[gcc/devel/omp/gcc-12] libgomp, nvptx: Add fallback for PTX versions lower than 4.1

[Kwok Yeung <kcy@gcc.gnu.org>]

https://gcc.gnu.org/g:1486a6a4a8d4a0714aaa3eab00a79e870cfbc9a6

commit 1486a6a4a8d4a0714aaa3eab00a79e870cfbc9a6
Author: Kwok Cheung Yeung <kcy@codesourcery.com>
Date:   Wed Jun 22 18:54:44 2022 +0100

    libgomp, nvptx: Add fallback for PTX versions lower than 4.1
    
    Avoid using the dynamic_smem_size register if the PTX version does not
    support it.
    
    This patch should be included when the 'libgomp, nvptx: low-latency memory
    allocator' patch is upstreamed.
    
    2022-06-21  Kwok Cheung Yeung  <kcy@codesourcery.com>
    
            libgomp/
            * config/nvptx/team.c (gomp_nvptx_main): Initialize shared_pool_size
            to zero.  Do not use dynamic_smem_size register if PTX version lower
            than 4.1.

Diff:
---
 libgomp/ChangeLog.omp       | 6 ++++++
 libgomp/config/nvptx/team.c | 5 ++++-
 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/libgomp/ChangeLog.omp b/libgomp/ChangeLog.omp
index 242cbbfa7a1..c79c592d97b 100644
--- a/libgomp/ChangeLog.omp
+++ b/libgomp/ChangeLog.omp
@@ -1,3 +1,9 @@
+2022-06-21  Kwok Cheung Yeung  <kcy@codesourcery.com>
+
+	* config/nvptx/team.c (gomp_nvptx_main): Initialize shared_pool_size
+	to zero.  Do not use dynamic_smem_size register if PTX version lower
+	than 4.1.
+
 2021-12-22  Andrew Stubbs  <ams@codesourcery.com>
 
 	* allocator.c (MEMSPACE_ALLOC): New macro.
diff --git a/libgomp/config/nvptx/team.c b/libgomp/config/nvptx/team.c
index c7b2c70dfa6..685610e00be 100644
--- a/libgomp/config/nvptx/team.c
+++ b/libgomp/config/nvptx/team.c
@@ -69,10 +69,13 @@ gomp_nvptx_main (void (*fn) (void *), void *fn_data)
 
       /* Find the low-latency heap details ....  */
       uint32_t *shared_pool;
-      uint32_t shared_pool_size;
+      uint32_t shared_pool_size = 0;
       asm ("cvta.shared.u64\t%0, __nvptx_lowlat_pool;" : "=r"(shared_pool));
+#if __PTX_ISA_VERSION_MAJOR__ > 4 \
+    || (__PTX_ISA_VERSION_MAJOR__ == 4 && __PTX_ISA_VERSION_MINOR__ >= 1)
       asm ("mov.u32\t%0, %%dynamic_smem_size;\n"
 	   : "=r"(shared_pool_size));
+#endif
 
       /* ... and initialize it with an empty free-chain.  */
       union {