Skip to content

[CIR] Implement Logical OR for VectorType #158668

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 1 commit into from
Sep 18, 2025
Merged

[CIR] Implement Logical OR for VectorType #158668

merged 1 commit into from
Sep 18, 2025

Conversation

AmrDeveloper
Copy link
Member

This change adds support for local OR op for VectorType

Issue #136487

@llvmbot llvmbot added clang Clang issues not falling into any other category ClangIR Anything related to the ClangIR project labels Sep 15, 2025
@llvmbot
Copy link
Member

llvmbot commented Sep 15, 2025

@llvm/pr-subscribers-clangir

Author: Amr Hesham (AmrDeveloper)

Changes

This change adds support for local OR op for VectorType

Issue #136487

Full diff: https://github.com/llvm/llvm-project/pull/158668.diff

3 Files Affected:

  • (modified) clang/lib/CIR/CodeGen/CIRGenExprScalar.cpp (+15-3)
  • (modified) clang/test/CIR/CodeGen/vector-ext.cpp (+40)
  • (modified) clang/test/CIR/CodeGen/vector.cpp (+40)
diff --git a/clang/lib/CIR/CodeGen/CIRGenExprScalar.cpp b/clang/lib/CIR/CodeGen/CIRGenExprScalar.cpp
index 2261e24fe44c2..b48d559958dff 100644
--- a/clang/lib/CIR/CodeGen/CIRGenExprScalar.cpp
+++ b/clang/lib/CIR/CodeGen/CIRGenExprScalar.cpp
@@ -872,7 +872,7 @@ class ScalarExprEmitter : public StmtVisitor<ScalarExprEmitter, mlir::Value> {
     if (ty.UseExcessPrecision(cgf.getContext())) {
       if (ty->getAs<VectorType>()) {
         assert(!cir::MissingFeatures::vectorType());
-        cgf.cgm.errorNYI("promotion to vector type");
+        cgf.cgm.errorNYI("getPromotionType: promotion to vector type");
         return QualType();
       }
       return cgf.getContext().FloatTy;
@@ -1086,8 +1086,20 @@ class ScalarExprEmitter : public StmtVisitor<ScalarExprEmitter, mlir::Value> {
 
   mlir::Value VisitBinLOr(const clang::BinaryOperator *e) {
     if (e->getType()->isVectorType()) {
-      assert(!cir::MissingFeatures::vectorType());
-      return {};
+      mlir::Location loc = cgf.getLoc(e->getExprLoc());
+      auto vecTy = mlir::cast<cir::VectorType>(cgf.convertType(e->getType()));
+      mlir::Value zeroValue = builder.getNullValue(vecTy.getElementType(), loc);
+      SmallVector<mlir::Value, 16> elements(vecTy.getSize(), zeroValue);
+      auto zeroVec = cir::VecCreateOp::create(builder, loc, vecTy, elements);
+
+      mlir::Value lhs = Visit(e->getLHS());
+      mlir::Value rhs = Visit(e->getRHS());
+
+      auto cmpOpKind = cir::CmpOpKind::ne;
+      lhs = cir::VecCmpOp::create(builder, loc, vecTy, cmpOpKind, lhs, zeroVec);
+      rhs = cir::VecCmpOp::create(builder, loc, vecTy, cmpOpKind, rhs, zeroVec);
+      mlir::Value vecOr = builder.createOr(loc, lhs, rhs);
+      return builder.createIntCast(vecOr, vecTy);
     }
 
     assert(!cir::MissingFeatures::instrumentation());
diff --git a/clang/test/CIR/CodeGen/vector-ext.cpp b/clang/test/CIR/CodeGen/vector-ext.cpp
index 2ee42187a6e94..ad94e6737c615 100644
--- a/clang/test/CIR/CodeGen/vector-ext.cpp
+++ b/clang/test/CIR/CodeGen/vector-ext.cpp
@@ -1176,3 +1176,43 @@ void foo21() {
 
 // OGCG: %[[SIZE:.*]] = alloca i64, align 8
 // OGCG: store i64 4, ptr %[[SIZE]], align 8
+
+void foo22() {
+  vi4 a;
+  vi4 b;
+  vi4 c = a || b;
+}
+
+// CIR: %[[A_ADDR:.*]] = cir.alloca !cir.vector<4 x !s32i>, !cir.ptr<!cir.vector<4 x !s32i>>, ["a"]
+// CIR: %[[B_ADDR:.*]] = cir.alloca !cir.vector<4 x !s32i>, !cir.ptr<!cir.vector<4 x !s32i>>, ["b"]
+// CIR: %[[C_ADDR:.*]] = cir.alloca !cir.vector<4 x !s32i>, !cir.ptr<!cir.vector<4 x !s32i>>, ["c", init]
+// CIR: %[[ZERO_VEC:.*]] = cir.const #cir.const_vector<[#cir.int<0> : !s32i, #cir.int<0> : !s32i, #cir.int<0> : !s32i, #cir.int<0> : !s32i]> : !cir.vector<4 x !s32i>
+// CIR: %[[TMP_A:.*]] = cir.load{{.*}} %[[A_ADDR]] : !cir.ptr<!cir.vector<4 x !s32i>>, !cir.vector<4 x !s32i>
+// CIR: %[[TMP_B:.*]] = cir.load{{.*}} %[[B_ADDR]] : !cir.ptr<!cir.vector<4 x !s32i>>, !cir.vector<4 x !s32i>
+// CIR: %[[NE_A_ZERO:.*]] = cir.vec.cmp(ne, %[[TMP_A]], %[[ZERO_VEC]]) : !cir.vector<4 x !s32i>, !cir.vector<4 x !s32i>
+// CIR: %[[NE_B_ZERO:.*]] = cir.vec.cmp(ne, %[[TMP_B]], %[[ZERO_VEC]]) : !cir.vector<4 x !s32i>, !cir.vector<4 x !s32i>
+// CIR: %[[RESULT:.*]] = cir.binop(or, %[[NE_A_ZERO]], %[[NE_B_ZERO]]) : !cir.vector<4 x !s32i>
+// CIR: cir.store{{.*}} %[[RESULT]], %[[C_ADDR]] : !cir.vector<4 x !s32i>, !cir.ptr<!cir.vector<4 x !s32i>>
+
+// LLVM: %[[A_ADDR:.*]] = alloca <4 x i32>, i64 1, align 16
+// LLVM: %[[B_ADDR:.*]] = alloca <4 x i32>, i64 1, align 16
+// LLVM: %[[C_ADDR:.*]] = alloca <4 x i32>, i64 1, align 16
+// LLVM: %[[TMP_A:.*]] = load <4 x i32>, ptr %[[A_ADDR]], align 16
+// LLVM: %[[TMP_B:.*]] = load <4 x i32>, ptr %[[B_ADDR]], align 16
+// LLVM: %[[NE_A_ZERO:.*]] = icmp ne <4 x i32> %[[TMP_A]], zeroinitializer
+// LLVM: %[[NE_A_ZERO_SEXT:.*]] = sext <4 x i1> %[[NE_A_ZERO]] to <4 x i32>
+// LLVM: %[[NE_B_ZERO:.*]] = icmp ne <4 x i32> %[[TMP_B]], zeroinitializer
+// LLVM: %[[NE_B_ZERO_SEXT:.*]] = sext <4 x i1> %[[NE_B_ZERO]] to <4 x i32>
+// LLVM: %[[RESULT:.*]] = or <4 x i32> %[[NE_A_ZERO_SEXT]], %[[NE_B_ZERO_SEXT]]
+// LLVM: store <4 x i32> %[[RESULT]], ptr %[[C_ADDR]], align 16
+
+// OGCG: %[[A_ADDR:.*]] = alloca <4 x i32>, align 16
+// OGCG: %[[B_ADDR:.*]] = alloca <4 x i32>, align 16
+// OGCG: %[[C_ADDR:.*]] = alloca <4 x i32>, align 16
+// OGCG: %[[TMP_A:.*]] = load <4 x i32>, ptr %[[A_ADDR]], align 16
+// OGCG: %[[TMP_B:.*]] = load <4 x i32>, ptr %[[B_ADDR]], align 16
+// OGCG: %[[NE_A_ZERO:.*]] = icmp ne <4 x i32> %[[TMP_A]], zeroinitializer
+// OGCG: %[[NE_B_ZERO:.*]] = icmp ne <4 x i32> %[[TMP_B]], zeroinitializer
+// OGCG: %[[VEC_OR:.*]] = or <4 x i1> %[[NE_A_ZERO]], %[[NE_B_ZERO]]
+// OGCG: %[[RESULT:.*]] = sext <4 x i1> %[[VEC_OR]] to <4 x i32>
+// OGCG: store <4 x i32> %[[RESULT]], ptr %[[C_ADDR]], align 16
diff --git a/clang/test/CIR/CodeGen/vector.cpp b/clang/test/CIR/CodeGen/vector.cpp
index 18fa90bd2cb3f..72acd8b395623 100644
--- a/clang/test/CIR/CodeGen/vector.cpp
+++ b/clang/test/CIR/CodeGen/vector.cpp
@@ -1218,3 +1218,43 @@ void foo24() {
 
 // OGCG: %[[SIZE:.*]] = alloca i64, align 8
 // OGCG: store i64 4, ptr %[[SIZE]], align 8
+
+void foo25() {
+  vi4 a;
+  vi4 b;
+  vi4 c = a || b;
+}
+
+// CIR: %[[A_ADDR:.*]] = cir.alloca !cir.vector<4 x !s32i>, !cir.ptr<!cir.vector<4 x !s32i>>, ["a"]
+// CIR: %[[B_ADDR:.*]] = cir.alloca !cir.vector<4 x !s32i>, !cir.ptr<!cir.vector<4 x !s32i>>, ["b"]
+// CIR: %[[C_ADDR:.*]] = cir.alloca !cir.vector<4 x !s32i>, !cir.ptr<!cir.vector<4 x !s32i>>, ["c", init]
+// CIR: %[[ZERO_VEC:.*]] = cir.const #cir.const_vector<[#cir.int<0> : !s32i, #cir.int<0> : !s32i, #cir.int<0> : !s32i, #cir.int<0> : !s32i]> : !cir.vector<4 x !s32i>
+// CIR: %[[TMP_A:.*]] = cir.load{{.*}} %[[A_ADDR]] : !cir.ptr<!cir.vector<4 x !s32i>>, !cir.vector<4 x !s32i>
+// CIR: %[[TMP_B:.*]] = cir.load{{.*}} %[[B_ADDR]] : !cir.ptr<!cir.vector<4 x !s32i>>, !cir.vector<4 x !s32i>
+// CIR: %[[NE_A_ZERO:.*]] = cir.vec.cmp(ne, %[[TMP_A]], %[[ZERO_VEC]]) : !cir.vector<4 x !s32i>, !cir.vector<4 x !s32i>
+// CIR: %[[NE_B_ZERO:.*]] = cir.vec.cmp(ne, %[[TMP_B]], %[[ZERO_VEC]]) : !cir.vector<4 x !s32i>, !cir.vector<4 x !s32i>
+// CIR: %[[RESULT:.*]] = cir.binop(or, %[[NE_A_ZERO]], %[[NE_B_ZERO]]) : !cir.vector<4 x !s32i>
+// CIR: cir.store{{.*}} %[[RESULT]], %[[C_ADDR]] : !cir.vector<4 x !s32i>, !cir.ptr<!cir.vector<4 x !s32i>>
+
+// LLVM: %[[A_ADDR:.*]] = alloca <4 x i32>, i64 1, align 16
+// LLVM: %[[B_ADDR:.*]] = alloca <4 x i32>, i64 1, align 16
+// LLVM: %[[C_ADDR:.*]] = alloca <4 x i32>, i64 1, align 16
+// LLVM: %[[TMP_A:.*]] = load <4 x i32>, ptr %[[A_ADDR]], align 16
+// LLVM: %[[TMP_B:.*]] = load <4 x i32>, ptr %[[B_ADDR]], align 16
+// LLVM: %[[NE_A_ZERO:.*]] = icmp ne <4 x i32> %[[TMP_A]], zeroinitializer
+// LLVM: %[[NE_A_ZERO_SEXT:.*]] = sext <4 x i1> %[[NE_A_ZERO]] to <4 x i32>
+// LLVM: %[[NE_B_ZERO:.*]] = icmp ne <4 x i32> %[[TMP_B]], zeroinitializer
+// LLVM: %[[NE_B_ZERO_SEXT:.*]] = sext <4 x i1> %[[NE_B_ZERO]] to <4 x i32>
+// LLVM: %[[RESULT:.*]] = or <4 x i32> %[[NE_A_ZERO_SEXT]], %[[NE_B_ZERO_SEXT]]
+// LLVM: store <4 x i32> %[[RESULT]], ptr %[[C_ADDR]], align 16
+
+// OGCG: %[[A_ADDR:.*]] = alloca <4 x i32>, align 16
+// OGCG: %[[B_ADDR:.*]] = alloca <4 x i32>, align 16
+// OGCG: %[[C_ADDR:.*]] = alloca <4 x i32>, align 16
+// OGCG: %[[TMP_A:.*]] = load <4 x i32>, ptr %[[A_ADDR]], align 16
+// OGCG: %[[TMP_B:.*]] = load <4 x i32>, ptr %[[B_ADDR]], align 16
+// OGCG: %[[NE_A_ZERO:.*]] = icmp ne <4 x i32> %[[TMP_A]], zeroinitializer
+// OGCG: %[[NE_B_ZERO:.*]] = icmp ne <4 x i32> %[[TMP_B]], zeroinitializer
+// OGCG: %[[VEC_OR:.*]] = or <4 x i1> %[[NE_A_ZERO]], %[[NE_B_ZERO]]
+// OGCG: %[[RESULT:.*]] = sext <4 x i1> %[[VEC_OR]] to <4 x i32>
+// OGCG: store <4 x i32> %[[RESULT]], ptr %[[C_ADDR]], align 16

@llvmbot
Copy link
Member

llvmbot commented Sep 15, 2025

@llvm/pr-subscribers-clang

Author: Amr Hesham (AmrDeveloper)

Changes

This change adds support for local OR op for VectorType

Issue #136487

Full diff: https://github.com/llvm/llvm-project/pull/158668.diff

3 Files Affected:

  • (modified) clang/lib/CIR/CodeGen/CIRGenExprScalar.cpp (+15-3)
  • (modified) clang/test/CIR/CodeGen/vector-ext.cpp (+40)
  • (modified) clang/test/CIR/CodeGen/vector.cpp (+40)
diff --git a/clang/lib/CIR/CodeGen/CIRGenExprScalar.cpp b/clang/lib/CIR/CodeGen/CIRGenExprScalar.cpp
index 2261e24fe44c2..b48d559958dff 100644
--- a/clang/lib/CIR/CodeGen/CIRGenExprScalar.cpp
+++ b/clang/lib/CIR/CodeGen/CIRGenExprScalar.cpp
@@ -872,7 +872,7 @@ class ScalarExprEmitter : public StmtVisitor<ScalarExprEmitter, mlir::Value> {
     if (ty.UseExcessPrecision(cgf.getContext())) {
       if (ty->getAs<VectorType>()) {
         assert(!cir::MissingFeatures::vectorType());
-        cgf.cgm.errorNYI("promotion to vector type");
+        cgf.cgm.errorNYI("getPromotionType: promotion to vector type");
         return QualType();
       }
       return cgf.getContext().FloatTy;
@@ -1086,8 +1086,20 @@ class ScalarExprEmitter : public StmtVisitor<ScalarExprEmitter, mlir::Value> {
 
   mlir::Value VisitBinLOr(const clang::BinaryOperator *e) {
     if (e->getType()->isVectorType()) {
-      assert(!cir::MissingFeatures::vectorType());
-      return {};
+      mlir::Location loc = cgf.getLoc(e->getExprLoc());
+      auto vecTy = mlir::cast<cir::VectorType>(cgf.convertType(e->getType()));
+      mlir::Value zeroValue = builder.getNullValue(vecTy.getElementType(), loc);
+      SmallVector<mlir::Value, 16> elements(vecTy.getSize(), zeroValue);
+      auto zeroVec = cir::VecCreateOp::create(builder, loc, vecTy, elements);
+
+      mlir::Value lhs = Visit(e->getLHS());
+      mlir::Value rhs = Visit(e->getRHS());
+
+      auto cmpOpKind = cir::CmpOpKind::ne;
+      lhs = cir::VecCmpOp::create(builder, loc, vecTy, cmpOpKind, lhs, zeroVec);
+      rhs = cir::VecCmpOp::create(builder, loc, vecTy, cmpOpKind, rhs, zeroVec);
+      mlir::Value vecOr = builder.createOr(loc, lhs, rhs);
+      return builder.createIntCast(vecOr, vecTy);
     }
 
     assert(!cir::MissingFeatures::instrumentation());
diff --git a/clang/test/CIR/CodeGen/vector-ext.cpp b/clang/test/CIR/CodeGen/vector-ext.cpp
index 2ee42187a6e94..ad94e6737c615 100644
--- a/clang/test/CIR/CodeGen/vector-ext.cpp
+++ b/clang/test/CIR/CodeGen/vector-ext.cpp
@@ -1176,3 +1176,43 @@ void foo21() {
 
 // OGCG: %[[SIZE:.*]] = alloca i64, align 8
 // OGCG: store i64 4, ptr %[[SIZE]], align 8
+
+void foo22() {
+  vi4 a;
+  vi4 b;
+  vi4 c = a || b;
+}
+
+// CIR: %[[A_ADDR:.*]] = cir.alloca !cir.vector<4 x !s32i>, !cir.ptr<!cir.vector<4 x !s32i>>, ["a"]
+// CIR: %[[B_ADDR:.*]] = cir.alloca !cir.vector<4 x !s32i>, !cir.ptr<!cir.vector<4 x !s32i>>, ["b"]
+// CIR: %[[C_ADDR:.*]] = cir.alloca !cir.vector<4 x !s32i>, !cir.ptr<!cir.vector<4 x !s32i>>, ["c", init]
+// CIR: %[[ZERO_VEC:.*]] = cir.const #cir.const_vector<[#cir.int<0> : !s32i, #cir.int<0> : !s32i, #cir.int<0> : !s32i, #cir.int<0> : !s32i]> : !cir.vector<4 x !s32i>
+// CIR: %[[TMP_A:.*]] = cir.load{{.*}} %[[A_ADDR]] : !cir.ptr<!cir.vector<4 x !s32i>>, !cir.vector<4 x !s32i>
+// CIR: %[[TMP_B:.*]] = cir.load{{.*}} %[[B_ADDR]] : !cir.ptr<!cir.vector<4 x !s32i>>, !cir.vector<4 x !s32i>
+// CIR: %[[NE_A_ZERO:.*]] = cir.vec.cmp(ne, %[[TMP_A]], %[[ZERO_VEC]]) : !cir.vector<4 x !s32i>, !cir.vector<4 x !s32i>
+// CIR: %[[NE_B_ZERO:.*]] = cir.vec.cmp(ne, %[[TMP_B]], %[[ZERO_VEC]]) : !cir.vector<4 x !s32i>, !cir.vector<4 x !s32i>
+// CIR: %[[RESULT:.*]] = cir.binop(or, %[[NE_A_ZERO]], %[[NE_B_ZERO]]) : !cir.vector<4 x !s32i>
+// CIR: cir.store{{.*}} %[[RESULT]], %[[C_ADDR]] : !cir.vector<4 x !s32i>, !cir.ptr<!cir.vector<4 x !s32i>>
+
+// LLVM: %[[A_ADDR:.*]] = alloca <4 x i32>, i64 1, align 16
+// LLVM: %[[B_ADDR:.*]] = alloca <4 x i32>, i64 1, align 16
+// LLVM: %[[C_ADDR:.*]] = alloca <4 x i32>, i64 1, align 16
+// LLVM: %[[TMP_A:.*]] = load <4 x i32>, ptr %[[A_ADDR]], align 16
+// LLVM: %[[TMP_B:.*]] = load <4 x i32>, ptr %[[B_ADDR]], align 16
+// LLVM: %[[NE_A_ZERO:.*]] = icmp ne <4 x i32> %[[TMP_A]], zeroinitializer
+// LLVM: %[[NE_A_ZERO_SEXT:.*]] = sext <4 x i1> %[[NE_A_ZERO]] to <4 x i32>
+// LLVM: %[[NE_B_ZERO:.*]] = icmp ne <4 x i32> %[[TMP_B]], zeroinitializer
+// LLVM: %[[NE_B_ZERO_SEXT:.*]] = sext <4 x i1> %[[NE_B_ZERO]] to <4 x i32>
+// LLVM: %[[RESULT:.*]] = or <4 x i32> %[[NE_A_ZERO_SEXT]], %[[NE_B_ZERO_SEXT]]
+// LLVM: store <4 x i32> %[[RESULT]], ptr %[[C_ADDR]], align 16
+
+// OGCG: %[[A_ADDR:.*]] = alloca <4 x i32>, align 16
+// OGCG: %[[B_ADDR:.*]] = alloca <4 x i32>, align 16
+// OGCG: %[[C_ADDR:.*]] = alloca <4 x i32>, align 16
+// OGCG: %[[TMP_A:.*]] = load <4 x i32>, ptr %[[A_ADDR]], align 16
+// OGCG: %[[TMP_B:.*]] = load <4 x i32>, ptr %[[B_ADDR]], align 16
+// OGCG: %[[NE_A_ZERO:.*]] = icmp ne <4 x i32> %[[TMP_A]], zeroinitializer
+// OGCG: %[[NE_B_ZERO:.*]] = icmp ne <4 x i32> %[[TMP_B]], zeroinitializer
+// OGCG: %[[VEC_OR:.*]] = or <4 x i1> %[[NE_A_ZERO]], %[[NE_B_ZERO]]
+// OGCG: %[[RESULT:.*]] = sext <4 x i1> %[[VEC_OR]] to <4 x i32>
+// OGCG: store <4 x i32> %[[RESULT]], ptr %[[C_ADDR]], align 16
diff --git a/clang/test/CIR/CodeGen/vector.cpp b/clang/test/CIR/CodeGen/vector.cpp
index 18fa90bd2cb3f..72acd8b395623 100644
--- a/clang/test/CIR/CodeGen/vector.cpp
+++ b/clang/test/CIR/CodeGen/vector.cpp
@@ -1218,3 +1218,43 @@ void foo24() {
 
 // OGCG: %[[SIZE:.*]] = alloca i64, align 8
 // OGCG: store i64 4, ptr %[[SIZE]], align 8
+
+void foo25() {
+  vi4 a;
+  vi4 b;
+  vi4 c = a || b;
+}
+
+// CIR: %[[A_ADDR:.*]] = cir.alloca !cir.vector<4 x !s32i>, !cir.ptr<!cir.vector<4 x !s32i>>, ["a"]
+// CIR: %[[B_ADDR:.*]] = cir.alloca !cir.vector<4 x !s32i>, !cir.ptr<!cir.vector<4 x !s32i>>, ["b"]
+// CIR: %[[C_ADDR:.*]] = cir.alloca !cir.vector<4 x !s32i>, !cir.ptr<!cir.vector<4 x !s32i>>, ["c", init]
+// CIR: %[[ZERO_VEC:.*]] = cir.const #cir.const_vector<[#cir.int<0> : !s32i, #cir.int<0> : !s32i, #cir.int<0> : !s32i, #cir.int<0> : !s32i]> : !cir.vector<4 x !s32i>
+// CIR: %[[TMP_A:.*]] = cir.load{{.*}} %[[A_ADDR]] : !cir.ptr<!cir.vector<4 x !s32i>>, !cir.vector<4 x !s32i>
+// CIR: %[[TMP_B:.*]] = cir.load{{.*}} %[[B_ADDR]] : !cir.ptr<!cir.vector<4 x !s32i>>, !cir.vector<4 x !s32i>
+// CIR: %[[NE_A_ZERO:.*]] = cir.vec.cmp(ne, %[[TMP_A]], %[[ZERO_VEC]]) : !cir.vector<4 x !s32i>, !cir.vector<4 x !s32i>
+// CIR: %[[NE_B_ZERO:.*]] = cir.vec.cmp(ne, %[[TMP_B]], %[[ZERO_VEC]]) : !cir.vector<4 x !s32i>, !cir.vector<4 x !s32i>
+// CIR: %[[RESULT:.*]] = cir.binop(or, %[[NE_A_ZERO]], %[[NE_B_ZERO]]) : !cir.vector<4 x !s32i>
+// CIR: cir.store{{.*}} %[[RESULT]], %[[C_ADDR]] : !cir.vector<4 x !s32i>, !cir.ptr<!cir.vector<4 x !s32i>>
+
+// LLVM: %[[A_ADDR:.*]] = alloca <4 x i32>, i64 1, align 16
+// LLVM: %[[B_ADDR:.*]] = alloca <4 x i32>, i64 1, align 16
+// LLVM: %[[C_ADDR:.*]] = alloca <4 x i32>, i64 1, align 16
+// LLVM: %[[TMP_A:.*]] = load <4 x i32>, ptr %[[A_ADDR]], align 16
+// LLVM: %[[TMP_B:.*]] = load <4 x i32>, ptr %[[B_ADDR]], align 16
+// LLVM: %[[NE_A_ZERO:.*]] = icmp ne <4 x i32> %[[TMP_A]], zeroinitializer
+// LLVM: %[[NE_A_ZERO_SEXT:.*]] = sext <4 x i1> %[[NE_A_ZERO]] to <4 x i32>
+// LLVM: %[[NE_B_ZERO:.*]] = icmp ne <4 x i32> %[[TMP_B]], zeroinitializer
+// LLVM: %[[NE_B_ZERO_SEXT:.*]] = sext <4 x i1> %[[NE_B_ZERO]] to <4 x i32>
+// LLVM: %[[RESULT:.*]] = or <4 x i32> %[[NE_A_ZERO_SEXT]], %[[NE_B_ZERO_SEXT]]
+// LLVM: store <4 x i32> %[[RESULT]], ptr %[[C_ADDR]], align 16
+
+// OGCG: %[[A_ADDR:.*]] = alloca <4 x i32>, align 16
+// OGCG: %[[B_ADDR:.*]] = alloca <4 x i32>, align 16
+// OGCG: %[[C_ADDR:.*]] = alloca <4 x i32>, align 16
+// OGCG: %[[TMP_A:.*]] = load <4 x i32>, ptr %[[A_ADDR]], align 16
+// OGCG: %[[TMP_B:.*]] = load <4 x i32>, ptr %[[B_ADDR]], align 16
+// OGCG: %[[NE_A_ZERO:.*]] = icmp ne <4 x i32> %[[TMP_A]], zeroinitializer
+// OGCG: %[[NE_B_ZERO:.*]] = icmp ne <4 x i32> %[[TMP_B]], zeroinitializer
+// OGCG: %[[VEC_OR:.*]] = or <4 x i1> %[[NE_A_ZERO]], %[[NE_B_ZERO]]
+// OGCG: %[[RESULT:.*]] = sext <4 x i1> %[[VEC_OR]] to <4 x i32>
+// OGCG: store <4 x i32> %[[RESULT]], ptr %[[C_ADDR]], align 16

@AmrDeveloper AmrDeveloper merged commit 36692aa into llvm:main Sep 18, 2025
12 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@bcardosolopes bcardosolopes bcardosolopes approved these changes

@lanza lanza Awaiting requested review from lanza lanza is a code owner

@xlauko xlauko Awaiting requested review from xlauko xlauko is a code owner

@andykaylor andykaylor Awaiting requested review from andykaylor andykaylor is a code owner

Assignees

No one assigned

Labels

clang Clang issues not falling into any other category ClangIR Anything related to the ClangIR project

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@AmrDeveloper @llvmbot @bcardosolopes