Update Haswell gemmsup fix for gcc 16 and later. (#891)

Details:
- The problem persists with gcc16 so enable the fix for gcc15 *and later* (thanks @negril).
- Disable all vectorization, not just SLP vectorization (thanks @thesamesam).

Author: devinamatthews

CREDITS

@@ -64,6 +64,7 @@ but many others have contributed code, ideas, and feedback, including
   Aaron Hutchinson         @Aaron-Hutchinson          (SiFive)
   Francisco Igual          @figual                    (Universidad Complutense de Madrid)
                            @j-bm
+  Sam James                @thesamesam
   Madeesh Kannan           @shadeMe
   Tony Kelman              @tkelman
   Lee Killough             @leekillough               (Tactical Computing Labs)
@@ -149,6 +150,7 @@ but many others have contributed code, ideas, and feedback, including
   Chenhan Yu               @ChenhanYu                 (The University of Texas at Austin)
   Roman Yurchak            @rth                       (Symerio)
   Stefano Zampini          @stefanozampini
+  Paul Zander              @negril
   M. Zhou                  @cdluminate
   Igor Zhuravlov           @jip                       (Far Eastern Federal University)
                            @AngryLoki

kernels/haswell/3/sup/bli_gemmsup_rv_haswell_asm_d6x8m.c

@@ -33,11 +33,10 @@
 
 */
 
-// This avoids a known issue with GCC15 ("error: bp cannot be used in asm here", #845).
-// Only check for version 15 since this may be fixed in 16 (**fingers crossed**), and also
-// make sure the compiler isn't clang since it also confusingly defines __GNUC__
-#if !defined(__clang__) && defined(__GNUC__) && __GNUC__ == 15
-#pragma GCC optimize("-fno-tree-slp-vectorize")
+// This avoids a known issue with GCC15+ ("error: bp cannot be used in asm here", #845).
+// Make sure the compiler isn't clang since it also confusingly defines __GNUC__
+#if !defined(__clang__) && defined(__GNUC__) && __GNUC__ >= 15
+#pragma GCC optimize("-fno-tree-vectorize")
 #endif
 
 #include "blis.h"

kernels/haswell/3/sup/bli_gemmsup_rv_haswell_asm_d6x8n.c

@@ -33,11 +33,10 @@
 
 */
 
-// This avoids a known issue with GCC15 ("error: bp cannot be used in asm here", #845).
-// Only check for version 15 since this may be fixed in 16 (**fingers crossed**), and also
-// make sure the compiler isn't clang since it also confusingly defines __GNUC__
-#if !defined(__clang__) && defined(__GNUC__) && __GNUC__ == 15
-#pragma GCC optimize("-fno-tree-slp-vectorize")
+// This avoids a known issue with GCC15+ ("error: bp cannot be used in asm here", #845).
+// Make sure the compiler isn't clang since it also confusingly defines __GNUC__
+#if !defined(__clang__) && defined(__GNUC__) && __GNUC__ >= 15
+#pragma GCC optimize("-fno-tree-vectorize")
 #endif
 
 #include "blis.h"

kernels/haswell/3/sup/bli_gemmsup_rv_haswell_asm_s6x16m.c

@@ -33,11 +33,10 @@
 
 */
 
-// This avoids a known issue with GCC15 ("error: bp cannot be used in asm here", #845).
-// Only check for version 15 since this may be fixed in 16 (**fingers crossed**), and also
-// make sure the compiler isn't clang since it also confusingly defines __GNUC__
-#if !defined(__clang__) && defined(__GNUC__) && __GNUC__ == 15
-#pragma GCC optimize("-fno-tree-slp-vectorize")
+// This avoids a known issue with GCC15+ ("error: bp cannot be used in asm here", #845).
+// Make sure the compiler isn't clang since it also confusingly defines __GNUC__
+#if !defined(__clang__) && defined(__GNUC__) && __GNUC__ >= 15
+#pragma GCC optimize("-fno-tree-vectorize")
 #endif
 
 #include "blis.h"

kernels/haswell/3/sup/bli_gemmsup_rv_haswell_asm_s6x16n.c

@@ -33,11 +33,10 @@
 
 */
 
-// This avoids a known issue with GCC15 ("error: bp cannot be used in asm here", #845).
-// Only check for version 15 since this may be fixed in 16 (**fingers crossed**), and also
-// make sure the compiler isn't clang since it also confusingly defines __GNUC__
-#if !defined(__clang__) && defined(__GNUC__) && __GNUC__ == 15
-#pragma GCC optimize("-fno-tree-slp-vectorize")
+// This avoids a known issue with GCC15+ ("error: bp cannot be used in asm here", #845).
+// Make sure the compiler isn't clang since it also confusingly defines __GNUC__
+#if !defined(__clang__) && defined(__GNUC__) && __GNUC__ >= 15
+#pragma GCC optimize("-fno-tree-vectorize")
 #endif
 
 #include "blis.h"