152 lines
5.9 KiB
Diff
152 lines
5.9 KiB
Diff
|
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
|