@@ -3684,10 +3684,19 @@ nvptx_expand_builtin (tree exp, rtx target, rtx ARG_UNUSED (subtarget),
}
}
+
/* Define dimension sizes for known hardware. */
#define PTX_VECTOR_LENGTH 32
#define PTX_WORKER_LENGTH 32
+/* Implement TARGET_SIMT_VF target hook: number of threads in a warp. */
+
+static int
+nvptx_simt_vf ()
+{
+ return PTX_VECTOR_LENGTH;
+}
+
/* Validate compute dimensions of an OpenACC offload or routine, fill
in non-unity defaults. FN_LEVEL indicates the level at which a
routine might spawn a loop. It is negative for non-routines. */
@@ -4258,6 +4267,9 @@ nvptx_goacc_reduction (gcall *call)
#undef TARGET_BUILTIN_DECL
#define TARGET_BUILTIN_DECL nvptx_builtin_decl
+#undef TARGET_SIMT_VF
+#define TARGET_SIMT_VF nvptx_simt_vf
+
#undef TARGET_GOACC_VALIDATE_DIMS
#define TARGET_GOACC_VALIDATE_DIMS nvptx_goacc_validate_dims
@@ -5765,6 +5765,10 @@ usable. In that case, the smaller the number is, the more desirable it is
to use it.
@end deftypefn
+@deftypefn {Target Hook} int TARGET_SIMT_VF (void)
+Return number of threads in SIMT thread group on the target.
+@end deftypefn
+
@deftypefn {Target Hook} bool TARGET_GOACC_VALIDATE_DIMS (tree @var{decl}, int *@var{dims}, int @var{fn_level})
This hook should check the launch dimensions provided for an OpenACC
compute region, or routine. Defaulted values are represented as -1
@@ -4260,6 +4260,8 @@ address; but often a machine-dependent strategy can generate better code.
@hook TARGET_SIMD_CLONE_USABLE
+@hook TARGET_SIMT_VF
+
@hook TARGET_GOACC_VALIDATE_DIMS
@hook TARGET_GOACC_DIM_LIMIT
@@ -1639,6 +1639,18 @@ int, (struct cgraph_node *), NULL)
HOOK_VECTOR_END (simd_clone)
+/* Functions relating to OpenMP SIMT vectorization transform. */
+#undef HOOK_PREFIX
+#define HOOK_PREFIX "TARGET_SIMT_"
+HOOK_VECTOR (TARGET_SIMT, simt)
+
+DEFHOOK
+(vf,
+"Return number of threads in SIMT thread group on the target.",
+int, (void), NULL)
+
+HOOK_VECTOR_END (simt)
+
/* Functions relating to openacc. */
#undef HOOK_PREFIX
#define HOOK_PREFIX "TARGET_GOACC_"
This patch adds a new target hook and implements it in a straightforward manner on NVPTX to indicate that the target is running in SIMT fashion with 32 threads in a synchronous group ("warp"). For use in OpenMP transforms. --- gcc/config/nvptx/nvptx.c | 12 ++++++++++++ gcc/doc/tm.texi | 4 ++++ gcc/doc/tm.texi.in | 2 ++ gcc/target.def | 12 ++++++++++++ 4 files changed, 30 insertions(+)