[PowerPC][Power10] Implement Test LSB by Byte Builtins in LLVM/Clang

[amyk]

Summary

This patch implements builtins for the following prototypes:

int vec_test_lsbb_all_ones (vector unsigned char a);  
int vec_test_lsbb_all_zeros (vector unsigned char a);

[amyk]

Updated to the correct indentation for the functions in altivec.h.

[lei]

LGTM

[amyk]

Updated revision to:

• add the MC test cases into vsx.s and vsx.txt.
• create a test file called builtins-ppc-p10vsx.ll to place all Power10 VSX builtins tests.

[amyk]

@lei Could you please take another look at this to see if this change is OK?

[steven.zhang]

llvm/test/MC/Disassembler/PowerPC/vsx.txt

2 ↗

(On Diff #274239)

So, this is for bigendian, where is the little endian disassemble tests ...

[lei]

encoding tests need to be placed in corresponding ppc64-encoding-ISA31* files

[amyk]

Update patch to:

• place MC tests in correct files

[lei]

LGTM thx!

clang/include/clang/Basic/BuiltinsPPC.def

 BUILTIN(__builtin_vsx_xvtstdcsp, "V4UiV4fIi", "")
 
 BUILTIN(__builtin_vsx_insertword, "V16UcV4UiV16UcIi", "")
 BUILTIN(__builtin_vsx_extractuword, "V2ULLiV16UcIi", "")
 
 BUILTIN(__builtin_vsx_xxpermdi, "v.", "t")
 BUILTIN(__builtin_vsx_xxsldwi, "v.", "t")
 
+BUILTIN(__builtin_vsx_xvtlsbb, "iV16Ucb", "")
+
 // Float 128 built-ins
 BUILTIN(__builtin_sqrtf128_round_to_odd, "LLdLLd", "")
 BUILTIN(__builtin_addf128_round_to_odd, "LLdLLdLLd", "")
 BUILTIN(__builtin_subf128_round_to_odd, "LLdLLdLLd", "")
 BUILTIN(__builtin_mulf128_round_to_odd, "LLdLLdLLd", "")
 BUILTIN(__builtin_divf128_round_to_odd, "LLdLLdLLd", "")
 BUILTIN(__builtin_fmaf128_round_to_odd, "LLdLLdLLdLLd", "")
 BUILTIN(__builtin_truncf128_round_to_odd, "dLLd", "")

clang/lib/Headers/altivec.h

 /*===---- altivec.h - Standard header for type generic math ---------------===*\
  *
  * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
  * See https://llvm.org/LICENSE.txt for license information.
  * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
  *
 \*===----------------------------------------------------------------------===*/
 
 #ifndef __ALTIVEC_H
 #define __ALTIVEC_H
 
 #ifndef __ALTIVEC__
 #error "AltiVec support not enabled"
 #endif
 
 /* Constants for mapping CR6 bits to predicate result. */
 
 #define __CR6_EQ 0
 #define __CR6_EQ_REV 1
 #define __CR6_LT 2
 #define __CR6_LT_REV 3
#define __VEC_CLASS_FP_NOT_NORMAL (__VEC_CLASS_FP_NAN        | \
                                    __VEC_CLASS_FP_INFINITY)
 
 #define __ATTRS_o_ai __attribute__((__overloadable__, __always_inline__))
 
 #ifdef __POWER9_VECTOR__
 #include <stddef.h>
 #endif
 
 static __inline__ vector signed char __ATTRS_o_ai vec_perm(
     vector signed char __a, vector signed char __b, vector unsigned char __c);
 
 static __inline__ vector unsigned char __ATTRS_o_ai
 vec_perm(vector unsigned char __a, vector unsigned char __b,
          vector unsigned char __c);
 
 static __inline__ vector bool char __ATTRS_o_ai
 vec_perm(vector bool char __a, vector bool char __b, vector unsigned char __c);
 
 static __inline__ vector short __ATTRS_o_ai vec_perm(vector signed short __a,
                                                      vector signed short __b,
                                                      vector unsigned char __c);
 
 static __inline__ vector unsigned short __ATTRS_o_ai
 vec_perm(vector unsigned short __a, vector unsigned short __b,
          vector unsigned char __c);
 
 static __inline__ vector bool short __ATTRS_o_ai vec_perm(
     vector bool short __a, vector bool short __b, vector unsigned char __c);
 
 static __inline__ vector pixel __ATTRS_o_ai vec_perm(vector pixel __a,
                                                      vector pixel __b,
                                                      vector unsigned char __c);

 static __inline__ vector unsigned char __ATTRS_o_ai
 vec_clrr(vector unsigned char __a, unsigned int __n) {
 #ifdef __LITTLE_ENDIAN__
   return __builtin_altivec_vclrlb((vector signed char)__a, __n);
 #else
   return __builtin_altivec_vclrrb((vector signed char)__a, __n);
 #endif
 }
+
+#ifdef __VSX__
+/* vec_test_lsbb_all_ones */
+
+static __inline__ int __ATTRS_o_ai
+vec_test_lsbb_all_ones(vector unsigned char __a) {
+    return __builtin_vsx_xvtlsbb(__a, 1);
+}
+
+/* vec_test_lsbb_all_zeros */
+
+static __inline__ int __ATTRS_o_ai
+vec_test_lsbb_all_zeros(vector unsigned char __a) {
+    return __builtin_vsx_xvtlsbb(__a, 0);
+}
+#endif /* __VSX__ */
 #endif /* __POWER10_VECTOR__ */
 
 #undef __ATTRS_o_ai
 
 #endif /* __ALTIVEC_H */

clang/test/CodeGen/builtins-ppc-p10vector.c

 
 vector unsigned char test_vec_clrr_uc(void) {
   // CHECK-BE: @llvm.ppc.altivec.vclrrb(<16 x i8>
   // CHECK-BE-NEXT: ret <16 x i8>
   // CHECK-LE: @llvm.ppc.altivec.vclrlb(<16 x i8>
   // CHECK-LE-NEXT: ret <16 x i8>
   return vec_clrr(vuca, uia);
 }
+
+int test_vec_test_lsbb_all_ones(void) {
+  // CHECK: @llvm.ppc.vsx.xvtlsbb(<16 x i8> %{{.+}}, i1 true
+  // CHECK-NEXT: ret i32
+  return vec_test_lsbb_all_ones(vuca);
+}
+
+int test_vec_test_lsbb_all_zeros(void) {
+  // CHECK: @llvm.ppc.vsx.xvtlsbb(<16 x i8> %{{.+}}, i1 false
+  // CHECK-NEXT: ret i32
+  return vec_test_lsbb_all_zeros(vuca);
+}

llvm/include/llvm/IR/IntrinsicsPowerPC.td

def int_ppc_vsx_xvcvhpsp :
                             [llvm_v8i16_ty],[IntrNoMem]>;
 def int_ppc_vsx_xxextractuw :
       PowerPC_VSX_Intrinsic<"xxextractuw",[llvm_v2i64_ty],
                             [llvm_v2i64_ty,llvm_i32_ty], [IntrNoMem]>;
 def int_ppc_vsx_xxinsertw :
       PowerPC_VSX_Intrinsic<"xxinsertw",[llvm_v4i32_ty],
                             [llvm_v4i32_ty,llvm_v2i64_ty,llvm_i32_ty],
                             [IntrNoMem]>;
+def int_ppc_vsx_xvtlsbb :
+      PowerPC_VSX_Intrinsic<"xvtlsbb", [llvm_i32_ty],
+                            [llvm_v16i8_ty, llvm_i1_ty], [IntrNoMem]>;
 def int_ppc_vsx_xxgenpcvbm :
       PowerPC_VSX_Intrinsic<"xxgenpcvbm", [llvm_v16i8_ty],
                             [llvm_v16i8_ty, llvm_i32_ty], [IntrNoMem]>;
 def int_ppc_vsx_xxgenpcvhm :
       PowerPC_VSX_Intrinsic<"xxgenpcvhm", [llvm_v8i16_ty],
                             [llvm_v8i16_ty, llvm_i32_ty], [IntrNoMem]>;
 def int_ppc_vsx_xxgenpcvwm :
       PowerPC_VSX_Intrinsic<"xxgenpcvwm", [llvm_v4i32_ty],

llvm/lib/Target/PowerPC/PPCInstrPrefix.td

class XForm_XT6_IMM5_VB5<bits<6> opcode, bits<10> xo, dag OOL, dag IOL,
   let Pattern = pattern;
   let Inst{6-10} = XT{4-0};
   let Inst{11-15} = IMM;
   let Inst{16-20} = VRB;
   let Inst{21-30} = xo;
   let Inst{31} = XT{5};
 }
 
+// [PO BF / XO2 B XO BX /]
+class XX2_BF3_XO5_XB6_XO9<bits<6> opcode, bits<5> xo2, bits<9> xo, dag OOL,
+                          dag IOL, string asmstr, InstrItinClass itin,
+                          list<dag> pattern>
+  : I<opcode, OOL, IOL, asmstr, itin> {
+  bits<3> BF;
+  bits<6> XB;
+
+  let Pattern = pattern;
+
+  let Inst{6-8}   = BF;
+  let Inst{9-10}  = 0;
+  let Inst{11-15} = xo2;
+  let Inst{16-20} = XB{4-0};
+  let Inst{21-29} = xo;
+  let Inst{30}    = XB{5};
+  let Inst{31}    = 0;
+}
+
 multiclass MLS_DForm_R_SI34_RTA5_MEM_p<bits<6> opcode, dag OOL, dag IOL,
                                        dag PCRel_IOL, string asmstr,
                                        InstrItinClass itin> {
   def NAME : MLS_DForm_R_SI34_RTA5_MEM<opcode, OOL, IOL,
                                        !strconcat(asmstr, ", 0"), itin, []>;
   def pc : MLS_DForm_R_SI34_RTA5_MEM<opcode, OOL, PCRel_IOL,
                                      !strconcat(asmstr, ", 1"), itin, []>,
                                      isPCRel;
let Predicates = [IsISA3_1] in {
    def VCLRLB : VXForm_1<397, (outs vrrc:$vD), (ins vrrc:$vA, gprc:$rB),
                          "vclrlb $vD, $vA, $rB", IIC_VecGeneral,
                          [(set v16i8:$vD,
                                (int_ppc_altivec_vclrlb v16i8:$vA, i32:$rB))]>;
    def VCLRRB : VXForm_1<461, (outs vrrc:$vD), (ins vrrc:$vA, gprc:$rB),
                          "vclrrb $vD, $vA, $rB", IIC_VecGeneral,
                          [(set v16i8:$vD,
                                (int_ppc_altivec_vclrrb v16i8:$vA, i32:$rB))]>;
+   def XVTLSBB : XX2_BF3_XO5_XB6_XO9<60, 2, 475, (outs crrc:$BF), (ins vsrc:$XB),
+                                     "xvtlsbb $BF, $XB", IIC_VecGeneral, []>;
 }
 
 //---------------------------- Anonymous Patterns ----------------------------//
 let Predicates = [IsISA3_1] in {
   def : Pat<(v16i8 (int_ppc_vsx_xxgenpcvbm v16i8:$VRB, imm:$IMM)),
             (v16i8 (COPY_TO_REGCLASS (XXGENPCVBM $VRB, imm:$IMM), VRRC))>;
   def : Pat<(v8i16 (int_ppc_vsx_xxgenpcvhm v8i16:$VRB, imm:$IMM)),
             (v8i16 (COPY_TO_REGCLASS (XXGENPCVHM $VRB, imm:$IMM), VRRC))>;
   def : Pat<(v4i32 (int_ppc_vsx_xxgenpcvwm v4i32:$VRB, imm:$IMM)),
             (v4i32 (COPY_TO_REGCLASS (XXGENPCVWM $VRB, imm:$IMM), VRRC))>;
   def : Pat<(v2i64 (int_ppc_vsx_xxgenpcvdm v2i64:$VRB, imm:$IMM)),
             (v2i64 (COPY_TO_REGCLASS (XXGENPCVDM $VRB, imm:$IMM), VRRC))>;
+  def : Pat<(i32 (int_ppc_vsx_xvtlsbb v16i8:$XB, -1)),
+            (EXTRACT_SUBREG (XVTLSBB (COPY_TO_REGCLASS $XB, VSRC)), sub_lt)>;
+  def : Pat<(i32 (int_ppc_vsx_xvtlsbb v16i8:$XB, 0)),
+            (EXTRACT_SUBREG (XVTLSBB (COPY_TO_REGCLASS $XB, VSRC)), sub_eq)>;
 }

llvm/test/CodeGen/PowerPC/p10-vsx-builtins.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -verify-machineinstrs -mtriple=powerpc64le-unknown-linux-gnu \
+; RUN:   -mcpu=pwr10 -ppc-asm-full-reg-names -ppc-vsr-nums-as-vr < %s | \
+; RUN:   FileCheck %s
+
+; This test case aims to test the builtins for VSX vector instructions
+; on Power10.
+
+declare i32 @llvm.ppc.vsx.xvtlsbb(<16 x i8>, i1)
+
+define signext i32 @test_vec_test_lsbb_all_ones(<16 x i8> %vuca) {
+; CHECK-LABEL: test_vec_test_lsbb_all_ones:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    xvtlsbb cr0, v2
+; CHECK-NEXT:    mfocrf r3, 128
+; CHECK-NEXT:    srwi r3, r3, 31
+; CHECK-NEXT:    extsw r3, r3
+; CHECK-NEXT:    blr
+entry:
+  %0 = tail call i32 @llvm.ppc.vsx.xvtlsbb(<16 x i8> %vuca, i1 1)
+  ret i32 %0
+}
+
+define signext i32 @test_vec_test_lsbb_all_zeros(<16 x i8> %vuca) {
+; CHECK-LABEL: test_vec_test_lsbb_all_zeros:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    xvtlsbb cr0, v2
+; CHECK-NEXT:    mfocrf r3, 128
+; CHECK-NEXT:    rlwinm r3, r3, 3, 31, 31
+; CHECK-NEXT:    extsw r3, r3
+; CHECK-NEXT:    blr
+entry:
+  %0 = tail call i32 @llvm.ppc.vsx.xvtlsbb(<16 x i8> %vuca, i1 0)
+  ret i32 %0
+}

llvm/test/MC/Disassembler/PowerPC/p10insts.txt

 # CHECK xxgenpcvdm 0, 1, 2
 0xf0 0x02 0x0f 0x6a
 
 # CHECK: vclrlb 1, 4, 3
 0x10 0x24 0x19 0x8d
 
 # CHECK: vclrrb 1, 4, 3
 0x10 0x24 0x19 0xcd
+
+# CHECK: xvtlsbb 1, 7
+0xf0 0x82 0x3f 0x6c

llvm/test/MC/PowerPC/p10.s

 # CHECK-LE: xxgenpcvdm 0, 1, 2                    # encoding: [0x6a,0x0f,0x02,0xf0]
             xxgenpcvdm 0, 1, 2
 # CHECK-BE: vclrlb 1, 4, 3                        # encoding: [0x10,0x24,0x19,0x8d]
 # CHECK-LE: vclrlb 1, 4, 3                        # encoding: [0x8d,0x19,0x24,0x10]
             vclrlb 1, 4, 3
 # CHECK-BE: vclrrb 1, 4, 3                        # encoding: [0x10,0x24,0x19,0xcd]
 # CHECK-LE: vclrrb 1, 4, 3                        # encoding: [0xcd,0x19,0x24,0x10]
             vclrrb 1, 4, 3
+# CHECK-BE: xvtlsbb 1, 7                          # encoding: [0xf0,0x82,0x3f,0x6c]
+# CHECK-LE: xvtlsbb 1, 7                          # encoding: [0x6c,0x3f,0x82,0xf0]
+            xvtlsbb 1, 7