POWER10: Change the packing format for bfloat16

As the new MMA instructions need the inputs in 4x2 order for bfloat16,
changing the format in copy/packing code.  This avoids permute instructions
in the gemm kernel inner loop.

Author: Rajalakshmi Srinivasaraghavan

kernel/power/KERNEL.POWER10

@@ -9,10 +9,10 @@ else
 
 SBGEMM_BETA = ../generic/gemm_beta.c
 SBGEMMKERNEL    = sbgemm_kernel_power10.c
-SBGEMMINCOPY    = ../generic/gemm_ncopy_16.c
-SBGEMMITCOPY    = ../generic/gemm_tcopy_16.c
-SBGEMMONCOPY    = ../generic/gemm_ncopy_8.c
-SBGEMMOTCOPY    = ../generic/gemm_tcopy_8.c
+SBGEMMINCOPY    = sbgemm_ncopy_16_power10.c
+SBGEMMITCOPY    = sbgemm_tcopy_16_power10.c
+SBGEMMONCOPY    = sbgemm_ncopy_8_power10.c
+SBGEMMOTCOPY    = sbgemm_tcopy_8_power10.c
 SBGEMMINCOPYOBJ =  sbgemm_incopy$(TSUFFIX).$(SUFFIX)
 SBGEMMITCOPYOBJ =  sbgemm_itcopy$(TSUFFIX).$(SUFFIX)
 SBGEMMONCOPYOBJ =  sbgemm_oncopy$(TSUFFIX).$(SUFFIX)