add cir tests, cast signed amts to unsigned

Author: moar55

clang/lib/CIR/CodeGen/CIRGenBuiltinX86.cpp

@@ -16,6 +16,7 @@
 #include "mlir/IR/ValueRange.h"
 #include "clang/Basic/Builtins.h"
 #include "clang/Basic/TargetBuiltins.h"
+#include "clang/CIR/Dialect/IR/CIRTypes.h"
 #include "clang/CIR/MissingFeatures.h"
 
 using namespace clang;
@@ -100,10 +101,17 @@ static mlir::Value emitX86FunnelShift(CIRGenFunction &cgf, const CallExpr *e,
   // Funnel shifts amounts are treated as modulo and types are all power-of-2
   // so we only care about the lowest log2 bits anyway.
   if (amt.getType() != ty) {
-    amt = cgf.getBuilder().createIntCast(
-        amt, mlir::cast<cir::VectorType>(ty).getElementType());
+    auto vecTy = mlir::cast<cir::VectorType>(ty);
+
+    auto numElems = vecTy.getSize();
+    cir::IntType vecElemType = mlir::cast<cir::IntType>(vecTy.getElementType());
+    auto signlessType =
+        cir::IntType::get(&cgf.getMLIRContext(), vecElemType.getWidth(), false);
+    amt = cgf.getBuilder().createIntCast(amt, signlessType);
+
     amt = cir::VecSplatOp::create(cgf.getBuilder(), cgf.getLoc(e->getExprLoc()),
-                                  ty, amt);
+                                  cir::VectorType::get(signlessType, numElems),
+                                  amt);
   }
 
   const std::string intrinsicName = isRight ? "fshr" : "fshl";

clang/test/CIR/CodeGen/X86/xop-builtin.c renamed to clang/test/CIR/CodeGen/X86/xop-builtins.c

@@ -39,4 +39,41 @@ __m128i test_mm_roti_epi8(__m128i a) {
   // OGCG: %[[CASTED_VAR:.*]] = bitcast <2 x i64> {{%.*}} to <16 x i8>
   // OGCG: {{%.*}} = call <16 x i8> @llvm.fshl.v16i8(<16 x i8> %[[CASTED_VAR]], <16 x i8> %[[CASTED_VAR]], <16 x i8> splat (i8 1))
   return _mm_roti_epi8(a, 1);
+}
+
+__m128i test_mm_roti_epi16(__m128i a) {
+  // CIR-LABEL: test_mm_roti_epi16
+  // CIR: {{%.*}} = cir.cast integral {{%.*}} : !{{[us]}}8i -> !u16i
+  // CIR: {{%.*}} = cir.vec.splat {{%.*}} : !{{[us]}}16i, !cir.vector<8 x !{{[us]}}16i> 
+  // CIR: {{%.*}} = cir.call_llvm_intrinsic "fshl" {{.*}} : (!cir.vector<8 x !{{[su]}}16i>, !cir.vector<8 x !{{[su]}}16i>, !cir.vector<8 x !{{[su]}}16i>) -> !cir.vector<8 x !{{[su]}}16i> 
+  // LLVM-LABEL: test_mm_roti_epi16
+  // LLVM: %[[CASTED_VAR:.*]] = bitcast <2 x i64> {{%.*}} to <8 x i16>
+  // LLVM: {{%.*}} = call <8 x i16> @llvm.fshl.v8i16(<8 x i16> %[[CASTED_VAR]], <8 x i16> %[[CASTED_VAR]], <8 x i16> splat (i16 50))
+  // OGCG-LABEL: test_mm_roti_epi16
+  // OGCG: %[[CASTED_VAR:.*]] = bitcast <2 x i64> {{%.*}} to <8 x i16>
+  // OGCG: {{%.*}} = call <8 x i16> @llvm.fshl.v8i16(<8 x i16> %[[CASTED_VAR]], <8 x i16> %[[CASTED_VAR]], <8 x i16> splat (i16 50))
+  return _mm_roti_epi16(a, 50);
+ }
+
+//NOTE: This only works as I expect for CIR but not for LLVMIR
+__m128i test_mm_roti_epi32(__m128i a) {
+  // CIR-LABEL: test_mm_roti_epi32
+  // CIR: {{%.*}} = cir.cast integral {{%.*}} : !{{[us]}}8i -> !u32i
+  // CIR: {{%.*}} = cir.vec.splat {{%.*}} : !{{[us]}}32i, !cir.vector<4 x !{{[us]}}32i> 
+  // CIR: {{%.*}} = cir.call_llvm_intrinsic "fshl" {{.*}} : (!cir.vector<4 x !{{[su]}}32i>, !cir.vector<4 x !{{[su]}}32i>, !cir.vector<4 x !{{[su]}}32i>) -> !cir.vector<4 x !{{[su]}}32i> 
+  return _mm_roti_epi32(a, -30);
+ }
+
+__m128i test_mm_roti_epi64(__m128i a) {
+  // CIR-LABEL: test_mm_roti_epi64
+  // CIR: {{%.*}} = cir.cast integral {{%.*}} : !{{[us]}}8i -> !u64i
+  // CIR: {{%.*}} = cir.vec.splat {{%.*}} : !{{.}}64i, !cir.vector<2 x !{{[us]}}64i> 
+  // CIR: {{%.*}} = cir.call_llvm_intrinsic "fshl" {{.*}} : (!cir.vector<2 x !{{[su]}}64i>, !cir.vector<2 x !{{[su]}}64i>, !cir.vector<2 x !u64i>) -> !cir.vector<2 x !{{[su]}}64i> 
+  // LLVM-LABEL: test_mm_roti_epi64
+  // LLVM: %[[VAR:.*]] = load <2 x i64>, ptr {{%.*}}, align 16
+  // LLVM: {{%.*}} = call <2 x i64> @llvm.fshl.v2i64(<2 x i64> %[[VAR]], <2 x i64> %[[VAR]], <2 x i64> splat (i64 100))
+  // OGCG-LABEL: test_mm_roti_epi64
+  // OGCG: %[[VAR:.*]] = load <2 x i64>, ptr {{%.*}}, align 16
+  // OGCG: {{%.*}} = call <2 x i64> @llvm.fshl.v2i64(<2 x i64> %[[VAR]], <2 x i64> %[[VAR]], <2 x i64> splat (i64 100))
+  return _mm_roti_epi64(a, 100);
  }