--- /dev/null
+/***************************************************************************
+Copyright (c) 2013, The OpenBLAS Project
+All rights reserved.
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are
+met:
+1. Redistributions of source code must retain the above copyright
+notice, this list of conditions and the following disclaimer.
+2. Redistributions in binary form must reproduce the above copyright
+notice, this list of conditions and the following disclaimer in
+the documentation and/or other materials provided with the
+distribution.
+3. Neither the name of the OpenBLAS project nor the names of
+its contributors may be used to endorse or promote products
+derived from this software without specific prior written permission.
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE OPENBLAS PROJECT OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE
+USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*****************************************************************************/
+
+/**************************************************************************************
+* 2013/11/14 Saar
+* BLASTEST : OK
+* CTEST : OK
+* TEST : OK
+*
+**************************************************************************************/
+
+#define ASSEMBLER
+#include "common.h"
+
+#define STACKSIZE 256
+
+#define OLD_INC_X [fp, #0 ]
+#define OLD_Y [fp, #4 ]
+#define OLD_INC_Y [fp, #8 ]
+
+
+#define N r0
+#define Y r1
+#define INC_X r2
+#define X r3
+#define INC_Y r4
+
+#define I r12
+
+#define X_PRE 512
+
+/**************************************************************************************
+* Macro definitions
+**************************************************************************************/
+
+/*****************************************************************************************/
+
+
+
+#if !defined(COMPLEX)
+
+#if defined(DOUBLE)
+
+.macro KERNEL_F4
+
+ pld [ X, #X_PRE ]
+ pld [ Y, #X_PRE ]
+ fldmiad X, { d0 - d3 }
+ fldmiad Y, { d4 - d7 }
+ fstmiad Y!, { d0 - d3 }
+ fstmiad X!, { d4 - d7}
+
+.endm
+
+
+.macro KERNEL_F1
+
+ fldmiad X, { d0 }
+ fldmiad Y, { d4 }
+ fstmiad Y!, { d0 }
+ fstmiad X!, { d4 }
+
+.endm
+
+.macro KERNEL_S1
+
+ fldmiad X, { d0 }
+ fldmiad Y, { d4 }
+ fstmiad Y, { d0 }
+ fstmiad X, { d4 }
+ add X, X, INC_X
+ add Y, Y, INC_Y
+
+.endm
+
+#else
+
+.macro KERNEL_F4
+
+ fldmias X, { s0 - s3 }
+ fldmias Y, { s4 - s7 }
+ fstmias Y!, { s0 - s3 }
+ fstmias X!, { s4 - s7}
+
+.endm
+
+
+.macro KERNEL_F1
+
+ fldmias X, { s0 }
+ fldmias Y, { s4 }
+ fstmias Y!, { s0 }
+ fstmias X!, { s4 }
+
+.endm
+
+.macro KERNEL_S1
+
+ fldmias X, { s0 }
+ fldmias Y, { s4 }
+ fstmias Y, { s0 }
+ fstmias X, { s4 }
+ add X, X, INC_X
+ add Y, Y, INC_Y
+
+.endm
+
+
+#endif
+
+#else
+
+#if defined(DOUBLE)
+
+.macro KERNEL_F4
+
+ pld [ X, #X_PRE ]
+ pld [ Y, #X_PRE ]
+ fldmiad X, { d0 - d3 }
+ fldmiad Y, { d4 - d7 }
+ fstmiad Y!, { d0 - d3 }
+ fstmiad X!, { d4 - d7}
+
+ pld [ X, #X_PRE ]
+ pld [ Y, #X_PRE ]
+ fldmiad X, { d0 - d3 }
+ fldmiad Y, { d4 - d7 }
+ fstmiad Y!, { d0 - d3 }
+ fstmiad X!, { d4 - d7}
+
+.endm
+
+.macro KERNEL_F1
+
+ fldmiad X, { d0 - d1 }
+ fldmiad Y, { d4 - d5 }
+ fstmiad Y!, { d0 - d1 }
+ fstmiad X!, { d4 - d5 }
+
+.endm
+
+.macro KERNEL_S1
+
+ fldmiad X, { d0 - d1 }
+ fldmiad Y, { d4 - d5 }
+ fstmiad Y, { d0 - d1 }
+ fstmiad X, { d4 - d5 }
+ add X, X, INC_X
+ add Y, Y, INC_Y
+
+.endm
+
+
+#else
+
+.macro KERNEL_F4
+
+ pld [ X, #X_PRE ]
+ pld [ Y, #X_PRE ]
+ fldmias X, { s0 - s3 }
+ fldmias Y, { s4 - s7 }
+ fstmias Y!, { s0 - s3 }
+ fstmias X!, { s4 - s7}
+
+ fldmias X, { s0 - s3 }
+ fldmias Y, { s4 - s7 }
+ fstmias Y!, { s0 - s3 }
+ fstmias X!, { s4 - s7}
+
+.endm
+
+.macro KERNEL_F1
+
+ fldmias X, { s0 - s1 }
+ fldmias Y, { s4 - s5 }
+ fstmias Y!, { s0 - s1 }
+ fstmias X!, { s4 - s5 }
+
+.endm
+
+.macro KERNEL_S1
+
+ fldmias X, { s0 - s1 }
+ fldmias Y, { s4 - s5 }
+ fstmias Y, { s0 - s1 }
+ fstmias X, { s4 - s5 }
+ add X, X, INC_X
+ add Y, Y, INC_Y
+
+.endm
+
+
+
+#endif
+
+#endif
+
+/**************************************************************************************
+* End of macro definitions
+**************************************************************************************/
+
+ PROLOGUE
+
+ .align 5
+ push {r4 , fp}
+ add fp, sp, #8
+
+ ldr INC_X , OLD_INC_X
+ ldr Y, OLD_Y
+ ldr INC_Y , OLD_INC_Y
+
+
+ cmp N, #0
+ ble swap_kernel_L999
+
+ cmp INC_X, #0
+ beq swap_kernel_L999
+
+ cmp INC_Y, #0
+ beq swap_kernel_L999
+
+ cmp INC_X, #1
+ bne swap_kernel_S_BEGIN
+
+ cmp INC_Y, #1
+ bne swap_kernel_S_BEGIN
+
+
+swap_kernel_F_BEGIN:
+
+
+ asrs I, N, #2 // I = N / 4
+ ble swap_kernel_F1
+
+ .align 5
+
+swap_kernel_F4:
+
+#if !defined(COMPLEX) && !defined(DOUBLE)
+ pld [ X, #X_PRE ]
+ pld [ Y, #X_PRE ]
+#endif
+
+ KERNEL_F4
+
+ subs I, I, #1
+ ble swap_kernel_F1
+
+ KERNEL_F4
+
+ subs I, I, #1
+ bne swap_kernel_F4
+
+swap_kernel_F1:
+
+ ands I, N, #3
+ ble swap_kernel_L999
+
+swap_kernel_F10:
+
+ KERNEL_F1
+
+ subs I, I, #1
+ bne swap_kernel_F10
+
+ b swap_kernel_L999
+
+swap_kernel_S_BEGIN:
+
+#if defined(COMPLEX)
+
+#if defined(DOUBLE)
+ lsl INC_X, INC_X, #4 // INC_X * SIZE * 2
+ lsl INC_Y, INC_Y, #4 // INC_Y * SIZE * 2
+#else
+ lsl INC_X, INC_X, #3 // INC_X * SIZE * 2
+ lsl INC_Y, INC_Y, #3 // INC_Y * SIZE * 2
+#endif
+
+#else
+
+#if defined(DOUBLE)
+ lsl INC_X, INC_X, #3 // INC_X * SIZE
+ lsl INC_Y, INC_Y, #3 // INC_Y * SIZE
+#else
+ lsl INC_X, INC_X, #2 // INC_X * SIZE
+ lsl INC_Y, INC_Y, #2 // INC_Y * SIZE
+#endif
+
+#endif
+
+
+ asrs I, N, #2 // I = N / 4
+ ble swap_kernel_S1
+
+ .align 5
+
+swap_kernel_S4:
+
+ KERNEL_S1
+ KERNEL_S1
+ KERNEL_S1
+ KERNEL_S1
+
+ subs I, I, #1
+ bne swap_kernel_S4
+
+swap_kernel_S1:
+
+ ands I, N, #3
+ ble swap_kernel_L999
+
+swap_kernel_S10:
+
+ KERNEL_S1
+
+ subs I, I, #1
+ bne swap_kernel_S10
+
+
+swap_kernel_L999:
+
+ mov r0, #0 // set return value
+
+ sub sp, fp, #8
+ pop {r4,fp}
+ bx lr
+
+ EPILOGUE
+