1 /***************************************************************************
2 Copyright (c) 2013, The OpenBLAS Project
4 Redistribution and use in source and binary forms, with or without
5 modification, are permitted provided that the following conditions are
7 1. Redistributions of source code must retain the above copyright
8 notice, this list of conditions and the following disclaimer.
9 2. Redistributions in binary form must reproduce the above copyright
10 notice, this list of conditions and the following disclaimer in
11 the documentation and/or other materials provided with the
13 3. Neither the name of the OpenBLAS project nor the names of
14 its contributors may be used to endorse or promote products
15 derived from this software without specific prior written permission.
16 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
17 AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
18 IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
19 ARE DISCLAIMED. IN NO EVENT SHALL THE OPENBLAS PROJECT OR CONTRIBUTORS BE
20 LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
21 DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
22 SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
23 CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
24 OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE
25 USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
26 *****************************************************************************/
28 /**************************************************************************************
34 **************************************************************************************/
47 /******************************************************
48 * [fp, #-128] - [fp, #-64] is reserved
49 * for store and restore of floating point
51 *******************************************************/
53 #define OLD_INC_Y [fp, #4 ]
61 /**************************************************************************************
63 **************************************************************************************/
70 fldmias X!, { s4 - s5 }
71 fldmias Y!, { s8 - s9 }
74 fldmias X!, { s6 - s7 }
78 fldmias Y!, { s10 - s11 }
85 fldmias X!, { s4 - s5 }
86 fldmias Y!, { s8 - s9 }
89 fldmias X!, { s6 - s7 }
93 fldmias Y!, { s10 - s11 }
103 fldmias X!, { s4 - s5 }
104 fldmias Y!, { s8 - s9 }
113 /*************************************************************************************************************************/
119 fldmias X, { s4 - s5 }
120 fldmias Y, { s8 - s9 }
128 fldmias X, { s4 - s5 }
129 fldmias Y, { s8 - s9 }
137 fldmias X, { s4 - s5 }
138 fldmias Y, { s8 - s9 }
146 fldmias X, { s4 - s5 }
147 fldmias Y, { s8 - s9 }
160 fldmias X, { s4 - s5 }
161 fldmias Y, { s8 - s9 }
173 /**************************************************************************************
174 * End of macro definitions
175 **************************************************************************************/
183 sub sp, sp, #STACKSIZE // reserve stack
186 vstm r4, { s8 - s15} // store floating point registers
188 movs r4, #0 // clear floating point register
207 bne cdot_kernel_S_BEGIN
210 bne cdot_kernel_S_BEGIN
214 asrs I, N, #2 // I = N / 4
240 lsl INC_X, INC_X, #3 // INC_X * SIZE * 2
241 lsl INC_Y, INC_Y, #3 // INC_Y * SIZE * 2
243 asrs I, N, #2 // I = N / 4
270 vldm r3, { s8 - s15} // restore floating point registers