qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Richard Henderson <rth@twiddle.net>
To: qemu-devel@nongnu.org
Cc: Aurelien Jarno <aurelien@aurel32.net>
Subject: [Qemu-devel] [PATCH 10/10] tcg: Optimize mulu2
Date: Tue,  2 Oct 2012 11:32:30 -0700	[thread overview]
Message-ID: <1349202750-16815-11-git-send-email-rth@twiddle.net> (raw)
In-Reply-To: <1349202750-16815-1-git-send-email-rth@twiddle.net>

Like add2, do operand ordering, constant folding, and dead operand
elimination.  The latter happens about 15% of all mulu2 during an
x86_64 bios boot.

Signed-off-by: Richard Henderson <rth@twiddle.net>
---
 tcg/optimize.c | 26 ++++++++++++++++++++++++++
 tcg/tcg-op.h   |  2 ++
 tcg/tcg.c      | 19 +++++++++++++++++++
 3 files changed, 47 insertions(+)

diff --git a/tcg/optimize.c b/tcg/optimize.c
index 05891ef..a06c8eb 100644
--- a/tcg/optimize.c
+++ b/tcg/optimize.c
@@ -543,6 +543,9 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
             swap_commutative(args[0], &args[2], &args[4]);
             swap_commutative(args[1], &args[3], &args[5]);
             break;
+        case INDEX_op_mulu2_i32:
+            swap_commutative(args[0], &args[2], &args[3]);
+            break;
         case INDEX_op_brcond2_i32:
             if (swap_commutative2(&args[0], &args[2])) {
                 args[4] = tcg_swap_cond(args[4]);
@@ -831,6 +834,29 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
             }
             goto do_default;
 
+        case INDEX_op_mulu2_i32:
+            if (temps[args[2]].state == TCG_TEMP_CONST
+                && temps[args[3]].state == TCG_TEMP_CONST) {
+                uint32_t a = temps[args[2]].val;
+                uint32_t b = temps[args[3]].val;
+                uint64_t r = (uint64_t)a * b;
+                TCGArg rl, rh;
+
+                /* We emit the extra nop when we emit the mulu2.  */
+                assert(gen_opc_buf[op_index + 1] == INDEX_op_nop);
+
+                rl = args[0];
+                rh = args[1];
+                gen_opc_buf[op_index] = INDEX_op_movi_i32;
+                gen_opc_buf[++op_index] = INDEX_op_movi_i32;
+                tcg_opt_gen_movi(&gen_args[0], rl, (uint32_t)r);
+                tcg_opt_gen_movi(&gen_args[2], rh, (uint32_t)(r >> 32));
+                gen_args += 4;
+                args += 4;
+                break;
+            }
+            goto do_default;
+
         case INDEX_op_brcond2_i32:
             tmp = do_constant_folding_cond2(&args[0], &args[2], args[4]);
             if (tmp != 2) {
diff --git a/tcg/tcg-op.h b/tcg/tcg-op.h
index 1f5a021..044e648 100644
--- a/tcg/tcg-op.h
+++ b/tcg/tcg-op.h
@@ -997,6 +997,8 @@ static inline void tcg_gen_mul_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
 
     tcg_gen_op4_i32(INDEX_op_mulu2_i32, TCGV_LOW(t0), TCGV_HIGH(t0),
                     TCGV_LOW(arg1), TCGV_LOW(arg2));
+    /* Allow the optimizer room to replace mulu2 with two moves.  */
+    tcg_gen_op0(INDEX_op_nop);
 
     tcg_gen_mul_i32(t1, TCGV_LOW(arg1), TCGV_HIGH(arg2));
     tcg_gen_add_i32(TCGV_HIGH(t0), TCGV_HIGH(t0), t1);
diff --git a/tcg/tcg.c b/tcg/tcg.c
index 21c1074..8280489 100644
--- a/tcg/tcg.c
+++ b/tcg/tcg.c
@@ -1337,6 +1337,25 @@ static void tcg_liveness_analysis(TCGContext *s)
             }
             goto do_not_remove;
 
+        case INDEX_op_mulu2_i32:
+            args -= 4;
+            nb_iargs = 2;
+            nb_oargs = 2;
+            /* Likewise, test for the high part of the operation dead.  */
+            if (dead_temps[args[1]]) {
+                if (dead_temps[args[0]]) {
+                    goto do_remove;
+                }
+                gen_opc_buf[op_index] = op = INDEX_op_mul_i32;
+                args[1] = args[2];
+                args[2] = args[3];
+                assert(gen_opc_buf[op_index + 1] == INDEX_op_nop);
+                tcg_set_nop(s, gen_opc_buf + op_index + 1, args + 3, 1);
+                /* Fall through and mark the single-word operation live.  */
+                nb_oargs = 1;
+            }
+            goto do_not_remove;
+
         default:
             /* XXX: optimize by hardcoding common cases (e.g. triadic ops) */
             args -= def->nb_args;
-- 
1.7.11.4

  parent reply	other threads:[~2012-10-02 18:34 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-10-02 18:32 [Qemu-devel] [PATCH v2 00/10] Double-word tcg/optimize improvements Richard Henderson
2012-10-02 18:32 ` [Qemu-devel] [PATCH 01/10] tcg: Split out swap_commutative as a subroutine Richard Henderson
2012-10-09 15:13   ` Aurelien Jarno
2012-10-09 15:23     ` Richard Henderson
2012-10-09 15:31       ` Aurelien Jarno
2012-10-09 16:40         ` Richard Henderson
2012-10-02 18:32 ` [Qemu-devel] [PATCH 02/10] tcg: Canonicalize add2 operand ordering Richard Henderson
2012-10-09 15:14   ` Aurelien Jarno
2012-10-02 18:32 ` [Qemu-devel] [PATCH 03/10] tcg: Swap commutative double-word comparisons Richard Henderson
2012-10-09 15:16   ` Aurelien Jarno
2012-10-09 15:31     ` Richard Henderson
2012-10-09 15:48       ` Aurelien Jarno
2012-10-02 18:32 ` [Qemu-devel] [PATCH 04/10] tcg: Use common code when failing to optimize Richard Henderson
2012-10-09 15:25   ` Aurelien Jarno
2012-10-09 15:33     ` Richard Henderson
2012-10-02 18:32 ` [Qemu-devel] [PATCH 05/10] tcg: Optimize double-word comparisons against zero Richard Henderson
2012-10-09 16:32   ` Aurelien Jarno
2012-10-02 18:32 ` [Qemu-devel] [PATCH 06/10] tcg: Split out subroutines from do_constant_folding_cond Richard Henderson
2012-10-09 16:33   ` Aurelien Jarno
2012-10-02 18:32 ` [Qemu-devel] [PATCH 07/10] tcg: Do constant folding on double-word comparisons Richard Henderson
2012-10-10  9:45   ` Aurelien Jarno
2012-10-02 18:32 ` [Qemu-devel] [PATCH 08/10] tcg: Constant fold add2 and sub2 Richard Henderson
2012-10-10  9:52   ` Aurelien Jarno
2012-10-02 18:32 ` [Qemu-devel] [PATCH 09/10] tcg: Optimize half-dead add2/sub2 Richard Henderson
2012-10-16 23:25   ` Aurelien Jarno
2012-10-02 18:32 ` Richard Henderson [this message]
2012-10-16 23:25   ` [Qemu-devel] [PATCH 10/10] tcg: Optimize mulu2 Aurelien Jarno
2012-10-17  1:09     ` Richard Henderson
2012-10-17 10:58       ` Avi Kivity
2012-10-17 16:41 ` [Qemu-devel] [PATCH v2 00/10] Double-word tcg/optimize improvements Aurelien Jarno

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=1349202750-16815-11-git-send-email-rth@twiddle.net \
    --to=rth@twiddle.net \
    --cc=aurelien@aurel32.net \
    --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 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).