AMDGPU: Add Clang builtin intrinsics for ds_swizzle

[cfang]

Summary

declare i32 @llvm.amdgcn.ds.swizzle(i32, i32) // The second argument is an immediate of i32.

[arsenm]

include/clang/Basic/BuiltinsAMDGPU.def

79 ↗

(On Diff #68574)

The constant operand should marked with I (and there should be a test that it errors with a non-constant)

[cfang]

Update based on Matt's comments:

1. Mark constant integer argument type as "Ii"
2. add error test when argument is not constant integer.

[arsenm]

LGTM

cfe/trunk/include/clang/Basic/BuiltinsAMDGPU.def

 BUILTIN(__builtin_amdgcn_s_memtime, "LUi", "n")
 BUILTIN(__builtin_amdgcn_s_sleep, "vIi", "n")
 BUILTIN(__builtin_amdgcn_uicmp, "LUiUiUiIi", "nc")
 BUILTIN(__builtin_amdgcn_uicmpl, "LUiLUiLUiIi", "nc")
 BUILTIN(__builtin_amdgcn_sicmp, "LUiiiIi", "nc")
 BUILTIN(__builtin_amdgcn_sicmpl, "LUiLiLiIi", "nc")
 BUILTIN(__builtin_amdgcn_fcmp, "LUiddIi", "nc")
 BUILTIN(__builtin_amdgcn_fcmpf, "LUiffIi", "nc")
+BUILTIN(__builtin_amdgcn_ds_swizzle, "iiIi", "nc")
 
 //===----------------------------------------------------------------------===//
 // VI+ only builtins.
 //===----------------------------------------------------------------------===//
 
 TARGET_BUILTIN(__builtin_amdgcn_s_memrealtime, "LUi", "n", "s-memrealtime")
 
 //===----------------------------------------------------------------------===//

cfe/trunk/lib/CodeGen/CGBuiltin.cpp

case AMDGPU::BI__builtin_amdgcn_div_fmasf: {
     llvm::Value *Src2 = EmitScalarExpr(E->getArg(2));
     llvm::Value *Src3 = EmitScalarExpr(E->getArg(3));
 
     llvm::Value *F = CGM.getIntrinsic(Intrinsic::amdgcn_div_fmas,
                                       Src0->getType());
     llvm::Value *Src3ToBool = Builder.CreateIsNotNull(Src3);
     return Builder.CreateCall(F, {Src0, Src1, Src2, Src3ToBool});
   }
+
+  case AMDGPU::BI__builtin_amdgcn_ds_swizzle:
+    return emitBinaryBuiltin(*this, E, Intrinsic::amdgcn_ds_swizzle);
   case AMDGPU::BI__builtin_amdgcn_div_fixup:
   case AMDGPU::BI__builtin_amdgcn_div_fixupf:
     return emitTernaryBuiltin(*this, E, Intrinsic::amdgcn_div_fixup);
   case AMDGPU::BI__builtin_amdgcn_trig_preop:
   case AMDGPU::BI__builtin_amdgcn_trig_preopf:
     return emitFPIntBuiltin(*this, E, Intrinsic::amdgcn_trig_preop);
   case AMDGPU::BI__builtin_amdgcn_rcp:
   case AMDGPU::BI__builtin_amdgcn_rcpf:

cfe/trunk/test/CodeGenOpenCL/builtins-amdgcn-error.cl

void test_fcmp_f32(global ulong* out, float a, float b, uint c)
   *out = __builtin_amdgcn_fcmpf(a, b, c); // expected-error {{argument to '__builtin_amdgcn_fcmpf' must be a constant integer}}
 }
 
 void test_fcmp_f64(global ulong* out, double a, double b, uint c)
 {
   *out = __builtin_amdgcn_fcmp(a, b, c); // expected-error {{argument to '__builtin_amdgcn_fcmp' must be a constant integer}}
 }
 
+void test_ds_swizzle(global int* out, int a, int b)
+{
+  *out = __builtin_amdgcn_ds_swizzle(a, b); // expected-error {{argument to '__builtin_amdgcn_ds_swizzle' must be a constant integer}}
+}

cfe/trunk/test/CodeGenOpenCL/builtins-amdgcn.cl

 
 // CHECK-LABEL: @test_uicmp_i64
 // CHECK: call i64 @llvm.amdgcn.icmp.i64(i64 %a, i64 %b, i32 35)
 void test_uicmp_i64(global ulong* out, ulong a, ulong b)
 {
   *out = __builtin_amdgcn_uicmpl(a, b, 30+5);
 }
 
+// CHECK-LABEL: @test_ds_swizzle
+// CHECK: call i32 @llvm.amdgcn.ds.swizzle(i32 %a, i32 32)
+void test_ds_swizzle(global int* out, int a)
+{
+  *out = __builtin_amdgcn_ds_swizzle(a, 32);
+}
+
 // CHECK-LABEL: @test_fcmp_f32
 // CHECK: call i64 @llvm.amdgcn.fcmp.f32(float %a, float %b, i32 5)
 void test_fcmp_f32(global ulong* out, float a, float b)
 {
   *out = __builtin_amdgcn_fcmpf(a, b, 5);
 }
 
 // CHECK-LABEL: @test_fcmp_f64