From: Tom de Vries <tdevries@suse.de>
Date: Wed, 19 Dec 2018 17:16:10 +0000 (+0000)
Subject: [nvptx] Add PTX_CTA_SIZE
X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=c4686fa91e3f4852f0182df220ced85b6ff0e13c;p=gcc.git

[nvptx] Add PTX_CTA_SIZE

2018-12-19  Tom de Vries  <tdevries@suse.de>

	* config/nvptx/nvptx.c (PTX_CTA_SIZE): Define.

From-SVN: r267281
---

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 7b0ca6357de..365d5931bcf 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,7 @@
+2018-12-19  Tom de Vries  <tdevries@suse.de>
+
+	* config/nvptx/nvptx.c (PTX_CTA_SIZE): Define.
+
 2018-12-19  Tom de Vries  <tdevries@suse.de>
 
 	* omp-offload.c (oacc_fn_attrib_level): Remove static.
diff --git a/gcc/config/nvptx/nvptx.c b/gcc/config/nvptx/nvptx.c
index 2a2d638e6d7..f4095ff5f55 100644
--- a/gcc/config/nvptx/nvptx.c
+++ b/gcc/config/nvptx/nvptx.c
@@ -86,6 +86,11 @@
 #define PTX_WORKER_LENGTH 32
 #define PTX_DEFAULT_RUNTIME_DIM 0 /* Defer to runtime.  */
 
+/* The PTX concept CTA (Concurrent Thread Array) maps on the CUDA concept thread
+   block, which has had a maximum number of threads of 1024 since CUDA version
+   2.x.  */
+#define PTX_CTA_SIZE 1024
+
 /* The various PTX memory areas an object might reside in.  */
 enum nvptx_data_area
 {