605df8d674
On POWER8 (ISA 2.07) lxvx and stxvx are defined to be extended mnemonics of lxvd2x and stxvd2x. For POWER9 (ISA 3.0) the HW architects in their infinite wisdom made lxvx and stxvx instructions in their own right. POWER9 aware GCC will use the POWER9 instruction for lxvx and stxvx causing these selftests to fail on POWER8. Further compounding the issue, because of the way -mvsx works it will cause the power9 instructions to be used regardless of -mcpu=power8 to GCC or -mpower8 to AS. The safest way to address the problem for now is to not use the extended mnemonic. We don't care how the CPU loads the values from memory since the tests only performs register comparisons, so using stdvd2x/lxvd2x does not impact the test. Signed-off-by: Cyril Bur <cyrilbur@gmail.com> Acked-by: Balbir Singh<bsingharora@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
72 lines
1.4 KiB
C
72 lines
1.4 KiB
C
/*
|
|
* Copyright 2015, Cyril Bur, IBM Corp.
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public License
|
|
* as published by the Free Software Foundation; either version
|
|
* 2 of the License, or (at your option) any later version.
|
|
*/
|
|
|
|
#include "basic_asm.h"
|
|
|
|
/*
|
|
* Careful this will 'clobber' vsx (by design), VSX are always
|
|
* volatile though so unlike vmx this isn't so much of an issue
|
|
* Still should avoid calling from C
|
|
*/
|
|
FUNC_START(load_vsx)
|
|
li r5,0
|
|
lxvd2x vs20,r5,r3
|
|
addi r5,r5,16
|
|
lxvd2x vs21,r5,r3
|
|
addi r5,r5,16
|
|
lxvd2x vs22,r5,r3
|
|
addi r5,r5,16
|
|
lxvd2x vs23,r5,r3
|
|
addi r5,r5,16
|
|
lxvd2x vs24,r5,r3
|
|
addi r5,r5,16
|
|
lxvd2x vs25,r5,r3
|
|
addi r5,r5,16
|
|
lxvd2x vs26,r5,r3
|
|
addi r5,r5,16
|
|
lxvd2x vs27,r5,r3
|
|
addi r5,r5,16
|
|
lxvd2x vs28,r5,r3
|
|
addi r5,r5,16
|
|
lxvd2x vs29,r5,r3
|
|
addi r5,r5,16
|
|
lxvd2x vs30,r5,r3
|
|
addi r5,r5,16
|
|
lxvd2x vs31,r5,r3
|
|
blr
|
|
FUNC_END(load_vsx)
|
|
|
|
FUNC_START(store_vsx)
|
|
li r5,0
|
|
stxvd2x vs20,r5,r3
|
|
addi r5,r5,16
|
|
stxvd2x vs21,r5,r3
|
|
addi r5,r5,16
|
|
stxvd2x vs22,r5,r3
|
|
addi r5,r5,16
|
|
stxvd2x vs23,r5,r3
|
|
addi r5,r5,16
|
|
stxvd2x vs24,r5,r3
|
|
addi r5,r5,16
|
|
stxvd2x vs25,r5,r3
|
|
addi r5,r5,16
|
|
stxvd2x vs26,r5,r3
|
|
addi r5,r5,16
|
|
stxvd2x vs27,r5,r3
|
|
addi r5,r5,16
|
|
stxvd2x vs28,r5,r3
|
|
addi r5,r5,16
|
|
stxvd2x vs29,r5,r3
|
|
addi r5,r5,16
|
|
stxvd2x vs30,r5,r3
|
|
addi r5,r5,16
|
|
stxvd2x vs31,r5,r3
|
|
blr
|
|
FUNC_END(store_vsx)
|