Merge pull request #4003 from martin-frbg/issue3995

Fix instabilities in CGEMM/CTRMM/DNRM2 on Apple M1/M2 under OSX

cpuid_arm64.c

@@ -267,9 +267,9 @@ int detect(void)
 	}
 #else
 #ifdef __APPLE__
-	sysctlbyname("hw.cpufamily",&value,&length,NULL,0);
-	if (value ==131287967|| value == 458787763 ) return CPU_VORTEX; //A12/M1
-	if (value == 3660830781) return CPU_VORTEX; //A15/M2
+	sysctlbyname("hw.cpufamily",&value64,&length64,NULL,0);
+	if (value64 ==131287967|| value64 == 458787763 ) return CPU_VORTEX; //A12/M1
+	if (value64 == 3660830781) return CPU_VORTEX; //A15/M2
 #endif
 	return CPU_ARMV8;	
 #endif

kernel/arm64/cgemm_kernel_8x4.S

@@ -49,7 +49,7 @@ USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 #define pCRow3		x15
 #define pA		x16
 #define alphaR		w17
-#define alphaI		w18
+#define alphaI		w19
 
 #define alpha0_R	s10
 #define alphaV0_R	v10.s[0]

kernel/arm64/cgemm_kernel_8x4_thunderx2t99.S

@@ -49,7 +49,7 @@ USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 #define pCRow3		x15
 #define pA		x16
 #define alphaR		w17
-#define alphaI		w18
+#define alphaI		w19
 
 #define alpha0_R	s10
 #define alphaV0_R	v10.s[0]

kernel/arm64/ctrmm_kernel_8x4.S

@@ -49,10 +49,10 @@ USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 #define pCRow3		x15
 #define pA		x16
 #define alphaR		w17
-#define alphaI		w18
-#define temp		x19
-#define tempOffset	x20
-#define tempK		x21
+#define alphaI		w19
+#define temp		x20
+#define tempOffset	x21
+#define tempK		x22
 
 #define alpha0_R	s10
 #define alphaV0_R	v10.s[0]

kernel/arm64/dznrm2_thunderx2t99.c

@@ -27,7 +27,7 @@ USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
 
 #include "common.h"
-
+#include <float.h>
 #include <arm_neon.h>
 
 #if defined(SMP)
@@ -404,7 +404,8 @@ FLOAT CNAME(BLASLONG n, FLOAT *x, BLASLONG inc_x)
 #else
 	nrm2_compute(n, x, inc_x, &ssq, &scale);
 #endif
-	if (fabs(scale) <1.e-300) return 0.;
+	volatile FLOAT sca = fabs(scale);
+	if (sca < DBL_MIN) return 0.;
 	ssq = sqrt(ssq) * scale;
 
 	return ssq;