Skip to content

Commit

Permalink
Upgrade thrust version to 1.15
Browse files Browse the repository at this point in the history
Compile times between 1.12 and 1.15 are comparable.
libcudf library size with 1.15 is < 1MB smaller compared to 1.12

Runtime Performance results:

```
                                                                                      Time             CPU      Time Old      Time New       CPU Old       CPU New
-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
COMPILED_BINARYOP/BM_compiled_binaryop<double, double, double, cudf::binary_operator::MOD>/100000/manual_time                             +0.0519         +0.0268            10            10            27            28
COMPILED_BINARYOP/BM_compiled_binaryop<int32_t, int64_t, double, cudf::binary_operator::PMOD>/10000/manual_time                           +0.0851         +0.0295             9            10            28            29
COMPILED_BINARYOP/BM_compiled_binaryop<int, int, int, cudf::binary_operator::SHIFT_LEFT>/10000/manual_time                                -0.0971         -0.0218             6             5            25            24
COMPILED_BINARYOP/BM_compiled_binaryop<double, int8_t, bool, cudf::binary_operator::LOGICAL_AND>/10000/manual_time                        -0.0717         -0.0196             7             6            26            25
COMPILED_BINARYOP/BM_compiled_binaryop<decimal32, decimal32, decimal32, cudf::binary_operator::NULL_MAX>/10000/manual_time                +0.0748         +0.0191             7             8            26            27
ReductionDictionary/float_max/10000/manual_time                                                                                           -0.0714         -0.0512         31498         29249         50665         48071
ReductionScan/int16_nulls/100000/manual_time                                                                                              -0.1073         -0.0562         17598         15710         35995         33974
Concatenate/BM_concatenate<int64_t, true>/4096/64/manual_time                                                                             -0.1211         -0.0844             0             0             0             0
OrcWrite/floats_file_output/31/0/32/1/0/manual_time                                                                                       +0.0227         +0.0576            84            86            78            83
CopyIfElse/int16/4096/manual_time                                                                                                         +0.0648         +0.0262             0             0             0             0
CopyIfElse/float64/262144/manual_time                                                                                                     +0.0609         +0.0192             0             0             0             0
CopyIfElse/int16_no_nulls/4096/manual_time                                                                                                +0.1355         +0.0219             0             0             0             0
CopyIfElse/int16_no_nulls/32768/manual_time                                                                                               +0.1582         +0.0395             0             0             0             0
CopyIfElse/uint32_no_nulls/4096/manual_time                                                                                               +0.1300         +0.0213             0             0             0             0
CopyIfElse/uint32_no_nulls/32768/manual_time                                                                                              +0.0500         +0.0155             0             0             0             0
CopyIfElse/float64_no_nulls/4096/manual_time                                                                                              +0.0583         +0.0083             0             0             0             0
TypeDispatcher/fp64_bandwidth_host/1/1024/1/manual_time                                                                                   +0.1010         +0.0236          3291          3623         22245         22771
TypeDispatcher/fp64_bandwidth_host/2/1024/1/manual_time                                                                                   +0.1157         +0.0309          4888          5453         23798         24533
TypeDispatcher/fp64_bandwidth_host/4/1024/1/manual_time                                                                                   +0.0901         +0.0324          8053          8779         26780         27647
TypeDispatcher/fp64_bandwidth_host/1/2048/1/manual_time                                                                                   +0.1191         +0.0246          3335          3732         22378         22928
TypeDispatcher/fp64_bandwidth_host/2/2048/1/manual_time                                                                                   +0.1349         +0.0321          4890          5550         23839         24604
TypeDispatcher/fp64_bandwidth_host/4/2048/1/manual_time                                                                                   +0.0622         +0.0177          8820          9369         27717         28207
TypeDispatcher/fp64_bandwidth_host/1/4096/1/manual_time                                                                                   +0.0951         +0.0229          3387          3709         22375         22888
TypeDispatcher/fp64_bandwidth_host/2/4096/1/manual_time                                                                                   +0.0507         +0.0125          5509          5788         24491         24796
TypeDispatcher/fp64_bandwidth_device/4/1024/1/manual_time                                                                                 +0.0601         +0.0266         10775         11422         29432         30215
TypeDispatcher/fp64_bandwidth_device/1/2048/1/manual_time                                                                                 +0.0618         +0.0290          9258          9831         27967         28778
TypeDispatcher/fp64_bandwidth_device/2/2048/1/manual_time                                                                                 +0.0516         +0.0218          9773         10277         28453         29073
TypeDispatcher/fp64_bandwidth_device/1/4096/1/manual_time                                                                                 +0.0653         +0.0259          9265          9869         27956         28681
TypeDispatcher/fp64_bandwidth_no/1/1024/1/manual_time                                                                                     +0.0868         +0.0275          3441          3739         22367         22983
TypeDispatcher/fp64_bandwidth_no/2/1024/1/manual_time                                                                                     +0.1635         +0.0396          3690          4293         22609         23503
TypeDispatcher/fp64_bandwidth_no/4/1024/1/manual_time                                                                                     +0.1144         +0.0316          4523          5040         23445         24186
TypeDispatcher/fp64_bandwidth_no/1/2048/1/manual_time                                                                                     +0.1469         +0.0413          3497          4011         22382         23306
TypeDispatcher/fp64_bandwidth_no/2/2048/1/manual_time                                                                                     +0.0550         +0.0216          4097          4323         23012         23509
TypeDispatcher/fp64_bandwidth_no/2/4096/1/manual_time                                                                                     +0.0510         +0.0151          4418          4643         23447         23800
TypeDispatcher/fp64_bandwidth_no/8/4096/1/manual_time                                                                                     +0.1093         +0.0235          6787          7528         26000         26612
TypeDispatcher/fp64_bandwidth_no/4/8192/1/manual_time                                                                                     +0.0608         +0.0071          5435          5766         24657         24832
SetNullmask/SetNullMaskKernel/1048576/manual_time                                                                                         -0.0949         -0.0022          3800          3440         22750         22699
StringExtract/four/32768/32/manual_time                                                                                                   +0.0578         +0.0570             1             1             1             1
StringExtract/eight/4096/32/manual_time                                                                                                   -0.0973         -0.0969             5             4             5             4
StringExtract/eight/4096/128/manual_time                                                                                                  -0.0882         -0.0879             5             5             5             5
StringExtract/eight/4096/512/manual_time                                                                                                  -0.0780         -0.0777             5             5             5             5
StringExtract/eight/4096/2048/manual_time                                                                                                 -0.0703         -0.0701             5             5             6             5
StringExtract/eight/4096/8192/manual_time                                                                                                 -0.0718         -0.0716             7             6             7             6
UrlDecode/BM_url_decode<10>/10000000/100/manual_time                                                                                      +0.0576         +0.0577            37            39            37            39
UrlDecode/BM_url_decode<50>/100000000/10/manual_time                                                                                      +0.0599         +0.0599           140           148           140           148
Shift/shift_half_nullable_out/1048576/manual_time                                                                                         -0.0813         -0.0745             0             0             0             0
Sort<false>/unstable_no_nulls/1024/8/manual_time                                                                                          -0.2900         -0.2832             1             1             1             1
Sort<false>/unstable_no_nulls/4096/8/manual_time                                                                                          -0.3819         -0.3739             1             1             1             1
Sort<false>/unstable_no_nulls/32768/8/manual_time                                                                                         -0.2767         -0.2714             1             1             1             1
Sort<false>/unstable_no_nulls/262144/8/manual_time                                                                                        -0.1866         -0.1840             1             1             1             1
Sort<true>/stable_no_nulls/1024/8/manual_time                                                                                             -0.2920         -0.2852             1             1             1             1
Sort<true>/stable_no_nulls/4096/8/manual_time                                                                                             -0.3818         -0.3737             1             1             1             1
Sort<true>/stable_no_nulls/32768/8/manual_time                                                                                            -0.2777         -0.2722             1             1             1             1
Sort<true>/stable_no_nulls/262144/8/manual_time                                                                                           -0.1886         -0.1859             1             1             1             1
Sort<false>/unstable/1024/8/manual_time                                                                                                   -0.2835         -0.2778             1             1             1             1
Sort<false>/unstable/4096/8/manual_time                                                                                                   -0.3425         -0.3365             1             1             1             1
Sort<false>/unstable/32768/8/manual_time                                                                                                  -0.2179         -0.2149             1             1             1             1
Sort<false>/unstable/262144/8/manual_time                                                                                                 -0.0930         -0.0922             2             2             2             2
Sort<true>/stable/1024/8/manual_time                                                                                                      -0.2874         -0.2817             1             1             1             1
Sort<true>/stable/4096/8/manual_time                                                                                                      -0.3490         -0.3429             1             1             1             1
Sort<true>/stable/32768/8/manual_time                                                                                                     -0.2232         -0.2202             1             1             1             1
Sort<true>/stable/262144/8/manual_time                                                                                                    -0.0964         -0.0955             2             2             2             2
Search/Table/4/1000000/manual_time                                                                                                        +0.0796         +0.0560             4             4             4             4
Gather/double_coalesce_x/8192/1/manual_time                                                                                               +0.0751         +0.0182          8503          9141         27316         27812
Gather/double_coalesce_x/16384/1/manual_time                                                                                              +0.0879         +0.0246          8641          9400         27247         27916
Gather/double_coalesce_x/8192/2/manual_time                                                                                               +0.0635         +0.0286         16209         17238         34700         35692
Gather/double_coalesce_x/1024/4/manual_time                                                                                               +0.0517         +0.0308         30234         31797         49033         50543
Gather/double_coalesce_x/4096/4/manual_time                                                                                               +0.0568         +0.0327         30768         32517         49409         51026
Gather/double_coalesce_x/2048/8/manual_time                                                                                               +0.0533         +0.0376         59436         62601         78176         81117
Gather/double_coalesce_o/16384/1/manual_time                                                                                              +0.0525         +0.0138          8921          9389         27447         27824
ReplaceClamp/float_no_nulls/10000/manual_time                                                                                             +0.0502         +0.0309         41663         43753         60740         62616
AST/BM_ast_transform<int32_t, TreeType::IMBALANCED_LEFT, true, true>/100000000/1/manual_time                                              +0.0581         +0.0579             8             9             8             9
```
  • Loading branch information
robertmaynard committed Dec 15, 2021
1 parent b3b299a commit 44fdb74
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion cpp/cmake/thirdparty/get_thrust.cmake
Original file line number Diff line number Diff line change
Expand Up @@ -80,6 +80,6 @@ function(find_and_configure_thrust VERSION)
endif()
endfunction()

set(CUDF_MIN_VERSION_Thrust 1.12.0)
set(CUDF_MIN_VERSION_Thrust 1.15.0)

find_and_configure_thrust(${CUDF_MIN_VERSION_Thrust})

0 comments on commit 44fdb74

Please sign in to comment.