Fix build on additional architectures (#740)

* Fix build on additional architectures

Instead of directly wrapping a platform-specific operation with a
preprocessor check against a gfx macro, it can be more flexible to
check a macro that can be overriden by the user. The gfx macro can then
just provide the default value for the macro, resulting in the same
default behaviour as if the gfx macro was checked directly but with
more control at build-time.

For example, to build rccl without using buffer_wbinvl1_vol on
gfx902, but still use the default on other archs, a user could
export CXXFLAGS='-Xarch_gfx902 -DRCCL_USE_WBINVL1_VOL=1' before
configuring the build. This flexibility isn't always necessary, but
it's nicer to have it and not need it than to need it and not have it.

* Define WARP_SIZE using warpSize builtin

src/collectives/device/prims_ll128.h

@@ -12,6 +12,14 @@
 
 #define NCCL_LL128_FLAGTHREAD (NCCL_LL128_LINEELEMS-1)
 
+#ifndef RCCL_USE_WBINVL1_VOL
+#if defined(__GFX8__) || defined(__GFX9__)
+#define RCCL_USE_WBINVL1_VOL 1
+#else
+#define RCCL_USE_WBINVL1_VOL 0
+#endif
+#endif
+
 template<typename T, typename RedOp, typename Fan, int Direct, int P2p>
 class Primitives<T, RedOp, Fan, Direct, ProtoLL128, P2p>:
   public PrimitivesWithoutDirect<Primitives<T, RedOp, Fan, Direct, ProtoLL128, P2p>> {
@@ -304,7 +312,7 @@ private:
       }
     }
 
-#if !defined(__gfx1030__) && !defined(__gfx1100__) && !defined(__gfx1101__) && !defined(__gfx1102__)
+#if RCCL_USE_WBINVL1_VOL
     if (tid == 0) __asm__ __volatile__("buffer_wbinvl1_vol");
 #endif
     /************************ Send **************************/

src/include/devcomm.h

@@ -53,11 +53,7 @@ union ncclLLFifoLine {
   int4 i4;
 };
 
-#if defined(__gfx1030__)  || defined(__gfx1100__) || defined(__gfx1101__) || defined(__gfx1102__)
-#define WARP_SIZE 32
-#else
-#define WARP_SIZE 64
-#endif
+#define WARP_SIZE warpSize
 #define MAXCHANNELS 32
 #define NCCL_MAX_NTHREADS 256
 #define NCCL_SIMPLE_MAX_NTHREADS NCCL_MAX_NTHREADS