Re: [Qemu-devel] [PATCH] ppc: Convert op_440_dlmzb to TCG

[Aurélien Jarno]

On Sat, Nov 29, 2008 at 03:35:21PM +0100, Andreas Färber wrote:
> Replace {op,do}_440_dlmzb and op_440_dlmzb_update_Rc with inline TCG  
> instructions.
> 
> The two loops of do_440_dlmzb are unrolled.
> 
> Signed-off-by: Andreas Faerber <address@hidden>

Doing loops with TCG is a bad idea as it is very inefficient.

> ---
>  Compile-tested on Linux/amd64.
> 
> diff --git a/target-ppc/op.c b/target-ppc/op.c
> index 5d2cfa1..a26b1da 100644
> --- a/target-ppc/op.c
> +++ b/target-ppc/op.c
> @@ -839,25 +839,6 @@ void OPPROTO op_4xx_tlbwe_hi (void)
>  }
>  #endif
> 
> -/* SPR micro-ops */
> -/* 440 specific */
> -void OPPROTO op_440_dlmzb (void)
> -{
> -    do_440_dlmzb();
> -    RETURN();
> -}
> -
> -void OPPROTO op_440_dlmzb_update_Rc (void)
> -{
> -    if (T0 == 8)
> -        T0 = 0x2;
> -    else if (T0 < 4)
> -        T0 = 0x4;
> -    else
> -        T0 = 0x8;
> -    RETURN();
> -}
> -
>  #if !defined(CONFIG_USER_ONLY)
>  void OPPROTO op_store_pir (void)
>  {
> diff --git a/target-ppc/op_helper.c b/target-ppc/op_helper.c
> index 6addc74..a055ee6 100644
> --- a/target-ppc/op_helper.c
> +++ b/target-ppc/op_helper.c
> @@ -1754,27 +1754,6 @@ void do_store_403_pb (int num)
>  }
>  #endif
> 
> -/* 440 specific */
> -void do_440_dlmzb (void)
> -{
> -    target_ulong mask;
> -    int i;
> -
> -    i = 1;
> -    for (mask = 0xFF000000; mask != 0; mask = mask >> 8) {
> -        if ((T0 & mask) == 0)
> -            goto done;
> -        i++;
> -    }
> -    for (mask = 0xFF000000; mask != 0; mask = mask >> 8) {
> -        if ((T1 & mask) == 0)
> -            break;
> -        i++;
> -    }
> - done:
> -    T0 = i;
> -}
> -
>  / 
> *****************************************************************************/
>  /* SPE extension helpers */
>  /* Use a table to make this quicker */
> diff --git a/target-ppc/op_helper.h b/target-ppc/op_helper.h
> index 1c046d8..aaaba5c 100644
> --- a/target-ppc/op_helper.h
> +++ b/target-ppc/op_helper.h
> @@ -112,9 +112,6 @@ void do_4xx_tlbwe_lo (void);
>  void do_4xx_tlbwe_hi (void);
>  #endif
> 
> -/* PowerPC 440 specific helpers */
> -void do_440_dlmzb (void);
> -
>  /* PowerPC 403 specific helpers */
>  #if !defined(CONFIG_USER_ONLY)
>  void do_load_403_pb (int num);
> diff --git a/target-ppc/translate.c b/target-ppc/translate.c
> index 95cb482..59533ac 100644
> --- a/target-ppc/translate.c
> +++ b/target-ppc/translate.c
> @@ -5872,12 +5872,49 @@ GEN_HANDLER(dlmzb, 0x1F, 0x0E, 0x02,  
> 0x00000000, PPC_440_SPEC)
>  {
>      tcg_gen_mov_tl(cpu_T[0], cpu_gpr[rS(ctx->opcode)]);
>      tcg_gen_mov_tl(cpu_T[1], cpu_gpr[rB(ctx->opcode)]);
> -    gen_op_440_dlmzb();
> +    TCGv t0 = tcg_temp_new();
> +    int endLabel = gen_new_label();
> +    int i = 1;
> +    target_ulong mask;
> +    for (mask = 0xFF000000; mask != 0; mask = mask >> 8) {
> +        tcg_gen_andi_tl(t0, cpu_T[0], mask);
> +        int nextLabel = gen_new_label();
> +        tcg_gen_brcondi_tl(TCG_COND_NE, t0, 0, nextLabel);
> +        tcg_gen_movi_tl(cpu_T[0], i++);
> +        tcg_gen_br(endLabel);
> +        gen_set_label(nextLabel);
> +    }
> +    for (mask = 0xFF000000; mask != 0; mask = mask >> 8) {
> +        tcg_gen_andi_tl(t0, cpu_T[1], mask);
> +        int nextLabel = gen_new_label();
> +        tcg_gen_brcondi_tl(TCG_COND_NE, t0, 0, nextLabel);
> +        tcg_gen_movi_tl(cpu_T[0], i++);
> +        tcg_gen_br(endLabel);
> +        gen_set_label(nextLabel);
> +    }
> +    tcg_gen_movi_tl(cpu_T[0], i);
> +    gen_set_label(endLabel);
> +    tcg_temp_free(t0);
>      tcg_gen_mov_tl(cpu_gpr[rA(ctx->opcode)], cpu_T[0]);
>      tcg_gen_andi_tl(cpu_xer, cpu_xer, ~0x7F);
>      tcg_gen_or_tl(cpu_xer, cpu_xer, cpu_T[0]);
>      if (Rc(ctx->opcode)) {
> -        gen_op_440_dlmzb_update_Rc();
> +        endLabel = gen_new_label();
> +        int nextLabel = gen_new_label();
> +        tcg_gen_brcondi_tl(TCG_COND_NE, cpu_T[0], 8, nextLabel);
> +        tcg_gen_movi_tl(cpu_T[0], 0x2);
> +        tcg_gen_br(endLabel);
> +
> +        gen_set_label(nextLabel);
> +        nextLabel = gen_new_label();
> +        tcg_gen_brcondi_tl(TCG_COND_GE, cpu_T[0], 4, nextLabel);
> +        tcg_gen_movi_tl(cpu_T[0], 0x4);
> +        tcg_gen_br(endLabel);
> +
> +        gen_set_label(nextLabel);
> +        tcg_gen_movi_tl(cpu_T[0], 0x8);
> +
> +        gen_set_label(endLabel);
>          tcg_gen_trunc_tl_i32(cpu_crf[0], cpu_T[0]);
>          tcg_gen_andi_i32(cpu_crf[0], cpu_crf[0], 0xf);
>      }
> 


> 


-- 
  .''`.  Aurelien Jarno             | GPG: 1024D/F1BCDB73
 : :' :  Debian developer           | Electrical Engineer
 `. `'   address@hidden         | address@hidden
   `-    people.debian.org/~aurel32 | www.aurel32.net