mirror of
https://github.com/amd/blis.git
synced 2026-07-17 17:17:44 +00:00
Merge branch 'dev'
This commit is contained in:
Field G. Van Zee
1
CREDITS
1
CREDITS
@@ -9,6 +9,7 @@ The BLIS framework was primarily authored by
|
||||
|
||||
but many others have contributed code and feedback, including
|
||||
|
||||
Sameer Agarwal @sandwichmaker (Google)
|
||||
Murtaza Ali (Texas Instruments)
|
||||
Sajid Ali @s-sajid-ali (Northwestern University)
|
||||
Erling Andersen @erling-d-andersen
|
||||
|
||||
@@ -50,17 +50,17 @@ Theoretical peak performance, in units of GFLOPS/core, is calculated as the
|
||||
product of:
|
||||
1. the maximum sustainable clock rate in GHz; and
|
||||
2. the maximum number of floating-point operations (flops) that can be
|
||||
executed per cycle.
|
||||
executed per cycle (per core).
|
||||
|
||||
Note that the maximum sustainable clock rate may change depending on the
|
||||
conditions.
|
||||
For example, on some systems the maximum clock rate is higher when only one
|
||||
core is active (e.g. single-threaded performance) versus when all cores are
|
||||
active (e.g. multithreaded performance).
|
||||
The maximum number of flops executable per cycle is generally computed as the
|
||||
product of:
|
||||
The maximum number of flops executable per cycle (per core) is generally
|
||||
computed as the product of:
|
||||
1. the maximum number of fused multiply-add (FMA) vector instructions that
|
||||
can be issued per cycle;
|
||||
can be issued per cycle (per core);
|
||||
2. the maximum number of elements that can be stored within a single vector
|
||||
register (for the datatype in question); and
|
||||
3. 2.0, since an FMA instruction fuses two operations (a multiply and an add).
|
||||
@@ -91,7 +91,7 @@ allow it to finish.
|
||||
|
||||
Where along the x-axis you focus your attention will depend on the segment of
|
||||
the problem size range that you care about most. Some people's applications
|
||||
depend heavily on smaller problems, where "small" can mean anything from 200
|
||||
depend heavily on smaller problems, where "small" can mean anything from 10
|
||||
to 1000 or even higher. Some people consider 1000 to be quite large, while
|
||||
others insist that 5000 is merely "medium." What each of us considers to be
|
||||
small, medium, or large (naturally) depends heavily on the kinds of dense
|
||||
@@ -133,10 +133,16 @@ size of interest so that we can better assist you.
|
||||
* sub-configuration exercised: `thunderx2`
|
||||
* OpenBLAS 52d3f7a
|
||||
* configured with `BINARY=64 NO_CBLAS=1 NO_LAPACK=1 NO_LAPACKE=1 USE_THREAD=0` (single-threaded)
|
||||
* configured with `BINARY=64 NO_CBLAS=1 NO_LAPACK=1 NO_LAPACKE=1 USE_THREAD=1 NUM_THREADS=56` (multithreaded)
|
||||
* configured with `BINARY=64 NO_CBLAS=1 NO_LAPACK=1 NO_LAPACKE=1 USE_THREAD=1 NUM_THREADS=56` (multithreaded, 56 cores)
|
||||
* Requested threading via `export OPENBLAS_NUM_THREADS=1` (single-threaded)
|
||||
* Requested threading via `export OPENBLAS_NUM_THREADS=28` (multithreaded, 28 cores)
|
||||
* Requested threading via `export OPENBLAS_NUM_THREADS=56` (multithreaded, 56 cores)
|
||||
* ARMPL 18.4
|
||||
* Requested threading via `export OMP_NUM_THREADS=1` (single-threaded)
|
||||
* Requested threading via `export OMP_NUM_THREADS=28` (multithreaded, 28 cores)
|
||||
* Requested threading via `export OMP_NUM_THREADS=56` (multithreaded, 56 cores)
|
||||
* Affinity:
|
||||
* Thread affinity for BLIS was specified manually via `GOMP_CPU_AFFINITY="0 1 2 3 ... 55"`. However, multithreaded OpenBLAS appears to revert to single-threaded execution if `GOMP_CPU_AFFINITY` is set. Therefore, when measuring OpenBLAS performance, the `GOMP_CPU_AFFINITY` was unset.
|
||||
* Thread affinity for BLIS was specified manually via `GOMP_CPU_AFFINITY="0 1 2 3 ... 55"`. However, multithreaded OpenBLAS appears to revert to single-threaded execution if `GOMP_CPU_AFFINITY` is set. Therefore, when measuring OpenBLAS performance, the `GOMP_CPU_AFFINITY` environment variable was unset.
|
||||
* Frequency throttling (via `cpupower`):
|
||||
* No changes made.
|
||||
* Comments:
|
||||
@@ -184,10 +190,23 @@ size of interest so that we can better assist you.
|
||||
* sub-configuration exercised: `skx`
|
||||
* OpenBLAS 0.3.5
|
||||
* configured with `BINARY=64 NO_CBLAS=1 NO_LAPACK=1 NO_LAPACKE=1 USE_THREAD=0` (single-threaded)
|
||||
* configured with `BINARY=64 NO_CBLAS=1 NO_LAPACK=1 NO_LAPACKE=1 USE_THREAD=1 NUM_THREADS=52` (multithreaded)
|
||||
* configured with `BINARY=64 NO_CBLAS=1 NO_LAPACK=1 NO_LAPACKE=1 USE_THREAD=1 NUM_THREADS=52` (multithreaded, 52 cores)
|
||||
* Requested threading via `export OPENBLAS_NUM_THREADS=1` (single-threaded)
|
||||
* Requested threading via `export OPENBLAS_NUM_THREADS=26` (multithreaded, 26 cores)
|
||||
* Requested threading via `export OPENBLAS_NUM_THREADS=52` (multithreaded, 52 cores)
|
||||
* Eigen 3.3.7
|
||||
* Prior to compilation, modified top-level `CMakeLists.txt` to ensure that `-march=native` was added to `CXX_FLAGS` variable (h/t Sameer Agarwal).
|
||||
* configured and built BLAS library via `mkdir build; cd build; cmake ..; make blas`
|
||||
* Requested threading via `export OMP_NUM_THREADS=1` (single-threaded)
|
||||
* Requested threading via `export OMP_NUM_THREADS=26` (multithreaded, 26 cores)
|
||||
* Requested threading via `export OMP_NUM_THREADS=52` (multithreaded, 52 cores)
|
||||
* **NOTE**: This version of Eigen does not provide multithreaded implementations of `symm`/`hemm`, `syrk`/`herk`, `trmm`, or `trsm`, and therefore those curves are omitted from the multithreaded graphs.
|
||||
* MKL 2019 update 1
|
||||
* Requested threading via `export MKL_NUM_THREADS=1` (single-threaded)
|
||||
* Requested threading via `export MKL_NUM_THREADS=26` (multithreaded, 26 cores)
|
||||
* Requested threading via `export MKL_NUM_THREADS=52` (multithreaded, 52 cores)
|
||||
* Affinity:
|
||||
* Thread affinity for BLIS was specified manually via `GOMP_CPU_AFFINITY="0 1 2 3 ... 51"`. However, multithreaded OpenBLAS appears to revert to single-threaded execution if `GOMP_CPU_AFFINITY` is set. Therefore, when measuring OpenBLAS performance, the `GOMP_CPU_AFFINITY` was unset.
|
||||
* Thread affinity for BLIS was specified manually via `GOMP_CPU_AFFINITY="0 1 2 3 ... 51"`. However, multithreaded OpenBLAS appears to revert to single-threaded execution if `GOMP_CPU_AFFINITY` is set. Therefore, when measuring OpenBLAS performance, the `GOMP_CPU_AFFINITY` environment variable was unset.
|
||||
* Frequency throttling (via `cpupower`):
|
||||
* No changes made.
|
||||
* Comments:
|
||||
@@ -235,10 +254,23 @@ size of interest so that we can better assist you.
|
||||
* sub-configuration exercised: `haswell`
|
||||
* OpenBLAS 0.3.5
|
||||
* configured with `BINARY=64 NO_CBLAS=1 NO_LAPACK=1 NO_LAPACKE=1 USE_THREAD=0` (single-threaded)
|
||||
* configured with `BINARY=64 NO_CBLAS=1 NO_LAPACK=1 NO_LAPACKE=1 USE_THREAD=1 NUM_THREADS=24` (multithreaded)
|
||||
* configured with `BINARY=64 NO_CBLAS=1 NO_LAPACK=1 NO_LAPACKE=1 USE_THREAD=1 NUM_THREADS=24` (multithreaded, 24 cores)
|
||||
* Requested threading via `export OPENBLAS_NUM_THREADS=1` (single-threaded)
|
||||
* Requested threading via `export OPENBLAS_NUM_THREADS=12` (multithreaded, 12 cores)
|
||||
* Requested threading via `export OPENBLAS_NUM_THREADS=24` (multithreaded, 24 cores)
|
||||
* Eigen 3.3.7
|
||||
* Prior to compilation, modified top-level `CMakeLists.txt` to ensure that `-march=native` was added to `CXX_FLAGS` variable (h/t Sameer Agarwal).
|
||||
* configured and built BLAS library via `mkdir build; cd build; cmake ..; make blas`
|
||||
* Requested threading via `export OMP_NUM_THREADS=1` (single-threaded)
|
||||
* Requested threading via `export OMP_NUM_THREADS=12` (multithreaded, 12 cores)
|
||||
* Requested threading via `export OMP_NUM_THREADS=24` (multithreaded, 24 cores)
|
||||
* **NOTE**: This version of Eigen does not provide multithreaded implementations of `symm`/`hemm`, `syrk`/`herk`, `trmm`, or `trsm`, and therefore those curves are omitted from the multithreaded graphs.
|
||||
* MKL 2018 update 2
|
||||
* Requested threading via `export MKL_NUM_THREADS=1` (single-threaded)
|
||||
* Requested threading via `export MKL_NUM_THREADS=12` (multithreaded, 12 cores)
|
||||
* Requested threading via `export MKL_NUM_THREADS=24` (multithreaded, 24 cores)
|
||||
* Affinity:
|
||||
* Thread affinity for BLIS was specified manually via `GOMP_CPU_AFFINITY="0 1 2 3 ... 23"`. However, multithreaded OpenBLAS appears to revert to single-threaded execution if `GOMP_CPU_AFFINITY` is set. Therefore, when measuring OpenBLAS performance, the `GOMP_CPU_AFFINITY` was unset.
|
||||
* Thread affinity for BLIS was specified manually via `GOMP_CPU_AFFINITY="0 1 2 3 ... 23"`. However, multithreaded OpenBLAS appears to revert to single-threaded execution if `GOMP_CPU_AFFINITY` is set. Therefore, when measuring OpenBLAS performance, the `GOMP_CPU_AFFINITY` environment variable was unset.
|
||||
* Frequency throttling (via `cpupower`):
|
||||
* No changes made.
|
||||
* Comments:
|
||||
@@ -287,10 +319,23 @@ size of interest so that we can better assist you.
|
||||
* sub-configuration exercised: `zen`
|
||||
* OpenBLAS 0.3.5
|
||||
* configured with `BINARY=64 NO_CBLAS=1 NO_LAPACK=1 NO_LAPACKE=1 USE_THREAD=0` (single-threaded)
|
||||
* configured with `BINARY=64 NO_CBLAS=1 NO_LAPACK=1 NO_LAPACKE=1 USE_THREAD=1 NUM_THREADS=64` (multithreaded)
|
||||
* configured with `BINARY=64 NO_CBLAS=1 NO_LAPACK=1 NO_LAPACKE=1 USE_THREAD=1 NUM_THREADS=64` (multithreaded, 64 cores)
|
||||
* Requested threading via `export OPENBLAS_NUM_THREADS=1` (single-threaded)
|
||||
* Requested threading via `export OPENBLAS_NUM_THREADS=32` (multithreaded, 32 cores)
|
||||
* Requested threading via `export OPENBLAS_NUM_THREADS=64` (multithreaded, 64 cores)
|
||||
* Eigen 3.3.7
|
||||
* Prior to compilation, modified top-level `CMakeLists.txt` to ensure that `-march=native` was added to `CXX_FLAGS` variable (h/t Sameer Agarwal).
|
||||
* configured and built BLAS library via `mkdir build; cd build; cmake ..; make blas`
|
||||
* Requested threading via `export OMP_NUM_THREADS=1` (single-threaded)
|
||||
* Requested threading via `export OMP_NUM_THREADS=32` (multithreaded, 32 cores)
|
||||
* Requested threading via `export OMP_NUM_THREADS=64` (multithreaded, 64 cores)
|
||||
* **NOTE**: This version of Eigen does not provide multithreaded implementations of `symm`/`hemm`, `syrk`/`herk`, `trmm`, or `trsm`, and therefore those curves are omitted from the multithreaded graphs.
|
||||
* MKL 2019 update 1
|
||||
* Requested threading via `export MKL_NUM_THREADS=1` (single-threaded)
|
||||
* Requested threading via `export MKL_NUM_THREADS=32` (multithreaded, 32 cores)
|
||||
* Requested threading via `export MKL_NUM_THREADS=64` (multithreaded, 64 cores)
|
||||
* Affinity:
|
||||
* Thread affinity for BLIS was specified manually via `GOMP_CPU_AFFINITY="0 1 2 3 ... 63"`. However, multithreaded OpenBLAS appears to revert to single-threaded execution if `GOMP_CPU_AFFINITY` is set. Therefore, when measuring OpenBLAS performance, the `GOMP_CPU_AFFINITY` was unset.
|
||||
* Thread affinity for BLIS was specified manually via `GOMP_CPU_AFFINITY="0 1 2 3 ... 63"`. However, multithreaded OpenBLAS appears to revert to single-threaded execution if `GOMP_CPU_AFFINITY` is set. Therefore, when measuring OpenBLAS performance, the `GOMP_CPU_AFFINITY` environment variable was unset.
|
||||
* Frequency throttling (via `cpupower`):
|
||||
* Driver: acpi-cpufreq
|
||||
* Governor: performance
|
||||
|
||||
Binary file not shown.
Binary file not shown.
|
Before Width: | Height: | Size: 102 KiB After Width: | Height: | Size: 107 KiB |
Binary file not shown.
Binary file not shown.
|
Before Width: | Height: | Size: 105 KiB After Width: | Height: | Size: 114 KiB |
Binary file not shown.
Binary file not shown.
|
Before Width: | Height: | Size: 66 KiB After Width: | Height: | Size: 76 KiB |
Binary file not shown.
Binary file not shown.
|
Before Width: | Height: | Size: 91 KiB After Width: | Height: | Size: 95 KiB |
Binary file not shown.
Binary file not shown.
|
Before Width: | Height: | Size: 90 KiB After Width: | Height: | Size: 97 KiB |
Binary file not shown.
Binary file not shown.
|
Before Width: | Height: | Size: 69 KiB After Width: | Height: | Size: 81 KiB |
Binary file not shown.
Binary file not shown.
|
Before Width: | Height: | Size: 98 KiB After Width: | Height: | Size: 102 KiB |
Binary file not shown.
Binary file not shown.
|
Before Width: | Height: | Size: 94 KiB After Width: | Height: | Size: 100 KiB |
Binary file not shown.
Binary file not shown.
|
Before Width: | Height: | Size: 75 KiB After Width: | Height: | Size: 83 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 92 KiB After Width: | Height: | Size: 92 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 100 KiB After Width: | Height: | Size: 100 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 70 KiB After Width: | Height: | Size: 70 KiB |
174
test/3/Makefile
174
test/3/Makefile
@@ -81,22 +81,11 @@ endif
|
||||
|
||||
|
||||
#
|
||||
# --- BLAS and LAPACK implementations ------------------------------------------
|
||||
# --- BLAS implementations -----------------------------------------------------
|
||||
#
|
||||
|
||||
# BLIS library and header path. This is simply wherever it was installed.
|
||||
#BLIS_LIB_PATH := $(INSTALL_PREFIX)/lib
|
||||
#BLIS_INC_PATH := $(INSTALL_PREFIX)/include/blis
|
||||
|
||||
# BLIS library.
|
||||
#BLIS_LIB := $(BLIS_LIB_PATH)/libblis.a
|
||||
|
||||
# BLAS library path(s). This is where the BLAS libraries reside.
|
||||
HOME_LIB_PATH := $(HOME)/flame/lib
|
||||
#VENDOR_LIB_PATH := /opt/apps/intel/13/composer_xe_2013.2.146/mkl/lib/intel64
|
||||
MKL_LIB_PATH := $(HOME)/intel/mkl/lib/intel64
|
||||
#VENDOR_LIB_PATH := ${MKLROOT}/lib/intel64
|
||||
#ICC_LIB_PATH := /opt/apps/intel/13/composer_xe_2013.2.146/compiler/lib/intel64
|
||||
HOME_LIB_PATH := $(HOME)/flame/lib
|
||||
|
||||
# OpenBLAS
|
||||
OPENBLAS_LIB := $(HOME_LIB_PATH)/libopenblas.a
|
||||
@@ -106,7 +95,13 @@ OPENBLASP_LIB := $(HOME_LIB_PATH)/libopenblasp.a
|
||||
#ATLAS_LIB := $(HOME_LIB_PATH)/libf77blas.a \
|
||||
# $(HOME_LIB_PATH)/libatlas.a
|
||||
|
||||
# Eigen
|
||||
EIGEN_INC := $(HOME)/flame/eigen/include/eigen3
|
||||
EIGEN_LIB := $(HOME_LIB_PATH)/libeigen_blas_static.a
|
||||
EIGENP_LIB := $(EIGEN_LIB)
|
||||
|
||||
# MKL
|
||||
MKL_LIB_PATH := $(HOME)/intel/mkl/lib/intel64
|
||||
MKL_LIB := -L$(MKL_LIB_PATH) \
|
||||
-lmkl_intel_lp64 \
|
||||
-lmkl_core \
|
||||
@@ -176,10 +171,19 @@ CFLAGS += -I$(TEST_SRC_PATH)
|
||||
# Locate the libblis library to which we will link.
|
||||
LIBBLIS_LINK := $(LIB_PATH)/$(LIBBLIS_L)
|
||||
|
||||
# Define a set of CFLAGS for use with C++ and Eigen.
|
||||
CXXFLAGS := $(subst -std=c99,-std=c++11,$(CFLAGS))
|
||||
CXXFLAGS += -I$(EIGEN_INC)
|
||||
|
||||
# Create a copy of CXXFLAGS without -fopenmp in order to disable multithreading.
|
||||
CXXFLAGS_ST := -march=native $(subst -fopenmp,,$(CXXFLAGS))
|
||||
CXXFLAGS_MT := -march=native $(CXXFLAGS)
|
||||
|
||||
|
||||
# Which library?
|
||||
BLI_DEF := -DBLIS
|
||||
BLA_DEF := -DBLAS
|
||||
EIG_DEF := -DEIGEN
|
||||
|
||||
# Complex implementation type
|
||||
D3MHW := -DIND=BLIS_3MH
|
||||
@@ -199,6 +203,7 @@ DNAT := -DIND=BLIS_NAT
|
||||
#STR_1M := -DSTR=\"1m\"
|
||||
STR_NAT := -DSTR=\"asm_blis\"
|
||||
STR_OBL := -DSTR=\"openblas\"
|
||||
STR_EIG := -DSTR=\"eigen\"
|
||||
STR_VEN := -DSTR=\"vendor\"
|
||||
|
||||
# Single or multithreaded string
|
||||
@@ -220,6 +225,7 @@ PDEF_2S := -DP_BEGIN=$(P2_BEGIN) -DP_INC=$(P2_INC) -DP_MAX=$(P2_MAX)
|
||||
all: all-st all-1s all-2s
|
||||
blis: blis-st blis-1s blis-2s
|
||||
openblas: openblas-st openblas-1s openblas-2s
|
||||
eigen: eigen-st eigen-1s eigen-2s
|
||||
vendor: vendor-st vendor-1s vendor-2s
|
||||
mkl: vendor
|
||||
armpl: vendor
|
||||
@@ -236,9 +242,10 @@ blis-2s: blis-nat-2s
|
||||
blis-nat: blis-nat-st blis-nat-1s blis-nat-2s
|
||||
|
||||
# Define the datatypes, operations, and implementations.
|
||||
DTS := s d c z
|
||||
OPS := gemm hemm herk trmm trsm
|
||||
IMPLS := asm_blis openblas vendor
|
||||
DTS := s d c z
|
||||
OPS := gemm hemm herk trmm trsm
|
||||
BIMPLS := asm_blis openblas vendor
|
||||
EIMPLS := eigen
|
||||
|
||||
# Define functions to construct object filenames from the datatypes and
|
||||
# operations given an implementation. We define one function for single-
|
||||
@@ -263,6 +270,13 @@ OPENBLAS_1S_BINS := $(patsubst %.o,%.x,$(OPENBLAS_1S_OBJS))
|
||||
OPENBLAS_2S_OBJS := $(call get-2s-objs,openblas)
|
||||
OPENBLAS_2S_BINS := $(patsubst %.o,%.x,$(OPENBLAS_2S_OBJS))
|
||||
|
||||
EIGEN_ST_OBJS := $(call get-st-objs,eigen)
|
||||
EIGEN_ST_BINS := $(patsubst %.o,%.x,$(EIGEN_ST_OBJS))
|
||||
EIGEN_1S_OBJS := $(call get-1s-objs,eigen)
|
||||
EIGEN_1S_BINS := $(patsubst %.o,%.x,$(EIGEN_1S_OBJS))
|
||||
EIGEN_2S_OBJS := $(call get-2s-objs,eigen)
|
||||
EIGEN_2S_BINS := $(patsubst %.o,%.x,$(EIGEN_2S_OBJS))
|
||||
|
||||
VENDOR_ST_OBJS := $(call get-st-objs,vendor)
|
||||
VENDOR_ST_BINS := $(patsubst %.o,%.x,$(VENDOR_ST_OBJS))
|
||||
VENDOR_1S_OBJS := $(call get-1s-objs,vendor)
|
||||
@@ -279,6 +293,10 @@ openblas-st: $(OPENBLAS_ST_BINS)
|
||||
openblas-1s: $(OPENBLAS_1S_BINS)
|
||||
openblas-2s: $(OPENBLAS_2S_BINS)
|
||||
|
||||
eigen-st: $(EIGEN_ST_BINS)
|
||||
eigen-1s: $(EIGEN_1S_BINS)
|
||||
eigen-2s: $(EIGEN_2S_BINS)
|
||||
|
||||
vendor-st: $(VENDOR_ST_BINS)
|
||||
vendor-1s: $(VENDOR_1S_BINS)
|
||||
vendor-2s: $(VENDOR_2S_BINS)
|
||||
@@ -293,9 +311,10 @@ armpl-2s: vendor-2s
|
||||
|
||||
# Mark the object files as intermediate so that make will remove them
|
||||
# automatically after building the binaries on which they depend.
|
||||
.INTERMEDIATE: $(BLIS_NAT_ST_OBJS) $(OPENBLAS_ST_OBJS) $(VENDOR_ST_OBJS)
|
||||
.INTERMEDIATE: $(BLIS_NAT_1S_OBJS) $(OPENBLAS_1S_OBJS) $(VENDOR_1S_OBJS)
|
||||
.INTERMEDIATE: $(BLIS_NAT_2S_OBJS) $(OPENBLAS_2S_OBJS) $(VENDOR_2S_OBJS)
|
||||
.INTERMEDIATE: $(BLIS_NAT_ST_OBJS) $(BLIS_NAT_1S_OBJS) $(BLIS_NAT_2S_OBJS)
|
||||
.INTERMEDIATE: $(OPENBLAS_ST_OBJS) $(OPENBLAS_1S_OBJS) $(OPENBLAS_2S_OBJS)
|
||||
.INTERMEDIATE: $(EIGEN_ST_OBJS) $(EIGEN_1S_OBJS) $(EIGEN_2S_OBJS)
|
||||
.INTERMEDIATE: $(VENDOR_ST_OBJS) $(VENDOR_1S_OBJS) $(VENDOR_2S_OBJS)
|
||||
|
||||
|
||||
# --Object file rules --
|
||||
@@ -305,41 +324,86 @@ armpl-2s: vendor-2s
|
||||
|
||||
# A function to return the datatype cpp macro def from the datatype
|
||||
# character.
|
||||
get-dt-cpp = -DDT=bli_$(1)type
|
||||
get-dt-cpp = $(strip \
|
||||
$(if $(findstring s,$(1)),-DDT=BLIS_FLOAT -DIS_FLOAT,\
|
||||
$(if $(findstring d,$(1)),-DDT=BLIS_DOUBLE -DIS_DOUBLE,\
|
||||
$(if $(findstring c,$(1)),-DDT=BLIS_SCOMPLEX -DIS_SCOMPLEX,\
|
||||
-DDT=BLIS_DCOMPLEX -DIS_DCOMPLEX))))
|
||||
|
||||
# A function to return other cpp macros that help the test driver
|
||||
# identify the implementation.
|
||||
#get-bl-cpp = $(strip \
|
||||
# $(if $(findstring blis,$(1)),$(STR_NAT) $(BLI_DEF),\
|
||||
# $(if $(findstring openblas,$(1)),$(STR_OBL) $(BLA_DEF),\
|
||||
# $(if $(findstring eigen,$(1)),$(STR_EIG) $(EIG_DEF),\
|
||||
# $(STR_VEN) $(BLA_DEF)))))
|
||||
|
||||
get-bl-cpp = $(strip \
|
||||
$(if $(findstring blis,$(1)),$(STR_NAT) $(BLI_DEF),\
|
||||
$(if $(findstring openblas,$(1)),$(STR_OBL) $(BLA_DEF),\
|
||||
$(STR_VEN) $(BLA_DEF))))
|
||||
$(if $(and $(findstring eigen,$(1)),\
|
||||
$(findstring gemm,$(2))),\
|
||||
$(STR_EIG) $(EIG_DEF),\
|
||||
$(if $(findstring eigen,$(1)),\
|
||||
$(STR_EIG) $(BLA_DEF),\
|
||||
$(STR_VEN) $(BLA_DEF))))))
|
||||
|
||||
|
||||
# Rules for BLIS and BLAS libraries.
|
||||
define make-st-rule
|
||||
test_$(1)$(2)_$(PS_MAX)_$(3)_st.o: test_$(op).c Makefile
|
||||
$(CC) $(CFLAGS) $(PDEF_ST) $(call get-dt-cpp,$(1)) $(call get-bl-cpp,$(3)) $(DNAT) $(STR_ST) -c $$< -o $$@
|
||||
$(CC) $(CFLAGS) $(PDEF_ST) $(call get-dt-cpp,$(1)) $(call get-bl-cpp,$(3),$(2)) $(DNAT) $(STR_ST) -c $$< -o $$@
|
||||
endef
|
||||
|
||||
define make-1s-rule
|
||||
test_$(1)$(2)_$(P1_MAX)_$(3)_1s.o: test_$(op).c Makefile
|
||||
$(CC) $(CFLAGS) $(PDEF_1S) $(call get-dt-cpp,$(1)) $(call get-bl-cpp,$(3)) $(DNAT) $(STR_1S) -c $$< -o $$@
|
||||
$(CC) $(CFLAGS) $(PDEF_1S) $(call get-dt-cpp,$(1)) $(call get-bl-cpp,$(3),$(2)) $(DNAT) $(STR_1S) -c $$< -o $$@
|
||||
endef
|
||||
|
||||
define make-2s-rule
|
||||
test_$(1)$(2)_$(P2_MAX)_$(3)_2s.o: test_$(op).c Makefile
|
||||
$(CC) $(CFLAGS) $(PDEF_2S) $(call get-dt-cpp,$(1)) $(call get-bl-cpp,$(3)) $(DNAT) $(STR_2S) -c $$< -o $$@
|
||||
$(CC) $(CFLAGS) $(PDEF_2S) $(call get-dt-cpp,$(1)) $(call get-bl-cpp,$(3),$(2)) $(DNAT) $(STR_2S) -c $$< -o $$@
|
||||
endef
|
||||
|
||||
$(foreach dt,$(DTS), \
|
||||
$(foreach op,$(OPS), \
|
||||
$(foreach im,$(IMPLS),$(eval $(call make-st-rule,$(dt),$(op),$(im))))))
|
||||
$(foreach im,$(BIMPLS),$(eval $(call make-st-rule,$(dt),$(op),$(im))))))
|
||||
|
||||
$(foreach dt,$(DTS), \
|
||||
$(foreach op,$(OPS), \
|
||||
$(foreach im,$(IMPLS),$(eval $(call make-1s-rule,$(dt),$(op),$(im))))))
|
||||
$(foreach im,$(BIMPLS),$(eval $(call make-1s-rule,$(dt),$(op),$(im))))))
|
||||
|
||||
$(foreach dt,$(DTS), \
|
||||
$(foreach op,$(OPS), \
|
||||
$(foreach im,$(IMPLS),$(eval $(call make-2s-rule,$(dt),$(op),$(im))))))
|
||||
$(foreach im,$(BIMPLS),$(eval $(call make-2s-rule,$(dt),$(op),$(im))))))
|
||||
|
||||
# Rules for Eigen.
|
||||
define make-eigst-rule
|
||||
test_$(1)$(2)_$(PS_MAX)_$(3)_st.o: test_$(op).c Makefile
|
||||
$(CXX) $(CXXFLAGS_ST) $(PDEF_ST) $(call get-dt-cpp,$(1)) $(call get-bl-cpp,$(3),$(2)) $(DNAT) $(STR_ST) -c $$< -o $$@
|
||||
endef
|
||||
|
||||
define make-eig1s-rule
|
||||
test_$(1)$(2)_$(P1_MAX)_$(3)_1s.o: test_$(op).c Makefile
|
||||
$(CXX) $(CXXFLAGS_MT) $(PDEF_1S) $(call get-dt-cpp,$(1)) $(call get-bl-cpp,$(3),$(2)) $(DNAT) $(STR_1S) -c $$< -o $$@
|
||||
endef
|
||||
|
||||
define make-eig2s-rule
|
||||
test_$(1)$(2)_$(P2_MAX)_$(3)_2s.o: test_$(op).c Makefile
|
||||
$(CXX) $(CXXFLAGS_MT) $(PDEF_2S) $(call get-dt-cpp,$(1)) $(call get-bl-cpp,$(3),$(2)) $(DNAT) $(STR_2S) -c $$< -o $$@
|
||||
endef
|
||||
|
||||
$(foreach dt,$(DTS), \
|
||||
$(foreach op,$(OPS), \
|
||||
$(foreach im,$(EIMPLS),$(eval $(call make-eigst-rule,$(dt),$(op),$(im))))))
|
||||
|
||||
$(foreach dt,$(DTS), \
|
||||
$(foreach op,$(OPS), \
|
||||
$(foreach im,$(EIMPLS),$(eval $(call make-eig1s-rule,$(dt),$(op),$(im))))))
|
||||
|
||||
$(foreach dt,$(DTS), \
|
||||
$(foreach op,$(OPS), \
|
||||
$(foreach im,$(EIMPLS),$(eval $(call make-eig2s-rule,$(dt),$(op),$(im))))))
|
||||
|
||||
|
||||
# -- Executable file rules --
|
||||
@@ -349,34 +413,44 @@ $(foreach im,$(IMPLS),$(eval $(call make-2s-rule,$(dt),$(op),$(im))))))
|
||||
# compatibility layer. This prevents BLIS from inadvertently getting called
|
||||
# for the BLAS routines we are trying to test with.
|
||||
|
||||
test_%_$(PS_MAX)_openblas_st.x: test_%_$(PS_MAX)_openblas_st.o $(LIBBLIS_LINK)
|
||||
$(LINKER) $(strip $< $(OPENBLAS_LIB) $(LIBBLIS_LINK) $(LDFLAGS) -o $@)
|
||||
|
||||
test_%_$(P1_MAX)_openblas_1s.x: test_%_$(P1_MAX)_openblas_1s.o $(LIBBLIS_LINK)
|
||||
$(LINKER) $(strip $< $(OPENBLASP_LIB) $(LIBBLIS_LINK) $(LDFLAGS) -o $@)
|
||||
|
||||
test_%_$(P2_MAX)_openblas_2s.x: test_%_$(P2_MAX)_openblas_2s.o $(LIBBLIS_LINK)
|
||||
$(LINKER) $(strip $< $(OPENBLASP_LIB) $(LIBBLIS_LINK) $(LDFLAGS) -o $@)
|
||||
|
||||
|
||||
test_%_$(PS_MAX)_vendor_st.x: test_%_$(PS_MAX)_vendor_st.o $(LIBBLIS_LINK)
|
||||
$(LINKER) $(strip $< $(VENDOR_LIB) $(LIBBLIS_LINK) $(LDFLAGS) -o $@)
|
||||
|
||||
test_%_$(P1_MAX)_vendor_1s.x: test_%_$(P1_MAX)_vendor_1s.o $(LIBBLIS_LINK)
|
||||
$(LINKER) $(strip $< $(VENDORP_LIB) $(LIBBLIS_LINK) $(LDFLAGS) -o $@)
|
||||
|
||||
test_%_$(P2_MAX)_vendor_2s.x: test_%_$(P2_MAX)_vendor_2s.o $(LIBBLIS_LINK)
|
||||
$(LINKER) $(strip $< $(VENDORP_LIB) $(LIBBLIS_LINK) $(LDFLAGS) -o $@)
|
||||
|
||||
|
||||
test_%_$(PS_MAX)_asm_blis_st.x: test_%_$(PS_MAX)_asm_blis_st.o $(LIBBLIS_LINK)
|
||||
$(LINKER) $(strip $< $(LIBBLIS_LINK) $(LDFLAGS) -o $@)
|
||||
$(CC) $(strip $< $(LIBBLIS_LINK) $(LDFLAGS) -o $@)
|
||||
|
||||
test_%_$(P1_MAX)_asm_blis_1s.x: test_%_$(P1_MAX)_asm_blis_1s.o $(LIBBLIS_LINK)
|
||||
$(LINKER) $(strip $< $(LIBBLIS_LINK) $(LDFLAGS) -o $@)
|
||||
$(CC) $(strip $< $(LIBBLIS_LINK) $(LDFLAGS) -o $@)
|
||||
|
||||
test_%_$(P2_MAX)_asm_blis_2s.x: test_%_$(P2_MAX)_asm_blis_2s.o $(LIBBLIS_LINK)
|
||||
$(LINKER) $(strip $< $(LIBBLIS_LINK) $(LDFLAGS) -o $@)
|
||||
$(CC) $(strip $< $(LIBBLIS_LINK) $(LDFLAGS) -o $@)
|
||||
|
||||
|
||||
test_%_$(PS_MAX)_openblas_st.x: test_%_$(PS_MAX)_openblas_st.o $(LIBBLIS_LINK)
|
||||
$(CC) $(strip $< $(OPENBLAS_LIB) $(LIBBLIS_LINK) $(LDFLAGS) -o $@)
|
||||
|
||||
test_%_$(P1_MAX)_openblas_1s.x: test_%_$(P1_MAX)_openblas_1s.o $(LIBBLIS_LINK)
|
||||
$(CC) $(strip $< $(OPENBLASP_LIB) $(LIBBLIS_LINK) $(LDFLAGS) -o $@)
|
||||
|
||||
test_%_$(P2_MAX)_openblas_2s.x: test_%_$(P2_MAX)_openblas_2s.o $(LIBBLIS_LINK)
|
||||
$(CC) $(strip $< $(OPENBLASP_LIB) $(LIBBLIS_LINK) $(LDFLAGS) -o $@)
|
||||
|
||||
|
||||
test_%_$(PS_MAX)_eigen_st.x: test_%_$(PS_MAX)_eigen_st.o $(LIBBLIS_LINK)
|
||||
$(CXX) $(strip $< $(EIGEN_LIB) $(LIBBLIS_LINK) $(LDFLAGS) -o $@)
|
||||
|
||||
test_%_$(P1_MAX)_eigen_1s.x: test_%_$(P1_MAX)_eigen_1s.o $(LIBBLIS_LINK)
|
||||
$(CXX) $(strip $< $(EIGENP_LIB) $(LIBBLIS_LINK) $(LDFLAGS) -o $@)
|
||||
|
||||
test_%_$(P2_MAX)_eigen_2s.x: test_%_$(P2_MAX)_eigen_2s.o $(LIBBLIS_LINK)
|
||||
$(CXX) $(strip $< $(EIGENP_LIB) $(LIBBLIS_LINK) $(LDFLAGS) -o $@)
|
||||
|
||||
|
||||
test_%_$(PS_MAX)_vendor_st.x: test_%_$(PS_MAX)_vendor_st.o $(LIBBLIS_LINK)
|
||||
$(CC) $(strip $< $(VENDOR_LIB) $(LIBBLIS_LINK) $(LDFLAGS) -o $@)
|
||||
|
||||
test_%_$(P1_MAX)_vendor_1s.x: test_%_$(P1_MAX)_vendor_1s.o $(LIBBLIS_LINK)
|
||||
$(CC) $(strip $< $(VENDORP_LIB) $(LIBBLIS_LINK) $(LDFLAGS) -o $@)
|
||||
|
||||
test_%_$(P2_MAX)_vendor_2s.x: test_%_$(P2_MAX)_vendor_2s.o $(LIBBLIS_LINK)
|
||||
$(CC) $(strip $< $(VENDORP_LIB) $(LIBBLIS_LINK) $(LDFLAGS) -o $@)
|
||||
|
||||
|
||||
# -- Clean rules --
|
||||
|
||||
@@ -1,9 +1,11 @@
|
||||
function r_val = plot_l3_perf( opname, ...
|
||||
data_blis, ...
|
||||
data_open, ...
|
||||
data_eige, ...
|
||||
data_vend, vend_str, ...
|
||||
nth, ...
|
||||
rows, cols, ...
|
||||
with_eigen, ...
|
||||
cfreq, ...
|
||||
dfps, ...
|
||||
theid )
|
||||
@@ -16,6 +18,7 @@ end
|
||||
% Set line properties.
|
||||
color_blis = 'k'; lines_blis = '-'; markr_blis = '';
|
||||
color_open = 'r'; lines_open = '--'; markr_open = 'o';
|
||||
color_eige = 'm'; lines_eige = '-.'; markr_eige = 'x';
|
||||
color_vend = 'b'; lines_vend = '-.'; markr_vend = '.';
|
||||
|
||||
% Compute the peak performance in terms of the number of double flops
|
||||
@@ -48,6 +51,7 @@ titlename = sprintf( titlename, title_opname );
|
||||
% Set the legend strings.
|
||||
blis_legend = sprintf( 'BLIS' );
|
||||
open_legend = sprintf( 'OpenBLAS' );
|
||||
eige_legend = sprintf( 'Eigen' );
|
||||
%vend_legend = sprintf( 'MKL' );
|
||||
%vend_legend = sprintf( 'ARMPL' );
|
||||
vend_legend = vend_str;
|
||||
@@ -96,6 +100,15 @@ blis_ln = line( x_axis( :, 1 ), data_blis( :, flopscol ) / nth, ...
|
||||
open_ln = line( x_axis( :, 1 ), data_open( :, flopscol ) / nth, ...
|
||||
'Color',color_open, 'LineStyle',lines_open, ...
|
||||
'LineWidth',linesize );
|
||||
if data_eige(1,1) ~= -1
|
||||
eige_ln = line( x_axis( :, 1 ), data_eige( :, flopscol ) / nth, ...
|
||||
'Color',color_eige, 'LineStyle',lines_eige, ...
|
||||
'LineWidth',linesize );
|
||||
else
|
||||
eige_ln = line( nan, nan, ...
|
||||
'Color',color_eige, 'LineStyle',lines_eige, ...
|
||||
'LineWidth',linesize );
|
||||
end
|
||||
vend_ln = line( x_axis( :, 1 ), data_vend( :, flopscol ) / nth, ...
|
||||
'Color',color_vend, 'LineStyle',lines_vend, ...
|
||||
'LineWidth',linesize );
|
||||
@@ -121,45 +134,41 @@ end
|
||||
if rows == 4 && cols == 5
|
||||
|
||||
if nth == 1 && theid == 3
|
||||
leg = legend( ...
|
||||
[ ...
|
||||
blis_ln ...
|
||||
open_ln ...
|
||||
vend_ln ...
|
||||
], ...
|
||||
blis_legend, ...
|
||||
open_legend, ...
|
||||
vend_legend, ...
|
||||
'Location', legend_loc );
|
||||
set( leg,'Box','off' );
|
||||
set( leg,'Color','none' );
|
||||
set( leg,'FontSize',fontsize-3 );
|
||||
set( leg,'Units','inches' );
|
||||
set( leg,'Position',[11.20 12.75 0.7 0.3 ] ); % (0,2br)
|
||||
if with_eigen == 1
|
||||
leg = legend( [ blis_ln open_ln eige_ln vend_ln ], ...
|
||||
blis_legend, open_legend, eige_legend, vend_legend, ...
|
||||
'Location', legend_loc );
|
||||
else
|
||||
leg = legend( [ blis_ln open_ln vend_ln ], ...
|
||||
blis_legend, open_legend, vend_legend, ...
|
||||
'Location', legend_loc );
|
||||
end
|
||||
set( leg,'Box','off','Color','none','Units','inches','FontSize',fontsize-3 );
|
||||
%set( leg,'Position',[11.20 12.81 0.7 0.3 ] ); % (0,2br)
|
||||
set( leg,'Position',[ 4.20 12.81 0.7 0.3 ] ); % (0,0br)
|
||||
elseif nth > 1 && theid == 4
|
||||
leg = legend( ...
|
||||
[ ...
|
||||
blis_ln ...
|
||||
open_ln ...
|
||||
vend_ln ...
|
||||
], ...
|
||||
blis_legend, ...
|
||||
open_legend, ...
|
||||
vend_legend, ...
|
||||
'Location', legend_loc );
|
||||
set( leg,'Box','off' );
|
||||
set( leg,'Color','none' );
|
||||
set( leg,'FontSize',fontsize-3 );
|
||||
set( leg,'Units','inches' );
|
||||
%set( leg,'Position',[7.70 12.75 0.7 0.3 ] ); % (0,1br)
|
||||
set( leg,'Position',[10.47 14.28 0.7 0.3 ] ); % (0,2tl)
|
||||
if with_eigen == 1
|
||||
leg = legend( [ blis_ln open_ln eige_ln vend_ln ], ...
|
||||
blis_legend, open_legend, eige_legend, vend_legend, ...
|
||||
'Location', legend_loc );
|
||||
else
|
||||
leg = legend( [ blis_ln open_ln vend_ln ], ...
|
||||
blis_legend, open_legend, vend_legend, ...
|
||||
'Location', legend_loc );
|
||||
end
|
||||
set( leg,'Box','off','Color','none','Units','inches','FontSize',fontsize-3 );
|
||||
%set( leg,'Position',[7.70 12.81 0.7 0.3 ] ); % (0,1br)
|
||||
set( leg,'Position',[10.47 14.17 0.7 0.3 ] ); % (0,2tl)
|
||||
end
|
||||
end
|
||||
%set( leg,'Position',[ 4.20 12.75 0.7 0.3 ] ); % (0,0br)
|
||||
%set( leg,'Position',[ 7.70 12.75 0.7 0.3 ] ); % (0,1br)
|
||||
%set( leg,'Position',[10.47 14.28 0.7 0.3 ] ); % (0,2tl)
|
||||
%set( leg,'Position',[11.20 12.75 0.7 0.3 ] ); % (0,2br)
|
||||
%set( leg,'Position',[13.95 14.28 0.7 0.3 ] ); % (0,3tl)
|
||||
%set( leg,'Position',[14.70 12.75 0.7 0.3 ] ); % (0,3br)
|
||||
%set( leg,'Position',[17.45 14.28 0.7 0.3 ] ); % (0,4tl)
|
||||
%set( leg,'Position',[18.22 12.75 0.7 0.3 ] ); % (0,4br)
|
||||
end
|
||||
end
|
||||
|
||||
set( ax1,'FontSize',fontsize );
|
||||
set( ax1,'TitleFontSizeMultiplier',1.0 ); % default is 1.1.
|
||||
|
||||
@@ -4,7 +4,8 @@ function r_val = plot_panel_4x5( cfreq, ...
|
||||
thr_str, ...
|
||||
dirpath, ...
|
||||
arch_str, ...
|
||||
vend_str )
|
||||
vend_str, ...
|
||||
with_eigen )
|
||||
|
||||
%cfreq = 1.8;
|
||||
%dflopspercycle = 32;
|
||||
@@ -13,6 +14,7 @@ function r_val = plot_panel_4x5( cfreq, ...
|
||||
% results.
|
||||
filetemp_blis = '%s/output_%s_%s_asm_blis.m';
|
||||
filetemp_open = '%s/output_%s_%s_openblas.m';
|
||||
filetemp_eige = '%s/output_%s_%s_eigen.m';
|
||||
filetemp_vend = '%s/output_%s_%s_vendor.m';
|
||||
|
||||
% Create a variable name "template" for the variables contained in the
|
||||
@@ -40,8 +42,8 @@ if 1 == 1 % matlab
|
||||
set(gcf,'PaperPosition', [0 0 11 15.0]);
|
||||
set(gcf,'PaperPositionMode','manual');
|
||||
else % octave 4.x
|
||||
set(gcf,'PaperSize', [15 19.0]);
|
||||
set(gcf,'PaperPositionMode','auto');
|
||||
set(gcf,'PaperSize', [15 19.0]);
|
||||
set(gcf,'PaperPositionMode','auto');
|
||||
end
|
||||
set(gcf,'PaperOrientation','landscape');
|
||||
|
||||
@@ -58,7 +60,7 @@ for opi = 1:n_opnames
|
||||
% Construct filenames for the data files from templates.
|
||||
file_blis = sprintf( filetemp_blis, dirpath, thr_str, opname );
|
||||
file_open = sprintf( filetemp_open, dirpath, thr_str, opname );
|
||||
file_vend = sprintf( filetemp_vend, dirpath, thr_str, opname );
|
||||
file_vend = sprintf( filetemp_vend, dirpath, thr_str, opname );
|
||||
|
||||
% Load the data files.
|
||||
%str = sprintf( ' Loading %s', file_blis ); disp(str);
|
||||
@@ -79,20 +81,38 @@ for opi = 1:n_opnames
|
||||
data_open = eval( var_open ); % e.g. data_st_sgemm_openblas( :, : );
|
||||
data_vend = eval( var_vend ); % e.g. data_st_sgemm_vendor( :, : );
|
||||
|
||||
% Only read Eigen data in select cases.
|
||||
if with_eigen == 1
|
||||
opname_u = opname; opname_u(1) = '_';
|
||||
if nth == 1 || strcmp( opname_u, '_gemm' )
|
||||
file_eige = sprintf( filetemp_eige, dirpath, thr_str, opname );
|
||||
run( file_eige )
|
||||
var_eige = sprintf( vartemp, thr_str, opname, 'eigen' );
|
||||
data_eige = eval( var_eige ); % e.g. data_st_sgemm_eigen( :, : );
|
||||
else
|
||||
data_eige(1,1) = -1;
|
||||
end
|
||||
else
|
||||
data_eige(1,1) = -1;
|
||||
end
|
||||
|
||||
% Plot one result in an m x n grid of plots, via the subplot()
|
||||
% function.
|
||||
plot_l3_perf( opname, ...
|
||||
data_blis, ...
|
||||
data_open, ...
|
||||
data_eige, ...
|
||||
data_vend, vend_str, ...
|
||||
nth, ...
|
||||
4, 5, ...
|
||||
with_eigen, ...
|
||||
cfreq, ...
|
||||
dflopspercycle, ...
|
||||
opi );
|
||||
|
||||
end
|
||||
|
||||
|
||||
% Construct the name of the file to which we will output the graph.
|
||||
outfile = sprintf( 'l3_perf_%s_nt%d.pdf', arch_str, nth );
|
||||
|
||||
|
||||
@@ -4,16 +4,32 @@ plot_panel_4x5(2.20,8,28,'1s','../results/tx2/20190205/jc4ic7','tx2_jc4ic7','ARM
|
||||
plot_panel_4x5(2.20,8,56,'2s','../results/tx2/20190205/jc8ic7','tx2_jc8ic7','ARMPL'); close; clear all;
|
||||
|
||||
% skx
|
||||
plot_panel_4x5(2.00,32,1, 'st','../results/skx/20190306/st', 'skx', 'MKL'); close; clear all;
|
||||
plot_panel_4x5(2.00,32,26,'1s','../results/skx/20190306/jc2ic13','skx_jc2ic13','MKL'); close; clear all;
|
||||
plot_panel_4x5(2.00,32,52,'2s','../results/skx/20190306/jc4ic13','skx_jc4ic13','MKL'); close; clear all;
|
||||
% pre-eigen:
|
||||
%plot_panel_4x5(2.00,32,1, 'st','../results/skx/20190306/st', 'skx', 'MKL'); close; clear all;
|
||||
%plot_panel_4x5(2.00,32,26,'1s','../results/skx/20190306/jc2ic13','skx_jc2ic13','MKL'); close; clear all;
|
||||
%plot_panel_4x5(2.00,32,52,'2s','../results/skx/20190306/jc4ic13','skx_jc4ic13','MKL'); close; clear all;
|
||||
% with eigen:
|
||||
plot_panel_4x5(2.00,32,1, 'st','../results/skx/merged20190306_0326/st', 'skx', 'MKL',1); close; clear all;
|
||||
plot_panel_4x5(2.00,32,26,'1s','../results/skx/merged20190306_0326/jc2ic13','skx_jc2ic13','MKL',1); close; clear all;
|
||||
plot_panel_4x5(2.00,32,52,'2s','../results/skx/merged20190306_0326/jc4ic13','skx_jc4ic13','MKL',1); close; clear all;
|
||||
|
||||
% has
|
||||
plot_panel_4x5(3.25,16,1, 'st','../results/has/20190206/st', 'has', 'MKL'); close; clear all;
|
||||
plot_panel_4x5(3.00,16,12,'1s','../results/has/20190206/jc2ic3jr2','has_jc2ic3jr2','MKL'); close; clear all;
|
||||
plot_panel_4x5(3.00,16,24,'2s','../results/has/20190206/jc4ic3jr2','has_jc4ic3jr2','MKL'); close; clear all;
|
||||
% pre-eigen:
|
||||
%plot_panel_4x5(3.25,16,1, 'st','../results/has/20190206/st', 'has', 'MKL',1); close; clear all;
|
||||
%plot_panel_4x5(3.00,16,12,'1s','../results/has/20190206/jc2ic3jr2','has_jc2ic3jr2','MKL',1); close; clear all;
|
||||
%plot_panel_4x5(3.00,16,24,'2s','../results/has/20190206/jc4ic3jr2','has_jc4ic3jr2','MKL',1); close; clear all;
|
||||
% with eigen:
|
||||
plot_panel_4x5(3.25,16,1, 'st','../results/has/merged20190206_0326/st', 'has', 'MKL',1); close; clear all;
|
||||
plot_panel_4x5(3.00,16,12,'1s','../results/has/merged20190206_0326/jc2ic3jr2','has_jc2ic3jr2','MKL',1); close; clear all;
|
||||
plot_panel_4x5(3.00,16,24,'2s','../results/has/merged20190206_0326/jc4ic3jr2','has_jc4ic3jr2','MKL',1); close; clear all;
|
||||
|
||||
% epyc
|
||||
plot_panel_4x5(3.00,8,1, 'st','../results/epyc/merged201903_0619/st','epyc', 'MKL'); close; clear all;
|
||||
plot_panel_4x5(2.55,8,32,'1s','../results/epyc/merged201903_0619/jc1ic8jr4','epyc_jc1ic8jr4','MKL'); close; clear all;
|
||||
plot_panel_4x5(2.55,8,64,'2s','../results/epyc/merged201903_0619/jc2ic8jr4','epyc_jc2ic8jr4','MKL'); close; clear all;
|
||||
% pre-eigen:
|
||||
%plot_panel_4x5(3.00,8,1, 'st','../results/epyc/merged201903_0619/st','epyc', 'MKL'); close; clear all;
|
||||
%plot_panel_4x5(2.55,8,32,'1s','../results/epyc/merged201903_0619/jc1ic8jr4','epyc_jc1ic8jr4','MKL'); close; clear all;
|
||||
%plot_panel_4x5(2.55,8,64,'2s','../results/epyc/merged201903_0619/jc2ic8jr4','epyc_jc2ic8jr4','MKL'); close; clear all;
|
||||
% with eigen:
|
||||
plot_panel_4x5(3.00,8,1, 'st','../results/epyc/merged20190306_0319_0326/st', 'epyc', 'MKL',1); close; clear all;
|
||||
plot_panel_4x5(2.55,8,32,'1s','../results/epyc/merged20190306_0319_0326/jc1ic8jr4','epyc_jc1ic8jr4','MKL',1); close; clear all;
|
||||
plot_panel_4x5(2.55,8,64,'2s','../results/epyc/merged20190306_0319_0326/jc2ic8jr4','epyc_jc2ic8jr4','MKL',1); close; clear all;
|
||||
|
||||
|
||||
@@ -21,7 +21,8 @@ if [ ${sys} = "blis" ]; then
|
||||
export GOMP_CPU_AFFINITY="0 1 2 3"
|
||||
|
||||
threads="jc1ic1jr1_2400
|
||||
jc2ic2jr1_4000"
|
||||
jc2ic3jr2_6000
|
||||
jc4ic3jr2_8000"
|
||||
|
||||
elif [ ${sys} = "stampede2" ]; then
|
||||
|
||||
@@ -70,18 +71,27 @@ test_dts="d s z c"
|
||||
test_ops="gemm hemm herk trmm trsm"
|
||||
|
||||
# Implementations to test.
|
||||
impls="all"
|
||||
#impls="other"
|
||||
#impls="blis"
|
||||
#impls="other"
|
||||
impls="eigen"
|
||||
#impls="all"
|
||||
|
||||
if [ "${impls}" = "blis" ]; then
|
||||
|
||||
test_impls="asm_blis"
|
||||
|
||||
elif [ "${impls}" = "eigen" ]; then
|
||||
|
||||
test_impls="eigen"
|
||||
|
||||
elif [ "${impls}" = "other" ]; then
|
||||
|
||||
test_impls="openblas vendor"
|
||||
|
||||
elif [ "${impls}" = "eigen" ]; then
|
||||
|
||||
test_impls="eigen"
|
||||
|
||||
else
|
||||
|
||||
test_impls="openblas asm_blis vendor"
|
||||
@@ -138,6 +148,15 @@ for th in ${threads}; do
|
||||
|
||||
for op in ${test_ops}; do
|
||||
|
||||
# Eigen does not support multithreading for hemm, herk, trmm,
|
||||
# or trsm. So if we're getting ready to execute an Eigen driver
|
||||
# for one of these operations and nt > 1, we skip this test.
|
||||
if [ "${im}" = "eigen" ] && \
|
||||
[ "${op}" != "gemm" ] && \
|
||||
[ "${nt}" != "1" ]; then
|
||||
continue;
|
||||
fi
|
||||
|
||||
# Find the threading suffix by probing the executable.
|
||||
binname=$(ls ${exec_root}_${dt}${op}_${psize}_${im}_*.x)
|
||||
suf_ext=${binname##*_}
|
||||
@@ -148,13 +167,24 @@ for th in ${threads}; do
|
||||
# Set the number of threads according to th.
|
||||
if [ "${suf}" = "1s" ] || [ "${suf}" = "2s" ]; then
|
||||
|
||||
export BLIS_JC_NT=${jc_nt}
|
||||
export BLIS_PC_NT=${pc_nt}
|
||||
export BLIS_IC_NT=${ic_nt}
|
||||
export BLIS_JR_NT=${jr_nt}
|
||||
export BLIS_IR_NT=${ir_nt}
|
||||
export OPENBLAS_NUM_THREADS=${nt}
|
||||
export MKL_NUM_THREADS=${nt}
|
||||
# Set the threading parameters based on the implementation
|
||||
# that we are preparing to run.
|
||||
if [ "${im}" = "asm_blis" ]; then
|
||||
unset OMP_NUM_THREADS
|
||||
export BLIS_JC_NT=${jc_nt}
|
||||
export BLIS_PC_NT=${pc_nt}
|
||||
export BLIS_IC_NT=${ic_nt}
|
||||
export BLIS_JR_NT=${jr_nt}
|
||||
export BLIS_IR_NT=${ir_nt}
|
||||
elif [ "${im}" = "openblas" ]; then
|
||||
unset OMP_NUM_THREADS
|
||||
export OPENBLAS_NUM_THREADS=${nt}
|
||||
elif [ "${im}" = "eigen" ]; then
|
||||
export OMP_NUM_THREADS=${nt}
|
||||
elif [ "${im}" = "vendor" ]; then
|
||||
unset OMP_NUM_THREADS
|
||||
export MKL_NUM_THREADS=${nt}
|
||||
fi
|
||||
export nt_use=${nt}
|
||||
|
||||
# Multithreaded OpenBLAS seems to have a problem running
|
||||
@@ -173,6 +203,7 @@ for th in ${threads}; do
|
||||
export BLIS_IC_NT=1
|
||||
export BLIS_JR_NT=1
|
||||
export BLIS_IR_NT=1
|
||||
export OMP_NUM_THREADS=1
|
||||
export OPENBLAS_NUM_THREADS=1
|
||||
export MKL_NUM_THREADS=1
|
||||
export nt_use=1
|
||||
|
||||
@@ -33,7 +33,15 @@
|
||||
*/
|
||||
|
||||
#include <unistd.h>
|
||||
#include "blis.h"
|
||||
#ifdef EIGEN
|
||||
#define BLIS_DISABLE_BLAS_DEFS
|
||||
#include "blis.h"
|
||||
#include <Eigen/Core>
|
||||
#include <Eigen/src/misc/blas.h>
|
||||
using namespace Eigen;
|
||||
#else
|
||||
#include "blis.h"
|
||||
#endif
|
||||
|
||||
//#define PRINT
|
||||
|
||||
@@ -161,6 +169,42 @@ int main( int argc, char** argv )
|
||||
bli_ind_enable_dt( ind, dt );
|
||||
#endif
|
||||
|
||||
#ifdef EIGEN
|
||||
double alpha_r, alpha_i;
|
||||
|
||||
bli_getsc( &alpha, &alpha_r, &alpha_i );
|
||||
|
||||
void* ap = bli_obj_buffer_at_off( &a );
|
||||
void* bp = bli_obj_buffer_at_off( &b );
|
||||
void* cp = bli_obj_buffer_at_off( &c );
|
||||
|
||||
const int os_a = bli_obj_col_stride( &a );
|
||||
const int os_b = bli_obj_col_stride( &b );
|
||||
const int os_c = bli_obj_col_stride( &c );
|
||||
|
||||
Stride<Dynamic,1> stride_a( os_a, 1 );
|
||||
Stride<Dynamic,1> stride_b( os_b, 1 );
|
||||
Stride<Dynamic,1> stride_c( os_c, 1 );
|
||||
|
||||
#if defined(IS_FLOAT)
|
||||
Map<MatrixXf, 0, Stride<Dynamic,1> > A( ( float* )ap, m, k, stride_a );
|
||||
Map<MatrixXf, 0, Stride<Dynamic,1> > B( ( float* )bp, k, n, stride_b );
|
||||
Map<MatrixXf, 0, Stride<Dynamic,1> > C( ( float* )cp, m, n, stride_c );
|
||||
#elif defined (IS_DOUBLE)
|
||||
Map<MatrixXd, 0, Stride<Dynamic,1> > A( ( double* )ap, m, k, stride_a );
|
||||
Map<MatrixXd, 0, Stride<Dynamic,1> > B( ( double* )bp, k, n, stride_b );
|
||||
Map<MatrixXd, 0, Stride<Dynamic,1> > C( ( double* )cp, m, n, stride_c );
|
||||
#elif defined (IS_SCOMPLEX)
|
||||
Map<MatrixXcf, 0, Stride<Dynamic,1> > A( ( std::complex<float>* )ap, m, k, stride_a );
|
||||
Map<MatrixXcf, 0, Stride<Dynamic,1> > B( ( std::complex<float>* )bp, k, n, stride_b );
|
||||
Map<MatrixXcf, 0, Stride<Dynamic,1> > C( ( std::complex<float>* )cp, m, n, stride_c );
|
||||
#elif defined (IS_DCOMPLEX)
|
||||
Map<MatrixXcd, 0, Stride<Dynamic,1> > A( ( std::complex<double>* )ap, m, k, stride_a );
|
||||
Map<MatrixXcd, 0, Stride<Dynamic,1> > B( ( std::complex<double>* )bp, k, n, stride_b );
|
||||
Map<MatrixXcd, 0, Stride<Dynamic,1> > C( ( std::complex<double>* )cp, m, n, stride_c );
|
||||
#endif
|
||||
#endif
|
||||
|
||||
dtime_save = DBL_MAX;
|
||||
|
||||
for ( r = 0; r < n_repeats; ++r )
|
||||
@@ -175,7 +219,7 @@ int main( int argc, char** argv )
|
||||
bli_printm( "c", &c, "%4.1f", "" );
|
||||
#endif
|
||||
|
||||
#ifdef BLIS
|
||||
#if defined(BLIS)
|
||||
|
||||
bli_gemm( &alpha,
|
||||
&a,
|
||||
@@ -183,21 +227,25 @@ int main( int argc, char** argv )
|
||||
&beta,
|
||||
&c );
|
||||
|
||||
#else
|
||||
#elif defined(EIGEN)
|
||||
|
||||
C.noalias() += alpha_r * A * B;
|
||||
|
||||
#else // if defined(BLAS)
|
||||
|
||||
if ( bli_is_float( dt ) )
|
||||
{
|
||||
f77_int mm = bli_obj_length( &c );
|
||||
f77_int kk = bli_obj_width_after_trans( &a );
|
||||
f77_int nn = bli_obj_width( &c );
|
||||
f77_int lda = bli_obj_col_stride( &a );
|
||||
f77_int ldb = bli_obj_col_stride( &b );
|
||||
f77_int ldc = bli_obj_col_stride( &c );
|
||||
float* alphap = bli_obj_buffer( &alpha );
|
||||
float* ap = bli_obj_buffer( &a );
|
||||
float* bp = bli_obj_buffer( &b );
|
||||
float* betap = bli_obj_buffer( &beta );
|
||||
float* cp = bli_obj_buffer( &c );
|
||||
f77_int mm = bli_obj_length( &c );
|
||||
f77_int kk = bli_obj_width_after_trans( &a );
|
||||
f77_int nn = bli_obj_width( &c );
|
||||
f77_int lda = bli_obj_col_stride( &a );
|
||||
f77_int ldb = bli_obj_col_stride( &b );
|
||||
f77_int ldc = bli_obj_col_stride( &c );
|
||||
float* alphap = ( float* )bli_obj_buffer( &alpha );
|
||||
float* ap = ( float* )bli_obj_buffer( &a );
|
||||
float* bp = ( float* )bli_obj_buffer( &b );
|
||||
float* betap = ( float* )bli_obj_buffer( &beta );
|
||||
float* cp = ( float* )bli_obj_buffer( &c );
|
||||
|
||||
sgemm_( &f77_transa,
|
||||
&f77_transb,
|
||||
@@ -212,17 +260,17 @@ int main( int argc, char** argv )
|
||||
}
|
||||
else if ( bli_is_double( dt ) )
|
||||
{
|
||||
f77_int mm = bli_obj_length( &c );
|
||||
f77_int kk = bli_obj_width_after_trans( &a );
|
||||
f77_int nn = bli_obj_width( &c );
|
||||
f77_int lda = bli_obj_col_stride( &a );
|
||||
f77_int ldb = bli_obj_col_stride( &b );
|
||||
f77_int ldc = bli_obj_col_stride( &c );
|
||||
double* alphap = bli_obj_buffer( &alpha );
|
||||
double* ap = bli_obj_buffer( &a );
|
||||
double* bp = bli_obj_buffer( &b );
|
||||
double* betap = bli_obj_buffer( &beta );
|
||||
double* cp = bli_obj_buffer( &c );
|
||||
f77_int mm = bli_obj_length( &c );
|
||||
f77_int kk = bli_obj_width_after_trans( &a );
|
||||
f77_int nn = bli_obj_width( &c );
|
||||
f77_int lda = bli_obj_col_stride( &a );
|
||||
f77_int ldb = bli_obj_col_stride( &b );
|
||||
f77_int ldc = bli_obj_col_stride( &c );
|
||||
double* alphap = ( double* )bli_obj_buffer( &alpha );
|
||||
double* ap = ( double* )bli_obj_buffer( &a );
|
||||
double* bp = ( double* )bli_obj_buffer( &b );
|
||||
double* betap = ( double* )bli_obj_buffer( &beta );
|
||||
double* cp = ( double* )bli_obj_buffer( &c );
|
||||
|
||||
dgemm_( &f77_transa,
|
||||
&f77_transb,
|
||||
@@ -237,17 +285,17 @@ int main( int argc, char** argv )
|
||||
}
|
||||
else if ( bli_is_scomplex( dt ) )
|
||||
{
|
||||
f77_int mm = bli_obj_length( &c );
|
||||
f77_int kk = bli_obj_width_after_trans( &a );
|
||||
f77_int nn = bli_obj_width( &c );
|
||||
f77_int lda = bli_obj_col_stride( &a );
|
||||
f77_int ldb = bli_obj_col_stride( &b );
|
||||
f77_int ldc = bli_obj_col_stride( &c );
|
||||
scomplex* alphap = bli_obj_buffer( &alpha );
|
||||
scomplex* ap = bli_obj_buffer( &a );
|
||||
scomplex* bp = bli_obj_buffer( &b );
|
||||
scomplex* betap = bli_obj_buffer( &beta );
|
||||
scomplex* cp = bli_obj_buffer( &c );
|
||||
f77_int mm = bli_obj_length( &c );
|
||||
f77_int kk = bli_obj_width_after_trans( &a );
|
||||
f77_int nn = bli_obj_width( &c );
|
||||
f77_int lda = bli_obj_col_stride( &a );
|
||||
f77_int ldb = bli_obj_col_stride( &b );
|
||||
f77_int ldc = bli_obj_col_stride( &c );
|
||||
scomplex* alphap = ( scomplex* )bli_obj_buffer( &alpha );
|
||||
scomplex* ap = ( scomplex* )bli_obj_buffer( &a );
|
||||
scomplex* bp = ( scomplex* )bli_obj_buffer( &b );
|
||||
scomplex* betap = ( scomplex* )bli_obj_buffer( &beta );
|
||||
scomplex* cp = ( scomplex* )bli_obj_buffer( &c );
|
||||
|
||||
cgemm_( &f77_transa,
|
||||
&f77_transb,
|
||||
@@ -262,17 +310,17 @@ int main( int argc, char** argv )
|
||||
}
|
||||
else if ( bli_is_dcomplex( dt ) )
|
||||
{
|
||||
f77_int mm = bli_obj_length( &c );
|
||||
f77_int kk = bli_obj_width_after_trans( &a );
|
||||
f77_int nn = bli_obj_width( &c );
|
||||
f77_int lda = bli_obj_col_stride( &a );
|
||||
f77_int ldb = bli_obj_col_stride( &b );
|
||||
f77_int ldc = bli_obj_col_stride( &c );
|
||||
dcomplex* alphap = bli_obj_buffer( &alpha );
|
||||
dcomplex* ap = bli_obj_buffer( &a );
|
||||
dcomplex* bp = bli_obj_buffer( &b );
|
||||
dcomplex* betap = bli_obj_buffer( &beta );
|
||||
dcomplex* cp = bli_obj_buffer( &c );
|
||||
f77_int mm = bli_obj_length( &c );
|
||||
f77_int kk = bli_obj_width_after_trans( &a );
|
||||
f77_int nn = bli_obj_width( &c );
|
||||
f77_int lda = bli_obj_col_stride( &a );
|
||||
f77_int ldb = bli_obj_col_stride( &b );
|
||||
f77_int ldc = bli_obj_col_stride( &c );
|
||||
dcomplex* alphap = ( dcomplex* )bli_obj_buffer( &alpha );
|
||||
dcomplex* ap = ( dcomplex* )bli_obj_buffer( &a );
|
||||
dcomplex* bp = ( dcomplex* )bli_obj_buffer( &b );
|
||||
dcomplex* betap = ( dcomplex* )bli_obj_buffer( &beta );
|
||||
dcomplex* cp = ( dcomplex* )bli_obj_buffer( &c );
|
||||
|
||||
zgemm_( &f77_transa,
|
||||
&f77_transb,
|
||||
|
||||
@@ -197,11 +197,11 @@ int main( int argc, char** argv )
|
||||
f77_int lda = bli_obj_col_stride( &a );
|
||||
f77_int ldb = bli_obj_col_stride( &b );
|
||||
f77_int ldc = bli_obj_col_stride( &c );
|
||||
float* alphap = bli_obj_buffer( &alpha );
|
||||
float* ap = bli_obj_buffer( &a );
|
||||
float* bp = bli_obj_buffer( &b );
|
||||
float* betap = bli_obj_buffer( &beta );
|
||||
float* cp = bli_obj_buffer( &c );
|
||||
float* alphap = ( float* )bli_obj_buffer( &alpha );
|
||||
float* ap = ( float* )bli_obj_buffer( &a );
|
||||
float* bp = ( float* )bli_obj_buffer( &b );
|
||||
float* betap = ( float* )bli_obj_buffer( &beta );
|
||||
float* cp = ( float* )bli_obj_buffer( &c );
|
||||
|
||||
ssymm_( &f77_side,
|
||||
&f77_uploa,
|
||||
@@ -220,11 +220,11 @@ int main( int argc, char** argv )
|
||||
f77_int lda = bli_obj_col_stride( &a );
|
||||
f77_int ldb = bli_obj_col_stride( &b );
|
||||
f77_int ldc = bli_obj_col_stride( &c );
|
||||
double* alphap = bli_obj_buffer( &alpha );
|
||||
double* ap = bli_obj_buffer( &a );
|
||||
double* bp = bli_obj_buffer( &b );
|
||||
double* betap = bli_obj_buffer( &beta );
|
||||
double* cp = bli_obj_buffer( &c );
|
||||
double* alphap = ( double* )bli_obj_buffer( &alpha );
|
||||
double* ap = ( double* )bli_obj_buffer( &a );
|
||||
double* bp = ( double* )bli_obj_buffer( &b );
|
||||
double* betap = ( double* )bli_obj_buffer( &beta );
|
||||
double* cp = ( double* )bli_obj_buffer( &c );
|
||||
|
||||
dsymm_( &f77_side,
|
||||
&f77_uploa,
|
||||
@@ -243,11 +243,19 @@ int main( int argc, char** argv )
|
||||
f77_int lda = bli_obj_col_stride( &a );
|
||||
f77_int ldb = bli_obj_col_stride( &b );
|
||||
f77_int ldc = bli_obj_col_stride( &c );
|
||||
scomplex* alphap = bli_obj_buffer( &alpha );
|
||||
scomplex* ap = bli_obj_buffer( &a );
|
||||
scomplex* bp = bli_obj_buffer( &b );
|
||||
scomplex* betap = bli_obj_buffer( &beta );
|
||||
scomplex* cp = bli_obj_buffer( &c );
|
||||
#ifdef EIGEN
|
||||
float* alphap = ( float* )bli_obj_buffer( &alpha );
|
||||
float* ap = ( float* )bli_obj_buffer( &a );
|
||||
float* bp = ( float* )bli_obj_buffer( &b );
|
||||
float* betap = ( float* )bli_obj_buffer( &beta );
|
||||
float* cp = ( float* )bli_obj_buffer( &c );
|
||||
#else
|
||||
scomplex* alphap = ( scomplex* )bli_obj_buffer( &alpha );
|
||||
scomplex* ap = ( scomplex* )bli_obj_buffer( &a );
|
||||
scomplex* bp = ( scomplex* )bli_obj_buffer( &b );
|
||||
scomplex* betap = ( scomplex* )bli_obj_buffer( &beta );
|
||||
scomplex* cp = ( scomplex* )bli_obj_buffer( &c );
|
||||
#endif
|
||||
|
||||
chemm_( &f77_side,
|
||||
&f77_uploa,
|
||||
@@ -266,11 +274,19 @@ int main( int argc, char** argv )
|
||||
f77_int lda = bli_obj_col_stride( &a );
|
||||
f77_int ldb = bli_obj_col_stride( &b );
|
||||
f77_int ldc = bli_obj_col_stride( &c );
|
||||
dcomplex* alphap = bli_obj_buffer( &alpha );
|
||||
dcomplex* ap = bli_obj_buffer( &a );
|
||||
dcomplex* bp = bli_obj_buffer( &b );
|
||||
dcomplex* betap = bli_obj_buffer( &beta );
|
||||
dcomplex* cp = bli_obj_buffer( &c );
|
||||
#ifdef EIGEN
|
||||
double* alphap = ( double* )bli_obj_buffer( &alpha );
|
||||
double* ap = ( double* )bli_obj_buffer( &a );
|
||||
double* bp = ( double* )bli_obj_buffer( &b );
|
||||
double* betap = ( double* )bli_obj_buffer( &beta );
|
||||
double* cp = ( double* )bli_obj_buffer( &c );
|
||||
#else
|
||||
dcomplex* alphap = ( dcomplex* )bli_obj_buffer( &alpha );
|
||||
dcomplex* ap = ( dcomplex* )bli_obj_buffer( &a );
|
||||
dcomplex* bp = ( dcomplex* )bli_obj_buffer( &b );
|
||||
dcomplex* betap = ( dcomplex* )bli_obj_buffer( &beta );
|
||||
dcomplex* cp = ( dcomplex* )bli_obj_buffer( &c );
|
||||
#endif
|
||||
|
||||
zhemm_( &f77_side,
|
||||
&f77_uploa,
|
||||
|
||||
@@ -36,7 +36,6 @@
|
||||
#include <unistd.h>
|
||||
#include "blis.h"
|
||||
|
||||
|
||||
//#define PRINT
|
||||
|
||||
int main( int argc, char** argv )
|
||||
@@ -190,14 +189,14 @@ int main( int argc, char** argv )
|
||||
|
||||
if ( bli_is_float( dt ) )
|
||||
{
|
||||
f77_int mm = bli_obj_length( &c );
|
||||
f77_int kk = bli_obj_width_after_trans( &a );
|
||||
f77_int lda = bli_obj_col_stride( &a );
|
||||
f77_int ldc = bli_obj_col_stride( &c );
|
||||
float* alphap = bli_obj_buffer( &alpha );
|
||||
float* ap = bli_obj_buffer( &a );
|
||||
float* betap = bli_obj_buffer( &beta );
|
||||
float* cp = bli_obj_buffer( &c );
|
||||
f77_int mm = bli_obj_length( &c );
|
||||
f77_int kk = bli_obj_width_after_trans( &a );
|
||||
f77_int lda = bli_obj_col_stride( &a );
|
||||
f77_int ldc = bli_obj_col_stride( &c );
|
||||
float* alphap = ( float* )bli_obj_buffer( &alpha );
|
||||
float* ap = ( float* )bli_obj_buffer( &a );
|
||||
float* betap = ( float* )bli_obj_buffer( &beta );
|
||||
float* cp = ( float* )bli_obj_buffer( &c );
|
||||
|
||||
ssyrk_( &f77_uploc,
|
||||
&f77_transa,
|
||||
@@ -210,14 +209,14 @@ int main( int argc, char** argv )
|
||||
}
|
||||
else if ( bli_is_double( dt ) )
|
||||
{
|
||||
f77_int mm = bli_obj_length( &c );
|
||||
f77_int kk = bli_obj_width_after_trans( &a );
|
||||
f77_int lda = bli_obj_col_stride( &a );
|
||||
f77_int ldc = bli_obj_col_stride( &c );
|
||||
double* alphap = bli_obj_buffer( &alpha );
|
||||
double* ap = bli_obj_buffer( &a );
|
||||
double* betap = bli_obj_buffer( &beta );
|
||||
double* cp = bli_obj_buffer( &c );
|
||||
f77_int mm = bli_obj_length( &c );
|
||||
f77_int kk = bli_obj_width_after_trans( &a );
|
||||
f77_int lda = bli_obj_col_stride( &a );
|
||||
f77_int ldc = bli_obj_col_stride( &c );
|
||||
double* alphap = ( double* )bli_obj_buffer( &alpha );
|
||||
double* ap = ( double* )bli_obj_buffer( &a );
|
||||
double* betap = ( double* )bli_obj_buffer( &beta );
|
||||
double* cp = ( double* )bli_obj_buffer( &c );
|
||||
|
||||
dsyrk_( &f77_uploc,
|
||||
&f77_transa,
|
||||
@@ -230,14 +229,21 @@ int main( int argc, char** argv )
|
||||
}
|
||||
else if ( bli_is_scomplex( dt ) )
|
||||
{
|
||||
f77_int mm = bli_obj_length( &c );
|
||||
f77_int kk = bli_obj_width_after_trans( &a );
|
||||
f77_int lda = bli_obj_col_stride( &a );
|
||||
f77_int ldc = bli_obj_col_stride( &c );
|
||||
float* alphap = bli_obj_buffer( &alpha );
|
||||
scomplex* ap = bli_obj_buffer( &a );
|
||||
float* betap = bli_obj_buffer( &beta );
|
||||
scomplex* cp = bli_obj_buffer( &c );
|
||||
f77_int mm = bli_obj_length( &c );
|
||||
f77_int kk = bli_obj_width_after_trans( &a );
|
||||
f77_int lda = bli_obj_col_stride( &a );
|
||||
f77_int ldc = bli_obj_col_stride( &c );
|
||||
#ifdef EIGEN
|
||||
float* alphap = ( float* )bli_obj_buffer( &alpha );
|
||||
float* ap = ( float* )bli_obj_buffer( &a );
|
||||
float* betap = ( float* )bli_obj_buffer( &beta );
|
||||
float* cp = ( float* )bli_obj_buffer( &c );
|
||||
#else
|
||||
float* alphap = ( float* )bli_obj_buffer( &alpha );
|
||||
scomplex* ap = ( scomplex* )bli_obj_buffer( &a );
|
||||
float* betap = ( float* )bli_obj_buffer( &beta );
|
||||
scomplex* cp = ( scomplex* )bli_obj_buffer( &c );
|
||||
#endif
|
||||
|
||||
cherk_( &f77_uploc,
|
||||
&f77_transa,
|
||||
@@ -250,14 +256,21 @@ int main( int argc, char** argv )
|
||||
}
|
||||
else if ( bli_is_dcomplex( dt ) )
|
||||
{
|
||||
f77_int mm = bli_obj_length( &c );
|
||||
f77_int kk = bli_obj_width_after_trans( &a );
|
||||
f77_int lda = bli_obj_col_stride( &a );
|
||||
f77_int ldc = bli_obj_col_stride( &c );
|
||||
double* alphap = bli_obj_buffer( &alpha );
|
||||
dcomplex* ap = bli_obj_buffer( &a );
|
||||
double* betap = bli_obj_buffer( &beta );
|
||||
dcomplex* cp = bli_obj_buffer( &c );
|
||||
f77_int mm = bli_obj_length( &c );
|
||||
f77_int kk = bli_obj_width_after_trans( &a );
|
||||
f77_int lda = bli_obj_col_stride( &a );
|
||||
f77_int ldc = bli_obj_col_stride( &c );
|
||||
#ifdef EIGEN
|
||||
double* alphap = ( double* )bli_obj_buffer( &alpha );
|
||||
double* ap = ( double* )bli_obj_buffer( &a );
|
||||
double* betap = ( double* )bli_obj_buffer( &beta );
|
||||
double* cp = ( double* )bli_obj_buffer( &c );
|
||||
#else
|
||||
double* alphap = ( double* )bli_obj_buffer( &alpha );
|
||||
dcomplex* ap = ( dcomplex* )bli_obj_buffer( &a );
|
||||
double* betap = ( double* )bli_obj_buffer( &beta );
|
||||
dcomplex* cp = ( dcomplex* )bli_obj_buffer( &c );
|
||||
#endif
|
||||
|
||||
zherk_( &f77_uploc,
|
||||
&f77_transa,
|
||||
|
||||
@@ -36,7 +36,6 @@
|
||||
#include <unistd.h>
|
||||
#include "blis.h"
|
||||
|
||||
|
||||
//#define PRINT
|
||||
|
||||
int main( int argc, char** argv )
|
||||
@@ -152,7 +151,7 @@ int main( int argc, char** argv )
|
||||
|
||||
bli_obj_create( dt, 1, 1, 0, 0, &alpha );
|
||||
|
||||
if ( bli_does_trans( side ) )
|
||||
if ( bli_is_left( side ) )
|
||||
bli_obj_create( dt, m, m, 0, 0, &a );
|
||||
else
|
||||
bli_obj_create( dt, n, n, 0, 0, &a );
|
||||
@@ -207,9 +206,9 @@ int main( int argc, char** argv )
|
||||
f77_int kk = bli_obj_width( &c );
|
||||
f77_int lda = bli_obj_col_stride( &a );
|
||||
f77_int ldc = bli_obj_col_stride( &c );
|
||||
float* alphap = bli_obj_buffer( &alpha );
|
||||
float* ap = bli_obj_buffer( &a );
|
||||
float* cp = bli_obj_buffer( &c );
|
||||
float* alphap = ( float* )bli_obj_buffer( &alpha );
|
||||
float* ap = ( float* )bli_obj_buffer( &a );
|
||||
float* cp = ( float* )bli_obj_buffer( &c );
|
||||
|
||||
strmm_( &f77_side,
|
||||
&f77_uploa,
|
||||
@@ -227,9 +226,9 @@ int main( int argc, char** argv )
|
||||
f77_int kk = bli_obj_width( &c );
|
||||
f77_int lda = bli_obj_col_stride( &a );
|
||||
f77_int ldc = bli_obj_col_stride( &c );
|
||||
double* alphap = bli_obj_buffer( &alpha );
|
||||
double* ap = bli_obj_buffer( &a );
|
||||
double* cp = bli_obj_buffer( &c );
|
||||
double* alphap = ( double* )bli_obj_buffer( &alpha );
|
||||
double* ap = ( double* )bli_obj_buffer( &a );
|
||||
double* cp = ( double* )bli_obj_buffer( &c );
|
||||
|
||||
dtrmm_( &f77_side,
|
||||
&f77_uploa,
|
||||
@@ -247,9 +246,15 @@ int main( int argc, char** argv )
|
||||
f77_int kk = bli_obj_width( &c );
|
||||
f77_int lda = bli_obj_col_stride( &a );
|
||||
f77_int ldc = bli_obj_col_stride( &c );
|
||||
scomplex* alphap = bli_obj_buffer( &alpha );
|
||||
scomplex* ap = bli_obj_buffer( &a );
|
||||
scomplex* cp = bli_obj_buffer( &c );
|
||||
#ifdef EIGEN
|
||||
float* alphap = ( float* )bli_obj_buffer( &alpha );
|
||||
float* ap = ( float* )bli_obj_buffer( &a );
|
||||
float* cp = ( float* )bli_obj_buffer( &c );
|
||||
#else
|
||||
scomplex* alphap = ( scomplex* )bli_obj_buffer( &alpha );
|
||||
scomplex* ap = ( scomplex* )bli_obj_buffer( &a );
|
||||
scomplex* cp = ( scomplex* )bli_obj_buffer( &c );
|
||||
#endif
|
||||
|
||||
ctrmm_( &f77_side,
|
||||
&f77_uploa,
|
||||
@@ -263,13 +268,19 @@ int main( int argc, char** argv )
|
||||
}
|
||||
else if ( bli_is_dcomplex( dt ) )
|
||||
{
|
||||
f77_int mm = bli_obj_length( &c );
|
||||
f77_int kk = bli_obj_width( &c );
|
||||
f77_int lda = bli_obj_col_stride( &a );
|
||||
f77_int ldc = bli_obj_col_stride( &c );
|
||||
dcomplex* alphap = bli_obj_buffer( &alpha );
|
||||
dcomplex* ap = bli_obj_buffer( &a );
|
||||
dcomplex* cp = bli_obj_buffer( &c );
|
||||
f77_int mm = bli_obj_length( &c );
|
||||
f77_int kk = bli_obj_width( &c );
|
||||
f77_int lda = bli_obj_col_stride( &a );
|
||||
f77_int ldc = bli_obj_col_stride( &c );
|
||||
#ifdef EIGEN
|
||||
double* alphap = ( double* )bli_obj_buffer( &alpha );
|
||||
double* ap = ( double* )bli_obj_buffer( &a );
|
||||
double* cp = ( double* )bli_obj_buffer( &c );
|
||||
#else
|
||||
dcomplex* alphap = ( dcomplex* )bli_obj_buffer( &alpha );
|
||||
dcomplex* ap = ( dcomplex* )bli_obj_buffer( &a );
|
||||
dcomplex* cp = ( dcomplex* )bli_obj_buffer( &c );
|
||||
#endif
|
||||
|
||||
ztrmm_( &f77_side,
|
||||
&f77_uploa,
|
||||
|
||||
@@ -36,7 +36,6 @@
|
||||
#include <unistd.h>
|
||||
#include "blis.h"
|
||||
|
||||
|
||||
//#define PRINT
|
||||
|
||||
int main( int argc, char** argv )
|
||||
@@ -152,7 +151,7 @@ int main( int argc, char** argv )
|
||||
|
||||
bli_obj_create( dt, 1, 1, 0, 0, &alpha );
|
||||
|
||||
if ( bli_does_trans( side ) )
|
||||
if ( bli_is_left( side ) )
|
||||
bli_obj_create( dt, m, m, 0, 0, &a );
|
||||
else
|
||||
bli_obj_create( dt, n, n, 0, 0, &a );
|
||||
@@ -211,9 +210,9 @@ int main( int argc, char** argv )
|
||||
f77_int kk = bli_obj_width( &c );
|
||||
f77_int lda = bli_obj_col_stride( &a );
|
||||
f77_int ldc = bli_obj_col_stride( &c );
|
||||
float* alphap = bli_obj_buffer( &alpha );
|
||||
float* ap = bli_obj_buffer( &a );
|
||||
float* cp = bli_obj_buffer( &c );
|
||||
float* alphap = ( float* )bli_obj_buffer( &alpha );
|
||||
float* ap = ( float* )bli_obj_buffer( &a );
|
||||
float* cp = ( float* )bli_obj_buffer( &c );
|
||||
|
||||
strsm_( &f77_side,
|
||||
&f77_uploa,
|
||||
@@ -231,9 +230,9 @@ int main( int argc, char** argv )
|
||||
f77_int kk = bli_obj_width( &c );
|
||||
f77_int lda = bli_obj_col_stride( &a );
|
||||
f77_int ldc = bli_obj_col_stride( &c );
|
||||
double* alphap = bli_obj_buffer( &alpha );
|
||||
double* ap = bli_obj_buffer( &a );
|
||||
double* cp = bli_obj_buffer( &c );
|
||||
double* alphap = ( double* )bli_obj_buffer( &alpha );
|
||||
double* ap = ( double* )bli_obj_buffer( &a );
|
||||
double* cp = ( double* )bli_obj_buffer( &c );
|
||||
|
||||
dtrsm_( &f77_side,
|
||||
&f77_uploa,
|
||||
@@ -251,9 +250,15 @@ int main( int argc, char** argv )
|
||||
f77_int kk = bli_obj_width( &c );
|
||||
f77_int lda = bli_obj_col_stride( &a );
|
||||
f77_int ldc = bli_obj_col_stride( &c );
|
||||
scomplex* alphap = bli_obj_buffer( &alpha );
|
||||
scomplex* ap = bli_obj_buffer( &a );
|
||||
scomplex* cp = bli_obj_buffer( &c );
|
||||
#ifdef EIGEN
|
||||
float* alphap = ( float* )bli_obj_buffer( &alpha );
|
||||
float* ap = ( float* )bli_obj_buffer( &a );
|
||||
float* cp = ( float* )bli_obj_buffer( &c );
|
||||
#else
|
||||
scomplex* alphap = ( scomplex* )bli_obj_buffer( &alpha );
|
||||
scomplex* ap = ( scomplex* )bli_obj_buffer( &a );
|
||||
scomplex* cp = ( scomplex* )bli_obj_buffer( &c );
|
||||
#endif
|
||||
|
||||
ctrsm_( &f77_side,
|
||||
&f77_uploa,
|
||||
@@ -267,13 +272,19 @@ int main( int argc, char** argv )
|
||||
}
|
||||
else if ( bli_is_dcomplex( dt ) )
|
||||
{
|
||||
f77_int mm = bli_obj_length( &c );
|
||||
f77_int kk = bli_obj_width( &c );
|
||||
f77_int lda = bli_obj_col_stride( &a );
|
||||
f77_int ldc = bli_obj_col_stride( &c );
|
||||
dcomplex* alphap = bli_obj_buffer( &alpha );
|
||||
dcomplex* ap = bli_obj_buffer( &a );
|
||||
dcomplex* cp = bli_obj_buffer( &c );
|
||||
f77_int mm = bli_obj_length( &c );
|
||||
f77_int kk = bli_obj_width( &c );
|
||||
f77_int lda = bli_obj_col_stride( &a );
|
||||
f77_int ldc = bli_obj_col_stride( &c );
|
||||
#ifdef EIGEN
|
||||
double* alphap = ( double* )bli_obj_buffer( &alpha );
|
||||
double* ap = ( double* )bli_obj_buffer( &a );
|
||||
double* cp = ( double* )bli_obj_buffer( &c );
|
||||
#else
|
||||
dcomplex* alphap = ( dcomplex* )bli_obj_buffer( &alpha );
|
||||
dcomplex* ap = ( dcomplex* )bli_obj_buffer( &a );
|
||||
dcomplex* cp = ( dcomplex* )bli_obj_buffer( &c );
|
||||
#endif
|
||||
|
||||
ztrsm_( &f77_side,
|
||||
&f77_uploa,
|
||||
|
||||
Reference in New Issue
Block a user