Compare commits
21 Commits
Author | SHA1 | Date | |
---|---|---|---|
|
709845b89e | ||
|
7268b7aa10 | ||
|
63d75114da | ||
|
9561fa26c1 | ||
|
1fb89d180f | ||
|
f128eda788 | ||
|
17da750ef6 | ||
|
4d0e90e529 | ||
|
202c1937a9 | ||
|
68ac25ef42 | ||
|
298208165a | ||
|
1a2f01f0f0 | ||
|
35e303b80a | ||
|
6af83c0231 | ||
|
8888d79619 | ||
|
d03b304c5a | ||
|
76d4dba820 | ||
|
13262e006a | ||
|
f086598d07 | ||
|
5b8ceef1ab | ||
|
c7f12adc64 |
1
.gitignore
vendored
1
.gitignore
vendored
@ -9,3 +9,4 @@ K7323DNow.tgz
|
|||||||
/ARMv732NEON.tar.bz2
|
/ARMv732NEON.tar.bz2
|
||||||
/lapack-3.5.0.tgz
|
/lapack-3.5.0.tgz
|
||||||
/atlas3.10.2.tar.bz2
|
/atlas3.10.2.tar.bz2
|
||||||
|
/POWER864LEVSXp4.tar.bz2
|
||||||
|
32
atlas-new_archdef_for_ppc64le.patch
Normal file
32
atlas-new_archdef_for_ppc64le.patch
Normal file
@ -0,0 +1,32 @@
|
|||||||
|
Subject: atlas new archdef for ppc64le
|
||||||
|
From: Michel Normand <normand@linux.vnet.ibm.com>
|
||||||
|
Date: Sun, 13 Jun 2014 18:02:47 +0200
|
||||||
|
|
||||||
|
Need to define different archdef names
|
||||||
|
for ppc64 (that is Big Endian) and ppc64le (that is Little Endian).
|
||||||
|
This is already done upstream in atlas 3.11.30 with issue
|
||||||
|
https://sourceforge.net/p/math-atlas/patches/66/
|
||||||
|
|
||||||
|
Required at least as long as I need the bypass of
|
||||||
|
atlas.3.10.2-ppc64le_do_not_use_files_with_lvx.patch
|
||||||
|
|
||||||
|
Signed-off-by: Michel Normand <normand@linux.vnet.ibm.com>
|
||||||
|
---
|
||||||
|
CONFIG/src/SpewMakeInc.c | 4 ++++
|
||||||
|
1 file changed, 4 insertions(+)
|
||||||
|
|
||||||
|
Index: ATLAS/CONFIG/src/SpewMakeInc.c
|
||||||
|
===================================================================
|
||||||
|
--- ATLAS.orig/CONFIG/src/SpewMakeInc.c
|
||||||
|
+++ ATLAS/CONFIG/src/SpewMakeInc.c
|
||||||
|
@@ -542,6 +542,10 @@ int main(int nargs, char **args)
|
||||||
|
fprintf(fpout, "# -------------------------------------------------\n");
|
||||||
|
fprintf(fpout, " ARCH = %s", machnam[mach]);
|
||||||
|
fprintf(fpout, "%d", ptrbits);
|
||||||
|
+ /* for ppc64le archi add 'LE' characters */
|
||||||
|
+ #if defined(__powerpc64__) && (__BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__)
|
||||||
|
+ fprintf(fpout, "%s", "LE");
|
||||||
|
+ #endif
|
||||||
|
if (ISAX)
|
||||||
|
fprintf(fpout, "%s", ISAXNAM[ISAX]);
|
||||||
|
if (!USEIEEE)
|
@ -20,12 +20,12 @@ index ab1eb9963d36678972a0a410905169aaa563dc64..27c6e316b442e09b0f46afac7940aaa1
|
|||||||
DYNlibs = liblapack.so libf77blas.so libcblas.so libatlas.so
|
DYNlibs = liblapack.so libf77blas.so libcblas.so libatlas.so
|
||||||
PTDYNlibs = liblapack.so libptf77blas.so libptcblas.so libatlas.so
|
PTDYNlibs = liblapack.so libptf77blas.so libptcblas.so libatlas.so
|
||||||
CDYNlibs = liblapack.so libcblas.so libatlas.so
|
CDYNlibs = liblapack.so libcblas.so libatlas.so
|
||||||
@@ -116,9 +118,12 @@ LDTRY:
|
@@ -116,9 +116,12 @@ LDTRY:
|
||||||
-rpath-link $(LIBINSTdir) \
|
-rpath-link $(LIBINSTdir) \
|
||||||
--whole-archive $(libas) --no-whole-archive $(LIBS)
|
--whole-archive $(libas) --no-whole-archive $(LIBS)
|
||||||
GCCTRY:
|
GCCTRY:
|
||||||
- $(GOODGCC) -shared -o $(outso) \
|
- $(GOODGCC) -shared -o $(outso) \
|
||||||
- -Wl,"rpath-link $(LIBINSTdir)" \
|
- -Wl,"-rpath-link $(LIBINSTdir)" \
|
||||||
+ $(GOODGCC) -shared -o $(outso).$(so_ver) \
|
+ $(GOODGCC) -shared -o $(outso).$(so_ver) \
|
||||||
+ \
|
+ \
|
||||||
+ -Wl,-soname,"$(outso).$(so_ver_major)" \
|
+ -Wl,-soname,"$(outso).$(so_ver_major)" \
|
||||||
|
131
atlas.3.10.2-add_power8_cpu.patch
Normal file
131
atlas.3.10.2-add_power8_cpu.patch
Normal file
@ -0,0 +1,131 @@
|
|||||||
|
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"))
|
220
atlas.3.10.2-ppc64le_abiv2.patch
Normal file
220
atlas.3.10.2-ppc64le_abiv2.patch
Normal file
@ -0,0 +1,220 @@
|
|||||||
|
From: Michel Normand <normand@linux.vnet.ibm.com>
|
||||||
|
Subject: atlas.3.10.2 ppc64le abiv2 patch
|
||||||
|
Date: Mon, 28 Jul 2014 04:29:05 -0400
|
||||||
|
|
||||||
|
atlas.3.10.2 abiv2 step2 complete the changes already present in atlas 3.10.2
|
||||||
|
* still some files with opd ABI V1 to be disabled for ABI V2
|
||||||
|
tune/blas/gemm/CASES/ATL_dmm4x4x32_ppc.c
|
||||||
|
tune/blas/gemm/CASES/ATL_dmm4x4x80_ppc.c
|
||||||
|
tune/blas/gemm/CASES/ATL_smm4x4x128_av.c
|
||||||
|
|
||||||
|
atlas.3.10.2 ppc64le abiv2 step3
|
||||||
|
* change offsets of parameters read from stack to avoid some segfaults.
|
||||||
|
(values changes 120 => 104 and 128 => 112 identified by gdb investigation)
|
||||||
|
|
||||||
|
Despite this step3 patch there are two Remaining problems for ppc64le archi:
|
||||||
|
* TODO: still have seg-faults in console during build/check
|
||||||
|
but is not critical (without make check) and rpm are generated on fedora.
|
||||||
|
unable to investigate because of problem tracked by issue 950
|
||||||
|
https://sourceforge.net/p/math-atlas/support-requests/950/
|
||||||
|
|
||||||
|
* TODO: make check failure because xsslvtst execution failure
|
||||||
|
related to vector assembly code that assumes big-endian env
|
||||||
|
as written in ATL_cmm4x4x128_av.c and ATL_smm4x4x128_av.c.
|
||||||
|
Would need significant work to support little-endian as per
|
||||||
|
endianess comments of all PowerPC vector instructions in:
|
||||||
|
https://www-01.ibm.com/chips/techlib/techlib.nsf/techdocs/FBFA164F824370F987256D6A006F424D/$file/vector_simd_pem.ppc.2005AUG23.pdf
|
||||||
|
|
||||||
|
Signed-off-by: Michel Normand <normand@linux.vnet.ibm.com>
|
||||||
|
---
|
||||||
|
tune/blas/gemm/CASES/ATL_cmm4x4x128_av.c | 7 +++++++
|
||||||
|
tune/blas/gemm/CASES/ATL_dmm4x4x2pf_av.c | 7 +++++++
|
||||||
|
tune/blas/gemm/CASES/ATL_dmm4x4x32_ppc.c | 9 ++++++++-
|
||||||
|
tune/blas/gemm/CASES/ATL_dmm4x4x80_ppc.c | 20 ++++++++++++++++++--
|
||||||
|
tune/blas/gemm/CASES/ATL_smm4x4x128_av.c | 23 ++++++++++++++++++++++-
|
||||||
|
5 files changed, 62 insertions(+), 4 deletions(-)
|
||||||
|
|
||||||
|
Index: ATLAS/tune/blas/gemm/CASES/ATL_dmm4x4x32_ppc.c
|
||||||
|
===================================================================
|
||||||
|
--- ATLAS.orig/tune/blas/gemm/CASES/ATL_dmm4x4x32_ppc.c
|
||||||
|
+++ ATLAS/tune/blas/gemm/CASES/ATL_dmm4x4x32_ppc.c
|
||||||
|
@@ -268,7 +268,7 @@ Mjoin(.,ATL_USERMM):
|
||||||
|
.globl Mjoin(_,ATL_USERMM)
|
||||||
|
Mjoin(_,ATL_USERMM):
|
||||||
|
#else
|
||||||
|
- #if defined(ATL_USE64BITS)
|
||||||
|
+ #if defined(ATL_USE64BITS) && _CALL_ELF != 2
|
||||||
|
/*
|
||||||
|
* Official Program Descripter section, seg fault w/o it on Linux/PPC64
|
||||||
|
*/
|
||||||
|
@@ -324,8 +324,15 @@ ATL_USERMM:
|
||||||
|
#endif
|
||||||
|
|
||||||
|
#ifdef ATL_USE64BITS
|
||||||
|
+#if _CALL_ELF == 2
|
||||||
|
+/* ABIv2 */
|
||||||
|
+ ld pC0, 104(r1)
|
||||||
|
+ ld incCn, 112(r1)
|
||||||
|
+#else
|
||||||
|
+/* ABIv1 */
|
||||||
|
ld pC0, 120(r1)
|
||||||
|
ld incCn, 128(r1)
|
||||||
|
+#endif
|
||||||
|
#elif defined(ATL_AS_OSX_PPC) || defined(ATL_AS_AIX_PPC)
|
||||||
|
lwz pC0, 68(r1)
|
||||||
|
lwz incCn, 72(r1)
|
||||||
|
Index: ATLAS/tune/blas/gemm/CASES/ATL_dmm4x4x80_ppc.c
|
||||||
|
===================================================================
|
||||||
|
--- ATLAS.orig/tune/blas/gemm/CASES/ATL_dmm4x4x80_ppc.c
|
||||||
|
+++ ATLAS/tune/blas/gemm/CASES/ATL_dmm4x4x80_ppc.c
|
||||||
|
@@ -170,13 +170,21 @@ void ATL_USERMM(const int M, const int N
|
||||||
|
const TYPE beta, TYPE *C, const int ldc)
|
||||||
|
(r10) 8(r1)
|
||||||
|
*******************************************************************************
|
||||||
|
-64 bit ABIs:
|
||||||
|
+64 bit ABIv1s:
|
||||||
|
r3 r4 r5 r6/f1
|
||||||
|
void ATL_USERMM(const int M, const int N, const int K, const TYPE alpha,
|
||||||
|
r7 r8 r9 r10
|
||||||
|
const TYPE *A, const int lda, const TYPE *B, const int ldb,
|
||||||
|
f2 120(r1) 128(r1)
|
||||||
|
const TYPE beta, TYPE *C, const int ldc)
|
||||||
|
+
|
||||||
|
+64 bit ABIv2s:
|
||||||
|
+ r3 r4 r5 r6/f1
|
||||||
|
+void ATL_USERMM(const int M, const int N, const int K, const TYPE alpha,
|
||||||
|
+ r7 r8 r9 r10
|
||||||
|
+ const TYPE *A, const int lda, const TYPE *B, const int ldb,
|
||||||
|
+ f2 104(r1) 112(r1)
|
||||||
|
+ const TYPE beta, TYPE *C, const int ldc)
|
||||||
|
#endif
|
||||||
|
#ifdef ATL_AS_AIX_PPC
|
||||||
|
.csect .text[PR]
|
||||||
|
@@ -202,7 +210,7 @@ Mjoin(.,ATL_USERMM):
|
||||||
|
.globl Mjoin(_,ATL_USERMM)
|
||||||
|
Mjoin(_,ATL_USERMM):
|
||||||
|
#else
|
||||||
|
- #if defined(ATL_USE64BITS)
|
||||||
|
+ #if defined(ATL_USE64BITS) && _CALL_ELF != 2
|
||||||
|
/*
|
||||||
|
* Official Program Descripter section, seg fault w/o it on Linux/PPC64
|
||||||
|
*/
|
||||||
|
@@ -257,9 +265,17 @@ ATL_USERMM:
|
||||||
|
#endif
|
||||||
|
#endif
|
||||||
|
|
||||||
|
+
|
||||||
|
#if defined (ATL_USE64BITS)
|
||||||
|
+#if _CALL_ELF == 2
|
||||||
|
+/* ABIv2 */
|
||||||
|
+ ld pC0, 104(r1)
|
||||||
|
+ ld incCn, 112(r1)
|
||||||
|
+#else
|
||||||
|
+/* ABIv1 */
|
||||||
|
ld pC0, 120(r1)
|
||||||
|
ld incCn, 128(r1)
|
||||||
|
+#endif
|
||||||
|
#elif defined(ATL_AS_OSX_PPC) || defined(ATL_AS_AIX_PPC)
|
||||||
|
lwz pC0, 68(r1)
|
||||||
|
lwz incCn, 72(r1)
|
||||||
|
Index: ATLAS/tune/blas/gemm/CASES/ATL_smm4x4x128_av.c
|
||||||
|
===================================================================
|
||||||
|
--- ATLAS.orig/tune/blas/gemm/CASES/ATL_smm4x4x128_av.c
|
||||||
|
+++ ATLAS/tune/blas/gemm/CASES/ATL_smm4x4x128_av.c
|
||||||
|
@@ -196,7 +196,7 @@ void ATL_USERMM(const int M, const int N
|
||||||
|
.globl Mjoin(_,ATL_USERMM)
|
||||||
|
Mjoin(_,ATL_USERMM):
|
||||||
|
#else
|
||||||
|
- #if defined(ATL_USE64BITS)
|
||||||
|
+ #if defined(ATL_USE64BITS) && _CALL_ELF != 2
|
||||||
|
/*
|
||||||
|
* Official Program Descripter section, seg fault w/o it on Linux/PPC64
|
||||||
|
*/
|
||||||
|
@@ -221,8 +221,15 @@ ATL_USERMM:
|
||||||
|
* kernel instead
|
||||||
|
*/
|
||||||
|
#if defined (ATL_USE64BITS)
|
||||||
|
+#if _CALL_ELF == 2
|
||||||
|
+/* ABIv2 */
|
||||||
|
+ ld r10, 104(r1)
|
||||||
|
+ ld r5, 112(r1)
|
||||||
|
+#else
|
||||||
|
+/* ABIv1 */
|
||||||
|
ld r10, 120(r1)
|
||||||
|
ld r5, 128(r1)
|
||||||
|
+#endif
|
||||||
|
#elif defined(ATL_AS_OSX_PPC)
|
||||||
|
lwz r10, 60(r1)
|
||||||
|
lwz r5, 64(r1)
|
||||||
|
@@ -285,8 +292,15 @@ ATL_USERMM:
|
||||||
|
eqv r0, r0, r0 /* all 1s */
|
||||||
|
ATL_WriteVRSAVE(r0) /* signal we use all vector regs */
|
||||||
|
#if defined (ATL_USE64BITS)
|
||||||
|
+#if _CALL_ELF == 2
|
||||||
|
+ /* ABIv2 */
|
||||||
|
+ ld pC0, FSIZE+104(r1)
|
||||||
|
+ ld ldc, FSIZE+112(r1)
|
||||||
|
+#else
|
||||||
|
+ /* ABIv1 */
|
||||||
|
ld pC0, FSIZE+120(r1)
|
||||||
|
ld ldc, FSIZE+128(r1)
|
||||||
|
+#endif
|
||||||
|
#elif defined(ATL_AS_OSX_PPC)
|
||||||
|
lwz pC0, FSIZE+60(r1)
|
||||||
|
lwz ldc, FSIZE+64(r1)
|
||||||
|
@@ -4258,8 +4272,15 @@ UNALIGNED_C:
|
||||||
|
eqv r0, r0, r0 /* all 1s */
|
||||||
|
ATL_WriteVRSAVE(r0) /* signal we use all vector regs */
|
||||||
|
#if defined (ATL_USE64BITS)
|
||||||
|
+#if _CALL_ELF == 2
|
||||||
|
+ /* ABIv2 */
|
||||||
|
+ ld pC0, FSIZE+104(r1)
|
||||||
|
+ ld ldc, FSIZE+112(r1)
|
||||||
|
+#else
|
||||||
|
+ /* ABIv1 */
|
||||||
|
ld pC0, FSIZE+120(r1)
|
||||||
|
ld ldc, FSIZE+128(r1)
|
||||||
|
+#endif
|
||||||
|
#elif defined(ATL_AS_OSX_PPC)
|
||||||
|
lwz pC0, FSIZE+60(r1)
|
||||||
|
lwz ldc, FSIZE+64(r1)
|
||||||
|
Index: ATLAS/tune/blas/gemm/CASES/ATL_cmm4x4x128_av.c
|
||||||
|
===================================================================
|
||||||
|
--- ATLAS.orig/tune/blas/gemm/CASES/ATL_cmm4x4x128_av.c
|
||||||
|
+++ ATLAS/tune/blas/gemm/CASES/ATL_cmm4x4x128_av.c
|
||||||
|
@@ -258,8 +258,15 @@ ATL_USERMM:
|
||||||
|
eqv r0, r0, r0 /* all 1s */
|
||||||
|
ATL_WriteVRSAVE(r0) /* signal we use all vector regs */
|
||||||
|
#if defined (ATL_USE64BITS)
|
||||||
|
+#if _CALL_ELF == 2
|
||||||
|
+/* ABIv2 */
|
||||||
|
+ ld pC0, FSIZE+104(r1)
|
||||||
|
+ ld ldc, FSIZE+112(r1)
|
||||||
|
+#else
|
||||||
|
+/* ABIv1 */
|
||||||
|
ld pC0, FSIZE+120(r1)
|
||||||
|
ld ldc, FSIZE+128(r1)
|
||||||
|
+#endif
|
||||||
|
#elif defined(ATL_AS_OSX_PPC)
|
||||||
|
lwz pC0, FSIZE+60(r1)
|
||||||
|
lwz ldc, FSIZE+64(r1)
|
||||||
|
Index: ATLAS/tune/blas/gemm/CASES/ATL_dmm4x4x2pf_av.c
|
||||||
|
===================================================================
|
||||||
|
--- ATLAS.orig/tune/blas/gemm/CASES/ATL_dmm4x4x2pf_av.c
|
||||||
|
+++ ATLAS/tune/blas/gemm/CASES/ATL_dmm4x4x2pf_av.c
|
||||||
|
@@ -405,8 +405,15 @@ Mjoin(_,ATL_USERMM):
|
||||||
|
*/
|
||||||
|
#ifdef ATL_GAS_LINUX_PPC
|
||||||
|
#ifdef ATL_USE64BITS
|
||||||
|
+ #if _CALL_ELF == 2
|
||||||
|
+ /* ABIv2 */
|
||||||
|
+ ld pC0, 104(r1)
|
||||||
|
+ ld incCn, 112(r1)
|
||||||
|
+ #else
|
||||||
|
+ /* ABIv1 */
|
||||||
|
ld pC0, 120(r1)
|
||||||
|
ld incCn, 128(r1)
|
||||||
|
+ #endif
|
||||||
|
#else
|
||||||
|
lwz incCn, FSIZE+8(r1)
|
||||||
|
#endif
|
151
atlas.3.10.2-ppc64le_do_not_use_files_with_lvx.patch
Normal file
151
atlas.3.10.2-ppc64le_do_not_use_files_with_lvx.patch
Normal file
@ -0,0 +1,151 @@
|
|||||||
|
From: Michel Normand <normand@linux.vnet.ibm.com>
|
||||||
|
Subject: atlas.3.10.2 ppc64le do not use files with lvx
|
||||||
|
Date: Tue, 12 Aug 2014 16:07:06 +0200
|
||||||
|
|
||||||
|
ppc64le do not use files with lvx
|
||||||
|
This is a temporary patch as long as the related files
|
||||||
|
are not ported yet to ppc64 little-endian.
|
||||||
|
|
||||||
|
Warning: patch to be applied only for ppc64le architecture
|
||||||
|
and will also need atlas-new_archdef_for_ppc64le.patch
|
||||||
|
|
||||||
|
Signed-off-by: Michel Normand <normand@linux.vnet.ibm.com>
|
||||||
|
---
|
||||||
|
tune/blas/gemm/CASES/ccases.flg | 6 +-----
|
||||||
|
tune/blas/gemm/CASES/dcases.flg | 8 +-------
|
||||||
|
tune/blas/gemm/CASES/dcases.vnb | 4 ----
|
||||||
|
tune/blas/gemm/CASES/scases.flg | 9 +--------
|
||||||
|
tune/blas/gemm/CASES/scases.vnb | 3 ---
|
||||||
|
tune/blas/gemm/CASES/zcases.flg | 8 +-------
|
||||||
|
6 files changed, 4 insertions(+), 34 deletions(-)
|
||||||
|
|
||||||
|
Index: ATLAS/tune/blas/gemm/CASES/ccases.flg
|
||||||
|
===================================================================
|
||||||
|
--- ATLAS.orig/tune/blas/gemm/CASES/ccases.flg
|
||||||
|
+++ ATLAS/tune/blas/gemm/CASES/ccases.flg
|
||||||
|
@@ -1,5 +1,5 @@
|
||||||
|
<ID> <flag> <mb> <nb> <kb> <muladd> <lat> <mu> <nu> <ku> <rout> "<Contributer>"
|
||||||
|
-24
|
||||||
|
+22
|
||||||
|
304 192 4 3 8 0 4 4 3 8 ATL_mm4x3x8p.c "R. Clint Whaley" \
|
||||||
|
gcc
|
||||||
|
-mcpu=ultrasparc -mtune=ultrasparc -fomit-frame-pointer -O
|
||||||
|
@@ -48,13 +48,9 @@ gcc
|
||||||
|
328 480 8 8 2 1 1 8 8 2 ATL_mm8x8x2.c "R. Clint Whaley" \
|
||||||
|
gcc
|
||||||
|
-fomit-frame-pointer -O2 -fno-tree-loop-optimize
|
||||||
|
-329 192 4 4 4 1 16 4 4 4 ATL_cmm4x4x128_av.c "R. Clint Whaley" \
|
||||||
|
-gcc
|
||||||
|
--x assembler-with-cpp
|
||||||
|
331 192 4 4 1 1 1 4 4 1 ATL_smm4x4xURx_mips.c "R. Clint Whaley" \
|
||||||
|
gcc
|
||||||
|
-x assembler-with-cpp -mips4
|
||||||
|
-332 192 8 2 4 1 0 8 2 4 ATL_smm8x2x4_av.c "IBM"
|
||||||
|
333 448 4 4 2 1 1 4 4 2 ATL_smm4x4x2pf_arm.c "R. Clint Whaley" \
|
||||||
|
gcc
|
||||||
|
-x assembler-with-cpp -mfpu=vfpv3
|
||||||
|
Index: ATLAS/tune/blas/gemm/CASES/scases.flg
|
||||||
|
===================================================================
|
||||||
|
--- ATLAS.orig/tune/blas/gemm/CASES/scases.flg
|
||||||
|
+++ ATLAS/tune/blas/gemm/CASES/scases.flg
|
||||||
|
@@ -1,5 +1,5 @@
|
||||||
|
<ID> <flag> <mb> <nb> <kb> <muladd> <lat> <mu> <nu> <ku> <rout> "<Contributer>"
|
||||||
|
-25
|
||||||
|
+22
|
||||||
|
304 192 4 3 8 0 4 4 3 8 ATL_mm4x3x8p.c "R. Clint Whaley" \
|
||||||
|
gcc
|
||||||
|
-mcpu=ultrasparc -mtune=ultrasparc -fomit-frame-pointer -O
|
||||||
|
@@ -48,16 +48,9 @@ gcc
|
||||||
|
328 480 8 8 2 1 1 8 8 2 ATL_mm8x8x2.c "R. Clint Whaley" \
|
||||||
|
gcc
|
||||||
|
-fomit-frame-pointer -O2 -fno-tree-loop-optimize
|
||||||
|
-329 192 4 4 4 1 16 4 4 4 ATL_smm4x4x128_av.c "R. Clint Whaley" \
|
||||||
|
-gcc
|
||||||
|
--x assembler-with-cpp
|
||||||
|
-330 200 92 92 92 1 16 92 92 92 ATL_smm4x4x128_av.c "R. Clint Whaley" \
|
||||||
|
-gcc
|
||||||
|
--x assembler-with-cpp
|
||||||
|
331 192 4 4 1 1 1 4 4 1 ATL_smm4x4xURx_mips.c "R. Clint Whaley" \
|
||||||
|
gcc
|
||||||
|
-x assembler-with-cpp -mips4
|
||||||
|
-332 192 8 2 4 1 0 8 2 4 ATL_smm8x2x4_av.c "IBM"
|
||||||
|
333 448 4 4 2 1 1 4 4 2 ATL_smm4x4x2pf_arm.c "R. Clint Whaley" \
|
||||||
|
gcc
|
||||||
|
-x assembler-with-cpp -mfpu=vfpv3
|
||||||
|
Index: ATLAS/tune/blas/gemm/CASES/scases.vnb
|
||||||
|
===================================================================
|
||||||
|
--- ATLAS.orig/tune/blas/gemm/CASES/scases.vnb
|
||||||
|
+++ ATLAS/tune/blas/gemm/CASES/scases.vnb
|
||||||
|
@@ -31,9 +31,6 @@
|
||||||
|
# Defaults: TA='t', TB='n', SSE=0, X87=0, LDBOT=1, RTKU=0, AOUTER=0,
|
||||||
|
# KBMAX=KU, KBMIN=KU, BETAN1=0, RTMN=1
|
||||||
|
#
|
||||||
|
-ID=1 ROUT='ATL_smm4x4x128_av.c' AUTH='R. Clint Whaley' MU=4 NU=4 KU=4 \
|
||||||
|
- LDKB=1 LDBOT=1 KBMIN=4 KBMAX=128 ASM=GAS_PPC \
|
||||||
|
- COMP='gcc' FLAGS='-x assembler-with-cpp'
|
||||||
|
ID=2 ROUT='ATL_smm4x4x16_av.c' AUTH='R. Clint Whaley' MU=4 NU=4 KU=16 \
|
||||||
|
LDKB=1 LDBOT=0 KBMIN=16 KBMAX=2048 ASM=GAS_SPARC \
|
||||||
|
COMP='gcc' FLAGS='-x assembler-with-cpp'
|
||||||
|
Index: ATLAS/tune/blas/gemm/CASES/dcases.flg
|
||||||
|
===================================================================
|
||||||
|
--- ATLAS.orig/tune/blas/gemm/CASES/dcases.flg
|
||||||
|
+++ ATLAS/tune/blas/gemm/CASES/dcases.flg
|
||||||
|
@@ -1,5 +1,5 @@
|
||||||
|
<ID> <flag> <mb> <nb> <kb> <muladd> <lat> <mu> <nu> <ku> <rout> "<Contributer>"
|
||||||
|
-32
|
||||||
|
+30
|
||||||
|
306 192 4 3 8 0 4 4 3 8 ATL_mm4x3x8p.c "R. Clint Whaley" \
|
||||||
|
gcc
|
||||||
|
-mcpu=ultrasparc -mtune=ultrasparc -fomit-frame-pointer -O -fno-schedule-insns -fno-schedule-insns2
|
||||||
|
@@ -79,12 +79,6 @@ gcc
|
||||||
|
336 192 4 4 1 1 1 4 4 1 ATL_dmm4x4xURx_mips.c "R. Clint Whaley" \
|
||||||
|
gcc
|
||||||
|
-x assembler-with-cpp -mips4
|
||||||
|
-337 192 4 4 1 1 16 4 4 1 ATL_dmm4x4x80_ppc.c "Whaley & Castaldo" \
|
||||||
|
-gcc
|
||||||
|
--x assembler-with-cpp
|
||||||
|
-338 192 8 4 2 1 0 8 4 2 ATL_dmm8x4x2_vsx.c "IBM" \
|
||||||
|
-gcc
|
||||||
|
--O3 -mvsx
|
||||||
|
339 448 4 4 2 1 1 4 4 2 ATL_dmm4x4x2pf_arm.c "R. Clint Whaley" \
|
||||||
|
gcc
|
||||||
|
-x assembler-with-cpp -mfpu=vfpv3
|
||||||
|
Index: ATLAS/tune/blas/gemm/CASES/dcases.vnb
|
||||||
|
===================================================================
|
||||||
|
--- ATLAS.orig/tune/blas/gemm/CASES/dcases.vnb
|
||||||
|
+++ ATLAS/tune/blas/gemm/CASES/dcases.vnb
|
||||||
|
@@ -53,10 +53,6 @@ ID=6 ROUT='ATL_dmm4x1x90_x87.c' AUTH='R
|
||||||
|
ID=7 ROUT='ATL_dmm8x1x120_sse2.c' AUTH='R. Clint Whaley' \
|
||||||
|
MU=8 NU=1 KU=1 KBMAX=512 ASM=GAS_x8664 BETAN1=1 \
|
||||||
|
COMP='gcc' FLAGS='-m64 -x assembler-with-cpp'
|
||||||
|
-ID=70 ROUT='ATL_dmm4x4x80_ppc.c' AUTH='R. Clint Whaley' TA='T', TB='N' \
|
||||||
|
- MU=4 NU=4 KU=1 KBMIN=1 KBMAX=80 ASM=GAS_PPC BETAN1=0 LDBOT=0 \
|
||||||
|
- LDAB=0 LDISKB=1 RTN=1 RTM=1 RTK=0 \
|
||||||
|
- COMP='gcc' FLAGS='-x assembler-with-cpp'
|
||||||
|
ID=80 ROUT='ATL_dmm4x4x16r8_US.c' AUTH='R. Clint Whaley' TA='T', TB='N' \
|
||||||
|
MU=4 NU=4 KU=24 KBMIN=24 KBMAX=512 ASM=GAS_SPARC BETAN1=0 \
|
||||||
|
LDAB=0 RTK=1 RTN=1 RTM=1 LDBOT=0 LDISKB=1 LDAB=1 \
|
||||||
|
Index: ATLAS/tune/blas/gemm/CASES/zcases.flg
|
||||||
|
===================================================================
|
||||||
|
--- ATLAS.orig/tune/blas/gemm/CASES/zcases.flg
|
||||||
|
+++ ATLAS/tune/blas/gemm/CASES/zcases.flg
|
||||||
|
@@ -1,5 +1,5 @@
|
||||||
|
<ID> <flag> <mb> <nb> <kb> <muladd> <lat> <mu> <nu> <ku> <rout> "<Contributer>"
|
||||||
|
-31
|
||||||
|
+29
|
||||||
|
306 192 4 3 8 0 4 4 3 8 ATL_mm4x3x8p.c "R. Clint Whaley" \
|
||||||
|
gcc
|
||||||
|
-mcpu=ultrasparc -mtune=ultrasparc -fomit-frame-pointer -O -fno-schedule-insns -fno-schedule-insns2
|
||||||
|
@@ -76,12 +76,6 @@ gcc
|
||||||
|
336 192 4 4 1 1 1 4 4 1 ATL_dmm4x4xURx_mips.c "R. Clint Whaley" \
|
||||||
|
gcc
|
||||||
|
-x assembler-with-cpp -mips4
|
||||||
|
-337 192 4 4 1 1 16 4 4 1 ATL_dmm4x4x80_ppc.c "Whaley & Castaldo" \
|
||||||
|
-gcc
|
||||||
|
--x assembler-with-cpp
|
||||||
|
-338 192 8 4 2 1 0 8 4 2 ATL_dmm8x4x2_vsx.c "IBM" \
|
||||||
|
-gcc
|
||||||
|
--O3 -mvsx
|
||||||
|
339 448 4 4 2 1 1 4 4 2 ATL_dmm4x4x2pf_arm.c "R. Clint Whaley" \
|
||||||
|
gcc
|
||||||
|
-x assembler-with-cpp -mfpu=vfpv3
|
1040
atlas.spec
1040
atlas.spec
File diff suppressed because it is too large
Load Diff
@ -1,18 +1,6 @@
|
|||||||
Subject: getdoublearr.stripwhite
|
diff -up ATLAS/include/atlas_genparse.h.than ATLAS/include/atlas_genparse.h
|
||||||
From: Michel Normand <normand@fr.ibm.com>
|
--- ATLAS/include/atlas_genparse.h.than 2015-11-26 10:53:55.056586198 -0500
|
||||||
|
+++ ATLAS/include/atlas_genparse.h 2015-11-26 10:56:00.168537914 -0500
|
||||||
GetDoubleArr must only handle the comma delimited list at string head
|
|
||||||
and ignore anything after the first blank character.
|
|
||||||
|
|
||||||
Signed-off-by: Michel Normand <normand@fr.ibm.com>
|
|
||||||
---
|
|
||||||
ATLAS/include/atlas_genparse.h | 16 ++++++++++++++--
|
|
||||||
1 file changed, 14 insertions(+), 2 deletions(-)
|
|
||||||
|
|
||||||
Index: atlas/ATLAS/include/atlas_genparse.h
|
|
||||||
===================================================================
|
|
||||||
--- atlas.orig/ATLAS/include/atlas_genparse.h
|
|
||||||
+++ atlas/ATLAS/include/atlas_genparse.h
|
|
||||||
@@ -149,13 +149,24 @@ static int asmNames2bitfield(char *str)
|
@@ -149,13 +149,24 @@ static int asmNames2bitfield(char *str)
|
||||||
}
|
}
|
||||||
|
|
||||||
@ -40,7 +28,7 @@ Index: atlas/ATLAS/include/atlas_genparse.h
|
|||||||
assert(sscanf(str, "%le", d) == 1);
|
assert(sscanf(str, "%le", d) == 1);
|
||||||
while (i < N)
|
while (i < N)
|
||||||
{
|
{
|
||||||
@@ -166,6 +177,7 @@ static int GetDoubleArr(char *str, int N
|
@@ -167,6 +178,7 @@ static int GetDoubleArr(char *str, int N
|
||||||
break;
|
break;
|
||||||
i++;
|
i++;
|
||||||
}
|
}
|
||||||
|
@ -1,6 +1,22 @@
|
|||||||
--- ./ATLAS.first/tune/blas/level3/invtrsm.c 2013-10-22 19:35:03.000000000 +0000
|
From: Michel Normand <normand@linux.vnet.ibm.com>
|
||||||
+++ ./ATLAS/tune/blas/level3/invtrsm.c 2013-10-23 21:24:01.000000000 +0000
|
Subject: initialize malloc memory.invtrsm.wms.oct23
|
||||||
@@ -525,6 +525,7 @@
|
Date: Mon, 14 Apr 2014 17:18:53 +0200
|
||||||
|
References: http://sourceforge.net/p/math-atlas/mailman/message/32471499/
|
||||||
|
|
||||||
|
initialize malloc memory invtrsm.c
|
||||||
|
|
||||||
|
|
||||||
|
Signed-off-by: Will Schmidt <will_schmidt@vnet.ibm.com>
|
||||||
|
Signed-off-by: Michel Normand <normand@linux.vnet.ibm.com>
|
||||||
|
---
|
||||||
|
ATLAS/tune/blas/level3/invtrsm.c | 1 +
|
||||||
|
1 file changed, 1 insertion(+)
|
||||||
|
|
||||||
|
Index: ATLAS/tune/blas/level3/invtrsm.c
|
||||||
|
===================================================================
|
||||||
|
--- ATLAS.orig/tune/blas/level3/invtrsm.c
|
||||||
|
+++ ATLAS/tune/blas/level3/invtrsm.c
|
||||||
|
@@ -525,6 +525,7 @@ static double RunTiming
|
||||||
a = A = malloc(i * ATL_MulBySize(incA));
|
a = A = malloc(i * ATL_MulBySize(incA));
|
||||||
if (A)
|
if (A)
|
||||||
{
|
{
|
||||||
|
@ -1,12 +0,0 @@
|
|||||||
diff -Naur ATLAS.orig/include/atlas_pca.h ATLAS/include/atlas_pca.h
|
|
||||||
--- ATLAS.orig/include/atlas_pca.h 2013-01-08 19:15:40.000000000 +0100
|
|
||||||
+++ ATLAS/include/atlas_pca.h 2014-10-23 13:45:36.956698637 +0200
|
|
||||||
@@ -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) || 1
|
|
||||||
#ifdef __GNUC__
|
|
||||||
#define ATL_membarrier __asm__ __volatile__ ("dcs")
|
|
||||||
/* #define ATL_USEPCA 1 */
|
|
@ -1,60 +0,0 @@
|
|||||||
--- atlas/ATLAS/tune/blas/gemm/CASES/ATL_dmm4x4x80_ppc.c 2013-12-05 19:19:57.000000000 +0100
|
|
||||||
+++ atlas/ATLAS/tune/blas/gemm/CASES/ATL_dmm4x4x80_ppc.c.new 2013-12-06 16:29:57.000000000 +0100
|
|
||||||
@@ -170,13 +170,21 @@ void ATL_USERMM(const int M, const int N
|
|
||||||
const TYPE beta, TYPE *C, const int ldc)
|
|
||||||
(r10) 8(r1)
|
|
||||||
*******************************************************************************
|
|
||||||
-64 bit ABIs:
|
|
||||||
+64 bit ABIv1s:
|
|
||||||
r3 r4 r5 r6/f1
|
|
||||||
void ATL_USERMM(const int M, const int N, const int K, const TYPE alpha,
|
|
||||||
r7 r8 r9 r10
|
|
||||||
const TYPE *A, const int lda, const TYPE *B, const int ldb,
|
|
||||||
f2 120(r1) 128(r1)
|
|
||||||
const TYPE beta, TYPE *C, const int ldc)
|
|
||||||
+
|
|
||||||
+64 bit ABIv2s:
|
|
||||||
+ r3 r4 r5 r6/f1
|
|
||||||
+void ATL_USERMM(const int M, const int N, const int K, const TYPE alpha,
|
|
||||||
+ r7 r8 r9 r10
|
|
||||||
+ const TYPE *A, const int lda, const TYPE *B, const int ldb,
|
|
||||||
+ f2 104(r1) 112(r1)
|
|
||||||
+ const TYPE beta, TYPE *C, const int ldc)
|
|
||||||
#endif
|
|
||||||
#ifdef ATL_AS_AIX_PPC
|
|
||||||
.csect .text[PR]
|
|
||||||
@@ -202,7 +210,7 @@ Mjoin(.,ATL_USERMM):
|
|
||||||
.globl Mjoin(_,ATL_USERMM)
|
|
||||||
Mjoin(_,ATL_USERMM):
|
|
||||||
#else
|
|
||||||
- #if defined(ATL_USE64BITS)
|
|
||||||
+ #if defined(ATL_USE64BITS) && _CALL_ELF != 2
|
|
||||||
/*
|
|
||||||
* Official Program Descripter section, seg fault w/o it on Linux/PPC64
|
|
||||||
*/
|
|
||||||
@@ -217,6 +225,7 @@ ATL_USERMM:
|
|
||||||
.globl Mjoin(.,ATL_USERMM)
|
|
||||||
Mjoin(.,ATL_USERMM):
|
|
||||||
#else
|
|
||||||
+/* ppc64 have no longer function descriptors in ABIv2 */
|
|
||||||
.globl ATL_USERMM
|
|
||||||
ATL_USERMM:
|
|
||||||
#endif
|
|
||||||
@@ -257,9 +266,17 @@ ATL_USERMM:
|
|
||||||
#endif
|
|
||||||
#endif
|
|
||||||
|
|
||||||
+
|
|
||||||
#if defined (ATL_USE64BITS)
|
|
||||||
+#if _CALL_ELF == 2
|
|
||||||
+/* ABIv2 */
|
|
||||||
+ ld pC0, 104(r1)
|
|
||||||
+ ld incCn, 112(r1)
|
|
||||||
+#else
|
|
||||||
+/* ABIv1 */
|
|
||||||
ld pC0, 120(r1)
|
|
||||||
ld incCn, 128(r1)
|
|
||||||
+#endif
|
|
||||||
#elif defined(ATL_AS_OSX_PPC) || defined(ATL_AS_AIX_PPC)
|
|
||||||
lwz pC0, 68(r1)
|
|
||||||
lwz incCn, 72(r1)
|
|
@ -1,37 +0,0 @@
|
|||||||
Subject: ppc64le remove vsx
|
|
||||||
From: Michel Normand <normand@fr.ibm.com>
|
|
||||||
|
|
||||||
temporarily remove the vsx related flags
|
|
||||||
as long as not supported for ppc64le
|
|
||||||
Note that also force as power4
|
|
||||||
|
|
||||||
Signed-off-by: Michel Normand <normand@fr.ibm.com>
|
|
||||||
diff -up ATLAS/CONFIG/src/atlcomp.txt.orig ATLAS/CONFIG/src/atlcomp.txt
|
|
||||||
--- ATLAS/CONFIG/src/atlcomp.txt.orig 2014-07-10 18:22:02.000000000 +0200
|
|
||||||
+++ ATLAS/CONFIG/src/atlcomp.txt 2015-07-09 09:44:07.270264073 +0200
|
|
||||||
@@ -191,9 +191,9 @@ MACH=PPCG5 OS=ALL LVL=1000 COMPS=dmc,icc
|
|
||||||
MACH=PPCG5 OS=ALL LVL=1000 COMPS=skc
|
|
||||||
'gcc' '-mpowerpc64 -maltivec -mabi=altivec -mcpu=970 -mtune=970 -O2 -mvrsave'
|
|
||||||
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'
|
|
||||||
+ 'gcc' '-O2 -m64 -mvrsave -funroll-all-loops'
|
|
||||||
MACH=POWER7 OS=ALL LVL=1010 COMPS=f77
|
|
||||||
- 'gfortran' '-O2 -mvsx -mcpu=power7 -mtune=power7 -m64 -mvrsave -funroll-all-loops'
|
|
||||||
+ 'gfortran' '-O2 -m64 -mvrsave -funroll-all-loops'
|
|
||||||
MACH=POWER6 OS=ALL LVL=1010 COMPS=icc,smc,dmc,skc,dkc,xcc,gcc
|
|
||||||
'gcc' '-mcpu=power6 -mtune=power6 -maltivec -O3 -fno-schedule-insns -fschedule-insns2 -minsert-sched-nops=2'
|
|
||||||
MACH=POWER5 OS=ALL LVL=1010 COMPS=icc,smc,dmc,skc,dkc,xcc,gcc
|
|
||||||
diff -up ATLAS/CONFIG/src/probe_comp.c.orig ATLAS/CONFIG/src/probe_comp.c
|
|
||||||
--- ATLAS/CONFIG/src/probe_comp.c.orig 2015-07-09 09:44:07.280264074 +0200
|
|
||||||
+++ ATLAS/CONFIG/src/probe_comp.c 2015-07-09 09:45:51.480266328 +0200
|
|
||||||
@@ -450,8 +450,8 @@ COMPNODE **GetDefaultComps(enum OSTYPE O
|
|
||||||
vp = "-mavx -mno-sse2avx -mfma";
|
|
||||||
else if ((vecexts & (1<<ISA_AVXMAC)))
|
|
||||||
vp = "-mavx2 -mfma";
|
|
||||||
- else if (vecexts & (1<<ISA_VSX))
|
|
||||||
- vp = "-mvsx";
|
|
||||||
+ /*else if (vecexts & (1<<ISA_VSX))
|
|
||||||
+ vp = "-mvsx";*/
|
|
||||||
else if (vecexts & (1<<ISA_AV))
|
|
||||||
vp = "-maltivec";
|
|
||||||
else if (vecexts & (1<<ISA_AVX))
|
|
30
sources
30
sources
@ -1,13 +1,17 @@
|
|||||||
a4e21f343dec8f22e7415e339f09f6da atlas3.10.2.tar.bz2
|
SHA512 (atlas3.10.3.tar.bz2) = bf17306f09f2aa973cb776e2c9eacfb2409ad4d95d19802e1c4e0597d0a099fccdb5eaafe273c2682a41e41a3c6fabc8bbba4ce03180cffea40ede5df1d1f56e
|
||||||
9ddf8c76e5e9781c542b712f704460e1 IBMz1032.tgz
|
SHA512 (IBMz1032.tgz) = f745187d75073de461d6948489dad3abea9a67ad10ec63e021160d3f61ae5be36e94768faa0e7e6e3158b1401bf954eae1e7e6416857b652415030836c6aba3d
|
||||||
ee4cbc1f15cb4cd5f5266969a4bc62a7 IBMz1064.tgz
|
SHA512 (IBMz1064.tgz) = 14fbc584a8711a0292c8be0dce962bd7ac12347b2d203c2a7b0cc66ea68ac57d5b88afc6778df39efea43077fcc70c6c63db365b5b4badb879ab6900b5296094
|
||||||
edd3cb5602c6282e4a30691e728bd064 IBMz19632.tgz
|
SHA512 (IBMz1264.tar.bz2) = 54bab951a818feb08fe5c671213db80d17bfefe75a3993d80655161219f018e87125c4ccc09c701cde45fd672a9856f4fff557ffc378c5b2fe7e9c6ebc3bd1de
|
||||||
21f630520058859ad0b8b798bd17dc5a IBMz19664.tgz
|
SHA512 (IBMz19632.tgz) = aa10213265866b3176efe1d9d204da170844573f7ab26a36551a174eab3951ccd5f54a5149f1351affc38c510162cce9e10eb2a830af32992cb3febe9e1ecafe
|
||||||
3f174cdcb4c964843f27dbfc4ad4b1c8 K7323DNow.tgz
|
SHA512 (IBMz19664.tgz) = 5837d5dfd04c31c304e1f454d0148bd412ec8853c50a7c3dcee9a61529bd04c30d68a0c7aae2bfa2c393fde3582fe36f98e6f5891b271b19562491298ba600b2
|
||||||
676548252837b1e458181111443f340f PPRO32.tgz
|
SHA512 (IBMz932.tar.bz2) = 8f71140d1b30d00ed44faea71e42ab3ff24917a62670f7becdb0d861bf4e7c3c972f9601d161439a518dcc87405c74af31cdd4e2996999a5da8452cc8d2a52df
|
||||||
ebb4732aff468bbc223e7f734252173b USII32.tgz
|
SHA512 (IBMz964.tar.bz2) = b7356e5b47615c64c9b2dd6a497f071e39d4d90f6dd42478fea1d7597cf21ea08123c480fde002aba181a2ad0eeb21acb61469c7e4b2e8961e4d72e5f86e14cc
|
||||||
31f8ae7583d290e5414a1a61ff6e7e39 USII64.tgz
|
SHA512 (PPRO32.tgz) = a30069e79f95a36b2c7125e7861218e9612bd92913db929ea98800201e7ca7d55c9a1480063c7d5a4c50fcb2b271907ce43cd9b229c694a5ee3b56561a7820e6
|
||||||
93f108a072913fa1dbb2fcb6ca7c229a IBMz932.tar.bz2
|
SHA512 (USII32.tgz) = e9d3b1f5ccd38fc364666205e33f7a927e96c3cebc35d9692cafe3b536697224f20702641f875421b200ff78774831fd5790174ef55c899e0cdb905e3ac2371f
|
||||||
f3e4ca175b5ffc49dce7f3c37f791827 IBMz964.tar.bz2
|
SHA512 (USII64.tgz) = 5bd654f8b45306a18f3ad2b593ba23012909ba5ad91614de5024b80998bde832d0ddc84d2c0c0e75dd28915f3c07ec40ac9351213b24e54028fbad4d385ebcc6
|
||||||
27e7baa49c588299260188afa78303dc POWER332.tar.bz2
|
SHA512 (POWER332.tar.bz2) = 95a7281dbb7a2d0897a58599577afdedba66e6e5edb73223efdeecd93b6706031139b9b58b14345449dccbf1abfa8275bc261f826c692282d14dc30320728c75
|
||||||
af1f95e19d7afaf0342fb1377ec94817 ARMv732NEON.tar.bz2
|
SHA512 (ARMv732NEON.tar.bz2) = 92acbdd8f7aebd841a10a13df85baa00c518dae388e1ee8dd4bc35fc461d732d2df2cfeae0a3614cea251b80a9ee6a5b49ad71ab8b36b98b70bda6d1c215c78d
|
||||||
|
SHA512 (ARMa732.tar) = 47d6564b5a439bc3778ccc79242220b236c7dc8d36e12ce6850c7e9a02e2379618322c003ba4490573c40b78227c2c3925222da4f4e5f87aab48eae192b45bb9
|
||||||
|
SHA512 (ARMa732.tar.bz2) = 8b83b59a32f18d2cd432c205efd4358b0000ce1685799f2f38a60532bc925e9cd871371d2dfd226ab8e30e830bf608f022d63bcd26f26f9fe74acab067bd4d4f
|
||||||
|
SHA512 (POWER864LEVSXp4.tar.bz2) = e2fa637061a4a4806bc091009c37ccd719c4c4051baf36ed451917e255375881fa168caa5ca296ae9c89bb28523d9015fda42a5dbc51aef4c66efbf6efd966d2
|
||||||
|
SHA512 (K7323DNow.tgz) = e1d5e4208ce454b5f5daa68663d2dd28a2bd3cc97496e4e1515df880b9ccd00bcc75bd820402c3b2bf8409f98500e43f2481fbf5dd480f7d0ba60fe2f82a1ac1
|
||||||
|
@ -1,24 +0,0 @@
|
|||||||
Subject: xlf.command.not.found
|
|
||||||
From: Michel Normand <normand@fr.ibm.com>
|
|
||||||
|
|
||||||
try to bypass error while building ppc64le
|
|
||||||
"make[2]: xlf: Command not found"
|
|
||||||
|
|
||||||
Signed-off-by: Michel Normand <normand@fr.ibm.com>
|
|
||||||
---
|
|
||||||
ATLAS/CONFIG/src/atlcomp.txt | 4 ++--
|
|
||||||
1 file changed, 2 insertions(+), 2 deletions(-)
|
|
||||||
|
|
||||||
Index: atlas/ATLAS/CONFIG/src/atlcomp.txt
|
|
||||||
===================================================================
|
|
||||||
--- atlas.orig/ATLAS/CONFIG/src/atlcomp.txt
|
|
||||||
+++ atlas/ATLAS/CONFIG/src/atlcomp.txt
|
|
||||||
@@ -199,7 +199,7 @@ MACH=POWER6 OS=ALL LVL=1010 COMPS=f77
|
|
||||||
MACH=POWER5 OS=ALL LVL=1010 COMPS=f77
|
|
||||||
'gfortran' '-mcpu=power5 -mtune=power5 -O3 -fno-schedule-insns -fno-rerun-loop-opt'
|
|
||||||
MACH=POWER7 OS=ALL LVL=1010 COMPS=f77
|
|
||||||
- 'xlf' '-qtune=pwr7 -qarch=pwr7 -O3 -qmaxmem=-1 -qfloat=hsflt'
|
|
||||||
+ 'gfortran' '-O2 -m64 -mvrsave -funroll-all-loops'
|
|
||||||
MACH=POWER5 OS=ALL LVL=1010 COMPS=f77
|
|
||||||
'xlf' '-qtune=pwr5 -qarch=pwr5 -O3 -qmaxmem=-1 -qfloat=hsflt'
|
|
||||||
MACH=POWER4 OS=ALL LVL=1010 COMPS=icc,dmc,smc,dkc,skc,xcc,gcc
|
|
Loading…
Reference in New Issue
Block a user