_int(DisasContext *s,
uint32_t insn)
g_assert_not_reached();
}
- genfn(tcg_res, tcg_op1, tcg_op2);
+ if (genenvfn) {
+ genenvfn(tcg_res, cpu_env, tcg_op1, tcg_op2);
+ } else {
+ genfn(tcg_res, tcg_op1, tcg_op2);
+ }
write_vec_element_i32(s, tcg_res, rd, pass, MO_32);
--
1.8.5
- [Qemu-devel] [PATCH 01/21] target-arm: A64: Add SIMD three-different multiply accumulate insns, (continued)
- [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
- [Qemu-devel] [PATCH 05/21] target-arm: A64: Add logic ops from SIMD 3 same group, Peter Maydell, 2014/01/26
- [Qemu-devel] [PATCH 14/21] target-arm: A64: Implement remaining integer scalar-3-same insns, Peter Maydell, 2014/01/26
- [Qemu-devel] [PATCH 03/21] target-arm: A64: Add SIMD scalar 3 same add, sub and compare ops, Peter Maydell, 2014/01/26
- [Qemu-devel] [PATCH 04/21] target-arm: A64: Add top level decode for SIMD 3-same group, Peter Maydell, 2014/01/26
- [Qemu-devel] [PATCH 07/21] target-arm: A64: Add simple SIMD 3-same floating point ops, Peter Maydell, 2014/01/26
- [Qemu-devel] [PATCH 09/21] target-arm: A64: Implement SIMD 3-reg-same shift and saturate insns,
Peter Maydell <=
- [Qemu-devel] [PATCH 06/21] target-arm: A64: Add integer ops from SIMD 3-same group, Peter Maydell, 2014/01/26
- [Qemu-devel] [PATCH 08/21] target-arm: A64: Add SIMD shift by immediate, Peter Maydell, 2014/01/26
- [Qemu-devel] [PATCH 12/21] tcg: Add TCGV_UNUSED_PTR, TCGV_IS_UNUSED_PTR, TCGV_EQUAL_PTR, Peter Maydell, 2014/01/26
- [Qemu-devel] [PATCH 15/21] target-arm: A64: Add SIMD simple 64 bit insns from scalar 2-reg misc, Peter Maydell, 2014/01/26
- [Qemu-devel] [PATCH 13/21] target-arm: A64: Implement scalar pairwise ops, Peter Maydell, 2014/01/26
- Re: [Qemu-devel] [PATCH 00/21] A64: Add Neon instructions, second and third sets, Peter Maydell, 2014/01/26