Emilio G. Cota <c...@braap.org> writes:
> This brings down the size of the struct from 56 to 32 bytes on 64-bit,
> and to 20 bytes on 32-bit. This leads to memory savings:
>
> Before:
> $ find . -name 'tcg.o' | xargs size
> text data bss dec hex filename
> 41131 29800 88 71019 1156b ./aarch64-softmmu/tcg/tcg.o
> 37969 29416 96 67481 10799 ./x86_64-linux-user/tcg/tcg.o
> 39354 28816 96 68266 10aaa ./arm-linux-user/tcg/tcg.o
> 40802 29096 88 69986 11162 ./arm-softmmu/tcg/tcg.o
> 39417 29672 88 69177 10e39 ./x86_64-softmmu/tcg/tcg.o
>
> After:
> $ find . -name 'tcg.o' | xargs size
> text data bss dec hex filename
> 40883 29800 88 70771 11473 ./aarch64-softmmu/tcg/tcg.o
> 37473 29416 96 66985 105a9 ./x86_64-linux-user/tcg/tcg.o
> 38858 28816 96 67770 108ba ./arm-linux-user/tcg/tcg.o
> 40554 29096 88 69738 1106a ./arm-softmmu/tcg/tcg.o
> 39169 29672 88 68929 10d41 ./x86_64-softmmu/tcg/tcg.o
>
> Note that using an entire byte for some enums that need less than
> that wastes a few bits (noticeable in 32 bits, where we use
> 20 bytes instead of 16) but avoids extraction code, which overall
> is a win--I've tested several variations of the patch, and the appended
> is the best performer for OpenSSL's bntest by a very small margin:
>
> Before:
> $ taskset -c 0 perf stat -r 15 -- x86_64-linux-user/qemu-x86_64
> img/bntest-x86_64 >/dev/null
> [...]
> Performance counter stats for 'x86_64-linux-user/qemu-x86_64
> img/bntest-x86_64' (15 runs):
>
> 10538.479833 task-clock (msec) # 0.999 CPUs utilized
> ( +- 0.38% )
> 772 context-switches # 0.073 K/sec
> ( +- 2.03% )
> 0 cpu-migrations # 0.000 K/sec
> ( +-100.00% )
> 2,207 page-faults # 0.209 K/sec
> ( +- 0.08% )
> 10.552871687 seconds time elapsed
> ( +- 0.39% )
>
> After:
> $ taskset -c 0 perf stat -r 15 -- x86_64-linux-user/qemu-x86_64
> img/bntest-x86_64 >/dev/null
> Performance counter stats for 'x86_64-linux-user/qemu-x86_64
> img/bntest-x86_64' (15 runs):
>
> 10459.968847 task-clock (msec) # 0.999 CPUs utilized
> ( +- 0.30% )
> 739 context-switches # 0.071 K/sec
> ( +- 1.71% )
> 0 cpu-migrations # 0.000 K/sec
> ( +- 68.14% )
> 2,204 page-faults # 0.211 K/sec
> ( +- 0.10% )
> 10.473900411 seconds time elapsed
> ( +- 0.30% )
I'll take that as a win condition ;-)
Reviewed-by: Alex Bennée <alex.ben...@linaro.org>
>
> Suggested-by: Stefan Weil <s...@weilnetz.de>
> Suggested-by: Richard Henderson <r...@twiddle.net>
> Signed-off-by: Emilio G. Cota <c...@braap.org>
> ---
> tcg/tcg.h | 26 ++++++++++++++------------
> 1 file changed, 14 insertions(+), 12 deletions(-)
>
> diff --git a/tcg/tcg.h b/tcg/tcg.h
> index add7f75..7f95132 100644
> --- a/tcg/tcg.h
> +++ b/tcg/tcg.h
> @@ -417,20 +417,19 @@ static inline TCGCond tcg_high_cond(TCGCond c)
> }
> }
>
> -#define TEMP_VAL_DEAD 0
> -#define TEMP_VAL_REG 1
> -#define TEMP_VAL_MEM 2
> -#define TEMP_VAL_CONST 3
> +typedef enum TCGTempVal {
> + TEMP_VAL_DEAD,
> + TEMP_VAL_REG,
> + TEMP_VAL_MEM,
> + TEMP_VAL_CONST,
> +} TCGTempVal;
>
> -/* XXX: optimize memory layout */
> typedef struct TCGTemp {
> - TCGType base_type;
> - TCGType type;
> - int val_type;
> - int reg;
> - tcg_target_long val;
> - int mem_reg;
> - intptr_t mem_offset;
> + unsigned int reg:8;
> + unsigned int mem_reg:8;
> + TCGTempVal val_type:8;
> + TCGType base_type:8;
> + TCGType type:8;
> unsigned int fixed_reg:1;
> unsigned int mem_coherent:1;
> unsigned int mem_allocated:1;
> @@ -438,6 +437,9 @@ typedef struct TCGTemp {
> basic blocks. Otherwise, it is not
> preserved across basic blocks. */
> unsigned int temp_allocated:1; /* never used for code gen */
> +
> + tcg_target_long val;
> + intptr_t mem_offset;
> const char *name;
> } TCGTemp;
--
Alex Bennée
