Added level-2 half-precision routines HGEMV/HGBMV/HHEMV/HHBMV/HHPMV/HSYMV/HSBMV/HSPMV/HTRMV/HTBMV/HTPMV

15 files changed, 353 insertions, 38 deletions

diff --git a/CHANGELOG b/CHANGELOG
index c971ab00..aba3d3f7 100644
--- a/CHANGELOG
+++ b/CHANGELOG
@@ -3,6 +3,7 @@ Development version (next release)
 - Added support for half-precision floating-point (fp16) in the library
 - Added half-precision routines:
   * Level-1: HSWAP/HSCAL/HCOPY/HAXPY/HDOT/HNRM2/HASUM/HSUM/iHAMAX/iHMAX/iHMIN
+  * Level-2: HGEMV/HGBMV/HHEMV/HHBMV/HHPMV/HSYMV/HSBMV/HSPMV/HTRMV/HTBMV/HTPMV
 
 Version 0.7.1
 - Improved performance of large power-of-2 xGEMM kernels for AMD GPUs
diff --git a/doc/clblast.md b/doc/clblast.md
index 77654d2b..91efd5fd 100644
--- a/doc/clblast.md
+++ b/doc/clblast.md
@@ -731,6 +731,14 @@ StatusCode CLBlastZgemv(const Layout layout, const Transpose a_transpose,
                         const cl_double2 beta,
                         cl_mem y_buffer, const size_t y_offset, const size_t y_inc,
                         cl_command_queue* queue, cl_event* event)
+StatusCode CLBlastHgemv(const Layout layout, const Transpose a_transpose,
+                        const size_t m, const size_t n,
+                        const cl_half alpha,
+                        const cl_mem a_buffer, const size_t a_offset, const size_t a_ld,
+                        const cl_mem x_buffer, const size_t x_offset, const size_t x_inc,
+                        const cl_half beta,
+                        cl_mem y_buffer, const size_t y_offset, const size_t y_inc,
+                        cl_command_queue* queue, cl_event* event)
 ```
 
 Arguments to GEMV:
@@ -807,6 +815,14 @@ StatusCode CLBlastZgbmv(const Layout layout, const Transpose a_transpose,
                         const cl_double2 beta,
                         cl_mem y_buffer, const size_t y_offset, const size_t y_inc,
                         cl_command_queue* queue, cl_event* event)
+StatusCode CLBlastHgbmv(const Layout layout, const Transpose a_transpose,
+                        const size_t m, const size_t n, const size_t kl, const size_t ku,
+                        const cl_half alpha,
+                        const cl_mem a_buffer, const size_t a_offset, const size_t a_ld,
+                        const cl_mem x_buffer, const size_t x_offset, const size_t x_inc,
+                        const cl_half beta,
+                        cl_mem y_buffer, const size_t y_offset, const size_t y_inc,
+                        cl_command_queue* queue, cl_event* event)
 ```
 
 Arguments to GBMV:
@@ -1046,6 +1062,14 @@ StatusCode CLBlastDsymv(const Layout layout, const Triangle triangle,
                         const double beta,
                         cl_mem y_buffer, const size_t y_offset, const size_t y_inc,
                         cl_command_queue* queue, cl_event* event)
+StatusCode CLBlastHsymv(const Layout layout, const Triangle triangle,
+                        const size_t n,
+                        const cl_half alpha,
+                        const cl_mem a_buffer, const size_t a_offset, const size_t a_ld,
+                        const cl_mem x_buffer, const size_t x_offset, const size_t x_inc,
+                        const cl_half beta,
+                        cl_mem y_buffer, const size_t y_offset, const size_t y_inc,
+                        cl_command_queue* queue, cl_event* event)
 ```
 
 Arguments to SYMV:
@@ -1105,6 +1129,14 @@ StatusCode CLBlastDsbmv(const Layout layout, const Triangle triangle,
                         const double beta,
                         cl_mem y_buffer, const size_t y_offset, const size_t y_inc,
                         cl_command_queue* queue, cl_event* event)
+StatusCode CLBlastHsbmv(const Layout layout, const Triangle triangle,
+                        const size_t n, const size_t k,
+                        const cl_half alpha,
+                        const cl_mem a_buffer, const size_t a_offset, const size_t a_ld,
+                        const cl_mem x_buffer, const size_t x_offset, const size_t x_inc,
+                        const cl_half beta,
+                        cl_mem y_buffer, const size_t y_offset, const size_t y_inc,
+                        cl_command_queue* queue, cl_event* event)
 ```
 
 Arguments to SBMV:
@@ -1165,6 +1197,14 @@ StatusCode CLBlastDspmv(const Layout layout, const Triangle triangle,
                         const double beta,
                         cl_mem y_buffer, const size_t y_offset, const size_t y_inc,
                         cl_command_queue* queue, cl_event* event)
+StatusCode CLBlastHspmv(const Layout layout, const Triangle triangle,
+                        const size_t n,
+                        const cl_half alpha,
+                        const cl_mem ap_buffer, const size_t ap_offset,
+                        const cl_mem x_buffer, const size_t x_offset, const size_t x_inc,
+                        const cl_half beta,
+                        cl_mem y_buffer, const size_t y_offset, const size_t y_inc,
+                        cl_command_queue* queue, cl_event* event)
 ```
 
 Arguments to SPMV:
@@ -1224,6 +1264,11 @@ StatusCode CLBlastZtrmv(const Layout layout, const Triangle triangle, const Tran
                         const cl_mem a_buffer, const size_t a_offset, const size_t a_ld,
                         cl_mem x_buffer, const size_t x_offset, const size_t x_inc,
                         cl_command_queue* queue, cl_event* event)
+StatusCode CLBlastHtrmv(const Layout layout, const Triangle triangle, const Transpose a_transpose, const Diagonal diagonal,
+                        const size_t n,
+                        const cl_mem a_buffer, const size_t a_offset, const size_t a_ld,
+                        cl_mem x_buffer, const size_t x_offset, const size_t x_inc,
+                        cl_command_queue* queue, cl_event* event)
 ```
 
 Arguments to TRMV:
@@ -1281,6 +1326,11 @@ StatusCode CLBlastZtbmv(const Layout layout, const Triangle triangle, const Tran
                         const cl_mem a_buffer, const size_t a_offset, const size_t a_ld,
                         cl_mem x_buffer, const size_t x_offset, const size_t x_inc,
                         cl_command_queue* queue, cl_event* event)
+StatusCode CLBlastHtbmv(const Layout layout, const Triangle triangle, const Transpose a_transpose, const Diagonal diagonal,
+                        const size_t n, const size_t k,
+                        const cl_mem a_buffer, const size_t a_offset, const size_t a_ld,
+                        cl_mem x_buffer, const size_t x_offset, const size_t x_inc,
+                        cl_command_queue* queue, cl_event* event)
 ```
 
 Arguments to TBMV:
@@ -1339,6 +1389,11 @@ StatusCode CLBlastZtpmv(const Layout layout, const Triangle triangle, const Tran
                         const cl_mem ap_buffer, const size_t ap_offset,
                         cl_mem x_buffer, const size_t x_offset, const size_t x_inc,
                         cl_command_queue* queue, cl_event* event)
+StatusCode CLBlastHtpmv(const Layout layout, const Triangle triangle, const Transpose a_transpose, const Diagonal diagonal,
+                        const size_t n,
+                        const cl_mem ap_buffer, const size_t ap_offset,
+                        cl_mem x_buffer, const size_t x_offset, const size_t x_inc,
+                        cl_command_queue* queue, cl_event* event)
 ```
 
 Arguments to TPMV:
diff --git a/include/clblast.h b/include/clblast.h
index 28c984c0..f0742614 100644
--- a/include/clblast.h
+++ b/include/clblast.h
@@ -220,7 +220,7 @@ StatusCode Min(const size_t n,
 // BLAS level-2 (matrix-vector) routines
 // =================================================================================================
 
-// General matrix-vector multiplication: SGEMV/DGEMV/CGEMV/ZGEMV
+// General matrix-vector multiplication: SGEMV/DGEMV/CGEMV/ZGEMV/HGEMV
 template <typename T>
 StatusCode Gemv(const Layout layout, const Transpose a_transpose,
                 const size_t m, const size_t n,
@@ -231,7 +231,7 @@ StatusCode Gemv(const Layout layout, const Transpose a_transpose,
                 cl_mem y_buffer, const size_t y_offset, const size_t y_inc,
                 cl_command_queue* queue, cl_event* event = nullptr);
 
-// General banded matrix-vector multiplication: SGBMV/DGBMV/CGBMV/ZGBMV
+// General banded matrix-vector multiplication: SGBMV/DGBMV/CGBMV/ZGBMV/HGBMV
 template <typename T>
 StatusCode Gbmv(const Layout layout, const Transpose a_transpose,
                 const size_t m, const size_t n, const size_t kl, const size_t ku,
@@ -275,7 +275,7 @@ StatusCode Hpmv(const Layout layout, const Triangle triangle,
                 cl_mem y_buffer, const size_t y_offset, const size_t y_inc,
                 cl_command_queue* queue, cl_event* event = nullptr);
 
-// Symmetric matrix-vector multiplication: SSYMV/DSYMV
+// Symmetric matrix-vector multiplication: SSYMV/DSYMV/HSYMV
 template <typename T>
 StatusCode Symv(const Layout layout, const Triangle triangle,
                 const size_t n,
@@ -286,7 +286,7 @@ StatusCode Symv(const Layout layout, const Triangle triangle,
                 cl_mem y_buffer, const size_t y_offset, const size_t y_inc,
                 cl_command_queue* queue, cl_event* event = nullptr);
 
-// Symmetric banded matrix-vector multiplication: SSBMV/DSBMV
+// Symmetric banded matrix-vector multiplication: SSBMV/DSBMV/HSBMV
 template <typename T>
 StatusCode Sbmv(const Layout layout, const Triangle triangle,
                 const size_t n, const size_t k,
@@ -297,7 +297,7 @@ StatusCode Sbmv(const Layout layout, const Triangle triangle,
                 cl_mem y_buffer, const size_t y_offset, const size_t y_inc,
                 cl_command_queue* queue, cl_event* event = nullptr);
 
-// Symmetric packed matrix-vector multiplication: SSPMV/DSPMV
+// Symmetric packed matrix-vector multiplication: SSPMV/DSPMV/HSPMV
 template <typename T>
 StatusCode Spmv(const Layout layout, const Triangle triangle,
                 const size_t n,
@@ -308,7 +308,7 @@ StatusCode Spmv(const Layout layout, const Triangle triangle,
                 cl_mem y_buffer, const size_t y_offset, const size_t y_inc,
                 cl_command_queue* queue, cl_event* event = nullptr);
 
-// Triangular matrix-vector multiplication: STRMV/DTRMV/CTRMV/ZTRMV
+// Triangular matrix-vector multiplication: STRMV/DTRMV/CTRMV/ZTRMV/HTRMV
 template <typename T>
 StatusCode Trmv(const Layout layout, const Triangle triangle, const Transpose a_transpose, const Diagonal diagonal,
                 const size_t n,
@@ -316,7 +316,7 @@ StatusCode Trmv(const Layout layout, const Triangle triangle, const Transpose a_
                 cl_mem x_buffer, const size_t x_offset, const size_t x_inc,
                 cl_command_queue* queue, cl_event* event = nullptr);
 
-// Triangular banded matrix-vector multiplication: STBMV/DTBMV/CTBMV/ZTBMV
+// Triangular banded matrix-vector multiplication: STBMV/DTBMV/CTBMV/ZTBMV/HTBMV
 template <typename T>
 StatusCode Tbmv(const Layout layout, const Triangle triangle, const Transpose a_transpose, const Diagonal diagonal,
                 const size_t n, const size_t k,
@@ -324,7 +324,7 @@ StatusCode Tbmv(const Layout layout, const Triangle triangle, const Transpose a_
                 cl_mem x_buffer, const size_t x_offset, const size_t x_inc,
                 cl_command_queue* queue, cl_event* event = nullptr);
 
-// Triangular packed matrix-vector multiplication: STPMV/DTPMV/CTPMV/ZTPMV
+// Triangular packed matrix-vector multiplication: STPMV/DTPMV/CTPMV/ZTPMV/HTPMV
 template <typename T>
 StatusCode Tpmv(const Layout layout, const Triangle triangle, const Transpose a_transpose, const Diagonal diagonal,
                 const size_t n,
diff --git a/include/clblast_c.h b/include/clblast_c.h
index 4dd76eb6..d0b89e19 100644
--- a/include/clblast_c.h
+++ b/include/clblast_c.h
@@ -418,7 +418,7 @@ StatusCode PUBLIC_API CLBlastiHmin(const size_t n,
 // BLAS level-2 (matrix-vector) routines
 // =================================================================================================
 
-// General matrix-vector multiplication: SGEMV/DGEMV/CGEMV/ZGEMV
+// General matrix-vector multiplication: SGEMV/DGEMV/CGEMV/ZGEMV/HGEMV
 StatusCode PUBLIC_API CLBlastSgemv(const Layout layout, const Transpose a_transpose,
                                    const size_t m, const size_t n,
                                    const float alpha,
@@ -451,8 +451,16 @@ StatusCode PUBLIC_API CLBlastZgemv(const Layout layout, const Transpose a_transp
                                    const cl_double2 beta,
                                    cl_mem y_buffer, const size_t y_offset, const size_t y_inc,
                                    cl_command_queue* queue, cl_event* event);
+StatusCode PUBLIC_API CLBlastHgemv(const Layout layout, const Transpose a_transpose,
+                                   const size_t m, const size_t n,
+                                   const cl_half alpha,
+                                   const cl_mem a_buffer, const size_t a_offset, const size_t a_ld,
+                                   const cl_mem x_buffer, const size_t x_offset, const size_t x_inc,
+                                   const cl_half beta,
+                                   cl_mem y_buffer, const size_t y_offset, const size_t y_inc,
+                                   cl_command_queue* queue, cl_event* event);
 
-// General banded matrix-vector multiplication: SGBMV/DGBMV/CGBMV/ZGBMV
+// General banded matrix-vector multiplication: SGBMV/DGBMV/CGBMV/ZGBMV/HGBMV
 StatusCode PUBLIC_API CLBlastSgbmv(const Layout layout, const Transpose a_transpose,
                                    const size_t m, const size_t n, const size_t kl, const size_t ku,
                                    const float alpha,
@@ -485,6 +493,14 @@ StatusCode PUBLIC_API CLBlastZgbmv(const Layout layout, const Transpose a_transp
                                    const cl_double2 beta,
                                    cl_mem y_buffer, const size_t y_offset, const size_t y_inc,
                                    cl_command_queue* queue, cl_event* event);
+StatusCode PUBLIC_API CLBlastHgbmv(const Layout layout, const Transpose a_transpose,
+                                   const size_t m, const size_t n, const size_t kl, const size_t ku,
+                                   const cl_half alpha,
+                                   const cl_mem a_buffer, const size_t a_offset, const size_t a_ld,
+                                   const cl_mem x_buffer, const size_t x_offset, const size_t x_inc,
+                                   const cl_half beta,
+                                   cl_mem y_buffer, const size_t y_offset, const size_t y_inc,
+                                   cl_command_queue* queue, cl_event* event);
 
 // Hermitian matrix-vector multiplication: CHEMV/ZHEMV
 StatusCode PUBLIC_API CLBlastChemv(const Layout layout, const Triangle triangle,
@@ -540,7 +556,7 @@ StatusCode PUBLIC_API CLBlastZhpmv(const Layout layout, const Triangle triangle,
                                    cl_mem y_buffer, const size_t y_offset, const size_t y_inc,
                                    cl_command_queue* queue, cl_event* event);
 
-// Symmetric matrix-vector multiplication: SSYMV/DSYMV
+// Symmetric matrix-vector multiplication: SSYMV/DSYMV/HSYMV
 StatusCode PUBLIC_API CLBlastSsymv(const Layout layout, const Triangle triangle,
                                    const size_t n,
                                    const float alpha,
@@ -557,8 +573,16 @@ StatusCode PUBLIC_API CLBlastDsymv(const Layout layout, const Triangle triangle,
                                    const double beta,
                                    cl_mem y_buffer, const size_t y_offset, const size_t y_inc,
                                    cl_command_queue* queue, cl_event* event);
+StatusCode PUBLIC_API CLBlastHsymv(const Layout layout, const Triangle triangle,
+                                   const size_t n,
+                                   const cl_half alpha,
+                                   const cl_mem a_buffer, const size_t a_offset, const size_t a_ld,
+                                   const cl_mem x_buffer, const size_t x_offset, const size_t x_inc,
+                                   const cl_half beta,
+                                   cl_mem y_buffer, const size_t y_offset, const size_t y_inc,
+                                   cl_command_queue* queue, cl_event* event);
 
-// Symmetric banded matrix-vector multiplication: SSBMV/DSBMV
+// Symmetric banded matrix-vector multiplication: SSBMV/DSBMV/HSBMV
 StatusCode PUBLIC_API CLBlastSsbmv(const Layout layout, const Triangle triangle,
                                    const size_t n, const size_t k,
                                    const float alpha,
@@ -575,8 +599,16 @@ StatusCode PUBLIC_API CLBlastDsbmv(const Layout layout, const Triangle triangle,
                                    const double beta,
                                    cl_mem y_buffer, const size_t y_offset, const size_t y_inc,
                                    cl_command_queue* queue, cl_event* event);
+StatusCode PUBLIC_API CLBlastHsbmv(const Layout layout, const Triangle triangle,
+                                   const size_t n, const size_t k,
+                                   const cl_half alpha,
+                                   const cl_mem a_buffer, const size_t a_offset, const size_t a_ld,
+                                   const cl_mem x_buffer, const size_t x_offset, const size_t x_inc,
+                                   const cl_half beta,
+                                   cl_mem y_buffer, const size_t y_offset, const size_t y_inc,
+                                   cl_command_queue* queue, cl_event* event);
 
-// Symmetric packed matrix-vector multiplication: SSPMV/DSPMV
+// Symmetric packed matrix-vector multiplication: SSPMV/DSPMV/HSPMV
 StatusCode PUBLIC_API CLBlastSspmv(const Layout layout, const Triangle triangle,
                                    const size_t n,
                                    const float alpha,
@@ -593,8 +625,16 @@ StatusCode PUBLIC_API CLBlastDspmv(const Layout layout, const Triangle triangle,
                                    const double beta,
                                    cl_mem y_buffer, const size_t y_offset, const size_t y_inc,
                                    cl_command_queue* queue, cl_event* event);
+StatusCode PUBLIC_API CLBlastHspmv(const Layout layout, const Triangle triangle,
+                                   const size_t n,
+                                   const cl_half alpha,
+                                   const cl_mem ap_buffer, const size_t ap_offset,
+                                   const cl_mem x_buffer, const size_t x_offset, const size_t x_inc,
+                                   const cl_half beta,
+                                   cl_mem y_buffer, const size_t y_offset, const size_t y_inc,
+                                   cl_command_queue* queue, cl_event* event);
 
-// Triangular matrix-vector multiplication: STRMV/DTRMV/CTRMV/ZTRMV
+// Triangular matrix-vector multiplication: STRMV/DTRMV/CTRMV/ZTRMV/HTRMV
 StatusCode PUBLIC_API CLBlastStrmv(const Layout layout, const Triangle triangle, const Transpose a_transpose, const Diagonal diagonal,
                                    const size_t n,
                                    const cl_mem a_buffer, const size_t a_offset, const size_t a_ld,
@@ -615,8 +655,13 @@ StatusCode PUBLIC_API CLBlastZtrmv(const Layout layout, const Triangle triangle,
                                    const cl_mem a_buffer, const size_t a_offset, const size_t a_ld,
                                    cl_mem x_buffer, const size_t x_offset, const size_t x_inc,
                                    cl_command_queue* queue, cl_event* event);
+StatusCode PUBLIC_API CLBlastHtrmv(const Layout layout, const Triangle triangle, const Transpose a_transpose, const Diagonal diagonal,
+                                   const size_t n,
+                                   const cl_mem a_buffer, const size_t a_offset, const size_t a_ld,
+                                   cl_mem x_buffer, const size_t x_offset, const size_t x_inc,
+                                   cl_command_queue* queue, cl_event* event);
 
-// Triangular banded matrix-vector multiplication: STBMV/DTBMV/CTBMV/ZTBMV
+// Triangular banded matrix-vector multiplication: STBMV/DTBMV/CTBMV/ZTBMV/HTBMV
 StatusCode PUBLIC_API CLBlastStbmv(const Layout layout, const Triangle triangle, const Transpose a_transpose, const Diagonal diagonal,
                                    const size_t n, const size_t k,
                                    const cl_mem a_buffer, const size_t a_offset, const size_t a_ld,
@@ -637,8 +682,13 @@ StatusCode PUBLIC_API CLBlastZtbmv(const Layout layout, const Triangle triangle,
                                    const cl_mem a_buffer, const size_t a_offset, const size_t a_ld,
                                    cl_mem x_buffer, const size_t x_offset, const size_t x_inc,
                                    cl_command_queue* queue, cl_event* event);
+StatusCode PUBLIC_API CLBlastHtbmv(const Layout layout, const Triangle triangle, const Transpose a_transpose, const Diagonal diagonal,
+                                   const size_t n, const size_t k,
+                                   const cl_mem a_buffer, const size_t a_offset, const size_t a_ld,
+                                   cl_mem x_buffer, const size_t x_offset, const size_t x_inc,
+                                   cl_command_queue* queue, cl_event* event);
 
-// Triangular packed matrix-vector multiplication: STPMV/DTPMV/CTPMV/ZTPMV
+// Triangular packed matrix-vector multiplication: STPMV/DTPMV/CTPMV/ZTPMV/HTPMV
 StatusCode PUBLIC_API CLBlastStpmv(const Layout layout, const Triangle triangle, const Transpose a_transpose, const Diagonal diagonal,
                                    const size_t n,
                                    const cl_mem ap_buffer, const size_t ap_offset,
@@ -659,6 +709,11 @@ StatusCode PUBLIC_API CLBlastZtpmv(const Layout layout, const Triangle triangle,
                                    const cl_mem ap_buffer, const size_t ap_offset,
                                    cl_mem x_buffer, const size_t x_offset, const size_t x_inc,
                                    cl_command_queue* queue, cl_event* event);
+StatusCode PUBLIC_API CLBlastHtpmv(const Layout layout, const Triangle triangle, const Transpose a_transpose, const Diagonal diagonal,
+                                   const size_t n,
+                                   const cl_mem ap_buffer, const size_t ap_offset,
+                                   cl_mem x_buffer, const size_t x_offset, const size_t x_inc,
+                                   cl_command_queue* queue, cl_event* event);
 
 // Solves a triangular system of equations: STRSV/DTRSV/CTRSV/ZTRSV
 StatusCode PUBLIC_API CLBlastStrsv(const Layout layout, const Triangle triangle, const Transpose a_transpose, const Diagonal diagonal,
diff --git a/scripts/generator/generator.py b/scripts/generator/generator.py
index 927c64f0..6881949b 100644
--- a/scripts/generator/generator.py
+++ b/scripts/generator/generator.py
@@ -81,20 +81,20 @@ routines = [
   Routine(True,  False, "1", "min",   T, [iS,iD,iC,iZ,iH], ["n"], [], ["x"], ["imin"], [], "2*n", "Index of minimum value in a vector (non-BLAS function)", "Finds the index of the minimum of the values in the x vector. The resulting integer index is stored in the imin buffer. This routine is the non-absolute minimum version of the IxAMAX BLAS routine.", []),
 ],
 [ # Level 2: matrix-vector
-  Routine(True,  True,  "2a", "gemv",  T,  [S,D,C,Z], ["m","n"], ["layout","a_transpose"], ["a","x"], ["y"], ["alpha","beta"], "", "General matrix-vector multiplication", "Performs the operation y = alpha * A * x + beta * y, in which x is an input vector, y is an input and output vector, A is an input matrix, and alpha and beta are scalars. The matrix A can optionally be transposed before performing the operation.", []),
-  Routine(True,  True,  "2a", "gbmv",  T,  [S,D,C,Z], ["m","n","kl","ku"], ["layout","a_transpose"], ["a","x"], ["y"], ["alpha","beta"], "", "General banded matrix-vector multiplication", "Same operation as xGEMV, but matrix A is banded instead.", []),
-  Routine(True,  True,  "2a", "hemv",  T,  [C,Z],     ["n"], ["layout","triangle"], ["a","x"], ["y"], ["alpha","beta"], "", "Hermitian matrix-vector multiplication", "Same operation as xGEMV, but matrix A is an Hermitian matrix instead.", []),
-  Routine(True,  True,  "2a", "hbmv",  T,  [C,Z],     ["n","k"], ["layout","triangle"], ["a","x"], ["y"], ["alpha","beta"], "", "Hermitian banded matrix-vector multiplication", "Same operation as xGEMV, but matrix A is an Hermitian banded matrix instead.", []),
-  Routine(True,  True,  "2a", "hpmv",  T,  [C,Z],     ["n"], ["layout","triangle"], ["ap","x"], ["y"], ["alpha","beta"], "", "Hermitian packed matrix-vector multiplication", "Same operation as xGEMV, but matrix A is an Hermitian packed matrix instead and represented as AP.", []),
-  Routine(True,  True,  "2a", "symv",  T,  [S,D],     ["n"], ["layout","triangle"], ["a","x"], ["y"], ["alpha","beta"], "", "Symmetric matrix-vector multiplication", "Same operation as xGEMV, but matrix A is symmetric instead.", []),
-  Routine(True,  True,  "2a", "sbmv",  T,  [S,D],     ["n","k"], ["layout","triangle"], ["a","x"], ["y"], ["alpha","beta"], "", "Symmetric banded matrix-vector multiplication", "Same operation as xGEMV, but matrix A is symmetric and banded instead.", []),
-  Routine(True,  True,  "2a", "spmv",  T,  [S,D],     ["n"], ["layout","triangle"], ["ap","x"], ["y"], ["alpha","beta"], "", "Symmetric packed matrix-vector multiplication", "Same operation as xGEMV, but matrix A is a symmetric packed matrix instead and represented as AP.", []),
-  Routine(True,  True,  "2a", "trmv",  T,  [S,D,C,Z], ["n"], ["layout","triangle","a_transpose","diagonal"], ["a"], ["x"], [], "n", "Triangular matrix-vector multiplication", "Same operation as xGEMV, but matrix A is triangular instead.", []),
-  Routine(True,  True,  "2a", "tbmv",  T,  [S,D,C,Z], ["n","k"], ["layout","triangle","a_transpose","diagonal"], ["a"], ["x"], [], "n", "Triangular banded matrix-vector multiplication", "Same operation as xGEMV, but matrix A is triangular and banded instead.", []),
-  Routine(True,  True,  "2a", "tpmv",  T,  [S,D,C,Z], ["n"], ["layout","triangle","a_transpose","diagonal"], ["ap"], ["x"], [], "n", "Triangular packed matrix-vector multiplication", "Same operation as xGEMV, but matrix A is a triangular packed matrix instead and repreented as AP.", []),
-  Routine(False, True,  "2a", "trsv",  T,  [S,D,C,Z], ["n"], ["layout","triangle","a_transpose","diagonal"], ["a"], ["x"], [], "", "Solves a triangular system of equations", "", []),
-  Routine(False, True,  "2a", "tbsv",  T,  [S,D,C,Z], ["n","k"], ["layout","triangle","a_transpose","diagonal"], ["a"], ["x"], [], "", "Solves a banded triangular system of equations", "", []),
-  Routine(False, True,  "2a", "tpsv",  T,  [S,D,C,Z], ["n"], ["layout","triangle","a_transpose","diagonal"], ["ap"], ["x"], [], "", "Solves a packed triangular system of equations", "", []),
+  Routine(True,  True,  "2a", "gemv",  T,  [S,D,C,Z,H], ["m","n"], ["layout","a_transpose"], ["a","x"], ["y"], ["alpha","beta"], "", "General matrix-vector multiplication", "Performs the operation y = alpha * A * x + beta * y, in which x is an input vector, y is an input and output vector, A is an input matrix, and alpha and beta are scalars. The matrix A can optionally be transposed before performing the operation.", []),
+  Routine(True,  True,  "2a", "gbmv",  T,  [S,D,C,Z,H], ["m","n","kl","ku"], ["layout","a_transpose"], ["a","x"], ["y"], ["alpha","beta"], "", "General banded matrix-vector multiplication", "Same operation as xGEMV, but matrix A is banded instead.", []),
+  Routine(True,  True,  "2a", "hemv",  T,  [C,Z],       ["n"], ["layout","triangle"], ["a","x"], ["y"], ["alpha","beta"], "", "Hermitian matrix-vector multiplication", "Same operation as xGEMV, but matrix A is an Hermitian matrix instead.", []),
+  Routine(True,  True,  "2a", "hbmv",  T,  [C,Z],       ["n","k"], ["layout","triangle"], ["a","x"], ["y"], ["alpha","beta"], "", "Hermitian banded matrix-vector multiplication", "Same operation as xGEMV, but matrix A is an Hermitian banded matrix instead.", []),
+  Routine(True,  True,  "2a", "hpmv",  T,  [C,Z],       ["n"], ["layout","triangle"], ["ap","x"], ["y"], ["alpha","beta"], "", "Hermitian packed matrix-vector multiplication", "Same operation as xGEMV, but matrix A is an Hermitian packed matrix instead and represented as AP.", []),
+  Routine(True,  True,  "2a", "symv",  T,  [S,D,H],     ["n"], ["layout","triangle"], ["a","x"], ["y"], ["alpha","beta"], "", "Symmetric matrix-vector multiplication", "Same operation as xGEMV, but matrix A is symmetric instead.", []),
+  Routine(True,  True,  "2a", "sbmv",  T,  [S,D,H],     ["n","k"], ["layout","triangle"], ["a","x"], ["y"], ["alpha","beta"], "", "Symmetric banded matrix-vector multiplication", "Same operation as xGEMV, but matrix A is symmetric and banded instead.", []),
+  Routine(True,  True,  "2a", "spmv",  T,  [S,D,H],     ["n"], ["layout","triangle"], ["ap","x"], ["y"], ["alpha","beta"], "", "Symmetric packed matrix-vector multiplication", "Same operation as xGEMV, but matrix A is a symmetric packed matrix instead and represented as AP.", []),
+  Routine(True,  True,  "2a", "trmv",  T,  [S,D,C,Z,H], ["n"], ["layout","triangle","a_transpose","diagonal"], ["a"], ["x"], [], "n", "Triangular matrix-vector multiplication", "Same operation as xGEMV, but matrix A is triangular instead.", []),
+  Routine(True,  True,  "2a", "tbmv",  T,  [S,D,C,Z,H], ["n","k"], ["layout","triangle","a_transpose","diagonal"], ["a"], ["x"], [], "n", "Triangular banded matrix-vector multiplication", "Same operation as xGEMV, but matrix A is triangular and banded instead.", []),
+  Routine(True,  True,  "2a", "tpmv",  T,  [S,D,C,Z,H], ["n"], ["layout","triangle","a_transpose","diagonal"], ["ap"], ["x"], [], "n", "Triangular packed matrix-vector multiplication", "Same operation as xGEMV, but matrix A is a triangular packed matrix instead and repreented as AP.", []),
+  Routine(False, True,  "2a", "trsv",  T,  [S,D,C,Z],   ["n"], ["layout","triangle","a_transpose","diagonal"], ["a"], ["x"], [], "", "Solves a triangular system of equations", "", []),
+  Routine(False, True,  "2a", "tbsv",  T,  [S,D,C,Z],   ["n","k"], ["layout","triangle","a_transpose","diagonal"], ["a"], ["x"], [], "", "Solves a banded triangular system of equations", "", []),
+  Routine(False, True,  "2a", "tpsv",  T,  [S,D,C,Z],   ["n"], ["layout","triangle","a_transpose","diagonal"], ["ap"], ["x"], [], "", "Solves a packed triangular system of equations", "", []),
   # Level 2: matrix update
   Routine(True,  True,  "2b", "ger",   T,  [S,D],     ["m","n"], ["layout"], ["x","y"], ["a"], ["alpha"], "", "General rank-1 matrix update", "", []),
   Routine(True,  True,  "2b", "geru",  T,  [C,Z],     ["m","n"], ["layout"], ["x","y"], ["a"], ["alpha"], "", "General rank-1 complex matrix update", "", []),
diff --git a/src/clblast.cc b/src/clblast.cc
index 098ff7f3..e89b41e8 100644
--- a/src/clblast.cc
+++ b/src/clblast.cc
@@ -607,7 +607,7 @@ template StatusCode PUBLIC_API Min<half>(const size_t,
 // BLAS level-2 (matrix-vector) routines
 // =================================================================================================
 
-// General matrix-vector multiplication: SGEMV/DGEMV/CGEMV/ZGEMV
+// General matrix-vector multiplication: SGEMV/DGEMV/CGEMV/ZGEMV/HGEMV
 template <typename T>
 StatusCode Gemv(const Layout layout, const Transpose a_transpose,
                 const size_t m, const size_t n,
@@ -661,8 +661,16 @@ template StatusCode PUBLIC_API Gemv<double2>(const Layout, const Transpose,
                                              const double2,
                                              cl_mem, const size_t, const size_t,
                                              cl_command_queue*, cl_event*);
+template StatusCode PUBLIC_API Gemv<half>(const Layout, const Transpose,
+                                          const size_t, const size_t,
+                                          const half,
+                                          const cl_mem, const size_t, const size_t,
+                                          const cl_mem, const size_t, const size_t,
+                                          const half,
+                                          cl_mem, const size_t, const size_t,
+                                          cl_command_queue*, cl_event*);
 
-// General banded matrix-vector multiplication: SGBMV/DGBMV/CGBMV/ZGBMV
+// General banded matrix-vector multiplication: SGBMV/DGBMV/CGBMV/ZGBMV/HGBMV
 template <typename T>
 StatusCode Gbmv(const Layout layout, const Transpose a_transpose,
                 const size_t m, const size_t n, const size_t kl, const size_t ku,
@@ -716,6 +724,14 @@ template StatusCode PUBLIC_API Gbmv<double2>(const Layout, const Transpose,
                                              const double2,
                                              cl_mem, const size_t, const size_t,
                                              cl_command_queue*, cl_event*);
+template StatusCode PUBLIC_API Gbmv<half>(const Layout, const Transpose,
+                                          const size_t, const size_t, const size_t, const size_t,
+                                          const half,
+                                          const cl_mem, const size_t, const size_t,
+                                          const cl_mem, const size_t, const size_t,
+                                          const half,
+                                          cl_mem, const size_t, const size_t,
+                                          cl_command_queue*, cl_event*);
 
 // Hermitian matrix-vector multiplication: CHEMV/ZHEMV
 template <typename T>
@@ -834,7 +850,7 @@ template StatusCode PUBLIC_API Hpmv<double2>(const Layout, const Triangle,
                                              cl_mem, const size_t, const size_t,
                                              cl_command_queue*, cl_event*);
 
-// Symmetric matrix-vector multiplication: SSYMV/DSYMV
+// Symmetric matrix-vector multiplication: SSYMV/DSYMV/HSYMV
 template <typename T>
 StatusCode Symv(const Layout layout, const Triangle triangle,
                 const size_t n,
@@ -872,8 +888,16 @@ template StatusCode PUBLIC_API Symv<double>(const Layout, const Triangle,
                                             const double,
                                             cl_mem, const size_t, const size_t,
                                             cl_command_queue*, cl_event*);
+template StatusCode PUBLIC_API Symv<half>(const Layout, const Triangle,
+                                          const size_t,
+                                          const half,
+                                          const cl_mem, const size_t, const size_t,
+                                          const cl_mem, const size_t, const size_t,
+                                          const half,
+                                          cl_mem, const size_t, const size_t,
+                                          cl_command_queue*, cl_event*);
 
-// Symmetric banded matrix-vector multiplication: SSBMV/DSBMV
+// Symmetric banded matrix-vector multiplication: SSBMV/DSBMV/HSBMV
 template <typename T>
 StatusCode Sbmv(const Layout layout, const Triangle triangle,
                 const size_t n, const size_t k,
@@ -911,8 +935,16 @@ template StatusCode PUBLIC_API Sbmv<double>(const Layout, const Triangle,
                                             const double,
                                             cl_mem, const size_t, const size_t,
                                             cl_command_queue*, cl_event*);
+template StatusCode PUBLIC_API Sbmv<half>(const Layout, const Triangle,
+                                          const size_t, const size_t,
+                                          const half,
+                                          const cl_mem, const size_t, const size_t,
+                                          const cl_mem, const size_t, const size_t,
+                                          const half,
+                                          cl_mem, const size_t, const size_t,
+                                          cl_command_queue*, cl_event*);
 
-// Symmetric packed matrix-vector multiplication: SSPMV/DSPMV
+// Symmetric packed matrix-vector multiplication: SSPMV/DSPMV/HSPMV
 template <typename T>
 StatusCode Spmv(const Layout layout, const Triangle triangle,
                 const size_t n,
@@ -950,8 +982,16 @@ template StatusCode PUBLIC_API Spmv<double>(const Layout, const Triangle,
                                             const double,
                                             cl_mem, const size_t, const size_t,
                                             cl_command_queue*, cl_event*);
+template StatusCode PUBLIC_API Spmv<half>(const Layout, const Triangle,
+                                          const size_t,
+                                          const half,
+                                          const cl_mem, const size_t,
+                                          const cl_mem, const size_t, const size_t,
+                                          const half,
+                                          cl_mem, const size_t, const size_t,
+                                          cl_command_queue*, cl_event*);
 
-// Triangular matrix-vector multiplication: STRMV/DTRMV/CTRMV/ZTRMV
+// Triangular matrix-vector multiplication: STRMV/DTRMV/CTRMV/ZTRMV/HTRMV
 template <typename T>
 StatusCode Trmv(const Layout layout, const Triangle triangle, const Transpose a_transpose, const Diagonal diagonal,
                 const size_t n,
@@ -987,8 +1027,13 @@ template StatusCode PUBLIC_API Trmv<double2>(const Layout, const Triangle, const
                                              const cl_mem, const size_t, const size_t,
                                              cl_mem, const size_t, const size_t,
                                              cl_command_queue*, cl_event*);
+template StatusCode PUBLIC_API Trmv<half>(const Layout, const Triangle, const Transpose, const Diagonal,
+                                          const size_t,
+                                          const cl_mem, const size_t, const size_t,
+                                          cl_mem, const size_t, const size_t,
+                                          cl_command_queue*, cl_event*);
 
-// Triangular banded matrix-vector multiplication: STBMV/DTBMV/CTBMV/ZTBMV
+// Triangular banded matrix-vector multiplication: STBMV/DTBMV/CTBMV/ZTBMV/HTBMV
 template <typename T>
 StatusCode Tbmv(const Layout layout, const Triangle triangle, const Transpose a_transpose, const Diagonal diagonal,
                 const size_t n, const size_t k,
@@ -1024,8 +1069,13 @@ template StatusCode PUBLIC_API Tbmv<double2>(const Layout, const Triangle, const
                                              const cl_mem, const size_t, const size_t,
                                              cl_mem, const size_t, const size_t,
                                              cl_command_queue*, cl_event*);
+template StatusCode PUBLIC_API Tbmv<half>(const Layout, const Triangle, const Transpose, const Diagonal,
+                                          const size_t, const size_t,
+                                          const cl_mem, const size_t, const size_t,
+                                          cl_mem, const size_t, const size_t,
+                                          cl_command_queue*, cl_event*);
 
-// Triangular packed matrix-vector multiplication: STPMV/DTPMV/CTPMV/ZTPMV
+// Triangular packed matrix-vector multiplication: STPMV/DTPMV/CTPMV/ZTPMV/HTPMV
 template <typename T>
 StatusCode Tpmv(const Layout layout, const Triangle triangle, const Transpose a_transpose, const Diagonal diagonal,
                 const size_t n,
@@ -1061,6 +1111,11 @@ template StatusCode PUBLIC_API Tpmv<double2>(const Layout, const Triangle, const
                                              const cl_mem, const size_t,
                                              cl_mem, const size_t, const size_t,
                                              cl_command_queue*, cl_event*);
+template StatusCode PUBLIC_API Tpmv<half>(const Layout, const Triangle, const Transpose, const Diagonal,
+                                          const size_t,
+                                          const cl_mem, const size_t,
+                                          cl_mem, const size_t, const size_t,
+                                          cl_command_queue*, cl_event*);
 
 // Solves a triangular system of equations: STRSV/DTRSV/CTRSV/ZTRSV
 template <typename T>
diff --git a/src/clblast_c.cc b/src/clblast_c.cc
index fd37462f..f1a81be5 100644
--- a/src/clblast_c.cc
+++ b/src/clblast_c.cc
@@ -838,6 +838,25 @@ StatusCode CLBlastZgemv(const Layout layout, const Transpose a_transpose,
                               queue, event);
   return static_cast<StatusCode>(status);
 }
+StatusCode CLBlastHgemv(const Layout layout, const Transpose a_transpose,
+                        const size_t m, const size_t n,
+                        const cl_half alpha,
+                        const cl_mem a_buffer, const size_t a_offset, const size_t a_ld,
+                        const cl_mem x_buffer, const size_t x_offset, const size_t x_inc,
+                        const cl_half beta,
+                        cl_mem y_buffer, const size_t y_offset, const size_t y_inc,
+                        cl_command_queue* queue, cl_event* event) {
+  auto status = clblast::Gemv(static_cast<clblast::Layout>(layout),
+                              static_cast<clblast::Transpose>(a_transpose),
+                              m, n,
+                              alpha,
+                              a_buffer, a_offset, a_ld,
+                              x_buffer, x_offset, x_inc,
+                              beta,
+                              y_buffer, y_offset, y_inc,
+                              queue, event);
+  return static_cast<StatusCode>(status);
+}
 
 // GBMV
 StatusCode CLBlastSgbmv(const Layout layout, const Transpose a_transpose,
@@ -916,6 +935,25 @@ StatusCode CLBlastZgbmv(const Layout layout, const Transpose a_transpose,
                               queue, event);
   return static_cast<StatusCode>(status);
 }
+StatusCode CLBlastHgbmv(const Layout layout, const Transpose a_transpose,
+                        const size_t m, const size_t n, const size_t kl, const size_t ku,
+                        const cl_half alpha,
+                        const cl_mem a_buffer, const size_t a_offset, const size_t a_ld,
+                        const cl_mem x_buffer, const size_t x_offset, const size_t x_inc,
+                        const cl_half beta,
+                        cl_mem y_buffer, const size_t y_offset, const size_t y_inc,
+                        cl_command_queue* queue, cl_event* event) {
+  auto status = clblast::Gbmv(static_cast<clblast::Layout>(layout),
+                              static_cast<clblast::Transpose>(a_transpose),
+                              m, n, kl, ku,
+                              alpha,
+                              a_buffer, a_offset, a_ld,
+                              x_buffer, x_offset, x_inc,
+                              beta,
+                              y_buffer, y_offset, y_inc,
+                              queue, event);
+  return static_cast<StatusCode>(status);
+}
 
 // HEMV
 StatusCode CLBlastChemv(const Layout layout, const Triangle triangle,
@@ -1076,6 +1114,25 @@ StatusCode CLBlastDsymv(const Layout layout, const Triangle triangle,
                               queue, event);
   return static_cast<StatusCode>(status);
 }
+StatusCode CLBlastHsymv(const Layout layout, const Triangle triangle,
+                        const size_t n,
+                        const cl_half alpha,
+                        const cl_mem a_buffer, const size_t a_offset, const size_t a_ld,
+                        const cl_mem x_buffer, const size_t x_offset, const size_t x_inc,
+                        const cl_half beta,
+                        cl_mem y_buffer, const size_t y_offset, const size_t y_inc,
+                        cl_command_queue* queue, cl_event* event) {
+  auto status = clblast::Symv(static_cast<clblast::Layout>(layout),
+                              static_cast<clblast::Triangle>(triangle),
+                              n,
+                              alpha,
+                              a_buffer, a_offset, a_ld,
+                              x_buffer, x_offset, x_inc,
+                              beta,
+                              y_buffer, y_offset, y_inc,
+                              queue, event);
+  return static_cast<StatusCode>(status);
+}
 
 // SBMV
 StatusCode CLBlastSsbmv(const Layout layout, const Triangle triangle,
@@ -1116,6 +1173,25 @@ StatusCode CLBlastDsbmv(const Layout layout, const Triangle triangle,
                               queue, event);
   return static_cast<StatusCode>(status);
 }
+StatusCode CLBlastHsbmv(const Layout layout, const Triangle triangle,
+                        const size_t n, const size_t k,
+                        const cl_half alpha,
+                        const cl_mem a_buffer, const size_t a_offset, const size_t a_ld,
+                        const cl_mem x_buffer, const size_t x_offset, const size_t x_inc,
+                        const cl_half beta,
+                        cl_mem y_buffer, const size_t y_offset, const size_t y_inc,
+                        cl_command_queue* queue, cl_event* event) {
+  auto status = clblast::Sbmv(static_cast<clblast::Layout>(layout),
+                              static_cast<clblast::Triangle>(triangle),
+                              n, k,
+                              alpha,
+                              a_buffer, a_offset, a_ld,
+                              x_buffer, x_offset, x_inc,
+                              beta,
+                              y_buffer, y_offset, y_inc,
+                              queue, event);
+  return static_cast<StatusCode>(status);
+}
 
 // SPMV
 StatusCode CLBlastSspmv(const Layout layout, const Triangle triangle,
@@ -1156,6 +1232,25 @@ StatusCode CLBlastDspmv(const Layout layout, const Triangle triangle,
                               queue, event);
   return static_cast<StatusCode>(status);
 }
+StatusCode CLBlastHspmv(const Layout layout, const Triangle triangle,
+                        const size_t n,
+                        const cl_half alpha,
+                        const cl_mem ap_buffer, const size_t ap_offset,
+                        const cl_mem x_buffer, const size_t x_offset, const size_t x_inc,
+                        const cl_half beta,
+                        cl_mem y_buffer, const size_t y_offset, const size_t y_inc,
+                        cl_command_queue* queue, cl_event* event) {
+  auto status = clblast::Spmv(static_cast<clblast::Layout>(layout),
+                              static_cast<clblast::Triangle>(triangle),
+                              n,
+                              alpha,
+                              ap_buffer, ap_offset,
+                              x_buffer, x_offset, x_inc,
+                              beta,
+                              y_buffer, y_offset, y_inc,
+                              queue, event);
+  return static_cast<StatusCode>(status);
+}
 
 // TRMV
 StatusCode CLBlastStrmv(const Layout layout, const Triangle triangle, const Transpose a_transpose, const Diagonal diagonal,
@@ -1218,6 +1313,21 @@ StatusCode CLBlastZtrmv(const Layout layout, const Triangle triangle, const Tran
                                        queue, event);
   return static_cast<StatusCode>(status);
 }
+StatusCode CLBlastHtrmv(const Layout layout, const Triangle triangle, const Transpose a_transpose, const Diagonal diagonal,
+                        const size_t n,
+                        const cl_mem a_buffer, const size_t a_offset, const size_t a_ld,
+                        cl_mem x_buffer, const size_t x_offset, const size_t x_inc,
+                        cl_command_queue* queue, cl_event* event) {
+  auto status = clblast::Trmv<half>(static_cast<clblast::Layout>(layout),
+                                    static_cast<clblast::Triangle>(triangle),
+                                    static_cast<clblast::Transpose>(a_transpose),
+                                    static_cast<clblast::Diagonal>(diagonal),
+                                    n,
+                                    a_buffer, a_offset, a_ld,
+                                    x_buffer, x_offset, x_inc,
+                                    queue, event);
+  return static_cast<StatusCode>(status);
+}
 
 // TBMV
 StatusCode CLBlastStbmv(const Layout layout, const Triangle triangle, const Transpose a_transpose, const Diagonal diagonal,
@@ -1280,6 +1390,21 @@ StatusCode CLBlastZtbmv(const Layout layout, const Triangle triangle, const Tran
                                        queue, event);
   return static_cast<StatusCode>(status);
 }
+StatusCode CLBlastHtbmv(const Layout layout, const Triangle triangle, const Transpose a_transpose, const Diagonal diagonal,
+                        const size_t n, const size_t k,
+                        const cl_mem a_buffer, const size_t a_offset, const size_t a_ld,
+                        cl_mem x_buffer, const size_t x_offset, const size_t x_inc,
+                        cl_command_queue* queue, cl_event* event) {
+  auto status = clblast::Tbmv<half>(static_cast<clblast::Layout>(layout),
+                                    static_cast<clblast::Triangle>(triangle),
+                                    static_cast<clblast::Transpose>(a_transpose),
+                                    static_cast<clblast::Diagonal>(diagonal),
+                                    n, k,
+                                    a_buffer, a_offset, a_ld,
+                                    x_buffer, x_offset, x_inc,
+                                    queue, event);
+  return static_cast<StatusCode>(status);
+}
 
 // TPMV
 StatusCode CLBlastStpmv(const Layout layout, const Triangle triangle, const Transpose a_transpose, const Diagonal diagonal,
@@ -1342,6 +1467,21 @@ StatusCode CLBlastZtpmv(const Layout layout, const Triangle triangle, const Tran
                                        queue, event);
   return static_cast<StatusCode>(status);
 }
+StatusCode CLBlastHtpmv(const Layout layout, const Triangle triangle, const Transpose a_transpose, const Diagonal diagonal,
+                        const size_t n,
+                        const cl_mem ap_buffer, const size_t ap_offset,
+                        cl_mem x_buffer, const size_t x_offset, const size_t x_inc,
+                        cl_command_queue* queue, cl_event* event) {
+  auto status = clblast::Tpmv<half>(static_cast<clblast::Layout>(layout),
+                                    static_cast<clblast::Triangle>(triangle),
+                                    static_cast<clblast::Transpose>(a_transpose),
+                                    static_cast<clblast::Diagonal>(diagonal),
+                                    n,
+                                    ap_buffer, ap_offset,
+                                    x_buffer, x_offset, x_inc,
+                                    queue, event);
+  return static_cast<StatusCode>(status);
+}
 
 // TRSV
 StatusCode CLBlastStrsv(const Layout layout, const Triangle triangle, const Transpose a_transpose, const Diagonal diagonal,
diff --git a/src/routines/level2/xgbmv.cc b/src/routines/level2/xgbmv.cc
index f90e26b2..7a30c34a 100644
--- a/src/routines/level2/xgbmv.cc
+++ b/src/routines/level2/xgbmv.cc
@@ -58,6 +58,7 @@ StatusCode Xgbmv<T>::DoGbmv(const Layout layout, const Transpose a_transpose,
 // =================================================================================================
 
 // Compiles the templated class
+template class Xgbmv<half>;
 template class Xgbmv<float>;
 template class Xgbmv<double>;
 template class Xgbmv<float2>;
diff --git a/src/routines/level2/xgemv.cc b/src/routines/level2/xgemv.cc
index 4d6437a2..71839e96 100644
--- a/src/routines/level2/xgemv.cc
+++ b/src/routines/level2/xgemv.cc
@@ -20,6 +20,7 @@ namespace clblast {
 // =================================================================================================
 
 // Specific implementations to get the memory-type based on a template argument
+template <> const Precision Xgemv<half>::precision_ = Precision::kHalf;
 template <> const Precision Xgemv<float>::precision_ = Precision::kSingle;
 template <> const Precision Xgemv<double>::precision_ = Precision::kDouble;
 template <> const Precision Xgemv<float2>::precision_ = Precision::kComplexSingle;
@@ -179,6 +180,7 @@ StatusCode Xgemv<T>::MatVec(const Layout layout, const Transpose a_transpose,
 // =================================================================================================
 
 // Compiles the templated class
+template class Xgemv<half>;
 template class Xgemv<float>;
 template class Xgemv<double>;
 template class Xgemv<float2>;
diff --git a/src/routines/level2/xsbmv.cc b/src/routines/level2/xsbmv.cc
index bc82c88d..66ba74e8 100644
--- a/src/routines/level2/xsbmv.cc
+++ b/src/routines/level2/xsbmv.cc
@@ -57,6 +57,7 @@ StatusCode Xsbmv<T>::DoSbmv(const Layout layout, const Triangle triangle,
 // =================================================================================================
 
 // Compiles the templated class
+template class Xsbmv<half>;
 template class Xsbmv<float>;
 template class Xsbmv<double>;
 
diff --git a/src/routines/level2/xspmv.cc b/src/routines/level2/xspmv.cc
index 6e00dcfa..589a97d4 100644
--- a/src/routines/level2/xspmv.cc
+++ b/src/routines/level2/xspmv.cc
@@ -57,6 +57,7 @@ StatusCode Xspmv<T>::DoSpmv(const Layout layout, const Triangle triangle,
 // =================================================================================================
 
 // Compiles the templated class
+template class Xspmv<half>;
 template class Xspmv<float>;
 template class Xspmv<double>;
 
diff --git a/src/routines/level2/xsymv.cc b/src/routines/level2/xsymv.cc
index a9eb284f..2a404a8a 100644
--- a/src/routines/level2/xsymv.cc
+++ b/src/routines/level2/xsymv.cc
@@ -57,6 +57,7 @@ StatusCode Xsymv<T>::DoSymv(const Layout layout, const Triangle triangle,
 // =================================================================================================
 
 // Compiles the templated class
+template class Xsymv<half>;
 template class Xsymv<float>;
 template class Xsymv<double>;
 
diff --git a/src/routines/level2/xtbmv.cc b/src/routines/level2/xtbmv.cc
index 47371c87..86e28dfb 100644
--- a/src/routines/level2/xtbmv.cc
+++ b/src/routines/level2/xtbmv.cc
@@ -72,6 +72,7 @@ StatusCode Xtbmv<T>::DoTbmv(const Layout layout, const Triangle triangle,
 // =================================================================================================
 
 // Compiles the templated class
+template class Xtbmv<half>;
 template class Xtbmv<float>;
 template class Xtbmv<double>;
 template class Xtbmv<float2>;
diff --git a/src/routines/level2/xtpmv.cc b/src/routines/level2/xtpmv.cc
index c63cb9b2..72445547 100644
--- a/src/routines/level2/xtpmv.cc
+++ b/src/routines/level2/xtpmv.cc
@@ -72,6 +72,7 @@ StatusCode Xtpmv<T>::DoTpmv(const Layout layout, const Triangle triangle,
 // =================================================================================================
 
 // Compiles the templated class
+template class Xtpmv<half>;
 template class Xtpmv<float>;
 template class Xtpmv<double>;
 template class Xtpmv<float2>;
diff --git a/src/routines/level2/xtrmv.cc b/src/routines/level2/xtrmv.cc
index 9111d41d..df6f85a3 100644
--- a/src/routines/level2/xtrmv.cc
+++ b/src/routines/level2/xtrmv.cc
@@ -72,6 +72,7 @@ StatusCode Xtrmv<T>::DoTrmv(const Layout layout, const Triangle triangle,
 // =================================================================================================
 
 // Compiles the templated class
+template class Xtrmv<half>;
 template class Xtrmv<float>;
 template class Xtrmv<double>;
 template class Xtrmv<float2>;