[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PATCH 04/10] target/arm: Convert Neon VSRA, VSRI, VRSHR, VRSRA 2-reg-sh
From: |
Peter Maydell |
Subject: |
[PATCH 04/10] target/arm: Convert Neon VSRA, VSRI, VRSHR, VRSRA 2-reg-shift insns to decodetree |
Date: |
Fri, 15 May 2020 15:20:50 +0100 |
Convert the VSRA, VSRI, VRSHR, VRSRA 2-reg-shift insns to decodetree.
(These are the last instructions in the group that are vectorized;
the rest all require looping over each element.)
Signed-off-by: Peter Maydell <address@hidden>
---
target/arm/neon-dp.decode | 63 +++++++++++++++++++++++++++++++++
target/arm/translate-neon.inc.c | 7 ++++
target/arm/translate.c | 52 +++------------------------
3 files changed, 74 insertions(+), 48 deletions(-)
diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
index 648812395f1..3ed10d1524e 100644
--- a/target/arm/neon-dp.decode
+++ b/target/arm/neon-dp.decode
@@ -233,6 +233,69 @@ VSHR_U_2sh 1111 001 1 1 . 01 .... .... 0000 0 .
. 1 .... \
VSHR_U_2sh 1111 001 1 1 . 001 ... .... 0000 0 . . 1 .... \
@2reg_shift size=0 shift=%neon_rshift_i3
+VSRA_S_2sh 1111 001 0 1 . ...... .... 0001 1 . . 1 .... \
+ @2reg_shift size=3 shift=%neon_rshift_i6
+VSRA_S_2sh 1111 001 0 1 . 1 ..... .... 0001 0 . . 1 .... \
+ @2reg_shift size=2 shift=%neon_rshift_i5
+VSRA_S_2sh 1111 001 0 1 . 01 .... .... 0001 0 . . 1 .... \
+ @2reg_shift size=1 shift=%neon_rshift_i4
+VSRA_S_2sh 1111 001 0 1 . 001 ... .... 0001 0 . . 1 .... \
+ @2reg_shift size=0 shift=%neon_rshift_i3
+
+VSRA_U_2sh 1111 001 1 1 . ...... .... 0001 1 . . 1 .... \
+ @2reg_shift size=3 shift=%neon_rshift_i6
+VSRA_U_2sh 1111 001 1 1 . 1 ..... .... 0001 0 . . 1 .... \
+ @2reg_shift size=2 shift=%neon_rshift_i5
+VSRA_U_2sh 1111 001 1 1 . 01 .... .... 0001 0 . . 1 .... \
+ @2reg_shift size=1 shift=%neon_rshift_i4
+VSRA_U_2sh 1111 001 1 1 . 001 ... .... 0001 0 . . 1 .... \
+ @2reg_shift size=0 shift=%neon_rshift_i3
+
+VRSHR_S_2sh 1111 001 0 1 . ...... .... 0010 1 . . 1 .... \
+ @2reg_shift size=3 shift=%neon_rshift_i6
+VRSHR_S_2sh 1111 001 0 1 . 1 ..... .... 0010 0 . . 1 .... \
+ @2reg_shift size=2 shift=%neon_rshift_i5
+VRSHR_S_2sh 1111 001 0 1 . 01 .... .... 0010 0 . . 1 .... \
+ @2reg_shift size=1 shift=%neon_rshift_i4
+VRSHR_S_2sh 1111 001 0 1 . 001 ... .... 0010 0 . . 1 .... \
+ @2reg_shift size=0 shift=%neon_rshift_i3
+
+VRSHR_U_2sh 1111 001 1 1 . ...... .... 0010 1 . . 1 .... \
+ @2reg_shift size=3 shift=%neon_rshift_i6
+VRSHR_U_2sh 1111 001 1 1 . 1 ..... .... 0010 0 . . 1 .... \
+ @2reg_shift size=2 shift=%neon_rshift_i5
+VRSHR_U_2sh 1111 001 1 1 . 01 .... .... 0010 0 . . 1 .... \
+ @2reg_shift size=1 shift=%neon_rshift_i4
+VRSHR_U_2sh 1111 001 1 1 . 001 ... .... 0010 0 . . 1 .... \
+ @2reg_shift size=0 shift=%neon_rshift_i3
+
+VRSRA_S_2sh 1111 001 0 1 . ...... .... 0011 1 . . 1 .... \
+ @2reg_shift size=3 shift=%neon_rshift_i6
+VRSRA_S_2sh 1111 001 0 1 . 1 ..... .... 0011 0 . . 1 .... \
+ @2reg_shift size=2 shift=%neon_rshift_i5
+VRSRA_S_2sh 1111 001 0 1 . 01 .... .... 0011 0 . . 1 .... \
+ @2reg_shift size=1 shift=%neon_rshift_i4
+VRSRA_S_2sh 1111 001 0 1 . 001 ... .... 0011 0 . . 1 .... \
+ @2reg_shift size=0 shift=%neon_rshift_i3
+
+VRSRA_U_2sh 1111 001 1 1 . ...... .... 0011 1 . . 1 .... \
+ @2reg_shift size=3 shift=%neon_rshift_i6
+VRSRA_U_2sh 1111 001 1 1 . 1 ..... .... 0011 0 . . 1 .... \
+ @2reg_shift size=2 shift=%neon_rshift_i5
+VRSRA_U_2sh 1111 001 1 1 . 01 .... .... 0011 0 . . 1 .... \
+ @2reg_shift size=1 shift=%neon_rshift_i4
+VRSRA_U_2sh 1111 001 1 1 . 001 ... .... 0011 0 . . 1 .... \
+ @2reg_shift size=0 shift=%neon_rshift_i3
+
+VSRI_2sh 1111 001 1 1 . ...... .... 0100 1 . . 1 .... \
+ @2reg_shift size=3 shift=%neon_rshift_i6
+VSRI_2sh 1111 001 1 1 . 1 ..... .... 0100 0 . . 1 .... \
+ @2reg_shift size=2 shift=%neon_rshift_i5
+VSRI_2sh 1111 001 1 1 . 01 .... .... 0100 0 . . 1 .... \
+ @2reg_shift size=1 shift=%neon_rshift_i4
+VSRI_2sh 1111 001 1 1 . 001 ... .... 0100 0 . . 1 .... \
+ @2reg_shift size=0 shift=%neon_rshift_i3
+
VSHL_2sh 1111 001 0 1 . shift:6 .... 0101 1 . . 1 .... \
@2reg_shift size=3
VSHL_2sh 1111 001 0 1 . 1 shift:5 .... 0101 0 . . 1 .... \
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
index 0475696835f..f4d42683aea 100644
--- a/target/arm/translate-neon.inc.c
+++ b/target/arm/translate-neon.inc.c
@@ -1366,6 +1366,13 @@ static bool do_vector_2sh(DisasContext *s,
arg_2reg_shift *a, GVecGen2iFn *fn)
DO_2SH(VSHL, tcg_gen_gvec_shli)
DO_2SH(VSLI, gen_gvec_sli)
+DO_2SH(VSRI, gen_gvec_sri)
+DO_2SH(VSRA_S, gen_gvec_ssra)
+DO_2SH(VSRA_U, gen_gvec_usra)
+DO_2SH(VRSHR_S, gen_gvec_srshr)
+DO_2SH(VRSHR_U, gen_gvec_urshr)
+DO_2SH(VRSRA_S, gen_gvec_srsra)
+DO_2SH(VRSRA_U, gen_gvec_ursra)
static bool trans_VSHR_S_2sh(DisasContext *s, arg_2reg_shift *a)
{
diff --git a/target/arm/translate.c b/target/arm/translate.c
index f2ccab1b21c..4a55986aad9 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -5297,6 +5297,10 @@ static int disas_neon_data_insn(DisasContext *s,
uint32_t insn)
switch (op) {
case 0: /* VSHR */
+ case 1: /* VSRA */
+ case 2: /* VRSHR */
+ case 3: /* VRSRA */
+ case 4: /* VSRI */
case 5: /* VSHL, VSLI */
return 1; /* handled by decodetree */
default:
@@ -5330,54 +5334,6 @@ static int disas_neon_data_insn(DisasContext *s,
uint32_t insn)
shift = shift - (1 << (size + 3));
}
- switch (op) {
- case 1: /* VSRA */
- /* Right shift comes here negative. */
- shift = -shift;
- if (u) {
- gen_gvec_usra(size, rd_ofs, rm_ofs, shift,
- vec_size, vec_size);
- } else {
- gen_gvec_ssra(size, rd_ofs, rm_ofs, shift,
- vec_size, vec_size);
- }
- return 0;
-
- case 2: /* VRSHR */
- /* Right shift comes here negative. */
- shift = -shift;
- if (u) {
- gen_gvec_urshr(size, rd_ofs, rm_ofs, shift,
- vec_size, vec_size);
- } else {
- gen_gvec_srshr(size, rd_ofs, rm_ofs, shift,
- vec_size, vec_size);
- }
- return 0;
-
- case 3: /* VRSRA */
- /* Right shift comes here negative. */
- shift = -shift;
- if (u) {
- gen_gvec_ursra(size, rd_ofs, rm_ofs, shift,
- vec_size, vec_size);
- } else {
- gen_gvec_srsra(size, rd_ofs, rm_ofs, shift,
- vec_size, vec_size);
- }
- return 0;
-
- case 4: /* VSRI */
- if (!u) {
- return 1;
- }
- /* Right shift comes here negative. */
- shift = -shift;
- gen_gvec_sri(size, rd_ofs, rm_ofs, shift,
- vec_size, vec_size);
- return 0;
- }
-
if (size == 3) {
count = q + 1;
} else {
--
2.20.1
- [PATCH 00/10] target/arm: Convert 2-reg-shift and 1-reg-imm Neon insns to decodetree, Peter Maydell, 2020/05/15
- [PATCH 01/10] target/arm: Remove unused GEN_NEON_INTEGER_OP macro, Peter Maydell, 2020/05/15
- [PATCH 02/10] target/arm: Convert Neon VSHL and VSLI 2-reg-shift insn to decodetree, Peter Maydell, 2020/05/15
- [PATCH 03/10] target/arm: Convert Neon VSHR 2-reg-shift insns to decodetree, Peter Maydell, 2020/05/15
- [PATCH 04/10] target/arm: Convert Neon VSRA, VSRI, VRSHR, VRSRA 2-reg-shift insns to decodetree,
Peter Maydell <=
- [PATCH 05/10] target/arm: Convert VQSHLU, VQSHL 2-reg-shift insns to decodetree, Peter Maydell, 2020/05/15
- [PATCH 06/10] target/arm: Convert Neon narrowing shifts with op==8 to decodetree, Peter Maydell, 2020/05/15
- [PATCH 07/10] target/arm: Convert Neon narrowing shifts with op==9 to decodetree, Peter Maydell, 2020/05/15
- [PATCH 08/10] target/arm: Convert Neon VSHLL, VMOVL to decodetree, Peter Maydell, 2020/05/15
- [PATCH 09/10] target/arm: Convert VCVT fixed-point ops to decodetree, Peter Maydell, 2020/05/15