Cleanups to ref99/README.md, test/3m4m/Makefile.

Details:
- Minor edits to sandbox/ref99/README.md.
- Removed cpp guards in sandbox/ref99/thread/blx_gemm_thread.h to be
  consistent with other headers in sandbox/ref99.
- Additional targets and related cleanups in test/3m4m/Makefile.

sandbox/ref99/README.md

@@ -112,21 +112,23 @@ working with the existing BLIS infrastructure.
 
 For example, with a BLIS sandbox you **can** do the following kinds of things:
 - use a different gemm algorithmic partitioning path than the default Goto-like
-algorithm;
+  algorithm;
 - experiment with different implementations of `packm` (not just `packm`
-kernels, which can already be customized within each sub-configuration);
+  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_gemmnat()`) to try to avoid some overhead;
 - create experimental implementations of new BLAS-like operations (provided
-that you also provide an implementation of `blis_gemmnat()`).
+  that you also provide an implementation of `blis_gemmnat()`).
 
 You **cannot**, however, use a sandbox to do the following kinds of things:
 - define new datatypes (half-precision, quad-precision, short integer, etc.)
-and expect the rest of BLIS to "know" how to handle them;
+  and expect the rest of BLIS to "know" how to handle them;
 - use a sandbox to replace the default implementation of a different level-3
   operation, such as Hermitian rank-k update;
-- change the existing BLIS APIs.
+- change the existing BLIS APIs;
+- remove support for one or more BLIS datatypes (to cut down on library size,
+  for example).
 
 Another important limitation is the fact that the build system currently uses
 "framework `CFLAGS`" when compiling the sandbox source files. These are the same

sandbox/ref99/thread/blx_gemm_thread.h

@@ -32,9 +32,6 @@
 
 */
 
-#ifndef BLIS_GEMM_THREAD_H
-#define BLIS_GEMM_THREAD_H
-
 // gemm internal function type
 typedef void (*gemmint_t)
      (
@@ -57,4 +54,3 @@ void blx_gemm_thread
        cntl_t*   cntl
      );
 
-#endif

test/3m4m/Makefile

@@ -214,22 +214,45 @@ PDEF_MT  := -DP_BEGIN=200 \
 # --- Targets/rules ------------------------------------------------------------
 #
 
+all:          all-st all-mt
+blis:         blis-st blis-mt
+blis-nat:     blis-nat-st blis-nat-mt
+openblas:     openblas-st openblas-mt
+mkl:          mkl-st mkl-mt
+
 all-st:       blis-st openblas-st mkl-st
 all-mt:       blis-mt openblas-mt mkl-mt
 
 blis-st:      blis-gemm-st
 blis-mt:      blis-gemm-mt
 
+blis-nat-st:  blis-gemm-nat-st
+blis-nat-mt:  blis-gemm-nat-mt
+
 openblas-st:  openblas-gemm-st
 openblas-mt:  openblas-gemm-mt
 
 mkl-st:       mkl-gemm-st
 mkl-mt:       mkl-gemm-mt
 
-blis-gemm-st: \
+blis-gemm-st: blis-gemm-nat-st \
+              blis-gemm-ind-st
+blis-gemm-mt: blis-gemm-nat-mt \
+              blis-gemm-ind-mt
+
+blis-gemm-nat-st: \
       test_sgemm_asm_blis_st.x \
       test_dgemm_asm_blis_st.x \
-      \
+      test_cgemm_asm_blis_st.x \
+      test_zgemm_asm_blis_st.x
+
+blis-gemm-nat-mt: \
+      test_sgemm_asm_blis_mt.x \
+      test_dgemm_asm_blis_mt.x \
+      test_cgemm_asm_blis_mt.x \
+      test_zgemm_asm_blis_mt.x
+
+blis-gemm-ind-st: \
       test_cgemm_3mhw_blis_st.x \
       test_zgemm_3mhw_blis_st.x \
       test_cgemm_3m1_blis_st.x \
@@ -241,14 +264,9 @@ blis-gemm-st: \
       test_cgemm_4m1a_blis_st.x \
       test_zgemm_4m1a_blis_st.x \
       test_cgemm_1m_blis_st.x \
-      test_zgemm_1m_blis_st.x \
+      test_zgemm_1m_blis_st.x
-      test_cgemm_asm_blis_st.x \
-      test_zgemm_asm_blis_st.x
 
-blis-gemm-mt: \
+blis-gemm-ind-mt: \
-      test_sgemm_asm_blis_mt.x \
-      test_dgemm_asm_blis_mt.x \
-      \
       test_cgemm_3mhw_blis_mt.x \
       test_zgemm_3mhw_blis_mt.x \
       test_cgemm_3m1_blis_mt.x \
@@ -260,9 +278,7 @@ blis-gemm-mt: \
       test_cgemm_4m1a_blis_mt.x \
       test_zgemm_4m1a_blis_mt.x \
       test_cgemm_1m_blis_mt.x \
-      test_zgemm_1m_blis_mt.x \
+      test_zgemm_1m_blis_mt.x
-      test_cgemm_asm_blis_mt.x \
-      test_zgemm_asm_blis_mt.x
 
 openblas-gemm-st: \
       test_sgemm_openblas_st.x \