qemu-devel.nongnu.org archive mirror
 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 07/17] target/arm: Convert Neon VQSHL, VRSHL, VQRSHL 3-reg-same insns to decodetree
Date: Tue, 12 May 2020 17:38:54 +0100	[thread overview]
Message-ID: <20200512163904.10918-8-peter.maydell@linaro.org> (raw)
In-Reply-To: <20200512163904.10918-1-peter.maydell@linaro.org>

Convert the VQSHL, VRSHL and VQRSHL insns in the 3-reg-same
group to decodetree. We have already implemented the size==0b11
case of these insns; this commit handles the remaining sizes.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/neon-dp.decode       | 47 +++++++++++++++++++++++----------
 target/arm/translate-neon.inc.c | 43 ++++++++++++++++++++++++++++++
 target/arm/translate.c          | 22 +++------------
 3 files changed, 79 insertions(+), 33 deletions(-)

diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
index 353cb1f4992..e0da5a39fc2 100644
--- a/target/arm/neon-dp.decode
+++ b/target/arm/neon-dp.decode
@@ -74,14 +74,6 @@ VCGE_S_3s        1111 001 0 0 . .. .... .... 0011 . . . 1 .... @3same
 VCGE_U_3s        1111 001 1 0 . .. .... .... 0011 . . . 1 .... @3same
 
 # The shift operations are of the form Vd = Vm << Vn.
-# By reversing the names of the fields here, we can use standard expanders.
-@3same_rev       .... ... . . . size:2 .... .... .... . q:1 . . .... \
-                 &3same vn=%vm_dp vm=%vn_dp vd=%vd_dp
-
-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
@@ -92,15 +84,42 @@ VSHL_U_3s        1111 001 1 0 . .. .... .... 0100 . . . 0 .... @3same_rev
 # 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_rev       .... ... . . . size:2 .... .... .... . q:1 . . .... \
+                 &3same vn=%vm_dp vm=%vn_dp vd=%vd_dp
+
+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 (as explained
+# by the comment for the @3same_rev format).
 @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
+{
+  VQSHL_S64_3s   1111 001 0 0 . .. .... .... 0100 . . . 1 .... @3same_64_rev
+  VQSHL_S_3s     1111 001 0 0 . .. .... .... 0100 . . . 1 .... @3same_rev
+}
+{
+  VQSHL_U64_3s   1111 001 1 0 . .. .... .... 0100 . . . 1 .... @3same_64_rev
+  VQSHL_U_3s     1111 001 1 0 . .. .... .... 0100 . . . 1 .... @3same_rev
+}
+{
+  VRSHL_S64_3s   1111 001 0 0 . .. .... .... 0101 . . . 0 .... @3same_64_rev
+  VRSHL_S_3s     1111 001 0 0 . .. .... .... 0101 . . . 0 .... @3same_rev
+}
+{
+  VRSHL_U64_3s   1111 001 1 0 . .. .... .... 0101 . . . 0 .... @3same_64_rev
+  VRSHL_U_3s     1111 001 1 0 . .. .... .... 0101 . . . 0 .... @3same_rev
+}
+{
+  VQRSHL_S64_3s  1111 001 0 0 . .. .... .... 0101 . . . 1 .... @3same_64_rev
+  VQRSHL_S_3s    1111 001 0 0 . .. .... .... 0101 . . . 1 .... @3same_rev
+}
+{
+  VQRSHL_U64_3s  1111 001 1 0 . .. .... .... 0101 . . . 1 .... @3same_64_rev
+  VQRSHL_U_3s    1111 001 1 0 . .. .... .... 0101 . . . 1 .... @3same_rev
+}
 
 VMAX_S_3s        1111 001 0 0 . .. .... .... 0110 . . . 0 .... @3same
 VMAX_U_3s        1111 001 1 0 . .. .... .... 0110 . . . 0 .... @3same
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
index e9da47171c6..7097c18f334 100644
--- a/target/arm/translate-neon.inc.c
+++ b/target/arm/translate-neon.inc.c
@@ -875,9 +875,52 @@ DO_3SAME_64_ENV(VQRSHL_U64, gen_helper_neon_qrshl_u64)
         return do_3same(s, a, gen_##INSN##_3s);                         \
     }
 
+/*
+ * Some helper functions need to be passed the cpu_env. In order
+ * to use those with the gvec APIs like tcg_gen_gvec_3() we need
+ * to create wrapper functions whose prototype is a NeonGenTwoOpFn()
+ * and which call a NeonGenTwoOpEnvFn().
+ */
+#define WRAP_ENV_FN(WRAPNAME, FUNC)                                     \
+    static void WRAPNAME(TCGv_i32 d, TCGv_i32 n, TCGv_i32 m)            \
+    {                                                                   \
+        FUNC(d, cpu_env, n, m);                                         \
+    }
+
+#define DO_3SAME_32_ENV(INSN, FUNC)                                     \
+    WRAP_ENV_FN(gen_##INSN##_tramp8, gen_helper_neon_##FUNC##8);        \
+    WRAP_ENV_FN(gen_##INSN##_tramp16, gen_helper_neon_##FUNC##16);      \
+    WRAP_ENV_FN(gen_##INSN##_tramp32, gen_helper_neon_##FUNC##32);      \
+    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 ops[4] = {                                \
+            { .fni4 = gen_##INSN##_tramp8 },                            \
+            { .fni4 = gen_##INSN##_tramp16 },                           \
+            { .fni4 = gen_##INSN##_tramp32 },                           \
+            { 0 },                                                      \
+        };                                                              \
+        tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, &ops[vece]); \
+    }                                                                   \
+    static bool trans_##INSN##_3s(DisasContext *s, arg_3same *a)        \
+    {                                                                   \
+        if (a->size > 2) {                                              \
+            return false;                                               \
+        }                                                               \
+        return do_3same(s, a, gen_##INSN##_3s);                         \
+    }
+
 DO_3SAME_32(VHADD_S, hadd_s)
 DO_3SAME_32(VHADD_U, hadd_u)
 DO_3SAME_32(VHSUB_S, hsub_s)
 DO_3SAME_32(VHSUB_U, hsub_u)
 DO_3SAME_32(VRHADD_S, rhadd_s)
 DO_3SAME_32(VRHADD_U, rhadd_u)
+DO_3SAME_32(VRSHL_S, rshl_s)
+DO_3SAME_32(VRSHL_U, rshl_u)
+
+DO_3SAME_32_ENV(VQSHL_S, qshl_s)
+DO_3SAME_32_ENV(VQSHL_U, qshl_u)
+DO_3SAME_32_ENV(VQRSHL_S, qrshl_s)
+DO_3SAME_32_ENV(VQRSHL_U, qrshl_u)
diff --git a/target/arm/translate.c b/target/arm/translate.c
index ebb899d846e..3aabb18720b 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -5439,6 +5439,9 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
         case NEON_3R_VHSUB:
         case NEON_3R_VABD:
         case NEON_3R_VABA:
+        case NEON_3R_VQSHL:
+        case NEON_3R_VRSHL:
+        case NEON_3R_VQRSHL:
             /* Already handled by decodetree */
             return 1;
         }
@@ -5449,17 +5452,6 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
         }
         pairwise = 0;
         switch (op) {
-        case NEON_3R_VQSHL:
-        case NEON_3R_VRSHL:
-        case NEON_3R_VQRSHL:
-            {
-                int rtmp;
-                /* Shift instruction operands are reversed.  */
-                rtmp = rn;
-                rn = rm;
-                rm = rtmp;
-            }
-            break;
         case NEON_3R_VPADD_VQRDMLAH:
         case NEON_3R_VPMAX:
         case NEON_3R_VPMIN:
@@ -5519,14 +5511,6 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
             tmp2 = neon_load_reg(rm, pass);
         }
         switch (op) {
-        case NEON_3R_VQSHL:
-            GEN_NEON_INTEGER_OP_ENV(qshl);
-            break;
-        case NEON_3R_VRSHL:
-            GEN_NEON_INTEGER_OP(rshl);
-            break;
-        case NEON_3R_VQRSHL:
-            GEN_NEON_INTEGER_OP_ENV(qrshl);
             break;
         case NEON_3R_VPMAX:
             GEN_NEON_INTEGER_OP(pmax);
-- 
2.20.1



  parent reply	other threads:[~2020-05-12 16:50 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 ` [PATCH v2 03/17] target/arm: Convert Neon 64-bit element 3-reg-same insns Peter Maydell
2020-05-13 20:27   ` 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 ` Peter Maydell [this message]
2020-05-13 16:55   ` [PATCH v2 07/17] target/arm: Convert Neon VQSHL, VRSHL, VQRSHL " 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=20200512163904.10918-8-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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).