diff mbox series

[02/10] target/arm: Convert Neon VSHL and VSLI 2-reg-shift insn to decodetree

Message ID 20200515142056.21346-3-peter.maydell@linaro.org
State Superseded
Headers show
Series target/arm: Convert 2-reg-shift and 1-reg-imm Neon insns to decodetree | expand

Commit Message

Peter Maydell May 15, 2020, 2:20 p.m. UTC 
Convert the VSHL and VSLI insns from the Neon 2-registers-and-a-shift
group to decodetree.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

---
 target/arm/neon-dp.decode       | 27 +++++++++++++++++++++++
 target/arm/translate-neon.inc.c | 38 +++++++++++++++++++++++++++++++++
 target/arm/translate.c          | 18 +++++++---------
 3 files changed, 73 insertions(+), 10 deletions(-)

-- 
2.20.1

Comments

Richard Henderson May 15, 2020, 10:16 p.m. UTC | #1 
On 5/15/20 7:20 AM, Peter Maydell wrote:
> Convert the VSHL and VSLI insns from the Neon 2-registers-and-a-shift

> group to decodetree.

> 

> Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

> ---

>  target/arm/neon-dp.decode       | 27 +++++++++++++++++++++++

>  target/arm/translate-neon.inc.c | 38 +++++++++++++++++++++++++++++++++

>  target/arm/translate.c          | 18 +++++++---------

>  3 files changed, 73 insertions(+), 10 deletions(-)


Reviewed-by: Richard Henderson <richard.henderson@linaro.org>



r~
diff mbox series

Patch

diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
index 8beb1db768b..df7b4798a5a 100644
--- a/target/arm/neon-dp.decode
+++ b/target/arm/neon-dp.decode
@@ -199,3 +199,30 @@  VRECPS_fp_3s     1111 001 0 0 . 0 . .... .... 1111 ... 1 .... @3same_fp
 VRSQRTS_fp_3s    1111 001 0 0 . 1 . .... .... 1111 ... 1 .... @3same_fp
 VMAXNM_fp_3s     1111 001 1 0 . 0 . .... .... 1111 ... 1 .... @3same_fp
 VMINNM_fp_3s     1111 001 1 0 . 1 . .... .... 1111 ... 1 .... @3same_fp
+
+######################################################################
+# 2-reg-and-shift grouping:
+# 1111 001 U 1 D immH:3 immL:3 Vd:4 opc:4 L Q M 1 Vm:4
+######################################################################
+&2reg_shift vm vd q shift size
+
+@2reg_shift      .... ... . . . ...... .... .... . q:1 . . .... \
+                 &2reg_shift vm=%vm_dp vd=%vd_dp
+
+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 .... \
+                 @2reg_shift size=2
+VSHL_2sh         1111 001 0 1 . 01 shift:4  .... 0101 0 . . 1 .... \
+                 @2reg_shift size=1
+VSHL_2sh         1111 001 0 1 . 001 shift:3 .... 0101 0 . . 1 .... \
+                 @2reg_shift size=0
+
+VSLI_2sh         1111 001 1 1 . shift:6     .... 0101 1 . . 1 .... \
+                 @2reg_shift size=3
+VSLI_2sh         1111 001 1 1 . 1 shift:5   .... 0101 0 . . 1 .... \
+                 @2reg_shift size=2
+VSLI_2sh         1111 001 1 1 . 01 shift:4  .... 0101 0 . . 1 .... \
+                 @2reg_shift size=1
+VSLI_2sh         1111 001 1 1 . 001 shift:3 .... 0101 0 . . 1 .... \
+                 @2reg_shift size=0
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
index 3fe65a0b080..305213fe6d9 100644
--- a/target/arm/translate-neon.inc.c
+++ b/target/arm/translate-neon.inc.c
@@ -1310,3 +1310,41 @@  static bool do_3same_fp_pair(DisasContext *s, arg_3same *a, VFPGen3OpSPFn *fn)
 DO_3S_FP_PAIR(VPADD, gen_helper_vfp_adds)
 DO_3S_FP_PAIR(VPMAX, gen_helper_vfp_maxs)
 DO_3S_FP_PAIR(VPMIN, gen_helper_vfp_mins)
+
+static bool do_vector_2sh(DisasContext *s, arg_2reg_shift *a, GVecGen2iFn *fn)
+{
+    /* Handle a 2-reg-shift insn which can be vectorized. */
+    int vec_size = a->q ? 16 : 8;
+    int rd_ofs = neon_reg_offset(a->vd, 0);
+    int rm_ofs = neon_reg_offset(a->vm, 0);
+
+    if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
+        return false;
+    }
+
+    /* UNDEF accesses to D16-D31 if they don't exist. */
+    if (!dc_isar_feature(aa32_simd_r32, s) &&
+        ((a->vd | a->vm) & 0x10)) {
+        return false;
+    }
+
+    if ((a->vm | a->vd) & a->q) {
+        return false;
+    }
+
+    if (!vfp_access_check(s)) {
+        return true;
+    }
+
+    fn(a->size, rd_ofs, rm_ofs, a->shift, vec_size, vec_size);
+    return true;
+}
+
+#define DO_2SH(INSN, FUNC)                                              \
+    static bool trans_##INSN##_2sh(DisasContext *s, arg_2reg_shift *a)  \
+    {                                                                   \
+        return do_vector_2sh(s, a, FUNC);                               \
+    }                                                                   \
+
+DO_2SH(VSHL, tcg_gen_gvec_shli)
+DO_2SH(VSLI, gen_gvec_sli)
diff --git a/target/arm/translate.c b/target/arm/translate.c
index c8296116d4b..d0a4a08f6d9 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -5294,6 +5294,14 @@  static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
         if ((insn & 0x00380080) != 0) {
             /* Two registers and shift.  */
             op = (insn >> 8) & 0xf;
+
+            switch (op) {
+            case 5: /* VSHL, VSLI */
+                return 1; /* handled by decodetree */
+            default:
+                break;
+            }
+
             if (insn & (1 << 7)) {
                 /* 64-bit shift. */
                 if (op > 7) {
@@ -5387,16 +5395,6 @@  static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
                     gen_gvec_sri(size, rd_ofs, rm_ofs, shift,
                                  vec_size, vec_size);
                     return 0;
-
-                case 5: /* VSHL, VSLI */
-                    if (u) { /* VSLI */
-                        gen_gvec_sli(size, rd_ofs, rm_ofs, shift,
-                                     vec_size, vec_size);
-                    } else { /* VSHL */
-                        tcg_gen_gvec_shli(size, rd_ofs, rm_ofs, shift,
-                                          vec_size, vec_size);
-                    }
-                    return 0;
                 }
 
                 if (size == 3) {