https://github.com/zjin-lcf updated https://github.com/llvm/llvm-project/pull/213691
>From 67c4e670046237b93eca42861948f0756d66431c Mon Sep 17 00:00:00 2001 From: Zheming Jin <[email protected]> Date: Mon, 3 Aug 2026 09:47:48 -0500 Subject: [PATCH 1/2] [libclc] Enable 64-bit atomics for nvptx64 The `__CLC_HAS_ATOMIC` guards in `clc_atomic_def.inc` and `clc_atomic_compare_exchange.inc` restrict atomics to 32-bit types for `__NVPTX__`. That exclusion was added to silence the "large atomic operation may incur significant performance penalty" warning on 32-bit targets, but `__NVPTX__` is defined for both nvptx and nvptx64. NVPTX sets `MaxAtomicInlineWidth` to the target pointer width, so nvptx64 lowers 64-bit atomics natively and never emits that warning; only the 32-bit nvptx target did. libclc no longer builds a 32-bit nvptx target (`LIBCLC_ARCHS_NVPTX` is just `nvptx64`), so the exclusion now only prevents nvptx64 from getting the 64-bit atomics that `atomic_decl.inc` declares unconditionally, leaving them declared but never defined. Restrict the 32-bit-only guard to `__SPIR32__`, so nvptx64 defines the 64-bit atomics. --- .../clc/lib/generic/atomic/clc_atomic_compare_exchange.inc | 6 +++--- libclc/clc/lib/generic/atomic/clc_atomic_def.inc | 6 +++--- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/libclc/clc/lib/generic/atomic/clc_atomic_compare_exchange.inc b/libclc/clc/lib/generic/atomic/clc_atomic_compare_exchange.inc index d28e3c72e465e..3d37ba52d370d 100644 --- a/libclc/clc/lib/generic/atomic/clc_atomic_compare_exchange.inc +++ b/libclc/clc/lib/generic/atomic/clc_atomic_compare_exchange.inc @@ -8,16 +8,16 @@ #ifdef __CLC_SCALAR -#if defined(__SPIR32__) || defined(__NVPTX__) +#ifdef __SPIR32__ #if (defined(__CLC_FPSIZE) && __CLC_FPSIZE <= 32) || \ (defined(__CLC_GENSIZE) && (__CLC_GENSIZE == 32)) #define __CLC_HAS_ATOMIC #endif -#else // defined(__SPIR32__) || defined(__NVPTX__) +#else // __SPIR32__ #if defined(__CLC_FPSIZE) || (__CLC_GENSIZE >= 32) #define __CLC_HAS_ATOMIC #endif -#endif // defined(__SPIR32__) || defined(__NVPTX__) +#endif // __SPIR32__ #ifdef __CLC_HAS_ATOMIC diff --git a/libclc/clc/lib/generic/atomic/clc_atomic_def.inc b/libclc/clc/lib/generic/atomic/clc_atomic_def.inc index 2af450ffbbe5c..bf40ff626fc81 100644 --- a/libclc/clc/lib/generic/atomic/clc_atomic_def.inc +++ b/libclc/clc/lib/generic/atomic/clc_atomic_def.inc @@ -8,16 +8,16 @@ #ifdef __CLC_SCALAR -#if defined(__SPIR32__) || defined(__NVPTX__) +#ifdef __SPIR32__ #if (defined(__CLC_FPSIZE) && __CLC_FPSIZE <= 32) || \ (defined(__CLC_GENSIZE) && (__CLC_GENSIZE == 32)) #define __CLC_HAS_ATOMIC #endif -#else // defined(__SPIR32__) || defined(__NVPTX__) +#else // __SPIR32__ #if defined(__CLC_FPSIZE) || (__CLC_GENSIZE >= 32) #define __CLC_HAS_ATOMIC #endif -#endif // defined(__SPIR32__) || defined(__NVPTX__) +#endif // __SPIR32__ #ifdef __CLC_HAS_ATOMIC >From cb876a72f383977c5b3ba4ab48d6ef43014f47a9 Mon Sep 17 00:00:00 2001 From: Zheming Jin <[email protected]> Date: Mon, 3 Aug 2026 22:45:59 -0400 Subject: [PATCH 2/2] [clang][NVPTX] Enable 64-bit atomic OpenCL extensions for nvptx64 libclc defines the 64-bit atomic builtins for nvptx64, but the NVPTX target did not advertise cl_khr_int64_base_atomics / cl_khr_int64_extended_atomics, so those builtins were never exposed. PTX supports 64-bit atomics natively on 64-bit targets, where NVPTXTargetInfo sets MaxAtomicInlineWidth to the target pointer width. Guard the extensions on getMaxAtomicInlineWidth() >= 64 so the 32-bit nvptx target is unaffected and keeps avoiding emulated 64-bit atomics. --- clang/lib/Basic/Targets/NVPTX.h | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/clang/lib/Basic/Targets/NVPTX.h b/clang/lib/Basic/Targets/NVPTX.h index 996b1a9730606..83243ae65374d 100644 --- a/clang/lib/Basic/Targets/NVPTX.h +++ b/clang/lib/Basic/Targets/NVPTX.h @@ -159,6 +159,13 @@ class LLVM_LIBRARY_VISIBILITY NVPTXTargetInfo : public TargetInfo { Opts["cl_khr_global_int32_extended_atomics"] = true; Opts["cl_khr_local_int32_base_atomics"] = true; Opts["cl_khr_local_int32_extended_atomics"] = true; + // PTX supports 64-bit atomics natively on 64-bit targets even though the + // NVIDIA OpenCL runtime does not report these extensions. libclc needs + // them enabled to define the 64-bit atomic builtins. + if (getMaxAtomicInlineWidth() >= 64) { + Opts["cl_khr_int64_base_atomics"] = true; + Opts["cl_khr_int64_extended_atomics"] = true; + } Opts["__opencl_c_images"] = true; Opts["__opencl_c_3d_image_writes"] = true; _______________________________________________ cfe-commits mailing list [email protected] https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
