All of lore.kernel.org
 help / color / mirror / Atom feed
From: Richard Henderson <rth@twiddle.net>
To: qemu-devel@nongnu.org
Cc: "Emilio G. Cota" <cota@braap.org>
Subject: [Qemu-devel] [PATCH v7 10/26] target/i386: optimize indirect branches
Date: Fri, 26 May 2017 14:16:22 -0700	[thread overview]
Message-ID: <20170526211638.32301-11-rth@twiddle.net> (raw)
In-Reply-To: <20170526211638.32301-1-rth@twiddle.net>

From: "Emilio G. Cota" <cota@braap.org>

Speed up indirect branches by jumping to the target if it is valid.

Softmmu measurements (see later commit for user-mode numbers):

Note: baseline (i.e. speedup == 1x) is QEMU v2.9.0.

-                  SPECint06 (test set), x86_64-softmmu (Ubuntu 16.04 guest). Host: Intel i7-4790K @ 4.00GHz

 2.4x +-+--------------------------------------------------------------------------------------------------------------+-+
      |                                                                                                                  |
      |   cross                                                                                                          |
 2.2x +cross+jr..........................................................................+++...........................+-+
      |                                                                                   |                              |
      |                                                                               +++ |                              |
   2x +-+..............................................................................|..|............................+-+
      |                                                                                |  |                              |
      |                                                                                |  |                              |
 1.8x +-+..............................................................................|####...........................+-+
      |                                                                                |# |#                             |
      |                                                                              **** |#                             |
 1.6x +-+............................................................................*.|*.|#...........................+-+
      |                                                                              * |* |#                             |
      |                                                                              * |* |#                             |
 1.4x +-+.......................................................................+++..*.|*.|#...........................+-+
      |                                                      ++++++             #### * |*++#             +++             |
      |                        +++                            |  |              #++# *++*  #          +++ |              |
 1.2x +-+......................###.....####....+++............|..|...........****..#.*..*..#....####...|.###.....####..+-+
      |        +++          **** #  ****  #    ####          ***###          *++*  # *  *  #    #++#  ****|#  +++#++#    |
      |    ****###     +++  *++* #  *++*  #  ++#  #    ####  *|* |#     +++  *  *  # *  *  #  ***  #  *| *|#  ****  #    |
   1x +-++-*++*++#++***###++*++*+#++*+-*++#+****++#++***++#+-*+*++#-+****##++*++*-+#+*++*-+#++*+*++#++*-+*+#++*++*++#-++-+
      |    *  *  #  * *  #  *  * #  *  *  # *  *  #  * *  #  *|* |#  *++* #  *  *  # *  *  #  * *  #  *  * #  *  *  #    |
      |    *  *  #  * *  #  *  * #  *  *  # *  *  #  * *  #  *+*++#  *  * #  *  *  # *  *  #  * *  #  *  * #  *  *  #    |
 0.8x +-+--****###--***###--****##--****###-****###--***###--***###--****##--****###-****###--***###--****##--****###--+-+
         astar   bzip2      gcc   gobmk h264ref   hmmlibquantum      mcf omnetpperlbench   sjengxalancbmk   hmean
  png: http://imgur.com/DU36YFU

NB. 'cross' represents the previous commit.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Emilio G. Cota <cota@braap.org>
Message-Id: <1493263764-18657-11-git-send-email-cota@braap.org>
Signed-off-by: Richard Henderson <rth@twiddle.net>
---
 target/i386/translate.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/target/i386/translate.c b/target/i386/translate.c
index ea113fe..674ec96 100644
--- a/target/i386/translate.c
+++ b/target/i386/translate.c
@@ -4996,7 +4996,7 @@ static target_ulong disas_insn(CPUX86State *env, DisasContext *s,
             gen_push_v(s, cpu_T1);
             gen_op_jmp_v(cpu_T0);
             gen_bnd_jmp(s);
-            gen_eob(s);
+            gen_jr(s, cpu_T0);
             break;
         case 3: /* lcall Ev */
             gen_op_ld_v(s, ot, cpu_T1, cpu_A0);
@@ -5014,7 +5014,8 @@ static target_ulong disas_insn(CPUX86State *env, DisasContext *s,
                                       tcg_const_i32(dflag - 1),
                                       tcg_const_i32(s->pc - s->cs_base));
             }
-            gen_eob(s);
+            tcg_gen_ld_tl(cpu_tmp4, cpu_env, offsetof(CPUX86State, eip));
+            gen_jr(s, cpu_tmp4);
             break;
         case 4: /* jmp Ev */
             if (dflag == MO_16) {
@@ -5022,7 +5023,7 @@ static target_ulong disas_insn(CPUX86State *env, DisasContext *s,
             }
             gen_op_jmp_v(cpu_T0);
             gen_bnd_jmp(s);
-            gen_eob(s);
+            gen_jr(s, cpu_T0);
             break;
         case 5: /* ljmp Ev */
             gen_op_ld_v(s, ot, cpu_T1, cpu_A0);
@@ -5037,7 +5038,8 @@ static target_ulong disas_insn(CPUX86State *env, DisasContext *s,
                 gen_op_movl_seg_T0_vm(R_CS);
                 gen_op_jmp_v(cpu_T1);
             }
-            gen_eob(s);
+            tcg_gen_ld_tl(cpu_tmp4, cpu_env, offsetof(CPUX86State, eip));
+            gen_jr(s, cpu_tmp4);
             break;
         case 6: /* push Ev */
             gen_push_v(s, cpu_T0);
@@ -6417,7 +6419,7 @@ static target_ulong disas_insn(CPUX86State *env, DisasContext *s,
         /* Note that gen_pop_T0 uses a zero-extending load.  */
         gen_op_jmp_v(cpu_T0);
         gen_bnd_jmp(s);
-        gen_eob(s);
+        gen_jr(s, cpu_T0);
         break;
     case 0xc3: /* ret */
         ot = gen_pop_T0(s);
@@ -6425,7 +6427,7 @@ static target_ulong disas_insn(CPUX86State *env, DisasContext *s,
         /* Note that gen_pop_T0 uses a zero-extending load.  */
         gen_op_jmp_v(cpu_T0);
         gen_bnd_jmp(s);
-        gen_eob(s);
+        gen_jr(s, cpu_T0);
         break;
     case 0xca: /* lret im */
         val = cpu_ldsw_code(env, s->pc);
-- 
2.9.4

  parent reply	other threads:[~2017-05-26 21:16 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-05-26 21:16 [Qemu-devel] [PATCH v7 00/26] tcg cross-tb optimizations Richard Henderson
2017-05-26 21:16 ` [Qemu-devel] [PATCH v7 01/26] target/nios2: Fix 64-bit ilp32 compilation Richard Henderson
2017-05-26 21:16 ` [Qemu-devel] [PATCH v7 02/26] tcg/sparc: Use the proper compilation flags for 32-bit Richard Henderson
2017-05-26 21:16 ` [Qemu-devel] [PATCH v7 03/26] qemu/atomic: Loosen restrictions for 64-bit ILP32 hosts Richard Henderson
2017-05-26 21:16 ` [Qemu-devel] [PATCH v7 04/26] tcg: Introduce goto_ptr opcode and tcg_gen_lookup_and_goto_ptr Richard Henderson
2017-05-26 21:16 ` [Qemu-devel] [PATCH v7 05/26] tcg/i386: implement goto_ptr Richard Henderson
2017-05-26 21:16 ` [Qemu-devel] [PATCH v7 06/26] target/arm: optimize cross-page direct jumps in softmmu Richard Henderson
2017-05-26 21:16 ` [Qemu-devel] [PATCH v7 07/26] target/arm: optimize indirect branches Richard Henderson
2017-05-26 21:16 ` [Qemu-devel] [PATCH v7 08/26] target/i386: introduce gen_jr helper to generate lookup_and_goto_ptr Richard Henderson
2017-05-26 21:16 ` [Qemu-devel] [PATCH v7 09/26] target/i386: optimize cross-page direct jumps in softmmu Richard Henderson
2017-05-26 21:16 ` Richard Henderson [this message]
2017-05-26 21:16 ` [Qemu-devel] [PATCH v7 11/26] tb-hash: improve tb_jmp_cache hash function in user mode Richard Henderson
2017-05-26 21:16 ` [Qemu-devel] [PATCH v7 12/26] tcg/ppc: Implement goto_ptr Richard Henderson
2017-05-26 21:16 ` [Qemu-devel] [PATCH v7 13/26] tcg/aarch64: " Richard Henderson
2017-05-26 21:16 ` [Qemu-devel] [PATCH v7 14/26] tcg/sparc: " Richard Henderson
2017-05-26 21:16 ` [Qemu-devel] [PATCH v7 15/26] tcg/s390: " Richard Henderson
2017-05-26 21:16 ` [Qemu-devel] [PATCH v7 16/26] tcg/arm: Clarify tcg_out_bx for arm4 host Richard Henderson
2017-05-27 16:41   ` Philippe Mathieu-Daudé
2017-05-26 21:16 ` [Qemu-devel] [PATCH v7 17/26] tcg/arm: Implement goto_ptr Richard Henderson
2017-05-26 21:16 ` [Qemu-devel] [PATCH v7 19/26] target/s390: Use tcg_gen_lookup_and_goto_ptr Richard Henderson
2017-05-26 21:16 ` [Qemu-devel] [PATCH v7 20/26] target/hppa: " Richard Henderson
2017-05-26 21:16 ` [Qemu-devel] [PATCH v7 21/26] target/aarch64: optimize cross-page direct jumps in softmmu Richard Henderson
2017-05-26 21:16 ` [Qemu-devel] [PATCH v7 22/26] target/aarch64: optimize indirect branches Richard Henderson
2017-05-26 21:16 ` [Qemu-devel] [PATCH v7 23/26] target/mips: optimize cross-page direct jumps in softmmu Richard Henderson
2017-05-26 21:16 ` [Qemu-devel] [PATCH v7 24/26] target/mips: optimize indirect branches Richard Henderson
2017-05-26 21:16 ` [Qemu-devel] [PATCH v7 25/26] target/alpha: Implement WTINT inline Richard Henderson
2017-05-26 21:16 ` [Qemu-devel] [PATCH v7 26/26] target/alpha: Use goto_tb for fallthru between TBs Richard Henderson

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=20170526211638.32301-11-rth@twiddle.net \
    --to=rth@twiddle.net \
    --cc=cota@braap.org \
    --cc=qemu-devel@nongnu.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.