[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Qemu-devel] [PATCH v6 13/25] tcg/aarch64: Implement goto_ptr
From: |
Aurelien Jarno |
Subject: |
Re: [Qemu-devel] [PATCH v6 13/25] tcg/aarch64: Implement goto_ptr |
Date: |
Sat, 6 May 2017 13:52:19 +0200 |
User-agent: |
NeoMutt/20170113 (1.7.2) |
On 2017-05-02 12:22, Richard Henderson wrote:
> Measurements:
>
> SPECint06 (test set), x86_64-linux-user. Host: APM
> 64-bit ARMv8 (Atlas/A57) @ 2.4 GHz
>
> 1.45x
> +-+-------------------------------------------------------------------------------------------------------------+-+
> | *****
> |
> | +++ * *
> +goto-ptr |
> 1.4x
> +-+...*****............................*...*....................................................................+-+
> | *+++* * *
> +++ |
> 1.35x
> +-+...*...*............................*...*...........................*****....................................+-+
> | * * * *
> *+++* |
> | * * * *
> * * |
> 1.3x
> +-+...*...*............................*...*...........................*...*....................................+-+
> | * * * *
> * * |
> | * * * *
> * * ***** |
> 1.25x
> +-+...*...*...........*****............*...*...........................*...*............*****...*...*...........+-+
> | * * * * * *
> * * *+++* * * |
> 1.2x
> +-+...*...*...........*...*............*...*...........................*...*............*...*...*...*...........+-+
> | * * * * * *
> * * * * * * |
> | * * * * * *
> * * * * * * ***** |
> 1.15x
> +-+...*...*...........*...*............*...*...........................*...*............*...*...*...*...*...*...+-+
> | * * * * * *
> * * +++ * * * * * * |
> | * * * * * *
> * * ***** * * * * * * |
> 1.1x
> +-+...*...*...........*...*....*****...*...*...*****...................*...*...*...*....*...*...*...*...*...*...+-+
> | * * * * * * * * * *
> * * * * * * * * * * |
> 1.05x
> +-+...*...*...........*...*....*...*...*...*...*...*...................*...*...*...*....*...*...*...*...*...*...+-+
> | * * ***** * * * * * * * *
> * * * * * * * * * * |
> | * * * * * * * * * * * * ***** *****
> * * * * * * * * * * |
> 1x
> +-+---*****---*****---*****----*****---*****---*****---*****---*****---*****---*****----*****---*****---*****---+-+
> astar bzip2 gcc gobmk h264ref hmmlibquantum mcf
> omnetpperlbench sjenxalancbmk hmean
> png: http://imgur.com/en9HE8L
>
> Tested-by: Emilio G. Cota <address@hidden>
> Signed-off-by: Richard Henderson <address@hidden>
> ---
> tcg/aarch64/tcg-target.h | 2 +-
> tcg/aarch64/tcg-target.inc.c | 22 ++++++++++++++++++++--
> 2 files changed, 21 insertions(+), 3 deletions(-)
>
> diff --git a/tcg/aarch64/tcg-target.h b/tcg/aarch64/tcg-target.h
> index b82eac4..55a46ac 100644
> --- a/tcg/aarch64/tcg-target.h
> +++ b/tcg/aarch64/tcg-target.h
> @@ -77,7 +77,7 @@ typedef enum {
> #define TCG_TARGET_HAS_mulsh_i32 0
> #define TCG_TARGET_HAS_extrl_i64_i32 0
> #define TCG_TARGET_HAS_extrh_i64_i32 0
> -#define TCG_TARGET_HAS_goto_ptr 0
> +#define TCG_TARGET_HAS_goto_ptr 1
>
> #define TCG_TARGET_HAS_div_i64 1
> #define TCG_TARGET_HAS_rem_i64 1
> diff --git a/tcg/aarch64/tcg-target.inc.c b/tcg/aarch64/tcg-target.inc.c
> index 290de6d..5f18545 100644
> --- a/tcg/aarch64/tcg-target.inc.c
> +++ b/tcg/aarch64/tcg-target.inc.c
> @@ -1357,8 +1357,13 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
>
> switch (opc) {
> case INDEX_op_exit_tb:
> - tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_X0, a0);
> - tcg_out_goto(s, tb_ret_addr);
> + /* Reuse the zeroing that exists for goto_ptr. */
> + if (a0 == 0) {
> + tcg_out_goto(s, s->code_gen_epilogue);
> + } else {
> + tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_X0, a0);
> + tcg_out_goto(s, tb_ret_addr);
> + }
> break;
>
> case INDEX_op_goto_tb:
> @@ -1374,6 +1379,10 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
> s->tb_jmp_reset_offset[a0] = tcg_current_code_size(s);
> break;
>
> + case INDEX_op_goto_ptr:
> + tcg_out_insn(s, 3207, BR, a0);
> + break;
> +
> case INDEX_op_br:
> tcg_out_goto_label(s, arg_label(a0));
> break;
> @@ -1735,6 +1744,7 @@ static const TCGTargetOpDef aarch64_op_defs[] = {
> { INDEX_op_exit_tb, { } },
> { INDEX_op_goto_tb, { } },
> { INDEX_op_br, { } },
> + { INDEX_op_goto_ptr, { "r" } },
>
> { INDEX_op_ld8u_i32, { "r", "r" } },
> { INDEX_op_ld8s_i32, { "r", "r" } },
> @@ -1942,6 +1952,14 @@ static void tcg_target_qemu_prologue(TCGContext *s)
> tcg_out_mov(s, TCG_TYPE_PTR, TCG_AREG0, tcg_target_call_iarg_regs[0]);
> tcg_out_insn(s, 3207, BR, tcg_target_call_iarg_regs[1]);
>
> + /*
> + * Return path for goto_ptr. Set return value to 0, a-la exit_tb,
> + * and fall through to the rest of the epilogue.
> + */
> + s->code_gen_epilogue = s->code_ptr;
> + tcg_out_movi(s, TCG_TYPE_REG, TCG_REG_X0, 0);
> +
> + /* TB epilogue */
> tb_ret_addr = s->code_ptr;
>
> /* Remove TCG locals stack space. */
Reviewed-by: Aurelien Jarno <address@hidden>
--
Aurelien Jarno GPG: 4096R/1DDD8C9B
address@hidden http://www.aurel32.net
- [Qemu-devel] [PATCH v6 06/25] target/arm: optimize cross-page direct jumps in softmmu, (continued)
- [Qemu-devel] [PATCH v6 06/25] target/arm: optimize cross-page direct jumps in softmmu, Richard Henderson, 2017/05/02
- [Qemu-devel] [PATCH v6 07/25] target/arm: optimize indirect branches, Richard Henderson, 2017/05/02
- [Qemu-devel] [PATCH v6 04/25] tcg: Introduce goto_ptr opcode and tcg_gen_lookup_and_goto_ptr, Richard Henderson, 2017/05/02
- [Qemu-devel] [PATCH v6 09/25] target/i386: optimize cross-page direct jumps in softmmu, Richard Henderson, 2017/05/02
- [Qemu-devel] [PATCH v6 08/25] target/i386: introduce gen_jr helper to generate lookup_and_goto_ptr, Richard Henderson, 2017/05/02
- [Qemu-devel] [PATCH v6 10/25] target/i386: optimize indirect branches, Richard Henderson, 2017/05/02
- [Qemu-devel] [PATCH v6 12/25] tcg/ppc: Implement goto_ptr, Richard Henderson, 2017/05/02
- [Qemu-devel] [PATCH v6 15/25] tcg/s390: Implement goto_ptr, Richard Henderson, 2017/05/02
- [Qemu-devel] [PATCH v6 13/25] tcg/aarch64: Implement goto_ptr, Richard Henderson, 2017/05/02
- Re: [Qemu-devel] [PATCH v6 13/25] tcg/aarch64: Implement goto_ptr,
Aurelien Jarno <=
- [Qemu-devel] [PATCH v6 11/25] tb-hash: improve tb_jmp_cache hash function in user mode, Richard Henderson, 2017/05/02
- [Qemu-devel] [PATCH v6 17/25] tcg/arm: Implement goto_ptr, Richard Henderson, 2017/05/02
- [Qemu-devel] [PATCH v6 14/25] tcg/sparc: Implement goto_ptr, Richard Henderson, 2017/05/02
- [Qemu-devel] [PATCH v6 16/25] tcg/arm: Clarify tcg_out_bx for arm4 host, Richard Henderson, 2017/05/02
- [Qemu-devel] [PATCH v6 19/25] target/hppa: Use tcg_gen_lookup_and_goto_ptr, Richard Henderson, 2017/05/02
- [Qemu-devel] [PATCH v6 20/25] target/alpha: Use tcg_gen_lookup_and_goto_ptr, Richard Henderson, 2017/05/02
- [Qemu-devel] [PATCH v6 18/25] target/s390: Use tcg_gen_lookup_and_goto_ptr, Richard Henderson, 2017/05/02
- [Qemu-devel] [PATCH v6 21/25] target/aarch64: optimize cross-page direct jumps in softmmu, Richard Henderson, 2017/05/02
- [Qemu-devel] [PATCH v6 22/25] target/aarch64: optimize indirect branches, Richard Henderson, 2017/05/02