summaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
authorCedric Nugteren <web@cedricnugteren.nl>2016-05-22 15:29:05 +0200
committerCedric Nugteren <web@cedricnugteren.nl>2016-05-22 15:29:05 +0200
commitb6268d0c22732d2d1b0832cbbf1a33c21a13b442 (patch)
tree1bbeec034fe2840c5783f5121f2969628c4200df /include
parent88551b40055a51800118865940626020d3fc064e (diff)
Added first tuning results for the half-precision xGEMV kernels
Diffstat (limited to 'include')
-rw-r--r--include/internal/database.h2
-rw-r--r--include/internal/database/xgemv.h18
2 files changed, 19 insertions, 1 deletions
diff --git a/include/internal/database.h b/include/internal/database.h
index d048e4f8..b3788666 100644
--- a/include/internal/database.h
+++ b/include/internal/database.h
@@ -69,7 +69,7 @@ class Database {
// The database consists of separate database entries, stored together in a vector
static const DatabaseEntry XaxpyHalf, XaxpySingle, XaxpyDouble, XaxpyComplexSingle, XaxpyComplexDouble;
static const DatabaseEntry XdotHalf, XdotSingle, XdotDouble, XdotComplexSingle, XdotComplexDouble;
- static const DatabaseEntry XgemvSingle, XgemvDouble, XgemvComplexSingle, XgemvComplexDouble;
+ static const DatabaseEntry XgemvHalf, XgemvSingle, XgemvDouble, XgemvComplexSingle, XgemvComplexDouble;
static const DatabaseEntry XgerSingle, XgerDouble, XgerComplexSingle, XgerComplexDouble;
static const DatabaseEntry XgemmSingle, XgemmDouble, XgemmComplexSingle, XgemmComplexDouble;
static const DatabaseEntry CopyHalf, CopySingle, CopyDouble, CopyComplexSingle, CopyComplexDouble;
diff --git a/include/internal/database/xgemv.h b/include/internal/database/xgemv.h
index bbbe62f6..c6e9d600 100644
--- a/include/internal/database/xgemv.h
+++ b/include/internal/database/xgemv.h
@@ -14,6 +14,24 @@
namespace clblast {
// =================================================================================================
+const Database::DatabaseEntry Database::XgemvHalf = {
+ "Xgemv", Precision::kHalf, {
+ { // Intel GPUs
+ kDeviceTypeGPU, "Intel", {
+ { "Intel(R) HD Graphics Skylake ULT GT2", { {"WGS1",256}, {"WPT1",1}, {"VW2",2}, {"WGS2",64}, {"WPT2",2}, {"VW3",4}, {"WGS3",64}, {"WPT3",4} } },
+ { "default", { {"WGS1",256}, {"WPT1",1}, {"VW2",2}, {"WGS2",64}, {"WPT2",2}, {"VW3",4}, {"WGS3",64}, {"WPT3",4} } },
+ }
+ },
+ { // Default
+ kDeviceTypeAll, "default", {
+ { "default", { {"WGS1",256}, {"WPT1",1}, {"VW2",2}, {"WGS2",64}, {"WPT2",2}, {"VW3",4}, {"WGS3",64}, {"WPT3",4} } },
+ }
+ },
+ }
+};
+
+// =================================================================================================
+
const Database::DatabaseEntry Database::XgemvSingle = {
"Xgemv", Precision::kSingle, {
{ // AMD GPUs