qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
* [Qemu-devel] [PATCH 06/12] target-arm: optimize arm load/store multiple ops
@ 2009-10-21 10:17 Juha.Riihimaki
  2009-10-23 22:48 ` Laurent Desnogues
  0 siblings, 1 reply; 2+ messages in thread
From: Juha.Riihimaki @ 2009-10-21 10:17 UTC (permalink / raw)
  To: qemu-devel

[-- Attachment #1: Type: text/plain, Size: 2605 bytes --]

ARM load/store multiple instructions can be slightly optimized by  
loading the register offset constant into a variable outside the  
register loop and using the preloaded variable inside the loop instead  
of reloading the offset value to a temporary variable on each loop  
iteration. This causes less TCG ops to be generated for a ARM load/ 
store multiple instruction.

Signed-off-by: Juha Riihimäki <juha.riihimaki@nokia.com>
---
diff --git a/target-arm/translate.c b/target-arm/translate.c
index e5a2881..bae1122 100644
--- a/target-arm/translate.c
+++ b/target-arm/translate.c
@@ -6852,6 +6852,7 @@ static void disas_arm_insn(CPUState * env,  
DisasContext *s)
                  }
                  rn = (insn >> 16) & 0xf;
                  addr = load_reg(s, rn);
+                tmp2 = tcg_const_i32(4);

                  /* compute total size */
                  loaded_base = 0;
@@ -6865,7 +6866,7 @@ static void disas_arm_insn(CPUState * env,  
DisasContext *s)
                  if (insn & (1 << 23)) {
                      if (insn & (1 << 24)) {
                          /* pre increment */
-                        tcg_gen_addi_i32(addr, addr, 4);
+                        tcg_gen_add_i32(addr, addr, tmp2);
                      } else {
                          /* post increment */
                      }
@@ -6918,7 +6919,7 @@ static void disas_arm_insn(CPUState * env,  
DisasContext *s)
                          j++;
                          /* no need to add after the last transfer */
                          if (j != n)
-                            tcg_gen_addi_i32(addr, addr, 4);
+                            tcg_gen_add_i32(addr, addr, tmp2);
                      }
                  }
                  if (insn & (1 << 21)) {
@@ -6928,7 +6929,7 @@ static void disas_arm_insn(CPUState * env,  
DisasContext *s)
                              /* pre increment */
                          } else {
                              /* post increment */
-                            tcg_gen_addi_i32(addr, addr, 4);
+                            tcg_gen_add_i32(addr, addr, tmp2);
                          }
                      } else {
                          if (insn & (1 << 24)) {
@@ -6944,6 +6945,7 @@ static void disas_arm_insn(CPUState * env,  
DisasContext *s)
                  } else {
                      dead_tmp(addr);
                  }
+                tcg_temp_free_i32(tmp2);
                  if (loaded_base) {
                      store_reg(s, rn, loaded_var);
                  }

[-- Attachment #2: translate.c.ldmstm.diff --]
[-- Type: application/octet-stream, Size: 2117 bytes --]

diff --git a/target-arm/translate.c b/target-arm/translate.c
index e5a2881..bae1122 100644
--- a/target-arm/translate.c
+++ b/target-arm/translate.c
@@ -6852,6 +6852,7 @@ static void disas_arm_insn(CPUState * env, DisasContext *s)
                 }
                 rn = (insn >> 16) & 0xf;
                 addr = load_reg(s, rn);
+                tmp2 = tcg_const_i32(4);
 
                 /* compute total size */
                 loaded_base = 0;
@@ -6865,7 +6866,7 @@ static void disas_arm_insn(CPUState * env, DisasContext *s)
                 if (insn & (1 << 23)) {
                     if (insn & (1 << 24)) {
                         /* pre increment */
-                        tcg_gen_addi_i32(addr, addr, 4);
+                        tcg_gen_add_i32(addr, addr, tmp2);
                     } else {
                         /* post increment */
                     }
@@ -6918,7 +6919,7 @@ static void disas_arm_insn(CPUState * env, DisasContext *s)
                         j++;
                         /* no need to add after the last transfer */
                         if (j != n)
-                            tcg_gen_addi_i32(addr, addr, 4);
+                            tcg_gen_add_i32(addr, addr, tmp2);
                     }
                 }
                 if (insn & (1 << 21)) {
@@ -6928,7 +6929,7 @@ static void disas_arm_insn(CPUState * env, DisasContext *s)
                             /* pre increment */
                         } else {
                             /* post increment */
-                            tcg_gen_addi_i32(addr, addr, 4);
+                            tcg_gen_add_i32(addr, addr, tmp2);
                         }
                     } else {
                         if (insn & (1 << 24)) {
@@ -6944,6 +6945,7 @@ static void disas_arm_insn(CPUState * env, DisasContext *s)
                 } else {
                     dead_tmp(addr);
                 }
+                tcg_temp_free_i32(tmp2);
                 if (loaded_base) {
                     store_reg(s, rn, loaded_var);
                 }

^ permalink raw reply related	[flat|nested] 2+ messages in thread

* Re: [Qemu-devel] [PATCH 06/12] target-arm: optimize arm load/store multiple ops
  2009-10-21 10:17 [Qemu-devel] [PATCH 06/12] target-arm: optimize arm load/store multiple ops Juha.Riihimaki
@ 2009-10-23 22:48 ` Laurent Desnogues
  0 siblings, 0 replies; 2+ messages in thread
From: Laurent Desnogues @ 2009-10-23 22:48 UTC (permalink / raw)
  To: Juha.Riihimaki; +Cc: qemu-devel

On Wed, Oct 21, 2009 at 12:17 PM,  <Juha.Riihimaki@nokia.com> wrote:
> ARM load/store multiple instructions can be slightly optimized by
> loading the register offset constant into a variable outside the
> register loop and using the preloaded variable inside the loop instead
> of reloading the offset value to a temporary variable on each loop
> iteration. This causes less TCG ops to be generated for a ARM load/
> store multiple instruction.
>
> Signed-off-by: Juha Riihimäki <juha.riihimaki@nokia.com>

Acked-by: Laurent Desnogues <laurent.desnogues@gmail.com>

> ---
> diff --git a/target-arm/translate.c b/target-arm/translate.c
> index e5a2881..bae1122 100644
> --- a/target-arm/translate.c
> +++ b/target-arm/translate.c
> @@ -6852,6 +6852,7 @@ static void disas_arm_insn(CPUState * env,
> DisasContext *s)
>                  }
>                  rn = (insn >> 16) & 0xf;
>                  addr = load_reg(s, rn);
> +                tmp2 = tcg_const_i32(4);
>
>                  /* compute total size */
>                  loaded_base = 0;
> @@ -6865,7 +6866,7 @@ static void disas_arm_insn(CPUState * env,
> DisasContext *s)
>                  if (insn & (1 << 23)) {
>                      if (insn & (1 << 24)) {
>                          /* pre increment */
> -                        tcg_gen_addi_i32(addr, addr, 4);
> +                        tcg_gen_add_i32(addr, addr, tmp2);
>                      } else {
>                          /* post increment */
>                      }
> @@ -6918,7 +6919,7 @@ static void disas_arm_insn(CPUState * env,
> DisasContext *s)
>                          j++;
>                          /* no need to add after the last transfer */
>                          if (j != n)
> -                            tcg_gen_addi_i32(addr, addr, 4);
> +                            tcg_gen_add_i32(addr, addr, tmp2);
>                      }
>                  }
>                  if (insn & (1 << 21)) {
> @@ -6928,7 +6929,7 @@ static void disas_arm_insn(CPUState * env,
> DisasContext *s)
>                              /* pre increment */
>                          } else {
>                              /* post increment */
> -                            tcg_gen_addi_i32(addr, addr, 4);
> +                            tcg_gen_add_i32(addr, addr, tmp2);
>                          }
>                      } else {
>                          if (insn & (1 << 24)) {
> @@ -6944,6 +6945,7 @@ static void disas_arm_insn(CPUState * env,
> DisasContext *s)
>                  } else {
>                      dead_tmp(addr);
>                  }
> +                tcg_temp_free_i32(tmp2);
>                  if (loaded_base) {
>                      store_reg(s, rn, loaded_var);
>                  }
>


Laurent

^ permalink raw reply	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2009-10-23 22:48 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2009-10-21 10:17 [Qemu-devel] [PATCH 06/12] target-arm: optimize arm load/store multiple ops Juha.Riihimaki
2009-10-23 22:48 ` Laurent Desnogues

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).