Kludge to fix cpuid dispatch on power

This needs fixing properly somehow, but using -O3 (at least with gcc 8.3),
we get this:

Program received signal SIGILL, Illegal instruction.
0x000000001004c660 in bli_cntx_init_power9_ref (cntx=0x103e06b0)
    at ref_kernels/bli_cntx_ref.c:456
456             for ( i = 0; i < BLIS_NUM_LEVEL3_OPS; ++i ) vfuncs[ i ] = NULL;
(gdb) bt
#0  0x000000001004c660 in bli_cntx_init_power9_ref (cntx=0x103e06b0)
    at ref_kernels/bli_cntx_ref.c:456
flame#1  0x000000001004c0a8 in bli_cntx_init_power9 (cntx=<optimized out>)
    at config/power9/bli_cntx_init_power9.c:42
flame#2  0x000000001003c85c in bli_gks_register_cntx (id=BLIS_ARCH_POWER9,
    nat_fp=0x1004c090 <bli_cntx_init_power9>,
    ref_fp=0x1004c0d0 <bli_cntx_init_power9_ref>, ind_fp=<optimized out>)
    at frame/base/bli_gks.c:373
flame#3  0x000000001003c97c in bli_gks_init () at frame/base/bli_gks.c:155
flame#4  0x000000001003cfe8 in bli_init_apis () at frame/base/bli_init.c:78
flame#5  0x00007ffff7e045a8 in __pthread_once_slow () from /lib64/libpthread.so.0
flame#6  0x00000000100492e8 in bli_pthread_once (once=<optimized out>,
    init=<optimized out>) at frame/thread/bli_pthread.c:314
flame#7  0x000000001003d138 in bli_init_once () at frame/base/bli_init.c:104
flame#8  bli_init_auto () at frame/base/bli_init.c:54
flame#9  0x0000000010011300 in cdotc_ (n=<optimized out>, x=<optimized out>,
    incx=<optimized out>, y=<optimized out>, incy=<optimized out>)
    at frame/compat/bla_dot.c:89
flame#10 0x0000000010002a48 in check2_ (sfac=0x103d14dc <sfac>)
    at blastest/src/cblat1.c:529
flame#11 0x0000000010001ef4 in main () at blastest/src/cblat1.c:112

Author: Dave Love

config/power8/make_defs.mk

@@ -57,7 +57,9 @@ endif
 ifeq ($(DEBUG_TYPE),noopt)
 COPTFLAGS      := -O0
 else
-COPTFLAGS      := -O3 -funroll-loops
+# Fixme: This should use -O3, but that breaks cpuid dispatch somehow,
+# and we end up executing power9 code on power8.
+COPTFLAGS      := -O2 -funroll-loops
 endif
 
 # Flags specific to optimized kernels.
@@ -71,7 +73,7 @@ endif
 # Flags specific to reference kernels.
 CROPTFLAGS     := $(CKOPTFLAGS)
 ifeq ($(CC_VENDOR),gcc)
-CRVECFLAGS     := $(CKVECFLAGS) -funsafe-math-optimizations -ffp-contract=fast
+CRVECFLAGS     := $(CKVECFLAGS) -funsafe-math-optimizations -ffp-contract=fast -O3
 else
 ifeq ($(CC_VENDOR),clang)
 CRVECFLAGS     := $(CKVECFLAGS) -funsafe-math-optimizations -ffp-contract=fast

config/power9/make_defs.mk

@@ -57,7 +57,9 @@ endif
 ifeq ($(DEBUG_TYPE),noopt)
 COPTFLAGS      := -O0
 else
-COPTFLAGS      := -O3 -funroll-loops
+# Fixme: This should use -O3, but that breaks cpuid dispatch somehow,
+# and we end up executing power9 code on power8.
+COPTFLAGS      := -O2 -funroll-loops
 endif
 
 # Flags specific to optimized kernels.
@@ -71,7 +73,7 @@ endif
 # Flags specific to reference kernels.
 CROPTFLAGS     := $(CKOPTFLAGS)
 ifeq ($(CC_VENDOR),gcc)
-CRVECFLAGS     := $(CKVECFLAGS) -funsafe-math-optimizations -ffp-contract=fast
+CRVECFLAGS     := $(CKVECFLAGS) -funsafe-math-optimizations -ffp-contract=fast -O3
 else
 ifeq ($(CC_VENDOR),clang)
 CRVECFLAGS     := $(CKVECFLAGS) -funsafe-math-optimizations -ffp-contract=fast