Add 64-bit versions of clz and family

Where algorithms naturally use 64-bit quantities, these functions will lend
themselves to even better optimisation under AArch64.

Also opt back in to the softload_gnu CI job, since this is one of the
components for which it already passes.

Version 0.21. Tagged as 'AsmUtils-0_21'

.gitlab-ci.yml

+variables:
+  ENABLE_JOBS: 'softload_gnu'
+
 include:
   - project: 'Support/CI'
     file: '/AsmUtils.yml'

VersionNum

-/* (0.20)
+/* (0.21)
  *
  * This file is automatically maintained by srccommit, do not edit manually.
  *
  */
-#define Module_MajorVersion_CMHG        0.20
+#define Module_MajorVersion_CMHG        0.21
 #define Module_MinorVersion_CMHG
-#define Module_Date_CMHG                25 Jun 2022
+#define Module_Date_CMHG                03 Aug 2022
 
-#define Module_MajorVersion             "0.20"
-#define Module_Version                  20
+#define Module_MajorVersion             "0.21"
+#define Module_Version                  21
 #define Module_MinorVersion             ""
-#define Module_Date                     "25 Jun 2022"
+#define Module_Date                     "03 Aug 2022"
 
-#define Module_ApplicationDate          "25-Jun-22"
+#define Module_ApplicationDate          "03-Aug-22"
 
 #define Module_ComponentName            "AsmUtils"
 
-#define Module_FullVersion              "0.20"
-#define Module_HelpVersion              "0.20 (25 Jun 2022)"
-#define Module_LibraryVersionInfo       "0:20"
+#define Module_FullVersion              "0.21"
+#define Module_HelpVersion              "0.21 (03 Aug 2022)"
+#define Module_LibraryVersionInfo       "0:21"

h/clz

@@ -42,6 +42,18 @@ extern unsigned int clo(unsigned int);
 extern unsigned int cto(unsigned int);
   /* Returns the number of trailing one bits in the argument, 0 ... 32 */
 
+extern unsigned int clz64(unsigned long long);
+  /* Returns the number of leading zero bits in the argument, 0 ... 64 */
+
+extern unsigned int ctz64(unsigned long long);
+  /* Returns the number of trailing zero bits in the argument, 0 ... 64 */
+
+extern unsigned int clo64(unsigned long long);
+  /* Returns the number of leading one bits in the argument, 0 ... 64 */
+
+extern unsigned int cto64(unsigned long long);
+  /* Returns the number of trailing one bits in the argument, 0 ... 64 */
+
 #ifdef __cplusplus
 }
 #endif

s/clz

@@ -27,6 +27,10 @@
         EXPORT  |ctz|
         EXPORT  |clo|
         EXPORT  |cto|
+        EXPORT  |clz64|
+        EXPORT  |ctz64|
+        EXPORT  |clo64|
+        EXPORT  |cto64|
 
 |clo|
       [ NoARMv5
@@ -107,4 +111,44 @@ table
         =  1, 15, 23, 20,  3, 11, 26,  9, 16, 24,  4, 27, 17,  5,  6,  7
       ]
 
+|clz64|
+        FunctionEntry "v1"
+        CMP     a2, #0
+        MOVNE   a1, a2
+        MOVNE   v1, #0
+        MOVEQ   v1, #32
+        BL      |clz|
+        ADD     a1, a1, v1
+        Return  "v1"
+
+|ctz64|
+        FunctionEntry "v1"
+        CMP     a1, #0
+        MOVEQ   a1, a2
+        MOVNE   v1, #0
+        MOVEQ   v1, #32
+        BL      |ctz|
+        ADD     a1, a1, v1
+        Return  "v1"
+
+|clo64|
+        FunctionEntry "v1"
+        CMP     a2, #-1
+        MOVNE   a1, a2
+        MOVNE   v1, #0
+        MOVEQ   v1, #32
+        BL      |clo|
+        ADD     a1, a1, v1
+        Return  "v1"
+
+|cto64|
+        FunctionEntry "v1"
+        CMP     a1, #-1
+        MOVEQ   a1, a2
+        MOVNE   v1, #0
+        MOVEQ   v1, #32
+        BL      |cto|
+        ADD     a1, a1, v1
+        Return  "v1"
+
         END