[SRC] Enable unroll=1 for gfx950 (#1602)

* [SRC] Enable unroll=1 for gfx950

* Fix typo from rebase in generate.py

* Support for unroll=1 and gfx90a when building for all GPU targets

---------

Signed-off-by: nileshnegi <Nilesh.Negi@amd.com>

src/include/nccl_common.h

@@ -72,9 +72,10 @@ typedef enum {
 
 #define NCCL_ALGO_PROTO_IGNORE -1.0
 
-#define NCCL_NUM_UNROLLS 2 // 2/4
-#define NCCL_UNROLL_2 0
-#define NCCL_UNROLL_4 1
+#define NCCL_NUM_UNROLLS 3 // 1/2/4
+#define NCCL_UNROLL_1 0
+#define NCCL_UNROLL_2 1
+#define NCCL_UNROLL_4 2
 
 #define NCCL_NUM_FLOATS 6 // half/float/double/rccl_bfloat16/rccl_float8/rccl_bfloat8
 #endif