[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Qemu-devel] [RFC v2 PATCH] tcg/softmmu: Increase size of TLB caches
From: |
Richard Henderson |
Subject: |
Re: [Qemu-devel] [RFC v2 PATCH] tcg/softmmu: Increase size of TLB caches |
Date: |
Mon, 28 Aug 2017 11:08:04 -0700 |
User-agent: |
Mozilla/5.0 (X11; Linux x86_64; rv:52.0) Gecko/20100101 Thunderbird/52.2.1 |
On 08/24/2017 08:58 AM, Pranith Kumar wrote:
> | TLB bits\vTLB entires | 8 | 16 | 32 |
> | 8 | 952.94(+0.0%) | 929.99(+2.4%) | 919.02(+3.6%) |
> | 10 | 898.92(+5.6%) | 886.13(+7.0%) | 887.03(+6.9%) |
> | 12 | 878.56(+7.8%) | 873.53(+8.3%)* | 875.34(+8.1%) |
Thanks for collecting this.
> @@ -89,7 +89,7 @@ typedef uint64_t target_ulong;
> * of tlb_table inside env (which is non-trivial but not huge).
> */
> #define CPU_TLB_BITS \
> - MIN(8, \
> + MIN(CPU_TLB_BITS_MAX, \
> TCG_TARGET_TLB_DISPLACEMENT_BITS - CPU_TLB_ENTRY_BITS - \
> (NB_MMU_MODES <= 1 ? 0 : \
> NB_MMU_MODES <= 2 ? 1 : \
> diff --git a/tcg/aarch64/tcg-target.h b/tcg/aarch64/tcg-target.h
> index 55a46ac825..f428e09c98 100644
> --- a/tcg/aarch64/tcg-target.h
> +++ b/tcg/aarch64/tcg-target.h
> @@ -15,6 +15,7 @@
>
> #define TCG_TARGET_INSN_UNIT_SIZE 4
> #define TCG_TARGET_TLB_DISPLACEMENT_BITS 24
> +#define CPU_TLB_BITS_MAX 12
I'd rather the definition in tcg-target.h reflect the actual maximum and limit
that to what we want (12) within cpu-defs.h. So, here maybe
#define TCG_TARGET_TLB_MAX_INDEX_BITS 32
etc.
r~