On 14-12-18 20:58, Tom de Vries wrote:
> 0012-nvptx-Add-axis_dim.patch
> diff --git a/gcc/config/nvptx/nvptx.c b/gcc/config/nvptx/nvptx.c
> index 74a0d4b04d9..02ecf12bd84 100644
> --- a/gcc/config/nvptx/nvptx.c
> +++ b/gcc/config/nvptx/nvptx.c
> @@ -2885,6 +2885,23 @@ struct offload_attrs
> int max_workers;
> };
>
> +/* Define entries for cfun->machine->axis_dim. */
> +
> +#define MACH_VECTOR_LENGTH 0
> +#define MACH_MAX_WORKERS 1
> +
> +static int ATTRIBUTE_UNUSED
> +nvptx_mach_max_workers ()
> +{
> + return cfun->machine->axis_dim[MACH_MAX_WORKERS];
> +}
> +
> +static int ATTRIBUTE_UNUSED
> +nvptx_mach_vector_length ()
> +{
> + return cfun->machine->axis_dim[MACH_VECTOR_LENGTH];
> +}
> +
> /* Loop structure of the function. The entire function is described as
> a NULL loop. */
>
> @@ -4832,6 +4849,9 @@ nvptx_reorg (void)
>
> populate_offload_attrs (&oa);
>
> + cfun->machine->axis_dim[MACH_VECTOR_LENGTH] = oa.vector_length;
> + cfun->machine->axis_dim[MACH_MAX_WORKERS] = oa.max_workers;
> +
This initialization here is done during pass_machine_reorg , but the
data is needed earlier, making it necessary there to call
populate_offload_attrs again, instead of using
nvptx_mach_vector_length/nvptx_mach_max_workers.
I've made the initialization lazy, which fixes that problem.
> /* If there is worker neutering, there must be vector
> neutering. Otherwise the hardware will fail. */
> gcc_assert (!(oa.mask & GOMP_DIM_MASK (GOMP_DIM_WORKER))
> diff --git a/gcc/config/nvptx/nvptx.h b/gcc/config/nvptx/nvptx.h
> index a2fe8b68b22..4059691a609 100644
> --- a/gcc/config/nvptx/nvptx.h
> +++ b/gcc/config/nvptx/nvptx.h
> @@ -218,6 +218,8 @@ struct GTY(()) machine_function
> int return_mode; /* Return mode of current fn.
> (machine_mode not defined yet.) */
> rtx axis_predicate[2]; /* Neutering predicates. */
> + int axis_dim[2]; /* Maximum number of threads on each axis, dim[0] is
> + vector_length, dim[1] is num_workers. */
> rtx unisimt_master; /* 'Master lane index' for -muniform-simt. */
> rtx unisimt_predicate; /* Predicate for -muniform-simt. */
> rtx unisimt_location; /* Mask location for -muniform-simt. */
> --
> 2.17.2
Committed as attached.
Thanks,
- Tom
[nvptx] Add nvptx_mach_vector_length, nvptx_mach_max_workers
The vector length and maximum number of workers are known compile-time. Make
these easily available during code generation via new functions.
2019-01-03 Tom de Vries <tdevr...@suse.de>
* config/nvptx/nvptx.c (MACH_VECTOR_LENGTH, MACH_MAX_WORKERS): Define.
(init_axis_dim, nvptx_mach_max_workers, nvptx_mach_vector_length): New
function.
* config/nvptx/nvptx.h (struct machine_function): Add axis_dims.
---
gcc/config/nvptx/nvptx.c | 41 +++++++++++++++++++++++++++++++++++++++++
gcc/config/nvptx/nvptx.h | 3 +++
2 files changed, 44 insertions(+)
diff --git a/gcc/config/nvptx/nvptx.c b/gcc/config/nvptx/nvptx.c
index f527429ce2d..52cbac957ce 100644
--- a/gcc/config/nvptx/nvptx.c
+++ b/gcc/config/nvptx/nvptx.c
@@ -2883,6 +2883,47 @@ struct offload_attrs
int vector_length;
};
+/* Define entries for cfun->machine->axis_dim. */
+
+#define MACH_VECTOR_LENGTH 0
+#define MACH_MAX_WORKERS 1
+
+static void populate_offload_attrs (offload_attrs *oa);
+
+static void
+init_axis_dim (void)
+{
+ offload_attrs oa;
+ int max_workers;
+
+ populate_offload_attrs (&oa);
+
+ if (oa.num_workers == 0)
+ max_workers = PTX_CTA_SIZE / oa.vector_length;
+ else
+ max_workers = oa.num_workers;
+
+ cfun->machine->axis_dim[MACH_VECTOR_LENGTH] = oa.vector_length;
+ cfun->machine->axis_dim[MACH_MAX_WORKERS] = max_workers;
+ cfun->machine->axis_dim_init_p = true;
+}
+
+static int ATTRIBUTE_UNUSED
+nvptx_mach_max_workers ()
+{
+ if (!cfun->machine->axis_dim_init_p)
+ init_axis_dim ();
+ return cfun->machine->axis_dim[MACH_MAX_WORKERS];
+}
+
+static int ATTRIBUTE_UNUSED
+nvptx_mach_vector_length ()
+{
+ if (!cfun->machine->axis_dim_init_p)
+ init_axis_dim ();
+ return cfun->machine->axis_dim[MACH_VECTOR_LENGTH];
+}
+
/* Loop structure of the function. The entire function is described as
a NULL loop. */
diff --git a/gcc/config/nvptx/nvptx.h b/gcc/config/nvptx/nvptx.h
index a2fe8b68b22..cb4404504c5 100644
--- a/gcc/config/nvptx/nvptx.h
+++ b/gcc/config/nvptx/nvptx.h
@@ -218,6 +218,9 @@ struct GTY(()) machine_function
int return_mode; /* Return mode of current fn.
(machine_mode not defined yet.) */
rtx axis_predicate[2]; /* Neutering predicates. */
+ int axis_dim[2]; /* Maximum number of threads on each axis, dim[0] is
+ vector_length, dim[1] is num_workers. */
+ bool axis_dim_init_p;
rtx unisimt_master; /* 'Master lane index' for -muniform-simt. */
rtx unisimt_predicate; /* Predicate for -muniform-simt. */
rtx unisimt_location; /* Mask location for -muniform-simt. */
