atlas/atlas.3.10.2-add_power8_cpu.patch
2015-11-26 17:13:02 +01:00

132 lines
6.2 KiB
Diff

From: Michel Normand <normand@linux.vnet.ibm.com>
Subject: atlas.3.10.2 add power8 cpu
Date: Thu, 18 Sep 2014 15:13:24 +0200
atlas.3.10.2 add Power8 cpu
tracked upstream by issue 67
https://sourceforge.net/p/math-atlas/patches/67/
Signed-off-by: Michel Normand <normand@linux.vnet.ibm.com>
---
CONFIG/ARCHS/Make.ext | 7 +++++++
CONFIG/include/atlconf.h | 6 +++---
CONFIG/src/atlcomp.txt | 6 ++++++
CONFIG/src/backend/archinfo_aix.c | 2 ++
CONFIG/src/backend/archinfo_linux.c | 1 +
include/atlas_pca.h | 2 +-
6 files changed, 20 insertions(+), 4 deletions(-)
Index: ATLAS/CONFIG/ARCHS/Make.ext
===================================================================
--- ATLAS.orig/CONFIG/ARCHS/Make.ext
+++ ATLAS/CONFIG/ARCHS/Make.ext
@@ -33,6 +33,7 @@ files = AMD64K10h32SSE3.tar.bz2 AMD64K10
MIPSR1xK64.tar.bz2 Makefile P432SSE2.tar.bz2 P4E32SSE3.tar.bz2 \
P4E64SSE3.tar.bz2 PIII32SSE1.tar.bz2 POWER432.tar.bz2 \
POWER464.tar.bz2 POWER564.tar.bz2 POWER764VSX.tar.bz2 \
+ POWER864VSX.tar.bz2 \
PPCG432AltiVec.tar.bz2 PPCG532AltiVec.tar.bz2 PPCG564AltiVec.tar.bz2 \
PPRO32.tar.bz2 USIII32.tar.bz2 USIII64.tar.bz2 USIV32.tar.bz2 \
USIV64.tar.bz2 UST232.tar.bz2 UST264.tar.bz2 atlas_test1.1.3.tar.bz2 \
@@ -308,6 +309,12 @@ POWER764VSX.tar.bz2 : $(basdr)/POWER764V
/tmp/POWER764VSX.tar POWER764VSX
bzip2 /tmp/POWER764VSX.tar
mv /tmp/POWER764VSX.tar.bz2 ./.
+POWER864VSX.tar.bz2 : $(basdr)/POWER864VSX
+ - rm -f /tmp/POWER864VSX.tar /tmp/POWER864VSX.tar.bz2
+ cd $(basdr) ; tar --dereference --exclude 'CVS' -c -f \
+ /tmp/POWER864VSX.tar POWER864VSX
+ bzip2 /tmp/POWER864VSX.tar
+ mv /tmp/POWER864VSX.tar.bz2 ./.
IBMz1032.tar.bz2 : $(basdr)/IBMz1032
- rm -f /tmp/IBMz1032.tar /tmp/IBMz1032.tar.bz2
cd $(basdr) ; tar --dereference --exclude 'CVS' -c -f \
Index: ATLAS/CONFIG/include/atlconf.h
===================================================================
--- ATLAS.orig/CONFIG/include/atlconf.h
+++ ATLAS/CONFIG/include/atlconf.h
@@ -18,10 +18,10 @@ enum OSTYPE {OSOther=0, OSLinux, OSSunOS
enum ARCHFAM {AFOther=0, AFPPC, AFSPARC, AFALPHA, AFX86, AFIA64, AFMIPS,
AFARM, AFS390};
-#define NMACH 52
+#define NMACH 53
static char *machnam[NMACH] =
{"UNKNOWN", "POWER3", "POWER4", "POWER5", "PPCG4", "PPCG5",
- "POWER6", "POWER7", "POWERe6500", "IBMz9", "IBMz10", "IBMz196",
+ "POWER6", "POWER7", "POWER8", "POWERe6500", "IBMz9", "IBMz10", "IBMz196",
"x86x87", "x86SSE1", "x86SSE2", "x86SSE3",
"P5", "P5MMX", "PPRO", "PII", "PIII", "PM", "CoreSolo",
"CoreDuo", "Core2Solo", "Core2", "Corei1", "Corei2", "Corei3",
@@ -31,7 +31,7 @@ static char *machnam[NMACH] =
"USI", "USII", "USIII", "USIV", "UST1", "UST2", "UnknownUS",
"MIPSR1xK", "MIPSICE9", "ARMv7"};
enum MACHTYPE {MACHOther, IbmPwr3, IbmPwr4, IbmPwr5, PPCG4, PPCG5,
- IbmPwr6, IbmPwr7, Pwre6500,
+ IbmPwr6, IbmPwr7, IbmPwr8, Pwre6500,
IbmZ9, IbmZ10, IbmZ196, /* s390(x) in Linux */
x86x87, x86SSE1, x86SSE2, x86SSE3, /* generic targets */
IntP5, IntP5MMX, IntPPRO, IntPII, IntPIII, IntPM, IntCoreS,
Index: ATLAS/CONFIG/src/atlcomp.txt
===================================================================
--- ATLAS.orig/CONFIG/src/atlcomp.txt
+++ ATLAS/CONFIG/src/atlcomp.txt
@@ -190,6 +190,10 @@ MACH=PPCG5 OS=ALL LVL=1000 COMPS=dmc,icc
'gcc' '-mpowerpc64 -maltivec -mabi=altivec -mcpu=970 -mtune=970 -O2'
MACH=PPCG5 OS=ALL LVL=1000 COMPS=skc
'gcc' '-mpowerpc64 -maltivec -mabi=altivec -mcpu=970 -mtune=970 -O2 -mvrsave'
+MACH=POWER8 OS=ALL LVL=1010 COMPS=icc,smc,dmc,skc,dkc,xcc,gcc
+ 'gcc' '-O2 -mvsx -mcpu=power8 -mtune=power8 -m64 -mvrsave -funroll-all-loops'
+MACH=POWER8 OS=ALL LVL=1010 COMPS=f77
+ 'gfortran' '-O2 -mvsx -mcpu=power8 -mtune=power8 -m64 -mvrsave -funroll-all-loops'
MACH=POWER7 OS=ALL LVL=1010 COMPS=icc,smc,dmc,skc,dkc,xcc,gcc
'gcc' '-O2 -mvsx -mcpu=power7 -mtune=power7 -m64 -mvrsave -funroll-all-loops'
MACH=POWER7 OS=ALL LVL=1010 COMPS=f77
@@ -210,6 +214,8 @@ MACH=POWER4 OS=ALL LVL=1010 COMPS=icc,dm
'gcc' '-mcpu=power4 -mtune=power4 -O3 -fno-schedule-insns -fno-rerun-loop-opt'
MACH=POWER4 OS=ALL LVL=1010 COMPS=f77
'xlf' '-qtune=pwr4 -qarch=pwr4 -O3 -qmaxmem=-1 -qfloat=hsflt'
+MACH=POWER8 OS=ALL LVL=1010 COMPS=f77
+ 'xlf' '-qtune=pwr8 -qarch=pwr8 -O3 -qmaxmem=-1 -qfloat=hsflt'
#
# IBM System z or zEnterprise.
# These compiler flags given by IBM; -O3 -funroll-loops are chosen because
Index: ATLAS/CONFIG/src/backend/archinfo_linux.c
===================================================================
--- ATLAS.orig/CONFIG/src/backend/archinfo_linux.c
+++ ATLAS/CONFIG/src/backend/archinfo_linux.c
@@ -77,6 +77,7 @@ enum MACHTYPE ProbeArch()
else if (strstr(res, "7455")) mach = PPCG4;
else if (strstr(res, "PPC970FX")) mach = PPCG5;
else if (strstr(res, "PPC970MP")) mach = PPCG5;
+ else if (strstr(res, "POWER8")) mach = IbmPwr8;
else if (strstr(res, "POWER7")) mach = IbmPwr7;
else if (strstr(res, "POWER6")) mach = IbmPwr6;
else if (strstr(res, "POWER5")) mach = IbmPwr5;
Index: ATLAS/include/atlas_pca.h
===================================================================
--- ATLAS.orig/include/atlas_pca.h
+++ ATLAS/include/atlas_pca.h
@@ -26,7 +26,7 @@
#endif
#elif defined(ATL_ARCH_POWER3) || defined(ATL_ARCH_POWER4) || \
defined(ATL_ARCH_POWER5) || defined(ATL_ARCH_POWER6) || \
- defined(ATL_ARCH_POWER7)
+ defined(ATL_ARCH_POWER7) || defined(ATL_ARCH_POWER8)
#ifdef __GNUC__
#define ATL_membarrier __asm__ __volatile__ ("dcs")
/* #define ATL_USEPCA 1 */
Index: ATLAS/CONFIG/src/backend/archinfo_aix.c
===================================================================
--- ATLAS.orig/CONFIG/src/backend/archinfo_aix.c
+++ ATLAS/CONFIG/src/backend/archinfo_aix.c
@@ -67,6 +67,8 @@ enum MACHTYPE ProbeArch()
{
if (strstr(res, "PowerPC_POWER5"))
mach = IbmPwr5;
+ else if (strstr(res, "PowerPC_POWER8"))
+ mach = IbmPwr8;
else if (strstr(res, "PowerPC_POWER7"))
mach = IbmPwr7;
else if (strstr(res, "PowerPC_POWER6"))