[CIR] Implement logical not for VectorType

[AmrDeveloper]

This change implements logical not for VectorType

[llvmbot]

@llvm/pr-subscribers-clangir

@llvm/pr-subscribers-clang

Author: Amr Hesham (AmrDeveloper)

Changes

This change implements logical not for VectorType

---

Full diff: https://github.com/llvm/llvm-project/pull/160762.diff

3 Files Affected:

• (modified) clang/lib/CIR/CodeGen/CIRGenExprScalar.cpp (+5-3)
• (modified) clang/test/CIR/CodeGen/vector-ext.cpp (+27-1)
• (modified) clang/test/CIR/CodeGen/vector.cpp (+27-1)

diff --git a/clang/lib/CIR/CodeGen/CIRGenExprScalar.cpp b/clang/lib/CIR/CodeGen/CIRGenExprScalar.cpp
index 3b22c689ecd9f..f6ee1a0f2dafa 100644
--- a/clang/lib/CIR/CodeGen/CIRGenExprScalar.cpp
+++ b/clang/lib/CIR/CodeGen/CIRGenExprScalar.cpp
@@ -2087,9 +2087,11 @@ mlir::Value ScalarExprEmitter::VisitUnaryLNot(const UnaryOperator *e) {
   if (e->getType()->isVectorType() &&
       e->getType()->castAs<VectorType>()->getVectorKind() ==
           VectorKind::Generic) {
-    assert(!cir::MissingFeatures::vectorType());
-    cgf.cgm.errorNYI(e->getSourceRange(), "vector logical not");
-    return {};
+    mlir::Value oper = Visit(e->getSubExpr());
+    mlir::Location loc = cgf.getLoc(e->getExprLoc());
+    mlir::Value zero = builder.getNullValue(oper.getType(), loc);
+    return cir::VecCmpOp::create(builder, loc, oper.getType(),
+                                 cir::CmpOpKind::eq, oper, zero);
   }
 
   // Compare operand to zero.
diff --git a/clang/test/CIR/CodeGen/vector-ext.cpp b/clang/test/CIR/CodeGen/vector-ext.cpp
index 287d016ff6d1e..8b5379a2b1a88 100644
--- a/clang/test/CIR/CodeGen/vector-ext.cpp
+++ b/clang/test/CIR/CodeGen/vector-ext.cpp
@@ -1295,4 +1295,30 @@ void foo23() {
 // OGCG: %[[NE_B_ZERO:.*]] = icmp ne <4 x i32> %[[TMP_B]], zeroinitializer
 // OGCG: %[[VEC_OR:.*]] = and <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
\ No newline at end of file
+// OGCG: store <4 x i32> %[[RESULT]], ptr %[[C_ADDR]], align 16
+
+void logical_not() {
+   vi4 a;
+   vi4 b = !a;
+}
+
+// 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", init]
+// CIR: %[[TMP_A:.*]] = cir.load{{.*}}) %[[A_ADDR]] : !cir.ptr<!cir.vector<4 x !s32i>>, !cir.vector<4 x !s32i>
+// CIR: %[[CONST_V0:.*]] = cir.const #cir.zero : !cir.vector<4 x !s32i>
+// CIR: %[[RESULT:.*]] = cir.vec.cmp(eq, %[[TMP_A]], %[[CONST_V0]]) : !cir.vector<4 x !s32i>, !cir.vector<4 x !s32i>
+// CIR: cir.store{{.*}} %[[RESULT]], %[[B_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: %[[TMP_A:.*]] = load <4 x i32>, ptr %[[A_ADDR]], align 16
+// LLVM: %[[RESULT:.*]] = icmp eq <4 x i32> %[[TMP_A]], zeroinitializer
+// LLVM: %[[RESULT_VI4:.*]] = sext <4 x i1> %[[RESULT]] to <4 x i32>
+// LLVM: store <4 x i32> %[[RESULT_VI4]], ptr %[[B_ADDR]], align 16
+
+// OGCG: %[[A_ADDR:.*]] = alloca <4 x i32>, align 16
+// OGCG: %[[B_ADDR:.*]] = alloca <4 x i32>, align 16
+// OGCG: %[[TMP_A:.*]] = load <4 x i32>, ptr %[[A_ADDR]], align 16
+// OGCG: %[[RESULT:.*]] = icmp eq <4 x i32> %[[TMP_A]], zeroinitializer
+// OGCG: %[[RESULT_VI4:.*]] = sext <4 x i1> %[[RESULT]] to <4 x i32>
+// OGCG: store <4 x i32> %[[RESULT_VI4]], ptr %[[B_ADDR]], align 16
diff --git a/clang/test/CIR/CodeGen/vector.cpp b/clang/test/CIR/CodeGen/vector.cpp
index d66c7a3d2aba6..24f8ed08dd169 100644
--- a/clang/test/CIR/CodeGen/vector.cpp
+++ b/clang/test/CIR/CodeGen/vector.cpp
@@ -1337,4 +1337,30 @@ void foo26() {
 // OGCG: %[[NE_B_ZERO:.*]] = icmp ne <4 x i32> %[[TMP_B]], zeroinitializer
 // OGCG: %[[VEC_OR:.*]] = and <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
\ No newline at end of file
+// OGCG: store <4 x i32> %[[RESULT]], ptr %[[C_ADDR]], align 16
+
+void logical_not() {
+   vi4 a;
+   vi4 b = !a;
+}
+
+// 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", init]
+// CIR: %[[TMP_A:.*]] = cir.load{{.*}}) %[[A_ADDR]] : !cir.ptr<!cir.vector<4 x !s32i>>, !cir.vector<4 x !s32i>
+// CIR: %[[CONST_V0:.*]] = cir.const #cir.zero : !cir.vector<4 x !s32i>
+// CIR: %[[RESULT:.*]] = cir.vec.cmp(eq, %[[TMP_A]], %[[CONST_V0]]) : !cir.vector<4 x !s32i>, !cir.vector<4 x !s32i>
+// CIR: cir.store{{.*}} %[[RESULT]], %[[B_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: %[[TMP_A:.*]] = load <4 x i32>, ptr %[[A_ADDR]], align 16
+// LLVM: %[[RESULT:.*]] = icmp eq <4 x i32> %[[TMP_A]], zeroinitializer
+// LLVM: %[[RESULT_VI4:.*]] = sext <4 x i1> %[[RESULT]] to <4 x i32>
+// LLVM: store <4 x i32> %[[RESULT_VI4]], ptr %[[B_ADDR]], align 16
+
+// OGCG: %[[A_ADDR:.*]] = alloca <4 x i32>, align 16
+// OGCG: %[[B_ADDR:.*]] = alloca <4 x i32>, align 16
+// OGCG: %[[TMP_A:.*]] = load <4 x i32>, ptr %[[A_ADDR]], align 16
+// OGCG: %[[RESULT:.*]] = icmp eq <4 x i32> %[[TMP_A]], zeroinitializer
+// OGCG: %[[RESULT_VI4:.*]] = sext <4 x i1> %[[RESULT]] to <4 x i32>
+// OGCG: store <4 x i32> %[[RESULT_VI4]], ptr %[[B_ADDR]], align 16

[andykaylor]

Can you also add a test for a floating-point type?

[andykaylor]

Actually, it looks like clang won't let you do this with floats and ext vector types, but with the GNU-style vector attribute, you get an interesting result:

https://godbolt.org/z/njdWcWEWM

[AmrDeveloper]

First time to know that float f = 0.0f/0.0f; results in -nan in GCC and nan in clang :D

https://godbolt.org/z/1qv3aMvP8

[andykaylor]

First time to know that float f = 0.0f/0.0f; results in -nan in GCC and nan in clang :D

Clang is constant folding the operation. The sign you get depends on the hardware.

https://godbolt.org/z/snWd9rdMb

[AmrDeveloper]

Wow, thanks for the information

[andykaylor]

lgtm