[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Qemu-devel] [PATCH v2 07/10] target-arm: optimize thumb2 load/stor
From: |
Laurent Desnogues |
Subject: |
Re: [Qemu-devel] [PATCH v2 07/10] target-arm: optimize thumb2 load/store multiple ops |
Date: |
Sat, 24 Oct 2009 19:32:01 +0200 |
On Sat, Oct 24, 2009 at 2:19 PM, <address@hidden> wrote:
> From: Juha Riihimäki <address@hidden>
>
> Thumb2 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 Thumb2 load/
> store multiple instruction if there are more than one register
> accessed, otherwise the amount of generated TCG ops will be the same.
>
> Signed-off-by: Juha Riihimäki <address@hidden>
Acked-by: Laurent Desnogues <address@hidden>
Laurent
> ---
> target-arm/translate.c | 4 +++-
> 1 files changed, 3 insertions(+), 1 deletions(-)
>
> diff --git a/target-arm/translate.c b/target-arm/translate.c
> index 9e924d4..353f638 100644
> --- a/target-arm/translate.c
> +++ b/target-arm/translate.c
> @@ -7374,6 +7374,7 @@ static int disas_thumb2_insn(CPUState *env,
> DisasContext *s, uint16_t insn_hw1)
> tcg_gen_addi_i32(addr, addr, -offset);
> }
>
> + tmp2 = tcg_const_i32(4);
> for (i = 0; i < 16; i++) {
> if ((insn & (1 << i)) == 0)
> continue;
> @@ -7390,8 +7391,9 @@ static int disas_thumb2_insn(CPUState *env,
> DisasContext *s, uint16_t insn_hw1)
> tmp = load_reg(s, i);
> gen_st32(tmp, addr, IS_USER(s));
> }
> - tcg_gen_addi_i32(addr, addr, 4);
> + tcg_gen_add_i32(addr, addr, tmp2);
> }
> + tcg_temp_free_i32(tmp2);
> if (insn & (1 << 21)) {
> /* Base register writeback. */
> if (insn & (1 << 24)) {
> --
> 1.6.5
>
>
>
>
- Re: [Qemu-devel] [PATCH v2 03/10] target-arm: allow modifying vfp fpexc en bit only, (continued)
[Qemu-devel] [PATCH v2 02/10] target-arm: add support for neon vld1.64/vst1.64 instructions, juha . riihimaki, 2009/10/24
[Qemu-devel] [PATCH v2 05/10] target-arm: optimize arm load/store multiple ops, juha . riihimaki, 2009/10/24
[Qemu-devel] [PATCH v2 07/10] target-arm: optimize thumb2 load/store multiple ops, juha . riihimaki, 2009/10/24
- Re: [Qemu-devel] [PATCH v2 07/10] target-arm: optimize thumb2 load/store multiple ops,
Laurent Desnogues <=
[Qemu-devel] [PATCH v2 09/10] target-arm: optimize neon vld/vst ops, juha . riihimaki, 2009/10/24
- Re: [Qemu-devel] [PATCH v2 09/10] target-arm: optimize neon vld/vst ops, Laurent Desnogues, 2009/10/25
- Re: [Qemu-devel] [PATCH v2 09/10] target-arm: optimize neon vld/vst ops, Juha.Riihimaki, 2009/10/26
- Re: [Qemu-devel] [PATCH v2 09/10] target-arm: optimize neon vld/vst ops, Laurent Desnogues, 2009/10/26
- Re: [Qemu-devel] [PATCH v2 09/10] target-arm: optimize neon vld/vst ops, Aurelien Jarno, 2009/10/26
- Re: [Qemu-devel] [PATCH v2 09/10] target-arm: optimize neon vld/vst ops, Juha.Riihimaki, 2009/10/29
- Re: [Qemu-devel] [PATCH v2 09/10] target-arm: optimize neon vld/vst ops, Laurent Desnogues, 2009/10/29
[Qemu-devel] [PATCH v2 06/10] target-arm: fix neon vsri, vshl and vsli ops, juha . riihimaki, 2009/10/24
[Qemu-devel] [PATCH v2 10/10] target-arm: fix neon shift helper functions, juha . riihimaki, 2009/10/24