All of lore.kernel.org
 help / color / mirror / Atom feed
From: Peter Maydell <peter.maydell@linaro.org>
To: qemu-arm@nongnu.org, qemu-devel@nongnu.org
Cc: Richard Henderson <richard.henderson@linaro.org>
Subject: [PATCH v2 03/17] target/arm: Convert Neon 64-bit element 3-reg-same insns
Date: Tue, 12 May 2020 17:38:50 +0100	[thread overview]
Message-ID: <20200512163904.10918-4-peter.maydell@linaro.org> (raw)
In-Reply-To: <20200512163904.10918-1-peter.maydell@linaro.org>

Convert the 64-bit element insns in the 3-reg-same group
to decodetree. This covers VQSHL, VRSHL and VQRSHL where
size==0b11.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/neon-dp.decode       | 21 ++++++++++++++++++
 target/arm/translate-neon.inc.c | 24 +++++++++++++++++++++
 target/arm/translate.c          | 38 ++-------------------------------
 3 files changed, 47 insertions(+), 36 deletions(-)

diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
index 68b0a44793f..fe649038547 100644
--- a/target/arm/neon-dp.decode
+++ b/target/arm/neon-dp.decode
@@ -73,6 +73,27 @@ VCGE_U_3s        1111 001 1 0 . .. .... .... 0011 . . . 1 .... @3same
 VSHL_S_3s        1111 001 0 0 . .. .... .... 0100 . . . 0 .... @3same_rev
 VSHL_U_3s        1111 001 1 0 . .. .... .... 0100 . . . 0 .... @3same_rev
 
+# Insns operating on 64-bit elements (size!=0b11 handled elsewhere)
+# The _rev suffix indicates that Vn and Vm are reversed. This is
+# the case for shifts. In the Arm ARM these insns are documented
+# with the Vm and Vn fields in their usual places, but in the
+# assembly the operands are listed "backwards", ie in the order
+# Dd, Dm, Dn where other insns use Dd, Dn, Dm. For QEMU we choose
+# to consider Vm and Vm as being in different fields in the insn,
+# which allows us to avoid special-casing shifts in the trans_
+# function code (where we would otherwise need to manually swap
+# the operands over to call Neon helper functions that are shared
+# with AArch64 which does not have this odd reversed-operand situation).
+@3same_64_rev    .... ... . . . 11 .... .... .... . q:1 . . .... \
+                 &3same vm=%vn_dp vn=%vm_dp vd=%vd_dp size=3
+
+VQSHL_S64_3s     1111 001 0 0 . .. .... .... 0100 . . . 1 .... @3same_64_rev
+VQSHL_U64_3s     1111 001 1 0 . .. .... .... 0100 . . . 1 .... @3same_64_rev
+VRSHL_S64_3s     1111 001 0 0 . .. .... .... 0101 . . . 0 .... @3same_64_rev
+VRSHL_U64_3s     1111 001 1 0 . .. .... .... 0101 . . . 0 .... @3same_64_rev
+VQRSHL_S64_3s    1111 001 0 0 . .. .... .... 0101 . . . 1 .... @3same_64_rev
+VQRSHL_U64_3s    1111 001 1 0 . .. .... .... 0101 . . . 1 .... @3same_64_rev
+
 VMAX_S_3s        1111 001 0 0 . .. .... .... 0110 . . . 0 .... @3same
 VMAX_U_3s        1111 001 1 0 . .. .... .... 0110 . . . 0 .... @3same
 VMIN_S_3s        1111 001 0 0 . .. .... .... 0110 . . . 1 .... @3same
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
index 03b3337e460..05c6dcdc9b9 100644
--- a/target/arm/translate-neon.inc.c
+++ b/target/arm/translate-neon.inc.c
@@ -825,3 +825,27 @@ static bool trans_SHA256SU1_3s(DisasContext *s, arg_SHA256SU1_3s *a)
 
     return true;
 }
+
+#define DO_3SAME_64(INSN, FUNC)                                         \
+    static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs,         \
+                                uint32_t rn_ofs, uint32_t rm_ofs,       \
+                                uint32_t oprsz, uint32_t maxsz)         \
+    {                                                                   \
+        static const GVecGen3 op = { .fni8 = FUNC };                    \
+        tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, &op);      \
+    }                                                                   \
+    DO_3SAME(INSN, gen_##INSN##_3s)
+
+#define DO_3SAME_64_ENV(INSN, FUNC)                                     \
+    static void gen_##INSN##_elt(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m)    \
+    {                                                                   \
+        FUNC(d, cpu_env, n, m);                                         \
+    }                                                                   \
+    DO_3SAME_64(INSN, gen_##INSN##_elt)
+
+DO_3SAME_64(VRSHL_S64, gen_helper_neon_rshl_s64)
+DO_3SAME_64(VRSHL_U64, gen_helper_neon_rshl_u64)
+DO_3SAME_64_ENV(VQSHL_S64, gen_helper_neon_qshl_s64)
+DO_3SAME_64_ENV(VQSHL_U64, gen_helper_neon_qshl_u64)
+DO_3SAME_64_ENV(VQRSHL_S64, gen_helper_neon_qrshl_s64)
+DO_3SAME_64_ENV(VQRSHL_U64, gen_helper_neon_qrshl_u64)
diff --git a/target/arm/translate.c b/target/arm/translate.c
index ee2b8d6f6e3..1ce3e182867 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -5459,42 +5459,8 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
         }
 
         if (size == 3) {
-            /* 64-bit element instructions. */
-            for (pass = 0; pass < (q ? 2 : 1); pass++) {
-                neon_load_reg64(cpu_V0, rn + pass);
-                neon_load_reg64(cpu_V1, rm + pass);
-                switch (op) {
-                case NEON_3R_VQSHL:
-                    if (u) {
-                        gen_helper_neon_qshl_u64(cpu_V0, cpu_env,
-                                                 cpu_V1, cpu_V0);
-                    } else {
-                        gen_helper_neon_qshl_s64(cpu_V0, cpu_env,
-                                                 cpu_V1, cpu_V0);
-                    }
-                    break;
-                case NEON_3R_VRSHL:
-                    if (u) {
-                        gen_helper_neon_rshl_u64(cpu_V0, cpu_V1, cpu_V0);
-                    } else {
-                        gen_helper_neon_rshl_s64(cpu_V0, cpu_V1, cpu_V0);
-                    }
-                    break;
-                case NEON_3R_VQRSHL:
-                    if (u) {
-                        gen_helper_neon_qrshl_u64(cpu_V0, cpu_env,
-                                                  cpu_V1, cpu_V0);
-                    } else {
-                        gen_helper_neon_qrshl_s64(cpu_V0, cpu_env,
-                                                  cpu_V1, cpu_V0);
-                    }
-                    break;
-                default:
-                    abort();
-                }
-                neon_store_reg64(cpu_V0, rd + pass);
-            }
-            return 0;
+            /* 64-bit element instructions: handled by decodetree */
+            return 1;
         }
         pairwise = 0;
         switch (op) {
-- 
2.20.1



  parent reply	other threads:[~2020-05-12 16:43 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-05-12 16:38 [PATCH v2 00/17] target/arm: Convert rest of Neon 3-reg-same to decodetree Peter Maydell
2020-05-12 16:38 ` [PATCH v2 01/17] target/arm: Convert Neon 3-reg-same VQRDMLAH/VQRDMLSH " Peter Maydell
2020-05-13 16:39   ` Richard Henderson
2020-05-12 16:38 ` [PATCH v2 02/17] target/arm: Convert Neon 3-reg-same SHA " Peter Maydell
2020-05-12 16:38 ` Peter Maydell [this message]
2020-05-13 20:27   ` [PATCH v2 03/17] target/arm: Convert Neon 64-bit element 3-reg-same insns Richard Henderson
2020-05-12 16:38 ` [PATCH v2 04/17] target/arm: Convert Neon VHADD " Peter Maydell
2020-05-13 16:47   ` Richard Henderson
2020-05-12 16:38 ` [PATCH v2 05/17] target/arm: Convert Neon VABA/VABD 3-reg-same to decodetree Peter Maydell
2020-05-13 16:48   ` Richard Henderson
2020-05-12 16:38 ` [PATCH v2 06/17] target/arm: Convert Neon VRHADD, VHSUB 3-reg-same insns " Peter Maydell
2020-05-13 16:50   ` Richard Henderson
2020-05-12 16:38 ` [PATCH v2 07/17] target/arm: Convert Neon VQSHL, VRSHL, VQRSHL " Peter Maydell
2020-05-13 16:55   ` Richard Henderson
2020-05-12 16:38 ` [PATCH v2 08/17] target/arm: Convert Neon VPMAX/VPMIN " Peter Maydell
2020-05-12 16:38 ` [PATCH v2 09/17] target/arm: Convert Neon VPADD " Peter Maydell
2020-05-12 16:38 ` [PATCH v2 10/17] target/arm: Convert Neon VQDMULH/VQRDMULH 3-reg-same " Peter Maydell
2020-05-13 16:58   ` Richard Henderson
2020-05-12 16:38 ` [PATCH v2 11/17] target/arm: Convert Neon VADD, VSUB, VABD 3-reg-same insns " Peter Maydell
2020-05-13 20:06   ` Richard Henderson
2020-05-12 16:38 ` [PATCH v2 12/17] target/arm: Convert Neon VPMIN/VPMAX/VPADD float " Peter Maydell
2020-05-12 16:39 ` [PATCH v2 13/17] target/arm: Convert Neon fp VMUL, VMLA, VMLS " Peter Maydell
2020-05-13 20:28   ` Richard Henderson
2020-05-12 16:39 ` [PATCH v2 14/17] target/arm: Convert Neon 3-reg-same compare " Peter Maydell
2020-05-12 16:39 ` [PATCH v2 15/17] target/arm: Move 'env' argument of recps_f32 and rsqrts_f32 helpers to usual place Peter Maydell
2020-05-13 20:16   ` Richard Henderson
2020-05-12 16:39 ` [PATCH v2 16/17] target/arm: Convert Neon fp VMAX/VMIN/VMAXNM/VMINNM/VRECPS/VRSQRTS to decodetree Peter Maydell
2020-05-13 20:20   ` Richard Henderson
2020-05-12 16:39 ` [PATCH v2 17/17] target/arm: Convert NEON VFMA, VFMS 3-reg-same insns " Peter Maydell
2020-05-12 23:44 ` [PATCH v2 00/17] target/arm: Convert rest of Neon 3-reg-same " no-reply

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200512163904.10918-4-peter.maydell@linaro.org \
    --to=peter.maydell@linaro.org \
    --cc=qemu-arm@nongnu.org \
    --cc=qemu-devel@nongnu.org \
    --cc=richard.henderson@linaro.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.