Merge commit 'cfa3db3f' into amd-main

* commit 'cfa3db3f':
  Fixed bug in mixed-dt gemm introduced in e9da642.
  Removed support for 3m, 4m induced methods.
  Updated do_sde.sh to get SDE from GitHub.
  Disable SDE testing of old AMD microarchitectures.
  Fixed substitution bug in configure.
  Allow use of 1m with mixing of row/col-pref ukrs.

AMD-Internal: [CPUPL-2698]
Change-Id: I961f0066243cf26aeb2e174e388b470133cc4a5f

Author: edwsmyth

CREDITS

@@ -92,6 +92,7 @@ but many others have contributed code and feedback, including
   Nathaniel Smith          @njsmith
   Shaden Smith             @ShadenSmith
   Tyler Smith              @tlrmchlsmth        (The University of Texas at Austin)
+  Snehith                  @ArcadioN09
   Paul Springer            @springer13         (RWTH Aachen University)
   Adam J. Stewart          @adamjstewart       (University of Illinois at Urbana-Champaign)
   Vladimir Sukarev

configure

@@ -729,13 +729,21 @@ read_registry_file()
 				if [ "${mem}" != "${mems_mem}" ]; then
 
 					#clist="${config_registry[$config]}"
-					clist=$(query_array "config_registry" ${config})
+					clisttmp=$(query_array "config_registry" ${config})
 
 					# Replace the current config with its constituent config set,
 					# canonicalize whitespace, and then remove duplicate config
 					# set names, if they exist. Finally, update the config registry
 					# with the new config list.
-					newclist=$(echo -e "${clist}" | sed -e "s/${mem}/${mems_mem}/g")
+					# NOTE: WE must use substitute_words() rather than a simple sed
+					# expression because we need to avoid matching partial strings.
+					# For example, if clist above contains "foo bar barsk" and we use
+					# sed to substitute "bee boo" as the members of "bar", the
+					# result would (incorrectly) be "foo bee boo bee boosk",
+					# which would then get reduced, via rm_duplicate_words(), to
+					# "foo bee boo boosk".
+					#newclist=$(echo -e "${clist}" | sed -e "s/${mem}/${mems_mem}/g")
+					newclist=$(substitute_words "${mem}" "${mems_mem}" "${clisttmp}")
 					newclist=$(canonicalize_ws "${newclist}")
 					newclist=$(rm_duplicate_words "${newclist}")
 
@@ -818,6 +826,13 @@ read_registry_file()
 					# canonicalize whitespace, and then remove duplicate kernel
 					# set names, if they exist. Finally, update the kernel registry
 					# with the new kernel list.
+					# NOTE: WE must use substitute_words() rather than a simple sed
+					# expression because we need to avoid matching partial strings.
+					# For example, if klist above contains "foo bar barsk" and we use
+					# sed to substitute "bee boo" as the members of "bar", the
+					# result would (incorrectly) be "foo bee boo bee boosk",
+					# which would then get reduced, via rm_duplicate_words(), to
+					# "foo bee boo boosk".
 					#newklist=$(echo -e "${klisttmp}" | sed -e "s/${ker}/${kers_ker}/g")
 					newklist=$(substitute_words "${ker}" "${kers_ker}" "${klisttmp}")
 					newklist=$(canonicalize_ws "${newklist}")

docs/BLISObjectAPI.md

@@ -2336,16 +2336,9 @@ char* bli_info_get_trsm_u_ukr_impl_string( ind_t method, num_t dt )
 ```
 
 Possible implementation (ie: the `ind_t method` argument) types are:
- * `BLIS_3MH`: Implementation based on the 3m method applied at the highest level, outside the 5th loop around the microkernel.
- * `BLIS_3M1`: Implementation based on the 3m method applied within the 1st loop around the microkernel.
- * `BLIS_4MH`: Implementation based on the 4m method applied at the highest level, outside the 5th loop around the microkernel.
- * `BLIS_4M1B`: Implementation based on the 4m method applied within the 1st loop around the microkernel. Computation is ordered such that the 1st loop is fissured into two loops, the first of which multiplies the real part of the current micropanel of packed matrix B (against all real and imaginary parts of packed matrix A), and the second of which multiplies the imaginary part of the current micropanel of packed matrix B.
- * `BLIS_4M1A`: Implementation based on the 4m method applied within the 1st loop around the microkernel. Computation is ordered such that real and imaginary components of the current micropanels are completely used before proceeding to the next virtual microkernel invocation.
  * `BLIS_1M`: Implementation based on the 1m method. (This is the default induced method when real domain kernels are present but complex kernels are missing.)
  * `BLIS_NAT`: Implementation based on "native" execution (ie: NOT an induced method).
 
-**NOTE**: `BLIS_3M3` and `BLIS_3M2` have been deprecated from the `typedef enum` of `ind_t`, and `BLIS_4M1B` is also effectively no longer available, though the `typedef enum` value still exists.
-
 Possible microkernel types (ie: the return values for `bli_info_get_*_ukr_impl_string()`) are:
  * `BLIS_REFERENCE_UKERNEL` (`"refrnce"`): This value is returned when the queried microkernel is provided by the reference implementation.
  * `BLIS_VIRTUAL_UKERNEL` (`"virtual"`): This value is returned when the queried microkernel is driven by a the "virtual" microkernel provided by an induced method. This happens for any `method` value that is not `BLIS_NAT` (ie: native), but only applies to the complex domain.

docs/BLISTypedAPI.md

@@ -2015,16 +2015,9 @@ char* bli_info_get_trsm_u_ukr_impl_string( ind_t method, num_t dt )
 ```
 
 Possible implementation (ie: the `ind_t method` argument) types are:
- * `BLIS_3MH`: Implementation based on the 3m method applied at the highest level, outside the 5th loop around the microkernel.
- * `BLIS_3M1`: Implementation based on the 3m method applied within the 1st loop around the microkernel.
- * `BLIS_4MH`: Implementation based on the 4m method applied at the highest level, outside the 5th loop around the microkernel.
- * `BLIS_4M1B`: Implementation based on the 4m method applied within the 1st loop around the microkernel. Computation is ordered such that the 1st loop is fissured into two loops, the first of which multiplies the real part of the current micropanel of packed matrix B (against all real and imaginary parts of packed matrix A), and the second of which multiplies the imaginary part of the current micropanel of packed matrix B.
- * `BLIS_4M1A`: Implementation based on the 4m method applied within the 1st loop around the microkernel. Computation is ordered such that real and imaginary components of the current micropanels are completely used before proceeding to the next virtual microkernel invocation.
  * `BLIS_1M`: Implementation based on the 1m method. (This is the default induced method when real domain kernels are present but complex kernels are missing.)
  * `BLIS_NAT`: Implementation based on "native" execution (ie: NOT an induced method).
 
-**NOTE**: `BLIS_3M3` and `BLIS_3M2` have been deprecated from the `typedef enum` of `ind_t`, and `BLIS_4M1B` is also effectively no longer available, though the `typedef enum` value still exists.
-
 Possible microkernel types (ie: the return values for `bli_info_get_*_ukr_impl_string()`) are:
  * `BLIS_REFERENCE_UKERNEL` (`"refrnce"`): This value is returned when the queried microkernel is provided by the reference implementation.
  * `BLIS_VIRTUAL_UKERNEL` (`"virtual"`): This value is returned when the queried microkernel is driven by a the "virtual" microkernel provided by an induced method. This happens for any `method` value that is not `BLIS_NAT` (ie: native), but only applies to the complex domain.

docs/Sandboxes.md

@@ -17,13 +17,9 @@ Simply put, a sandbox in BLIS provides an alternative implementation to the
 `gemm` operation.
 
 To get a little more specific, a sandbox provides an alternative implementation
-to the function `bli_gemmnat()`, which is the object-based API call for
-computing the `gemm` operation via native execution.
-
-**Note**: Native execution simply means that an induced method will not be used.
-It's what you probably already think of when you think of implementing the
-`gemm` operation: a series of loops around an optimized (usually assembly-based)
-microkernel with some packing functions thrown in at various levels.
+to the function `bli_gemm_ex()`, which is the
+[expert interface](BLISObjectAPI.md##basic-vs-expert-interfaces) for calling the
+[object-based API](BLISObjectAPI.md#gemm) for the `gemm` operation.
 
 Why sandboxes? Sometimes you want to experiment with tweaks or changes to
 the `gemm` operation, but you want to do so in a simple environment rather than
@@ -45,18 +41,11 @@ corresponds to a sub-directory of `sandbox` named `gemmlike`. (Reminder: the
 `auto` argument is the configuration target and thus unrelated to
 sandboxes.)
 
-NOTE: If you want your sandbox implementation to handle *all* problem
-sizes and shapes, you'll need to disable the skinny/unpacked "sup"
-sub-framework within BLIS, which is enabled by default. This can be
-done by passing the `--disable-sup-handling` option to configure:
-```
-$ ./configure --enable-sandbox=gemmlike --disable-sup-handling auto
-```
-If you leave sup enabled, the sup implementation will, at runtime, detect
-and handle certain smaller problem sizes upstream of where BLIS calls
-`bli_gemmnat()` while all other problems will fall to your sandbox
-implementation. Thus, you should only leave sup enabled if you are fine
-with those smaller problems being handled by sup.
+NOTE: Using your own sandbox implementation means that BLIS will call your
+sandbox for *all* problem sizes and shapes, for *all* datatypes supported
+by BLIS. If you intend to only implement a subset of this functionality
+within your sandbox, you should be sure to redirect execution back into
+the core framework for the parts that you don't wish to reimplement yourself.
 
 As `configure` runs, you should get output that includes lines
 similar to:
@@ -67,13 +56,12 @@ configure:   sandbox/gemmlike
 And when you build BLIS, the last files to be compiled will be the source
 code in the specified sandbox:
 ```
-Compiling obj/haswell/sandbox/gemmlike/bli_gemmnat.o ('haswell' CFLAGS for sandboxes)
 Compiling obj/haswell/sandbox/gemmlike/bls_gemm.o ('haswell' CFLAGS for sandboxes)
 Compiling obj/haswell/sandbox/gemmlike/bls_gemm_bp_var1.o ('haswell' CFLAGS for sandboxes)
 ...
 ```
 That's it! After the BLIS library is built, it will contain your chosen
-sandbox's implementation of `bli_gemmnat()` instead of the default
+sandbox's implementation of `bli_gemm_ex()` instead of the default BLIS
 implementation.
 
 ## Sandbox rules
@@ -97,15 +85,15 @@ Note that `blis.h` already contains all of its definitions inside of an
 `extern "C"` block, so you should be able to `#include "blis.h"` from your
 C++11 source code without any issues.
 
-3. All of your code to replace BLIS's default implementation of `bli_gemmnat()`
+3. All of your code to replace BLIS's default implementation of `bli_gemm_ex()`
 should reside in the named sandbox directory, or some directory therein.
 (Obviously.) For example, the "gemmlike" sandbox is located in
 `sandbox/gemmlike`. All of the code associated with this sandbox will be
 contained within `sandbox/gemmlike`. Note that you absolutely *may* include
 additional code and interfaces within the sandbox, if you wish -- code and
 interfaces that are not directly or indirectly needed for satisfying the
 the "contract" set forth by the sandbox (i.e., including a local definition
-of`bli_gemmnat()`).
+of`bli_gemm_ex()`).
 
 4. The *only* header file that is required of your sandbox is `bli_sandbox.h`.
 It must be named `bli_sandbox.h` because `blis.h` will `#include` this file
@@ -119,12 +107,12 @@ you should only place things (e.g. prototypes or type definitions) in
 (b) an *application* that calls your sandbox-enabled BLIS library.
 Usually, neither of these situations will require any of your local definitions
 since those local definitions are only needed to define your sandbox
-implementation of `bli_gemmnat()`, and this function is already prototyped by
+implementation of `bli_gemm_ex()`, and this function is already prototyped by
 BLIS. *But if you are adding additional APIs and/or operations to the sandbox
-that are unrelated to `bli_gemmnat()`, then you'll want to `#include` those
+that are unrelated to `bli_gemm_ex()`, then you'll want to `#include` those
 function prototypes from within `bli_sandbox.h`*
 
-5. Your definition of `bli_gemmnat()` should be the **only function you define**
+5. Your definition of `bli_gemm_ex()` should be the **only function you define**
 in your sandbox that begins with `bli_`. If you define other functions that
 begin with `bli_`, you risk a namespace collision with existing framework
 functions. To guarantee safety, please prefix your locally-defined sandbox
@@ -147,9 +135,9 @@ For example, with a BLIS sandbox you **can** do the following kinds of things:
   kernels, which can already be customized within each sub-configuration);
 - try inlining your functions manually;
 - pivot away from using `obj_t` objects at higher algorithmic level (such as
-  immediately after calling `bli_gemmnat()`) to try to avoid some overhead;
+  immediately after calling `bli_gemm_ex()`) to try to avoid some overhead;
 - create experimental implementations of new BLAS-like operations (provided
-  that you also provide an implementation of `bli_gemmnat()`).
+  that you also provide an implementation of `bli_gemm_ex()`).
 
 You **cannot**, however, use a sandbox to do the following kinds of things:
 - define new datatypes (half-precision, quad-precision, short integer, etc.)
@@ -167,17 +155,17 @@ Another important limitation is the fact that the build system currently uses
 # Example framework CFLAGS used by 'haswell' sub-configuration
 -O3 -Wall -Wno-unused-function -Wfatal-errors -fPIC -std=c99
 -D_POSIX_C_SOURCE=200112L -I./include/haswell -I./frame/3/
--I./frame/ind/ukernels/ -I./frame/1m/ -I./frame/1f/ -I./frame/1/
--I./frame/include -DBLIS_VERSION_STRING=\"0.3.2-51\"
+-I./frame/1m/ -I./frame/1f/ -I./frame/1/ -I./frame/include
+-DBLIS_VERSION_STRING=\"0.3.2-51\"
 ```
 which are likely more general-purpose than the `CFLAGS` used for, say,
 optimized kernels or even reference kernels.
 ```
 # Example optimized kernel CFLAGS used by 'haswell' sub-configuration
 -O3 -mavx2 -mfma -mfpmath=sse -march=core-avx2 -Wall -Wno-unused-function
 -Wfatal-errors -fPIC -std=c99 -D_POSIX_C_SOURCE=200112L -I./include/haswell
--I./frame/3/ -I./frame/ind/ukernels/ -I./frame/1m/ -I./frame/1f/ -I./frame/1/
--I./frame/include -DBLIS_VERSION_STRING=\"0.3.2-51\"
+-I./frame/3/ -I./frame/1m/ -I./frame/1f/ -I./frame/1/ -I./frame/include
+-DBLIS_VERSION_STRING=\"0.3.2-51\"
 ```
 (To see precisely which flags are being employed for any given file, enable
 verbosity at compile-time via `make V=1`.) Compiling sandboxes with these more

docs/Testsuite.md

@@ -128,11 +128,6 @@ sdcz    # Datatype(s) to test:
 300     # Problem size: maximum to test
 100     # Problem size: increment between experiments
         # Complex level-3 implementations to test
-1       #   3mh  ('1' = enable; '0' = disable)
-1       #   3m1  ('1' = enable; '0' = disable)
-1       #   4mh  ('1' = enable; '0' = disable)
-1       #   4m1b ('1' = enable; '0' = disable)
-1       #   4m1a ('1' = enable; '0' = disable)
 1       #   1m   ('1' = enable; '0' = disable)
 1       #   native ('1' = enable; '0' = disable)
 1       # Simulate application-level threading:
@@ -169,7 +164,7 @@ _**Test gemm with mixed-precision operands?**_ This boolean determines whether `
 
 _**Problem size.**_ These values determine the first problem size to test, the maximum problem size to test, and the increment between problem sizes. Note that the maximum problem size only bounds the range of problem sizes; it is not guaranteed to be tested. Example: If the initial problem size is 128, the maximum is 1000, and the increment is 64, then the last problem size to be tested will be 960.
 
-_**Complex level-3 implementations to test.**_ With the exception of the switch marked `native`, these switches control whether experimental complex domain implementations are tested (when applicable). These implementations employ induced methods complex matrix multiplication and apply to some (though not all) of the level-3 operations. If you don't know what these are, you can ignore them. The `native` switch corresponds to native execution of complex domain level-3 operations, which we test by default. We also test the `1m` method, since it is the induced method of choice when complex microkernels are not available. Note that all of these induced method tests (including `native`) are automatically disabled if the `c` and `z` datatypes are disabled.
+_**Complex level-3 implementations to test.**_ This section lists which complex domain implementations of level-3 operations are tested. If you don't know what these are, you can ignore them. The `native` switch corresponds to native execution of complex domain level-3 operations, which we test by default. We also test the `1m` method, since it is the induced method of choice when optimized complex microkernels are not available. Note that all of these induced method tests (including `native`) are automatically disabled if the `c` and `z` datatypes are disabled.
 
 _**Simulate application-level threading.**_ This setting specifies the number of threads the testsuite will spawn, and is meant to allow the user to exercise BLIS as a multithreaded application might if it were to make multiple concurrent calls to BLIS operations. (Note that the threading controlled by this option is orthogonal to, and has no effect on, whatever multithreading may be employed _within_ BLIS, as specified by the environment variables described in the [Multithreading](Multithreading.md) documentation.) When this option is set to 1, the testsuite is run with only one thread. When set to n > 1 threads, the spawned threads will parallelize (in round-robin fashion) the total set of tests specified by the testsuite input files, executing them in roughly the same order as that of a sequential execution.
 

frame/1m/bli_l1m_ft_ker.h

@@ -110,28 +110,6 @@ typedef void (*PASTECH3(ch,opname,_ker,tsuf)) \
 
 INSERT_GENTDEF( unpackm_cxk )
 
-// packm_3mis_ker
-// packm_4mi_ker
-
-#undef  GENTDEF
-#define GENTDEF( ctype, ch, opname, tsuf ) \
-\
-typedef void (*PASTECH3(ch,opname,_ker,tsuf)) \
-     ( \
-       conj_t           conja, \
-       dim_t            cdim, \
-       dim_t            n, \
-       dim_t            n_max, \
-       ctype*  restrict kappa, \
-       ctype*  restrict a, inc_t inca, inc_t lda, \
-       ctype*  restrict p, inc_t is_p, inc_t ldp, \
-       cntx_t* restrict cntx  \
-     );
-
-INSERT_GENTDEF( packm_cxk_3mis )
-INSERT_GENTDEF( packm_cxk_4mi )
-
-// packm_rih_ker
 // packm_1er_ker
 
 #undef  GENTDEF
@@ -150,12 +128,8 @@ typedef void (*PASTECH3(ch,opname,_ker,tsuf)) \
        cntx_t* restrict cntx  \
      );
 
-INSERT_GENTDEF( packm_cxk_rih )
 INSERT_GENTDEF( packm_cxk_1er )
 
 
-
-
-
 #endif
 

frame/1m/bli_l1m_ker.h

@@ -74,51 +74,6 @@ INSERT_GENTPROT_BASIC0( unpackm_14xk_ker_name )
 INSERT_GENTPROT_BASIC0( unpackm_16xk_ker_name )
 
 
-// 3mis packm kernels
-
-#undef  GENTPROT
-#define GENTPROT PACKM_3MIS_KER_PROT
-
-INSERT_GENTPROT_BASIC0( packm_2xk_3mis_ker_name )
-INSERT_GENTPROT_BASIC0( packm_4xk_3mis_ker_name )
-INSERT_GENTPROT_BASIC0( packm_6xk_3mis_ker_name )
-INSERT_GENTPROT_BASIC0( packm_8xk_3mis_ker_name )
-INSERT_GENTPROT_BASIC0( packm_10xk_3mis_ker_name )
-INSERT_GENTPROT_BASIC0( packm_12xk_3mis_ker_name )
-INSERT_GENTPROT_BASIC0( packm_14xk_3mis_ker_name )
-INSERT_GENTPROT_BASIC0( packm_16xk_3mis_ker_name )
-
-
-// 4mi packm kernels
-
-#undef  GENTPROT
-#define GENTPROT PACKM_4MI_KER_PROT
-
-INSERT_GENTPROT_BASIC0( packm_2xk_4mi_ker_name )
-INSERT_GENTPROT_BASIC0( packm_4xk_4mi_ker_name )
-INSERT_GENTPROT_BASIC0( packm_6xk_4mi_ker_name )
-INSERT_GENTPROT_BASIC0( packm_8xk_4mi_ker_name )
-INSERT_GENTPROT_BASIC0( packm_10xk_4mi_ker_name )
-INSERT_GENTPROT_BASIC0( packm_12xk_4mi_ker_name )
-INSERT_GENTPROT_BASIC0( packm_14xk_4mi_ker_name )
-INSERT_GENTPROT_BASIC0( packm_16xk_4mi_ker_name )
-
-
-// rih packm kernels
-
-#undef  GENTPROT
-#define GENTPROT PACKM_RIH_KER_PROT
-
-INSERT_GENTPROT_BASIC0( packm_2xk_rih_ker_name )
-INSERT_GENTPROT_BASIC0( packm_4xk_rih_ker_name )
-INSERT_GENTPROT_BASIC0( packm_6xk_rih_ker_name )
-INSERT_GENTPROT_BASIC0( packm_8xk_rih_ker_name )
-INSERT_GENTPROT_BASIC0( packm_10xk_rih_ker_name )
-INSERT_GENTPROT_BASIC0( packm_12xk_rih_ker_name )
-INSERT_GENTPROT_BASIC0( packm_14xk_rih_ker_name )
-INSERT_GENTPROT_BASIC0( packm_16xk_rih_ker_name )
-
-
 // 1e/1r packm kernels
 
 #undef  GENTPROT