Optimizations to cross-page chaining and indirect branches make
performance more sensitive to the hit rate of tb_jmp_cache.
The constraint of reserving some bits for the page number
lowers the achievable quality of the hashing function.
However, user-mode does not have this requirement. Thus,
with this change we use for user-mode a hashing function that
is both faster and of better quality than the previous one.
Measurements:
Note: baseline (i.e. speedup == 1x) is QEMU v2.9.0.
- SPECint06 (test set), x86_64-linux-user. Host:
Intel i7-6700K @ 4.00GHz
2x
+-+--------------------------------------------------------------------------------------------------------------+-+
|
+++++ |
| jr+noinline
| | |
| jr+inline
++%%@ |
1.8x +-+jr+hash+noinline
+..............................................|%%@...................................+-+
|jr+multhash+inline
|%%@+ |
| jr+hash+inline
+$$$%@ |
|
++##|$%@ +++ |
1.6x
+-+....................................................................|##|$%@....................+%%%...........+-+
| @@+
**#+$%@ $$+% |
| $$$%@+
+**#+$%@ ++++ ++$$+%@ |
| ++++ $ $%@
**# $%@ +$$%@@+++$$ %@ |
1.4x
+-+.....................+%%%@..........##+$%@..........................**#.$%@...........+$$%.@***$$.%@..........+-+
| ++$$+%@ ##+$%@
**# $%@ $$% @* *#$+%@ |
| ***#$ %@ +**# $%@
**# $%@ +###$% @* *#$ %@ |
| *+*#$ %@ +%%@+**# $%@
**# $%@ **+#$% @*+*#$ %@ +%%%@+ |
1.2x
+-+..................*.*#$.%@***#$$%@+**#.$%@..........................**#.$%@.........**.#$%.@*.*#$.%@***#$+%@+.+-+
| +++ * *#$ %@* *# $%@ **# $%@ +++++++
**# $%@ +++%%@@** #$% @* *#$ %@*+*#$ %@ |
| ++###$%+ * *#$ %@* *# $%@ **# $%@ **##$%@@
**# $%@+**#$$%+@** #$% @* *#$ %@* *#$ %@ |
| +**+#$%@@ ++$$@@@* *#$ %@* *# $%@ **# $%@ ** #$% @+###++@@++++%%%+
**# $%@ **# $% @** #$% @* *#$ %@* *#$ %@ |
1x
+-++-**+#$%-@**##$%+@*+*#$+%@*+*#+$%@+**#+$%@+**+#$%+@**+#$+@@***#$+%@+**#+$%@+**#+$%+@**+#$%+@*+*#$+%@*-*#$+%@-++-+
| ** #$% @** #$% @* *#$ %@* *# $%@ **# $%@ ** #$% @** #$%%@* *#$ %@
**# $%@ **# $% @** #$% @* *#$ %@* *#$ %@ |
| ** #$% @** #$% @* *#$ %@* *# $%@ **# $%@ ** #$% @** #$+%@* *#$ %@
**# $%@ **# $% @** #$% @* *#$ %@* *#$ %@ |
| ** #$% @** #$% @* *#$ %@* *# $%@ **# $%@ ** #$% @** #$ %@* *#$ %@
**# $%@ **# $% @** #$% @* *#$ %@* *#$ %@ |
0.8x
+-+--**##$%@@**##$%@@***#$%%@***#$$%@-**#$$%@-**##$%@@**##$%%@***#$%%@-**#$$%@-**#$$%@@**##$%@@***#$%%@***#$%%@--+-+
astar bzip2 gcc gobmk h264ref hmmlibquantum mcf
omnetpperlbench sjengxalancbmk hmean
png: http://imgur.com/1ZJGjzV
Here I also tried the hash function suggested by Paolo ("multhash"):
return ((uint64_t) (pc * 2654435761) >> 32) & ();
As you can see it is just as good as the other new function ("hash"),
but I kept "hash" because with it all benchmarks have speedup > 1.
- SPECint06 (train set), x86_64-linux-user. Host:
Intel i7-6700K @ 4.00GHz
2.6x
+-+--------------------------------------------------------------------------------------------------------------+-+
|
|
| jr+inline
|
2.4x
+jr+inline+hash....................................................................................###...........+-+
|
# # |
|
# # |
2.2x
+-+................................................................................................#.#...........+-+
|
# # |
|
# # |
2x
+-+................................................................................................#.#...........+-+
|
# # |
|
**** # |
1.8x
+-+.............................................................................................*..*.#...........+-+
|
+++ #### * * # |
|
#### ****++# * * # |
1.6x
+-+......................................+++...........................****..#.*++*..#..........*..*.#...........+-+
| ####
*++* # * * # +++ * * # |
| +++ ++#++# *
* # * * # #### * * # |
1.4x
+-+...................+++###..........****..#..........................*..*..#.*..*..#....#..#..*..*.#...........+-+
| ****+# * * # *
* # * * # *** # * * # #### |
| *++* # +++ * * # *
* # * * # *+* # * * # ****++# |
1.2x
+-+...................*..*.#..****###.*..*..#..........................*..*..#.*..*..#..*.*..#..*..*.#..*..*..#..+-+
| ****### +++ * * # * * # * * # *
* # * * # * * # * * # * * # |
| * *++# ***### * * # * * # * * # *
* # * * # * * # * * # * * # |
1x
+-+--****###--***###--****##--****###-****###--***###--***###--****##--****###-****###--***###--****##--****###--+-+
astar bzip2 gcc gobmk h264ref hmmlibquantum mcf
omnetpperlbench sjengxalancbmk hmean
png: http://imgur.com/1D2VFze
- NBench, x86_64-linux-user. Host: Intel
i7-6700K @ 4.00GHz
1.1x
+-+-------------------------------------------------------------------------------------------------------------+-+
|
|
| jr+inline
|
1.08x +jr+hash+noinline
+..............................+++.....................................................+-+
| jr+hash+inline |
|
| +++|
|
| | |+++
|
1.06x
+-+....................................................|.|.|....................................................+-+
| |###|
+++++ |
| |#|#|
###$$$ |
1.04x
+-+.........................+++....+++.+++.............|#|#$$$..............................++#|#++$............+-+
| |+++ |+++| ****|#| $
+++ |#+# $ |
| | | | | | * |*+#| $
|+++ **** # $ |
| +++ +++ | | ****| | * |* #++$
| |+++ * |* # $ |
1.02x
+-+....|..................|####$$.*.|*|$$$$.++++++++.*.|*.#..$..........****|.|............*++*.#..$.++++++++...+-+
| ***+++ |# |#|$ * |*##| $ | | | * |* # $
* |*| | +++ * * # $ ***###$$ |
| *|* |+++ +++ +++ *** |#|$ * |*|#| $ ***###$$ *++* # $ +++
* |*##$$$ ####++ * * # $ *+*++# $ |
1x
+-++-+*+*###+++****-$$$$+*+*++#+$+*++*+#++$+*+*++#+$+*++*-#++$+++-++$$$+*++*+#++$+***++#$$+*++*-#++$+*+*++#+$+-++-+
| * *++#$$ *++*|$++$ *|*++# $ * *+#++$ *+*++#|$ * * # $ *** |$+$
* *|#| $ *+* #+$ * * # $ * * # $ |
| * * #+$ * *## $ *+* # $ * * # $ * * #+$ * * # $ *+*### $
* *|#++$ * * # $ * * # $ * * # $ |
| * * # $ * *|# $ * * # $ * * # $ * * # $ * * # $ * *++# $
* *+# $ * * # $ * * # $ * * # $ |
0.98x
+-+...*.*..#.$.*..*+#..$.*.*..#.$.*..*.#..$.*.*..#.$.*..*.#..$.*.*..#.$.*..*.#..$.*.*..#.$.*..*.#..$.*.*..#.$...+-+
| * * # $ * * # $ * * # $ * * # $ * * # $ * * # $ * * # $
* * # $ * * # $ * * # $ * * # $ |
| * * # $ * * # $ * * # $ * * # $ * * # $ * * # $ * * # $
* * # $ * * # $ * * # $ * * # $ |
0.96x
+-+---***###$$-****##$$$-***###$$-****##$$$-***###$$-****##$$$-***###$$-****##$$$-***###$$-****##$$$-***###$$---+-+
ASSIGNMENT BITFIELD FOURFP EMULATION HUFFMAN LU DECOMPOSITIONEURAL
NNUMERIC SOSTRING SORT hmean
png: http://imgur.com/xK9YfOB
- NBench, arm-linux-user. Host: Intel
i7-4790K @ 4.00GHz
1.3x
+-+-------------------------------------------------------------------------------------------------------------+-+
| ####
+++ |
| jr+inline #++#
#### |
1.25x
+jr+hash+inline..............#..#...........................................#++#................................+-+
| # #
# # |
| # #
# # |
| # #
# # |
1.2x
+-+..........................#..#..................................####.....#..#................................+-+
| # # +++#++#
# # |
| # # ***** #
# # |
1.15x
+-+..........................#..#..............................*+++*..#.....#..#................................+-+
| # # * * #
**** # |
| # # * * #
*++* # |
| # # * * #
* * # |
1.1x
+-+..........................#..#...............+++............*...*..#..*..*..#................................+-+
| # # +++#### * * #
* * # #### |
| # # ***** # * * #
* * # # # |
1.05x
+-+..........................#..#...........*...*..#...........*...*..#..*..*..#...............####......#..#...+-+
| # # +++ * * # * * #
* * # #++# ***** # |
| +++# # ****### * * # ****### * * #
* * # +++# # * * # |
| ++++++ ****### ***** # *++*++# * * # *++*++# * * #
* * # ++++++ **** # * * # |
1x
+-++-+*****###++*++*++#++*+-+*++#+-*++*++#-+*+++*-+#++*++*++#++*+-+*++#+-*++*++#-+*****###++*++*++#++*+-+*++#+-++-+
| *+++*++# * * # * * # * * # * * # * * # * * #
* * # * * # * * # * * # |
| * * # * * # * * # * * # * * # * * # * * #
* * # * * # * * # * * # |
0.95x
+-+---*****###--****###--*****###--****###--*****###--****###--*****###--****###--*****###--****###--*****###---+-+
ASSIGNMENT BITFIELD FOURFP EMULATION HUFFMAN LU DECOMPOSITIONEURAL
NNUMERIC SOSTRING SORT hmean
png: http://imgur.com/uhIEOA1
Signed-off-by: Emilio G. Cota <c...@braap.org>
---
include/exec/tb-hash.h | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/include/exec/tb-hash.h b/include/exec/tb-hash.h
index 2c27490..b1fe2d0 100644
--- a/include/exec/tb-hash.h
+++ b/include/exec/tb-hash.h
@@ -22,6 +22,8 @@
#include "exec/tb-hash-xx.h"
+#ifdef CONFIG_SOFTMMU
+
/* Only the bottom TB_JMP_PAGE_BITS of the jump cache hash bits vary for
addresses on the same page. The top bits are the same. This allows
TLB invalidation to quickly clear a subset of the hash table. */
@@ -45,6 +47,16 @@ static inline unsigned int
tb_jmp_cache_hash_func(target_ulong pc)
| (tmp & TB_JMP_ADDR_MASK));
}
+#else
+
+/* In user-mode we can get better hashing because we do not have a TLB */
+static inline unsigned int tb_jmp_cache_hash_func(target_ulong pc)
+{
+ return (pc ^ (pc >> TB_JMP_CACHE_BITS)) & (TB_JMP_CACHE_SIZE - 1);
+}
+
+#endif /* CONFIG_SOFTMMU */
+
static inline
uint32_t tb_hash_func(tb_page_addr_t phys_pc, target_ulong pc, uint32_t flags)
{
--
2.7.4
