summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--README.md5
-rw-r--r--src/database/kernels/copy.hpp6
-rw-r--r--src/database/kernels/pad.hpp6
-rw-r--r--src/database/kernels/padtranspose.hpp4
-rw-r--r--src/database/kernels/transpose.hpp6
-rw-r--r--src/database/kernels/xaxpy.hpp10
-rw-r--r--src/database/kernels/xdot.hpp6
-rw-r--r--src/database/kernels/xgemm.hpp4
-rw-r--r--src/database/kernels/xgemm_direct.hpp12
-rw-r--r--src/database/kernels/xgemv.hpp3
-rw-r--r--src/database/kernels/xgemv_fast.hpp2
-rw-r--r--src/database/kernels/xgemv_fast_rot.hpp2
-rw-r--r--src/database/kernels/xger.hpp6
13 files changed, 58 insertions, 14 deletions
diff --git a/README.md b/README.md
index 12d6271c..f44a401c 100644
--- a/README.md
+++ b/README.md
@@ -111,8 +111,9 @@ The CLBlast library will be tuned in the future for the most commonly used OpenC
- GeForce GTX 750 Ti
- GeForce GTX 980
- GeForce GTX 1070
- - GeForce GTX Titan
- - GeForce GTX Titan X
+ - GeForce GTX TITAN
+ - GeForce GTX TITAN Black
+ - GeForce GTX TITAN X
- Tesla K20m
- Tesla K40m
* AMD GPUs:
diff --git a/src/database/kernels/copy.hpp b/src/database/kernels/copy.hpp
index 3283e429..3a569bf3 100644
--- a/src/database/kernels/copy.hpp
+++ b/src/database/kernels/copy.hpp
@@ -90,6 +90,7 @@ const Database::DatabaseEntry CopySingle = {
{ "GeForce GTX 750 Ti", { {"COPY_DIMX",16}, {"COPY_DIMY",32}, {"COPY_VW",2}, {"COPY_WPT",2} } },
{ "GeForce GTX 980", { {"COPY_DIMX",32}, {"COPY_DIMY",16}, {"COPY_VW",1}, {"COPY_WPT",1} } },
{ "GeForce GTX TITAN", { {"COPY_DIMX",32}, {"COPY_DIMY",8}, {"COPY_VW",2}, {"COPY_WPT",4} } },
+ { "GeForce GTX TITAN Black", { {"COPY_DIMX",8}, {"COPY_DIMY",32}, {"COPY_VW",4}, {"COPY_WPT",8} } },
{ "GeForce GTX TITAN X", { {"COPY_DIMX",32}, {"COPY_DIMY",8}, {"COPY_VW",1}, {"COPY_WPT",2} } },
{ "Tesla K20m", { {"COPY_DIMX",8}, {"COPY_DIMY",8}, {"COPY_VW",4}, {"COPY_WPT",4} } },
{ "Tesla K40m", { {"COPY_DIMX",8}, {"COPY_DIMY",8}, {"COPY_VW",4}, {"COPY_WPT",2} } },
@@ -154,6 +155,7 @@ const Database::DatabaseEntry CopyComplexSingle = {
{ "GeForce GTX 750", { {"COPY_DIMX",16}, {"COPY_DIMY",8}, {"COPY_VW",1}, {"COPY_WPT",2} } },
{ "GeForce GTX 750 Ti", { {"COPY_DIMX",16}, {"COPY_DIMY",32}, {"COPY_VW",1}, {"COPY_WPT",1} } },
{ "GeForce GTX 980", { {"COPY_DIMX",8}, {"COPY_DIMY",8}, {"COPY_VW",1}, {"COPY_WPT",1} } },
+ { "GeForce GTX TITAN Black", { {"COPY_DIMX",16}, {"COPY_DIMY",8}, {"COPY_VW",1}, {"COPY_WPT",1} } },
{ "GeForce GTX TITAN X", { {"COPY_DIMX",16}, {"COPY_DIMY",8}, {"COPY_VW",1}, {"COPY_WPT",1} } },
{ "Tesla K20m", { {"COPY_DIMX",8}, {"COPY_DIMY",8}, {"COPY_VW",1}, {"COPY_WPT",4} } },
{ "Tesla K40m", { {"COPY_DIMX",16}, {"COPY_DIMY",8}, {"COPY_VW",1}, {"COPY_WPT",1} } },
@@ -214,10 +216,11 @@ const Database::DatabaseEntry CopyDouble = {
{ "GeForce GTX 750 Ti", { {"COPY_DIMX",16}, {"COPY_DIMY",8}, {"COPY_VW",2}, {"COPY_WPT",1} } },
{ "GeForce GTX 980", { {"COPY_DIMX",32}, {"COPY_DIMY",8}, {"COPY_VW",2}, {"COPY_WPT",1} } },
{ "GeForce GTX TITAN", { {"COPY_DIMX",16}, {"COPY_DIMY",32}, {"COPY_VW",2}, {"COPY_WPT",2} } },
+ { "GeForce GTX TITAN Black", { {"COPY_DIMX",16}, {"COPY_DIMY",8}, {"COPY_VW",2}, {"COPY_WPT",8} } },
{ "GeForce GTX TITAN X", { {"COPY_DIMX",32}, {"COPY_DIMY",16}, {"COPY_VW",1}, {"COPY_WPT",1} } },
{ "Tesla K20m", { {"COPY_DIMX",8}, {"COPY_DIMY",8}, {"COPY_VW",2}, {"COPY_WPT",1} } },
{ "Tesla K40m", { {"COPY_DIMX",8}, {"COPY_DIMY",8}, {"COPY_VW",2}, {"COPY_WPT",2} } },
- { "default", { {"COPY_DIMX",32}, {"COPY_DIMY",16}, {"COPY_VW",2}, {"COPY_WPT",1} } },
+ { "default", { {"COPY_DIMX",32}, {"COPY_DIMY",8}, {"COPY_VW",2}, {"COPY_WPT",1} } },
}
},
{ // Default
@@ -274,6 +277,7 @@ const Database::DatabaseEntry CopyComplexDouble = {
{ "GeForce GTX 750 Ti", { {"COPY_DIMX",16}, {"COPY_DIMY",16}, {"COPY_VW",1}, {"COPY_WPT",1} } },
{ "GeForce GTX 980", { {"COPY_DIMX",8}, {"COPY_DIMY",8}, {"COPY_VW",1}, {"COPY_WPT",1} } },
{ "GeForce GTX TITAN", { {"COPY_DIMX",16}, {"COPY_DIMY",16}, {"COPY_VW",1}, {"COPY_WPT",1} } },
+ { "GeForce GTX TITAN Black", { {"COPY_DIMX",8}, {"COPY_DIMY",8}, {"COPY_VW",1}, {"COPY_WPT",2} } },
{ "GeForce GTX TITAN X", { {"COPY_DIMX",16}, {"COPY_DIMY",8}, {"COPY_VW",1}, {"COPY_WPT",1} } },
{ "Tesla K20m", { {"COPY_DIMX",8}, {"COPY_DIMY",8}, {"COPY_VW",1}, {"COPY_WPT",2} } },
{ "Tesla K40m", { {"COPY_DIMX",8}, {"COPY_DIMY",8}, {"COPY_VW",1}, {"COPY_WPT",1} } },
diff --git a/src/database/kernels/pad.hpp b/src/database/kernels/pad.hpp
index f7e06212..62a22014 100644
--- a/src/database/kernels/pad.hpp
+++ b/src/database/kernels/pad.hpp
@@ -90,6 +90,7 @@ const Database::DatabaseEntry PadSingle = {
{ "GeForce GTX 750 Ti", { {"PAD_DIMX",16}, {"PAD_DIMY",8}, {"PAD_WPTX",4}, {"PAD_WPTY",1} } },
{ "GeForce GTX 980", { {"PAD_DIMX",16}, {"PAD_DIMY",8}, {"PAD_WPTX",1}, {"PAD_WPTY",1} } },
{ "GeForce GTX TITAN", { {"PAD_DIMX",32}, {"PAD_DIMY",8}, {"PAD_WPTX",2}, {"PAD_WPTY",1} } },
+ { "GeForce GTX TITAN Black", { {"PAD_DIMX",32}, {"PAD_DIMY",8}, {"PAD_WPTX",1}, {"PAD_WPTY",2} } },
{ "GeForce GTX TITAN X", { {"PAD_DIMX",16}, {"PAD_DIMY",16}, {"PAD_WPTX",1}, {"PAD_WPTY",1} } },
{ "Tesla K20m", { {"PAD_DIMX",32}, {"PAD_DIMY",8}, {"PAD_WPTX",2}, {"PAD_WPTY",1} } },
{ "Tesla K40m", { {"PAD_DIMX",32}, {"PAD_DIMY",8}, {"PAD_WPTX",1}, {"PAD_WPTY",1} } },
@@ -162,10 +163,11 @@ const Database::DatabaseEntry PadComplexSingle = {
{ "GeForce GTX 750 Ti", { {"PAD_DIMX",16}, {"PAD_DIMY",8}, {"PAD_WPTX",1}, {"PAD_WPTY",1} } },
{ "GeForce GTX 980", { {"PAD_DIMX",16}, {"PAD_DIMY",16}, {"PAD_WPTX",1}, {"PAD_WPTY",1} } },
{ "GeForce GTX TITAN", { {"PAD_DIMX",16}, {"PAD_DIMY",8}, {"PAD_WPTX",2}, {"PAD_WPTY",1} } },
+ { "GeForce GTX TITAN Black", { {"PAD_DIMX",16}, {"PAD_DIMY",8}, {"PAD_WPTX",1}, {"PAD_WPTY",2} } },
{ "GeForce GTX TITAN X", { {"PAD_DIMX",16}, {"PAD_DIMY",8}, {"PAD_WPTX",1}, {"PAD_WPTY",1} } },
{ "Tesla K20m", { {"PAD_DIMX",32}, {"PAD_DIMY",8}, {"PAD_WPTX",1}, {"PAD_WPTY",2} } },
{ "Tesla K40m", { {"PAD_DIMX",16}, {"PAD_DIMY",8}, {"PAD_WPTX",1}, {"PAD_WPTY",1} } },
- { "default", { {"PAD_DIMX",16}, {"PAD_DIMY",8}, {"PAD_WPTX",1}, {"PAD_WPTY",1} } },
+ { "default", { {"PAD_DIMX",32}, {"PAD_DIMY",8}, {"PAD_WPTX",1}, {"PAD_WPTY",2} } },
}
},
{ // Default
@@ -222,6 +224,7 @@ const Database::DatabaseEntry PadDouble = {
{ "GeForce GTX 750 Ti", { {"PAD_DIMX",8}, {"PAD_DIMY",16}, {"PAD_WPTX",1}, {"PAD_WPTY",1} } },
{ "GeForce GTX 980", { {"PAD_DIMX",8}, {"PAD_DIMY",16}, {"PAD_WPTX",1}, {"PAD_WPTY",1} } },
{ "GeForce GTX TITAN", { {"PAD_DIMX",32}, {"PAD_DIMY",8}, {"PAD_WPTX",1}, {"PAD_WPTY",1} } },
+ { "GeForce GTX TITAN Black", { {"PAD_DIMX",16}, {"PAD_DIMY",8}, {"PAD_WPTX",1}, {"PAD_WPTY",1} } },
{ "GeForce GTX TITAN X", { {"PAD_DIMX",16}, {"PAD_DIMY",8}, {"PAD_WPTX",1}, {"PAD_WPTY",1} } },
{ "Tesla K20m", { {"PAD_DIMX",32}, {"PAD_DIMY",8}, {"PAD_WPTX",1}, {"PAD_WPTY",1} } },
{ "Tesla K40m", { {"PAD_DIMX",16}, {"PAD_DIMY",8}, {"PAD_WPTX",1}, {"PAD_WPTY",2} } },
@@ -282,6 +285,7 @@ const Database::DatabaseEntry PadComplexDouble = {
{ "GeForce GTX 750 Ti", { {"PAD_DIMX",16}, {"PAD_DIMY",32}, {"PAD_WPTX",1}, {"PAD_WPTY",1} } },
{ "GeForce GTX 980", { {"PAD_DIMX",16}, {"PAD_DIMY",16}, {"PAD_WPTX",1}, {"PAD_WPTY",1} } },
{ "GeForce GTX TITAN", { {"PAD_DIMX",8}, {"PAD_DIMY",32}, {"PAD_WPTX",1}, {"PAD_WPTY",2} } },
+ { "GeForce GTX TITAN Black", { {"PAD_DIMX",16}, {"PAD_DIMY",8}, {"PAD_WPTX",1}, {"PAD_WPTY",4} } },
{ "GeForce GTX TITAN X", { {"PAD_DIMX",16}, {"PAD_DIMY",8}, {"PAD_WPTX",1}, {"PAD_WPTY",1} } },
{ "Tesla K20m", { {"PAD_DIMX",8}, {"PAD_DIMY",8}, {"PAD_WPTX",1}, {"PAD_WPTY",2} } },
{ "Tesla K40m", { {"PAD_DIMX",8}, {"PAD_DIMY",8}, {"PAD_WPTX",1}, {"PAD_WPTY",1} } },
diff --git a/src/database/kernels/padtranspose.hpp b/src/database/kernels/padtranspose.hpp
index 7e672b10..609ccd45 100644
--- a/src/database/kernels/padtranspose.hpp
+++ b/src/database/kernels/padtranspose.hpp
@@ -90,6 +90,7 @@ const Database::DatabaseEntry PadtransposeSingle = {
{ "GeForce GTX 750 Ti", { {"PADTRA_PAD",1}, {"PADTRA_TILE",32}, {"PADTRA_WPT",2} } },
{ "GeForce GTX 980", { {"PADTRA_PAD",0}, {"PADTRA_TILE",16}, {"PADTRA_WPT",1} } },
{ "GeForce GTX TITAN", { {"PADTRA_PAD",1}, {"PADTRA_TILE",16}, {"PADTRA_WPT",2} } },
+ { "GeForce GTX TITAN Black", { {"PADTRA_PAD",1}, {"PADTRA_TILE",32}, {"PADTRA_WPT",2} } },
{ "GeForce GTX TITAN X", { {"PADTRA_PAD",1}, {"PADTRA_TILE",32}, {"PADTRA_WPT",1} } },
{ "Tesla K20m", { {"PADTRA_PAD",1}, {"PADTRA_TILE",16}, {"PADTRA_WPT",2} } },
{ "Tesla K40m", { {"PADTRA_PAD",1}, {"PADTRA_TILE",32}, {"PADTRA_WPT",2} } },
@@ -162,6 +163,7 @@ const Database::DatabaseEntry PadtransposeComplexSingle = {
{ "GeForce GTX 750 Ti", { {"PADTRA_PAD",1}, {"PADTRA_TILE",16}, {"PADTRA_WPT",1} } },
{ "GeForce GTX 980", { {"PADTRA_PAD",0}, {"PADTRA_TILE",16}, {"PADTRA_WPT",1} } },
{ "GeForce GTX TITAN", { {"PADTRA_PAD",1}, {"PADTRA_TILE",16}, {"PADTRA_WPT",1} } },
+ { "GeForce GTX TITAN Black", { {"PADTRA_PAD",0}, {"PADTRA_TILE",16}, {"PADTRA_WPT",1} } },
{ "GeForce GTX TITAN X", { {"PADTRA_PAD",1}, {"PADTRA_TILE",32}, {"PADTRA_WPT",1} } },
{ "Tesla K20m", { {"PADTRA_PAD",0}, {"PADTRA_TILE",16}, {"PADTRA_WPT",1} } },
{ "Tesla K40m", { {"PADTRA_PAD",1}, {"PADTRA_TILE",16}, {"PADTRA_WPT",1} } },
@@ -222,6 +224,7 @@ const Database::DatabaseEntry PadtransposeDouble = {
{ "GeForce GTX 750 Ti", { {"PADTRA_PAD",1}, {"PADTRA_TILE",32}, {"PADTRA_WPT",2} } },
{ "GeForce GTX 980", { {"PADTRA_PAD",1}, {"PADTRA_TILE",32}, {"PADTRA_WPT",1} } },
{ "GeForce GTX TITAN", { {"PADTRA_PAD",0}, {"PADTRA_TILE",16}, {"PADTRA_WPT",1} } },
+ { "GeForce GTX TITAN Black", { {"PADTRA_PAD",0}, {"PADTRA_TILE",16}, {"PADTRA_WPT",1} } },
{ "GeForce GTX TITAN X", { {"PADTRA_PAD",1}, {"PADTRA_TILE",32}, {"PADTRA_WPT",1} } },
{ "Tesla K20m", { {"PADTRA_PAD",0}, {"PADTRA_TILE",16}, {"PADTRA_WPT",1} } },
{ "Tesla K40m", { {"PADTRA_PAD",1}, {"PADTRA_TILE",16}, {"PADTRA_WPT",1} } },
@@ -282,6 +285,7 @@ const Database::DatabaseEntry PadtransposeComplexDouble = {
{ "GeForce GTX 750 Ti", { {"PADTRA_PAD",1}, {"PADTRA_TILE",8}, {"PADTRA_WPT",2} } },
{ "GeForce GTX 980", { {"PADTRA_PAD",0}, {"PADTRA_TILE",16}, {"PADTRA_WPT",1} } },
{ "GeForce GTX TITAN", { {"PADTRA_PAD",1}, {"PADTRA_TILE",16}, {"PADTRA_WPT",1} } },
+ { "GeForce GTX TITAN Black", { {"PADTRA_PAD",0}, {"PADTRA_TILE",16}, {"PADTRA_WPT",1} } },
{ "GeForce GTX TITAN X", { {"PADTRA_PAD",1}, {"PADTRA_TILE",32}, {"PADTRA_WPT",1} } },
{ "Tesla K20m", { {"PADTRA_PAD",1}, {"PADTRA_TILE",16}, {"PADTRA_WPT",1} } },
{ "Tesla K40m", { {"PADTRA_PAD",1}, {"PADTRA_TILE",16}, {"PADTRA_WPT",1} } },
diff --git a/src/database/kernels/transpose.hpp b/src/database/kernels/transpose.hpp
index 7fe7dd6f..54da15a7 100644
--- a/src/database/kernels/transpose.hpp
+++ b/src/database/kernels/transpose.hpp
@@ -90,6 +90,7 @@ const Database::DatabaseEntry TransposeSingle = {
{ "GeForce GTX 750 Ti", { {"TRA_DIM",32}, {"TRA_PAD",1}, {"TRA_SHUFFLE",0}, {"TRA_WPT",2} } },
{ "GeForce GTX 980", { {"TRA_DIM",16}, {"TRA_PAD",0}, {"TRA_SHUFFLE",0}, {"TRA_WPT",1} } },
{ "GeForce GTX TITAN", { {"TRA_DIM",8}, {"TRA_PAD",1}, {"TRA_SHUFFLE",0}, {"TRA_WPT",4} } },
+ { "GeForce GTX TITAN Black", { {"TRA_DIM",8}, {"TRA_PAD",1}, {"TRA_SHUFFLE",0}, {"TRA_WPT",4} } },
{ "GeForce GTX TITAN X", { {"TRA_DIM",16}, {"TRA_PAD",0}, {"TRA_SHUFFLE",0}, {"TRA_WPT",4} } },
{ "Tesla K20m", { {"TRA_DIM",8}, {"TRA_PAD",0}, {"TRA_SHUFFLE",0}, {"TRA_WPT",4} } },
{ "Tesla K40m", { {"TRA_DIM",8}, {"TRA_PAD",1}, {"TRA_SHUFFLE",0}, {"TRA_WPT",4} } },
@@ -156,6 +157,7 @@ const Database::DatabaseEntry TransposeComplexSingle = {
{ "GeForce GTX 750 Ti", { {"TRA_DIM",16}, {"TRA_PAD",1}, {"TRA_SHUFFLE",0}, {"TRA_WPT",1} } },
{ "GeForce GTX 980", { {"TRA_DIM",16}, {"TRA_PAD",1}, {"TRA_SHUFFLE",0}, {"TRA_WPT",1} } },
{ "GeForce GTX TITAN", { {"TRA_DIM",16}, {"TRA_PAD",0}, {"TRA_SHUFFLE",0}, {"TRA_WPT",1} } },
+ { "GeForce GTX TITAN Black", { {"TRA_DIM",16}, {"TRA_PAD",1}, {"TRA_SHUFFLE",0}, {"TRA_WPT",1} } },
{ "GeForce GTX TITAN X", { {"TRA_DIM",32}, {"TRA_PAD",1}, {"TRA_SHUFFLE",0}, {"TRA_WPT",1} } },
{ "Tesla K20m", { {"TRA_DIM",16}, {"TRA_PAD",0}, {"TRA_SHUFFLE",0}, {"TRA_WPT",1} } },
{ "Tesla K40m", { {"TRA_DIM",16}, {"TRA_PAD",1}, {"TRA_SHUFFLE",0}, {"TRA_WPT",1} } },
@@ -164,7 +166,7 @@ const Database::DatabaseEntry TransposeComplexSingle = {
},
{ // Default
kDeviceTypeAll, "default", {
- { "default", { {"TRA_DIM",16}, {"TRA_PAD",1}, {"TRA_SHUFFLE",1}, {"TRA_WPT",2} } },
+ { "default", { {"TRA_DIM",16}, {"TRA_PAD",1}, {"TRA_SHUFFLE",0}, {"TRA_WPT",1} } },
}
},
}
@@ -216,6 +218,7 @@ const Database::DatabaseEntry TransposeDouble = {
{ "GeForce GTX 750 Ti", { {"TRA_DIM",32}, {"TRA_PAD",1}, {"TRA_SHUFFLE",0}, {"TRA_WPT",2} } },
{ "GeForce GTX 980", { {"TRA_DIM",16}, {"TRA_PAD",0}, {"TRA_SHUFFLE",0}, {"TRA_WPT",2} } },
{ "GeForce GTX TITAN", { {"TRA_DIM",8}, {"TRA_PAD",0}, {"TRA_SHUFFLE",0}, {"TRA_WPT",2} } },
+ { "GeForce GTX TITAN Black", { {"TRA_DIM",16}, {"TRA_PAD",1}, {"TRA_SHUFFLE",0}, {"TRA_WPT",2} } },
{ "GeForce GTX TITAN X", { {"TRA_DIM",32}, {"TRA_PAD",1}, {"TRA_SHUFFLE",0}, {"TRA_WPT",1} } },
{ "Tesla K20m", { {"TRA_DIM",16}, {"TRA_PAD",1}, {"TRA_SHUFFLE",0}, {"TRA_WPT",2} } },
{ "Tesla K40m", { {"TRA_DIM",16}, {"TRA_PAD",1}, {"TRA_SHUFFLE",1}, {"TRA_WPT",2} } },
@@ -270,6 +273,7 @@ const Database::DatabaseEntry TransposeComplexDouble = {
{ "GeForce GTX 750 Ti", { {"TRA_DIM",16}, {"TRA_PAD",1}, {"TRA_SHUFFLE",0}, {"TRA_WPT",1} } },
{ "GeForce GTX 980", { {"TRA_DIM",32}, {"TRA_PAD",1}, {"TRA_SHUFFLE",0}, {"TRA_WPT",1} } },
{ "GeForce GTX TITAN", { {"TRA_DIM",16}, {"TRA_PAD",1}, {"TRA_SHUFFLE",0}, {"TRA_WPT",1} } },
+ { "GeForce GTX TITAN Black", { {"TRA_DIM",16}, {"TRA_PAD",0}, {"TRA_SHUFFLE",0}, {"TRA_WPT",1} } },
{ "GeForce GTX TITAN X", { {"TRA_DIM",32}, {"TRA_PAD",1}, {"TRA_SHUFFLE",0}, {"TRA_WPT",1} } },
{ "Tesla K20m", { {"TRA_DIM",16}, {"TRA_PAD",1}, {"TRA_SHUFFLE",0}, {"TRA_WPT",1} } },
{ "Tesla K40m", { {"TRA_DIM",16}, {"TRA_PAD",1}, {"TRA_SHUFFLE",0}, {"TRA_WPT",1} } },
diff --git a/src/database/kernels/xaxpy.hpp b/src/database/kernels/xaxpy.hpp
index c64ffd21..53d2446f 100644
--- a/src/database/kernels/xaxpy.hpp
+++ b/src/database/kernels/xaxpy.hpp
@@ -90,6 +90,7 @@ const Database::DatabaseEntry XaxpySingle = {
{ "GeForce GTX 750 Ti", { {"VW",2}, {"WGS",64}, {"WPT",1} } },
{ "GeForce GTX 980", { {"VW",1}, {"WGS",1024}, {"WPT",1} } },
{ "GeForce GTX TITAN", { {"VW",4}, {"WGS",256}, {"WPT",1} } },
+ { "GeForce GTX TITAN Black", { {"VW",4}, {"WGS",128}, {"WPT",4} } },
{ "GeForce GTX TITAN X", { {"VW",1}, {"WGS",64}, {"WPT",1} } },
{ "Tesla K20m", { {"VW",4}, {"WGS",128}, {"WPT",1} } },
{ "Tesla K40m", { {"VW",4}, {"WGS",128}, {"WPT",1} } },
@@ -162,6 +163,7 @@ const Database::DatabaseEntry XaxpyComplexSingle = {
{ "GeForce GTX 750 Ti", { {"VW",1}, {"WGS",512}, {"WPT",1} } },
{ "GeForce GTX 980", { {"VW",1}, {"WGS",64}, {"WPT",1} } },
{ "GeForce GTX TITAN", { {"VW",1}, {"WGS",256}, {"WPT",1} } },
+ { "GeForce GTX TITAN Black", { {"VW",1}, {"WGS",128}, {"WPT",2} } },
{ "GeForce GTX TITAN X", { {"VW",1}, {"WGS",512}, {"WPT",1} } },
{ "Tesla K20m", { {"VW",1}, {"WGS",128}, {"WPT",1} } },
{ "Tesla K40m", { {"VW",1}, {"WGS",128}, {"WPT",1} } },
@@ -222,15 +224,16 @@ const Database::DatabaseEntry XaxpyDouble = {
{ "GeForce GTX 750 Ti", { {"VW",1}, {"WGS",256}, {"WPT",2} } },
{ "GeForce GTX 980", { {"VW",1}, {"WGS",256}, {"WPT",1} } },
{ "GeForce GTX TITAN", { {"VW",2}, {"WGS",1024}, {"WPT",1} } },
+ { "GeForce GTX TITAN Black", { {"VW",2}, {"WGS",128}, {"WPT",1} } },
{ "GeForce GTX TITAN X", { {"VW",1}, {"WGS",512}, {"WPT",1} } },
{ "Tesla K20m", { {"VW",2}, {"WGS",128}, {"WPT",1} } },
{ "Tesla K40m", { {"VW",2}, {"WGS",128}, {"WPT",1} } },
- { "default", { {"VW",1}, {"WGS",128}, {"WPT",1} } },
+ { "default", { {"VW",2}, {"WGS",1024}, {"WPT",1} } },
}
},
{ // Default
kDeviceTypeAll, "default", {
- { "default", { {"VW",1}, {"WGS",64}, {"WPT",1} } },
+ { "default", { {"VW",1}, {"WGS",128}, {"WPT",2} } },
}
},
}
@@ -282,6 +285,7 @@ const Database::DatabaseEntry XaxpyComplexDouble = {
{ "GeForce GTX 750 Ti", { {"VW",1}, {"WGS",64}, {"WPT",2} } },
{ "GeForce GTX 980", { {"VW",1}, {"WGS",1024}, {"WPT",1} } },
{ "GeForce GTX TITAN", { {"VW",1}, {"WGS",64}, {"WPT",4} } },
+ { "GeForce GTX TITAN Black", { {"VW",1}, {"WGS",128}, {"WPT",4} } },
{ "GeForce GTX TITAN X", { {"VW",1}, {"WGS",1024}, {"WPT",1} } },
{ "Tesla K20m", { {"VW",1}, {"WGS",64}, {"WPT",1} } },
{ "Tesla K40m", { {"VW",1}, {"WGS",64}, {"WPT",1} } },
@@ -290,7 +294,7 @@ const Database::DatabaseEntry XaxpyComplexDouble = {
},
{ // Default
kDeviceTypeAll, "default", {
- { "default", { {"VW",1}, {"WGS",256}, {"WPT",1} } },
+ { "default", { {"VW",1}, {"WGS",128}, {"WPT",1} } },
}
},
}
diff --git a/src/database/kernels/xdot.hpp b/src/database/kernels/xdot.hpp
index 0e6fe2f2..4712cc04 100644
--- a/src/database/kernels/xdot.hpp
+++ b/src/database/kernels/xdot.hpp
@@ -73,6 +73,7 @@ const Database::DatabaseEntry XdotSingle = {
{ "GeForce GTX 750", { {"WGS1",128}, {"WGS2",32} } },
{ "GeForce GTX 750 Ti", { {"WGS1",64}, {"WGS2",32} } },
{ "GeForce GTX 980", { {"WGS1",256}, {"WGS2",32} } },
+ { "GeForce GTX TITAN Black", { {"WGS1",512}, {"WGS2",64} } },
{ "GeForce GTX TITAN X", { {"WGS1",256}, {"WGS2",32} } },
{ "Tesla K20m", { {"WGS1",1024}, {"WGS2",32} } },
{ "default", { {"WGS1",256}, {"WGS2",256} } },
@@ -127,6 +128,7 @@ const Database::DatabaseEntry XdotComplexSingle = {
{ "GeForce GTX 750", { {"WGS1",64}, {"WGS2",32} } },
{ "GeForce GTX 750 Ti", { {"WGS1",64}, {"WGS2",32} } },
{ "GeForce GTX 980", { {"WGS1",256}, {"WGS2",64} } },
+ { "GeForce GTX TITAN Black", { {"WGS1",128}, {"WGS2",64} } },
{ "GeForce GTX TITAN X", { {"WGS1",256}, {"WGS2",32} } },
{ "Tesla K20m", { {"WGS1",512}, {"WGS2",32} } },
{ "default", { {"WGS1",512}, {"WGS2",64} } },
@@ -170,9 +172,10 @@ const Database::DatabaseEntry XdotDouble = {
{ "GeForce GTX 750", { {"WGS1",64}, {"WGS2",256} } },
{ "GeForce GTX 750 Ti", { {"WGS1",128}, {"WGS2",64} } },
{ "GeForce GTX 980", { {"WGS1",128}, {"WGS2",32} } },
+ { "GeForce GTX TITAN Black", { {"WGS1",128}, {"WGS2",64} } },
{ "GeForce GTX TITAN X", { {"WGS1",256}, {"WGS2",32} } },
{ "Tesla K20m", { {"WGS1",512}, {"WGS2",32} } },
- { "default", { {"WGS1",256}, {"WGS2",64} } },
+ { "default", { {"WGS1",128}, {"WGS2",64} } },
}
},
{ // Default
@@ -213,6 +216,7 @@ const Database::DatabaseEntry XdotComplexDouble = {
{ "GeForce GTX 750", { {"WGS1",256}, {"WGS2",32} } },
{ "GeForce GTX 750 Ti", { {"WGS1",64}, {"WGS2",32} } },
{ "GeForce GTX 980", { {"WGS1",64}, {"WGS2",32} } },
+ { "GeForce GTX TITAN Black", { {"WGS1",128}, {"WGS2",32} } },
{ "GeForce GTX TITAN X", { {"WGS1",128}, {"WGS2",32} } },
{ "Tesla K20m", { {"WGS1",128}, {"WGS2",32} } },
{ "default", { {"WGS1",128}, {"WGS2",64} } },
diff --git a/src/database/kernels/xgemm.hpp b/src/database/kernels/xgemm.hpp
index 6842a405..aa95b1f6 100644
--- a/src/database/kernels/xgemm.hpp
+++ b/src/database/kernels/xgemm.hpp
@@ -83,6 +83,7 @@ const Database::DatabaseEntry XgemmSingle = {
{ "GeForce GTX 750 Ti", { {"KWG",16}, {"KWI",2}, {"MDIMA",16}, {"MDIMC",16}, {"MWG",128}, {"NDIMB",32}, {"NDIMC",8}, {"NWG",64}, {"SA",1}, {"SB",1}, {"STRM",0}, {"STRN",1}, {"VWM",8}, {"VWN",2} } },
{ "GeForce GTX 980", { {"KWG",16}, {"KWI",2}, {"MDIMA",16}, {"MDIMC",16}, {"MWG",64}, {"NDIMB",16}, {"NDIMC",8}, {"NWG",128}, {"SA",1}, {"SB",1}, {"STRM",1}, {"STRN",0}, {"VWM",4}, {"VWN",8} } },
{ "GeForce GTX TITAN", { {"KWG",16}, {"KWI",8}, {"MDIMA",32}, {"MDIMC",16}, {"MWG",64}, {"NDIMB",8}, {"NDIMC",8}, {"NWG",64}, {"SA",1}, {"SB",1}, {"STRM",1}, {"STRN",0}, {"VWM",2}, {"VWN",2} } },
+ { "GeForce GTX TITAN Black", { {"KWG",16}, {"KWI",2}, {"MDIMA",16}, {"MDIMC",8}, {"MWG",64}, {"NDIMB",16}, {"NDIMC",16}, {"NWG",64}, {"SA",1}, {"SB",1}, {"STRM",1}, {"STRN",0}, {"VWM",4}, {"VWN",1} } },
{ "GeForce GTX TITAN X", { {"KWG",16}, {"KWI",2}, {"MDIMA",8}, {"MDIMC",16}, {"MWG",128}, {"NDIMB",8}, {"NDIMC",8}, {"NWG",128}, {"SA",1}, {"SB",1}, {"STRM",1}, {"STRN",1}, {"VWM",4}, {"VWN",8} } },
{ "Tesla K20m", { {"KWG",16}, {"KWI",2}, {"MDIMA",32}, {"MDIMC",16}, {"MWG",64}, {"NDIMB",16}, {"NDIMC",8}, {"NWG",64}, {"SA",1}, {"SB",1}, {"STRM",1}, {"STRN",0}, {"VWM",2}, {"VWN",4} } },
{ "Tesla K40m", { {"KWG",16}, {"KWI",8}, {"MDIMA",16}, {"MDIMC",8}, {"MWG",64}, {"NDIMB",16}, {"NDIMC",16}, {"NWG",128}, {"SA",1}, {"SB",1}, {"STRM",1}, {"STRN",0}, {"VWM",2}, {"VWN",4} } },
@@ -155,6 +156,7 @@ const Database::DatabaseEntry XgemmComplexSingle = {
{ "GeForce GTX 750 Ti", { {"KWG",16}, {"KWI",2}, {"MDIMA",16}, {"MDIMC",8}, {"MWG",32}, {"NDIMB",32}, {"NDIMC",16}, {"NWG",64}, {"SA",1}, {"SB",1}, {"STRM",1}, {"STRN",0}, {"VWM",1}, {"VWN",2} } },
{ "GeForce GTX 980", { {"KWG",32}, {"KWI",8}, {"MDIMA",32}, {"MDIMC",32}, {"MWG",64}, {"NDIMB",16}, {"NDIMC",16}, {"NWG",64}, {"SA",1}, {"SB",1}, {"STRM",1}, {"STRN",0}, {"VWM",2}, {"VWN",1} } },
{ "GeForce GTX TITAN", { {"KWG",16}, {"KWI",8}, {"MDIMA",16}, {"MDIMC",16}, {"MWG",64}, {"NDIMB",32}, {"NDIMC",16}, {"NWG",64}, {"SA",1}, {"SB",1}, {"STRM",1}, {"STRN",0}, {"VWM",1}, {"VWN",1} } },
+ { "GeForce GTX TITAN Black", { {"KWG",16}, {"KWI",2}, {"MDIMA",8}, {"MDIMC",16}, {"MWG",64}, {"NDIMB",8}, {"NDIMC",8}, {"NWG",32}, {"SA",0}, {"SB",1}, {"STRM",1}, {"STRN",0}, {"VWM",1}, {"VWN",2} } },
{ "GeForce GTX TITAN X", { {"KWG",16}, {"KWI",2}, {"MDIMA",8}, {"MDIMC",8}, {"MWG",64}, {"NDIMB",8}, {"NDIMC",8}, {"NWG",32}, {"SA",1}, {"SB",0}, {"STRM",1}, {"STRN",1}, {"VWM",1}, {"VWN",4} } },
{ "Tesla K20m", { {"KWG",32}, {"KWI",2}, {"MDIMA",8}, {"MDIMC",16}, {"MWG",64}, {"NDIMB",8}, {"NDIMC",16}, {"NWG",64}, {"SA",1}, {"SB",0}, {"STRM",0}, {"STRN",0}, {"VWM",1}, {"VWN",4} } },
{ "Tesla K40m", { {"KWG",16}, {"KWI",2}, {"MDIMA",32}, {"MDIMC",32}, {"MWG",32}, {"NDIMB",32}, {"NDIMC",8}, {"NWG",64}, {"SA",0}, {"SB",1}, {"STRM",0}, {"STRN",0}, {"VWM",1}, {"VWN",1} } },
@@ -215,6 +217,7 @@ const Database::DatabaseEntry XgemmDouble = {
{ "GeForce GTX 750 Ti", { {"KWG",32}, {"KWI",2}, {"MDIMA",8}, {"MDIMC",8}, {"MWG",32}, {"NDIMB",16}, {"NDIMC",16}, {"NWG",32}, {"SA",0}, {"SB",0}, {"STRM",0}, {"STRN",0}, {"VWM",4}, {"VWN",2} } },
{ "GeForce GTX 980", { {"KWG",32}, {"KWI",8}, {"MDIMA",16}, {"MDIMC",8}, {"MWG",64}, {"NDIMB",32}, {"NDIMC",32}, {"NWG",128}, {"SA",0}, {"SB",0}, {"STRM",1}, {"STRN",0}, {"VWM",2}, {"VWN",4} } },
{ "GeForce GTX TITAN", { {"KWG",16}, {"KWI",8}, {"MDIMA",16}, {"MDIMC",8}, {"MWG",32}, {"NDIMB",16}, {"NDIMC",32}, {"NWG",128}, {"SA",1}, {"SB",1}, {"STRM",1}, {"STRN",1}, {"VWM",2}, {"VWN",2} } },
+ { "GeForce GTX TITAN Black", { {"KWG",16}, {"KWI",2}, {"MDIMA",16}, {"MDIMC",8}, {"MWG",16}, {"NDIMB",16}, {"NDIMC",8}, {"NWG",16}, {"SA",1}, {"SB",1}, {"STRM",1}, {"STRN",0}, {"VWM",1}, {"VWN",1} } },
{ "GeForce GTX TITAN X", { {"KWG",16}, {"KWI",8}, {"MDIMA",16}, {"MDIMC",16}, {"MWG",16}, {"NDIMB",16}, {"NDIMC",16}, {"NWG",16}, {"SA",0}, {"SB",0}, {"STRM",0}, {"STRN",0}, {"VWM",1}, {"VWN",1} } },
{ "Tesla K20m", { {"KWG",16}, {"KWI",2}, {"MDIMA",32}, {"MDIMC",8}, {"MWG",32}, {"NDIMB",16}, {"NDIMC",16}, {"NWG",64}, {"SA",1}, {"SB",0}, {"STRM",0}, {"STRN",0}, {"VWM",1}, {"VWN",1} } },
{ "Tesla K40m", { {"KWG",32}, {"KWI",2}, {"MDIMA",16}, {"MDIMC",8}, {"MWG",64}, {"NDIMB",16}, {"NDIMC",32}, {"NWG",128}, {"SA",1}, {"SB",0}, {"STRM",1}, {"STRN",1}, {"VWM",2}, {"VWN",4} } },
@@ -274,6 +277,7 @@ const Database::DatabaseEntry XgemmComplexDouble = {
{ "GeForce GTX 750", { {"KWG",32}, {"KWI",2}, {"MDIMA",8}, {"MDIMC",32}, {"MWG",32}, {"NDIMB",8}, {"NDIMC",8}, {"NWG",64}, {"SA",0}, {"SB",0}, {"STRM",1}, {"STRN",0}, {"VWM",1}, {"VWN",4} } },
{ "GeForce GTX 750 Ti", { {"KWG",32}, {"KWI",2}, {"MDIMA",8}, {"MDIMC",8}, {"MWG",16}, {"NDIMB",8}, {"NDIMC",8}, {"NWG",32}, {"SA",0}, {"SB",0}, {"STRM",0}, {"STRN",0}, {"VWM",1}, {"VWN",1} } },
{ "GeForce GTX 980", { {"KWG",16}, {"KWI",2}, {"MDIMA",16}, {"MDIMC",8}, {"MWG",32}, {"NDIMB",8}, {"NDIMC",16}, {"NWG",128}, {"SA",0}, {"SB",0}, {"STRM",1}, {"STRN",1}, {"VWM",2}, {"VWN",2} } },
+ { "GeForce GTX TITAN Black", { {"KWG",16}, {"KWI",2}, {"MDIMA",16}, {"MDIMC",16}, {"MWG",32}, {"NDIMB",16}, {"NDIMC",8}, {"NWG",32}, {"SA",0}, {"SB",1}, {"STRM",1}, {"STRN",1}, {"VWM",1}, {"VWN",1} } },
{ "GeForce GTX TITAN X", { {"KWG",32}, {"KWI",8}, {"MDIMA",16}, {"MDIMC",16}, {"MWG",128}, {"NDIMB",16}, {"NDIMC",16}, {"NWG",32}, {"SA",0}, {"SB",0}, {"STRM",1}, {"STRN",0}, {"VWM",1}, {"VWN",1} } },
{ "Tesla K20m", { {"KWG",32}, {"KWI",2}, {"MDIMA",32}, {"MDIMC",8}, {"MWG",32}, {"NDIMB",16}, {"NDIMC",16}, {"NWG",64}, {"SA",0}, {"SB",0}, {"STRM",1}, {"STRN",0}, {"VWM",1}, {"VWN",1} } },
{ "Tesla K40m", { {"KWG",16}, {"KWI",8}, {"MDIMA",8}, {"MDIMC",8}, {"MWG",32}, {"NDIMB",32}, {"NDIMC",16}, {"NWG",32}, {"SA",0}, {"SB",0}, {"STRM",1}, {"STRN",0}, {"VWM",1}, {"VWN",1} } },
diff --git a/src/database/kernels/xgemm_direct.hpp b/src/database/kernels/xgemm_direct.hpp
index fff201bc..c83a9b0d 100644
--- a/src/database/kernels/xgemm_direct.hpp
+++ b/src/database/kernels/xgemm_direct.hpp
@@ -45,7 +45,8 @@ const Database::DatabaseEntry XgemmDirectSingle = {
{ // NVIDIA GPUs
kDeviceTypeGPU, "NVIDIA", {
{ "GeForce GTX 750 Ti", { {"KWID",2}, {"MDIMAD",8}, {"MDIMCD",8}, {"NDIMBD",8}, {"NDIMCD",8}, {"PADA",1}, {"PADB",1}, {"VWMD",4}, {"VWND",2}, {"WGD",32} } },
- { "default", { {"KWID",2}, {"MDIMAD",8}, {"MDIMCD",8}, {"NDIMBD",8}, {"NDIMCD",8}, {"PADA",1}, {"PADB",1}, {"VWMD",4}, {"VWND",2}, {"WGD",32} } },
+ { "GeForce GTX TITAN Black", { {"KWID",2}, {"MDIMAD",8}, {"MDIMCD",8}, {"NDIMBD",16}, {"NDIMCD",16}, {"PADA",1}, {"PADB",1}, {"VWMD",4}, {"VWND",2}, {"WGD",32} } },
+ { "default", { {"KWID",2}, {"MDIMAD",8}, {"MDIMCD",8}, {"NDIMBD",16}, {"NDIMCD",16}, {"PADA",1}, {"PADB",1}, {"VWMD",4}, {"VWND",2}, {"WGD",32} } },
}
},
{ // Default
@@ -76,7 +77,8 @@ const Database::DatabaseEntry XgemmDirectComplexSingle = {
{ // NVIDIA GPUs
kDeviceTypeGPU, "NVIDIA", {
{ "GeForce GTX 750 Ti", { {"KWID",16}, {"MDIMAD",8}, {"MDIMCD",8}, {"NDIMBD",16}, {"NDIMCD",8}, {"PADA",1}, {"PADB",1}, {"VWMD",2}, {"VWND",1}, {"WGD",16} } },
- { "default", { {"KWID",16}, {"MDIMAD",8}, {"MDIMCD",8}, {"NDIMBD",16}, {"NDIMCD",8}, {"PADA",1}, {"PADB",1}, {"VWMD",2}, {"VWND",1}, {"WGD",16} } },
+ { "GeForce GTX TITAN Black", { {"KWID",2}, {"MDIMAD",8}, {"MDIMCD",8}, {"NDIMBD",16}, {"NDIMCD",16}, {"PADA",1}, {"PADB",1}, {"VWMD",1}, {"VWND",1}, {"WGD",16} } },
+ { "default", { {"KWID",2}, {"MDIMAD",8}, {"MDIMCD",8}, {"NDIMBD",8}, {"NDIMCD",8}, {"PADA",1}, {"PADB",1}, {"VWMD",1}, {"VWND",2}, {"WGD",16} } },
}
},
{ // Default
@@ -101,7 +103,8 @@ const Database::DatabaseEntry XgemmDirectDouble = {
{ // NVIDIA GPUs
kDeviceTypeGPU, "NVIDIA", {
{ "GeForce GTX 750 Ti", { {"KWID",2}, {"MDIMAD",8}, {"MDIMCD",8}, {"NDIMBD",8}, {"NDIMCD",8}, {"PADA",1}, {"PADB",1}, {"VWMD",2}, {"VWND",4}, {"WGD",32} } },
- { "default", { {"KWID",2}, {"MDIMAD",8}, {"MDIMCD",8}, {"NDIMBD",8}, {"NDIMCD",8}, {"PADA",1}, {"PADB",1}, {"VWMD",2}, {"VWND",4}, {"WGD",32} } },
+ { "GeForce GTX TITAN Black", { {"KWID",8}, {"MDIMAD",16}, {"MDIMCD",16}, {"NDIMBD",16}, {"NDIMCD",8}, {"PADA",1}, {"PADB",0}, {"VWMD",1}, {"VWND",1}, {"WGD",16} } },
+ { "default", { {"KWID",2}, {"MDIMAD",8}, {"MDIMCD",8}, {"NDIMBD",8}, {"NDIMCD",8}, {"PADA",1}, {"PADB",1}, {"VWMD",1}, {"VWND",2}, {"WGD",16} } },
}
},
{ // Default
@@ -126,7 +129,8 @@ const Database::DatabaseEntry XgemmDirectComplexDouble = {
{ // NVIDIA GPUs
kDeviceTypeGPU, "NVIDIA", {
{ "GeForce GTX 750 Ti", { {"KWID",2}, {"MDIMAD",32}, {"MDIMCD",32}, {"NDIMBD",8}, {"NDIMCD",8}, {"PADA",1}, {"PADB",1}, {"VWMD",1}, {"VWND",1}, {"WGD",32} } },
- { "default", { {"KWID",2}, {"MDIMAD",32}, {"MDIMCD",32}, {"NDIMBD",8}, {"NDIMCD",8}, {"PADA",1}, {"PADB",1}, {"VWMD",1}, {"VWND",1}, {"WGD",32} } },
+ { "GeForce GTX TITAN Black", { {"KWID",2}, {"MDIMAD",8}, {"MDIMCD",8}, {"NDIMBD",8}, {"NDIMCD",8}, {"PADA",1}, {"PADB",1}, {"VWMD",1}, {"VWND",1}, {"WGD",8} } },
+ { "default", { {"KWID",2}, {"MDIMAD",16}, {"MDIMCD",16}, {"NDIMBD",8}, {"NDIMCD",8}, {"PADA",1}, {"PADB",1}, {"VWMD",1}, {"VWND",1}, {"WGD",16} } },
}
},
{ // Default
diff --git a/src/database/kernels/xgemv.hpp b/src/database/kernels/xgemv.hpp
index f0125d53..c3811c59 100644
--- a/src/database/kernels/xgemv.hpp
+++ b/src/database/kernels/xgemv.hpp
@@ -83,6 +83,7 @@ const Database::DatabaseEntry XgemvSingle = {
{ "GeForce GTX 750 Ti", { {"WGS1",32}, {"WPT1",1} } },
{ "GeForce GTX 980", { {"WGS1",128}, {"WPT1",1} } },
{ "GeForce GTX TITAN", { {"WGS1",256}, {"WPT1",1} } },
+ { "GeForce GTX TITAN Black", { {"WGS1",256}, {"WPT1",1} } },
{ "GeForce GTX TITAN X", { {"WGS1",256}, {"WPT1",1} } },
{ "Tesla K20m", { {"WGS1",128}, {"WPT1",1} } },
{ "Tesla K40m", { {"WGS1",256}, {"WPT1",1} } },
@@ -147,6 +148,7 @@ const Database::DatabaseEntry XgemvComplexSingle = {
{ "GeForce GTX 750", { {"WGS1",128}, {"WPT1",1} } },
{ "GeForce GTX 750 Ti", { {"WGS1",32}, {"WPT1",1} } },
{ "GeForce GTX TITAN", { {"WGS1",256}, {"WPT1",1} } },
+ { "GeForce GTX TITAN Black", { {"WGS1",32}, {"WPT1",1} } },
{ "default", { {"WGS1",64}, {"WPT1",1} } },
}
},
@@ -197,6 +199,7 @@ const Database::DatabaseEntry XgemvDouble = {
{ "GeForce GTX 750 Ti", { {"WGS1",32}, {"WPT1",1} } },
{ "GeForce GTX 980", { {"WGS1",64}, {"WPT1",1} } },
{ "GeForce GTX TITAN", { {"WGS1",256}, {"WPT1",1} } },
+ { "GeForce GTX TITAN Black", { {"WGS1",32}, {"WPT1",1} } },
{ "GeForce GTX TITAN X", { {"WGS1",64}, {"WPT1",1} } },
{ "Tesla K20m", { {"WGS1",256}, {"WPT1",1} } },
{ "Tesla K40m", { {"WGS1",256}, {"WPT1",1} } },
diff --git a/src/database/kernels/xgemv_fast.hpp b/src/database/kernels/xgemv_fast.hpp
index 51837c25..9abd33e1 100644
--- a/src/database/kernels/xgemv_fast.hpp
+++ b/src/database/kernels/xgemv_fast.hpp
@@ -83,6 +83,7 @@ const Database::DatabaseEntry XgemvFastSingle = {
{ "GeForce GTX 750 Ti", { {"VW2",2}, {"WGS2",32}, {"WPT2",2} } },
{ "GeForce GTX 980", { {"VW2",1}, {"WGS2",256}, {"WPT2",1} } },
{ "GeForce GTX TITAN", { {"VW2",1}, {"WGS2",256}, {"WPT2",1} } },
+ { "GeForce GTX TITAN Black", { {"VW2",1}, {"WGS2",256}, {"WPT2",1} } },
{ "GeForce GTX TITAN X", { {"VW2",1}, {"WGS2",64}, {"WPT2",1} } },
{ "Tesla K20m", { {"VW2",1}, {"WGS2",256}, {"WPT2",1} } },
{ "Tesla K40m", { {"VW2",1}, {"WGS2",256}, {"WPT2",1} } },
@@ -194,6 +195,7 @@ const Database::DatabaseEntry XgemvFastDouble = {
{ "GeForce GTX 750 Ti", { {"VW2",1}, {"WGS2",32}, {"WPT2",2} } },
{ "GeForce GTX 980", { {"VW2",1}, {"WGS2",64}, {"WPT2",1} } },
{ "GeForce GTX TITAN", { {"VW2",1}, {"WGS2",256}, {"WPT2",1} } },
+ { "GeForce GTX TITAN Black", { {"VW2",1}, {"WGS2",256}, {"WPT2",1} } },
{ "GeForce GTX TITAN X", { {"VW2",1}, {"WGS2",128}, {"WPT2",1} } },
{ "Tesla K20m", { {"VW2",1}, {"WGS2",128}, {"WPT2",1} } },
{ "Tesla K40m", { {"VW2",1}, {"WGS2",256}, {"WPT2",1} } },
diff --git a/src/database/kernels/xgemv_fast_rot.hpp b/src/database/kernels/xgemv_fast_rot.hpp
index 8969052d..49650a38 100644
--- a/src/database/kernels/xgemv_fast_rot.hpp
+++ b/src/database/kernels/xgemv_fast_rot.hpp
@@ -56,6 +56,7 @@ const Database::DatabaseEntry XgemvFastRotSingle = {
kDeviceTypeGPU, "NVIDIA", {
{ "GeForce GTX 750 Ti", { {"VW3",8}, {"WGS3",32}, {"WPT3",32} } },
{ "GeForce GTX TITAN", { {"VW3",1}, {"WGS3",16}, {"WPT3",16} } },
+ { "GeForce GTX TITAN Black", { {"VW3",4}, {"WGS3",128}, {"WPT3",16} } },
{ "default", { {"VW3",8}, {"WGS3",32}, {"WPT3",32} } },
}
},
@@ -123,6 +124,7 @@ const Database::DatabaseEntry XgemvFastRotDouble = {
kDeviceTypeGPU, "NVIDIA", {
{ "GeForce GTX 750 Ti", { {"VW3",4}, {"WGS3",32}, {"WPT3",16} } },
{ "GeForce GTX TITAN", { {"VW3",1}, {"WGS3",16}, {"WPT3",16} } },
+ { "GeForce GTX TITAN Black", { {"VW3",1}, {"WGS3",16}, {"WPT3",16} } },
{ "default", { {"VW3",4}, {"WGS3",32}, {"WPT3",16} } },
}
},
diff --git a/src/database/kernels/xger.hpp b/src/database/kernels/xger.hpp
index ac1a714c..a80f9860 100644
--- a/src/database/kernels/xger.hpp
+++ b/src/database/kernels/xger.hpp
@@ -81,6 +81,7 @@ const Database::DatabaseEntry XgerSingle = {
{ "GeForce GTX 750", { {"WGS1",64}, {"WGS2",16}, {"WPT",4} } },
{ "GeForce GTX 750 Ti", { {"WGS1",64}, {"WGS2",1}, {"WPT",2} } },
{ "GeForce GTX TITAN", { {"WGS1",32}, {"WGS2",4}, {"WPT",2} } },
+ { "GeForce GTX TITAN Black", { {"WGS1",32}, {"WGS2",4}, {"WPT",2} } },
{ "default", { {"WGS1",128}, {"WGS2",1}, {"WPT",2} } },
}
},
@@ -141,7 +142,8 @@ const Database::DatabaseEntry XgerComplexSingle = {
{ "GeForce GTX 750", { {"WGS1",32}, {"WGS2",16}, {"WPT",4} } },
{ "GeForce GTX 750 Ti", { {"WGS1",32}, {"WGS2",8}, {"WPT",2} } },
{ "GeForce GTX TITAN", { {"WGS1",16}, {"WGS2",16}, {"WPT",2} } },
- { "default", { {"WGS1",64}, {"WGS2",2}, {"WPT",2} } },
+ { "GeForce GTX TITAN Black", { {"WGS1",16}, {"WGS2",16}, {"WPT",2} } },
+ { "default", { {"WGS1",128}, {"WGS2",2}, {"WPT",2} } },
}
},
{ // Default
@@ -190,6 +192,7 @@ const Database::DatabaseEntry XgerDouble = {
{ "GeForce GTX 750", { {"WGS1",256}, {"WGS2",2}, {"WPT",2} } },
{ "GeForce GTX 750 Ti", { {"WGS1",32}, {"WGS2",16}, {"WPT",1} } },
{ "GeForce GTX TITAN", { {"WGS1",16}, {"WGS2",8}, {"WPT",2} } },
+ { "GeForce GTX TITAN Black", { {"WGS1",32}, {"WGS2",4}, {"WPT",2} } },
{ "default", { {"WGS1",64}, {"WGS2",2}, {"WPT",2} } },
}
},
@@ -239,6 +242,7 @@ const Database::DatabaseEntry XgerComplexDouble = {
{ "GeForce GTX 750", { {"WGS1",8}, {"WGS2",32}, {"WPT",4} } },
{ "GeForce GTX 750 Ti", { {"WGS1",32}, {"WGS2",8}, {"WPT",2} } },
{ "GeForce GTX TITAN", { {"WGS1",32}, {"WGS2",4}, {"WPT",2} } },
+ { "GeForce GTX TITAN Black", { {"WGS1",16}, {"WGS2",16}, {"WPT",2} } },
{ "default", { {"WGS1",16}, {"WGS2",8}, {"WPT",2} } },
}
},