[clang] f8b68c7 - [SPIR-V] Add builtin/intrinsic for subgroup ballot (#174862)

[via cfe-commits]

Author: Joseph Huber
Date: 2026-01-08T12:01:15-06:00
New Revision: f8b68c7b74704892ce308049fbc045e4b8b30d4d

URL: https://github.com/llvm/llvm-project/commit/f8b68c7b74704892ce308049fbc045e4b8b30d4d
DIFF: https://github.com/llvm/llvm-project/commit/f8b68c7b74704892ce308049fbc045e4b8b30d4d.diff

LOG: [SPIR-V] Add builtin/intrinsic for subgroup ballot (#174862)

Summary:
This patch adds an LLVM intrinsic and lowering for a subgroup ballot and
a corresponding clang builtin. This uses the already present support but
provides in a way accessible to other targets. With this and
https://github.com/llvm/llvm-project/pull/174655 we should be able to
most of the basic functions, like shuffling, active masks, and
reductions. More work will be needed for canonicalizing / exposing the
SPIR-V functions, but these are the fundamental builtins I need.

Added: 
    clang/test/CodeGenSPIRV/Builtins/subgroup.c
    clang/test/SemaSPIRV/BuiltIns/subgroup-errors.c

Modified: 
    clang/include/clang/Basic/BuiltinsSPIRVCommon.td
    llvm/include/llvm/IR/IntrinsicsSPIRV.td

Removed: 
    


################################################################################
diff  --git a/clang/include/clang/Basic/BuiltinsSPIRVCommon.td b/clang/include/clang/Basic/BuiltinsSPIRVCommon.td
index d2ef6f99a0502..495851ed1727a 100644
--- a/clang/include/clang/Basic/BuiltinsSPIRVCommon.td
+++ b/clang/include/clang/Basic/BuiltinsSPIRVCommon.td
@@ -21,3 +21,5 @@ def subgroup_local_invocation_id : SPIRVBuiltin<"uint32_t()", [NoThrow, Const]>;
 def distance : SPIRVBuiltin<"void(...)", [NoThrow, Const]>;
 def length : SPIRVBuiltin<"void(...)", [NoThrow, Const]>;
 def smoothstep : SPIRVBuiltin<"void(...)", [NoThrow, Const, CustomTypeChecking]>;
+
+def subgroup_ballot : SPIRVBuiltin<"_ExtVector<4, uint32_t>(bool)", [NoThrow, Const]>;

diff  --git a/clang/test/CodeGenSPIRV/Builtins/subgroup.c b/clang/test/CodeGenSPIRV/Builtins/subgroup.c
new file mode 100644
index 0000000000000..2ae2013c3c23e
--- /dev/null
+++ b/clang/test/CodeGenSPIRV/Builtins/subgroup.c
@@ -0,0 +1,15 @@
+// RUN: %clang_cc1 -O1 -triple spirv64 -fsycl-is-device -x c++ %s -emit-llvm -o - | FileCheck %s --check-prefixes=CHECK
+// RUN: %clang_cc1 -O1 -triple spirv64 -cl-std=CL3.0 -x cl %s -emit-llvm -o - | FileCheck %s --check-prefixes=CHECK
+// RUN: %clang_cc1 -O1 -triple spirv32 -cl-std=CL3.0 -x cl %s -emit-llvm -o - | FileCheck %s --check-prefixes=CHECK
+
+#if defined(__cplusplus)
+typedef bool _Bool;
+#endif
+typedef unsigned __attribute__((ext_vector_type(4))) int4;
+
+// CHECK: @{{.*}}test_subgroup_shuffle{{.*}}(
+// CHECK-NEXT:  [[ENTRY:.*:]]
+// CHECK-NEXT:    tail call <4 x i32> @llvm.spv.wave.ballot(i1 %i)
+[[clang::sycl_external]] int4 test_subgroup_shuffle(_Bool i) {
+    return __builtin_spirv_subgroup_ballot(i);
+}

diff  --git a/clang/test/SemaSPIRV/BuiltIns/subgroup-errors.c b/clang/test/SemaSPIRV/BuiltIns/subgroup-errors.c
new file mode 100644
index 0000000000000..5ef9f499efd31
--- /dev/null
+++ b/clang/test/SemaSPIRV/BuiltIns/subgroup-errors.c
@@ -0,0 +1,13 @@
+// RUN: %clang_cc1 -O1 -Wno-unused-value -triple spirv64 -fsycl-is-device -verify %s -o -
+// RUN: %clang_cc1 -O1 -Wno-unused-value -triple spirv64 -verify %s -cl-std=CL3.0 -x cl -o -
+// RUN: %clang_cc1 -O1 -Wno-unused-value -triple spirv32 -verify %s -cl-std=CL3.0 -x cl -o -
+
+typedef unsigned __attribute__((ext_vector_type(4))) int4;
+
+void ballot(_Bool c) {
+  int4 x;
+  x = __builtin_spirv_subgroup_ballot(c);
+  x = __builtin_spirv_subgroup_ballot(1);
+  x = __builtin_spirv_subgroup_ballot(x); // expected-error{{parameter of incompatible type}}
+  int y = __builtin_spirv_subgroup_ballot(c); // expected-error{{with an expression of incompatible type}}
+}

diff  --git a/llvm/include/llvm/IR/IntrinsicsSPIRV.td b/llvm/include/llvm/IR/IntrinsicsSPIRV.td
index 0e23d19a01c20..bcb533780b58c 100644
--- a/llvm/include/llvm/IR/IntrinsicsSPIRV.td
+++ b/llvm/include/llvm/IR/IntrinsicsSPIRV.td
@@ -120,7 +120,8 @@ def int_spv_rsqrt : DefaultAttrsIntrinsic<[LLVMMatchType<0>], [llvm_anyfloat_ty]
   def int_spv_wave_active_countbits : DefaultAttrsIntrinsic<[llvm_i32_ty], [llvm_i1_ty], [IntrConvergent, IntrNoMem]>;
   def int_spv_wave_all : DefaultAttrsIntrinsic<[llvm_i1_ty], [llvm_i1_ty], [IntrConvergent, IntrNoMem]>;
   def int_spv_wave_any : DefaultAttrsIntrinsic<[llvm_i1_ty], [llvm_i1_ty], [IntrConvergent, IntrNoMem]>;
-  def int_spv_wave_ballot : DefaultAttrsIntrinsic<[llvm_v4i32_ty], [llvm_i1_ty], [IntrConvergent, IntrNoMem]>;
+  def int_spv_wave_ballot : ClangBuiltin<"__builtin_spirv_subgroup_ballot">,
+    DefaultAttrsIntrinsic<[llvm_v4i32_ty], [llvm_i1_ty], [IntrConvergent, IntrNoMem]>;
   def int_spv_wave_reduce_umax : DefaultAttrsIntrinsic<[llvm_any_ty], [LLVMMatchType<0>], [IntrConvergent, IntrNoMem]>;
   def int_spv_wave_reduce_max : DefaultAttrsIntrinsic<[llvm_any_ty], [LLVMMatchType<0>], [IntrConvergent, IntrNoMem]>;
   def int_spv_wave_reduce_min : DefaultAttrsIntrinsic<[llvm_any_ty], [LLVMMatchType<0>], [IntrConvergent, IntrNoMem]>;