[PowerPC][Power10] Implement Vector Clear Left/Rightmost Bytes Builtins in LLVM/Clang

[amyk]

Summary

This patch implements builtins for the following prototypes:

vector signed char vec_clrl (vector signed char a, unsigned int n);
vector unsigned char vec_clrl (vector unsigned char a, unsigned int n);
vector signed char vec_clrr (vector signed char a, unsigned int n);
vector signed char vec_clrr (vector unsigned char a, unsigned int n);

Depends on D80935

[lei]

LGTM
Minor nit to be addressed during commit.

llvm/lib/Target/PowerPC/PPCInstrPrefix.td

522

nit: indentation.

526

nit: indentation

clang/include/clang/Basic/BuiltinsPPC.def

 BUILTIN(__builtin_altivec_vrldmi, "V2ULLiV2ULLiV2ULLiV2ULLi", "")
 BUILTIN(__builtin_altivec_vrlwnm, "V4UiV4UiV4Ui", "")
 BUILTIN(__builtin_altivec_vrldnm, "V2ULLiV2ULLiV2ULLi", "")
 
 // P10 Vector Parallel Bits built-ins.
 BUILTIN(__builtin_altivec_vpdepd, "V2ULLiV2ULLiV2ULLi", "")
 BUILTIN(__builtin_altivec_vpextd, "V2ULLiV2ULLiV2ULLi", "")
 
+// P10 Vector Clear Bytes built-ins.
+BUILTIN(__builtin_altivec_vclrlb, "V16cV16cUi", "")
+BUILTIN(__builtin_altivec_vclrrb, "V16cV16cUi", "")
+
 // VSX built-ins.
 
 BUILTIN(__builtin_vsx_lxvd2x, "V2divC*", "")
 BUILTIN(__builtin_vsx_lxvw4x, "V4iivC*", "")
 BUILTIN(__builtin_vsx_lxvd2x_be, "V2dSLLivC*", "")
 BUILTIN(__builtin_vsx_lxvw4x_be, "V4iSLLivC*", "")
 
 BUILTIN(__builtin_vsx_stxvd2x, "vV2div*", "")

clang/lib/Headers/altivec.h

 }
 
 /* vec_pext */
 
 static __inline__ vector unsigned long long __ATTRS_o_ai
 vec_pext(vector unsigned long long __a, vector unsigned long long __b) {
   return __builtin_altivec_vpextd(__a, __b);
 }
+
+/* vec_clrl */
+
+static __inline__ vector signed char __ATTRS_o_ai
+vec_clrl(vector signed char __a, unsigned int __n) {
+#ifdef __LITTLE_ENDIAN__
+  return __builtin_altivec_vclrrb(__a, __n);
+#else
+  return __builtin_altivec_vclrlb( __a, __n);
+#endif
+}
+
+static __inline__ vector unsigned char __ATTRS_o_ai
+vec_clrl(vector unsigned char __a, unsigned int __n) {
+#ifdef __LITTLE_ENDIAN__
+  return __builtin_altivec_vclrrb((vector signed char)__a, __n);
+#else
+  return __builtin_altivec_vclrlb((vector signed char)__a, __n);
+#endif
+}
+
+/* vec_clrr */
+
+static __inline__ vector signed char __ATTRS_o_ai
+vec_clrr(vector signed char __a, unsigned int __n) {
+#ifdef __LITTLE_ENDIAN__
+  return __builtin_altivec_vclrlb(__a, __n);
+#else
+  return __builtin_altivec_vclrrb( __a, __n);
+#endif
+}
+
+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
+}
 #endif /* __POWER10_VECTOR__ */
 
 #undef __ATTRS_o_ai
 
 #endif /* __ALTIVEC_H */

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

 // REQUIRES: powerpc-registered-target
 // RUN: %clang_cc1 -target-feature +vsx -target-feature +altivec \
 // RUN:   -target-cpu pwr10 -triple powerpc64le-unknown-unknown -emit-llvm %s \
 // RUN:   -o - | FileCheck %s
 
 #include <altivec.h>
 
+vector signed char vsca;
+vector unsigned char vuca;
 vector unsigned long long vulla, vullb;
+unsigned int uia;
 
 vector unsigned long long test_vpdepd(void) {
   // CHECK: @llvm.ppc.altivec.vpdepd(<2 x i64>
   // CHECK-NEXT: ret <2 x i64>
   return vec_pdep(vulla, vullb);
 }
 
 vector unsigned long long test_vpextd(void) {
   // CHECK: @llvm.ppc.altivec.vpextd(<2 x i64>
   // CHECK-NEXT: ret <2 x i64>
   return vec_pext(vulla, vullb);
 }
+
+vector signed char test_vec_vclrl_sc(void) {
+  // CHECK-BE: @llvm.ppc.altivec.vclrlb(<16 x i8>
+  // CHECK-BE-NEXT: ret <16 x i8>
+  // CHECK-LE: @llvm.ppc.altivec.vclrrb(<16 x i8>
+  // CHECK-LE-NEXT: ret <16 x i8>
+  return vec_clrl(vsca, uia);
+}
+
+vector unsigned char test_vec_clrl_uc(void) {
+  // CHECK-BE: @llvm.ppc.altivec.vclrlb(<16 x i8>
+  // CHECK-BE-NEXT: ret <16 x i8>
+  // CHECK-LE: @llvm.ppc.altivec.vclrrb(<16 x i8>
+  // CHECK-LE-NEXT: ret <16 x i8>
+  return vec_clrl(vuca, uia);
+}
+
+vector signed char test_vec_vclrr_sc(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(vsca, uia);
+}
+
+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);
+}

llvm/include/llvm/IR/IntrinsicsPowerPC.td

let TargetPrefix = "ppc" in {  // All intrinsics start with "llvm.ppc.".
 
   // P10 Vector Parallel Bits Deposit/Extract Doubleword Builtins.
   def int_ppc_altivec_vpdepd : GCCBuiltin<"__builtin_altivec_vpdepd">,
               Intrinsic<[llvm_v2i64_ty], [llvm_v2i64_ty, llvm_v2i64_ty],
                         [IntrNoMem]>;
   def int_ppc_altivec_vpextd : GCCBuiltin<"__builtin_altivec_vpextd">,
               Intrinsic<[llvm_v2i64_ty], [llvm_v2i64_ty, llvm_v2i64_ty],
                         [IntrNoMem]>;
+
+   // P10 Vector Clear Bytes
+   def int_ppc_altivec_vclrlb :  GCCBuiltin<"__builtin_altivec_vclrlb">,
+               Intrinsic<[llvm_v16i8_ty], [llvm_v16i8_ty, llvm_i32_ty],
+                         [IntrNoMem]>;
+   def int_ppc_altivec_vclrrb :  GCCBuiltin<"__builtin_altivec_vclrrb">,
+               Intrinsic<[llvm_v16i8_ty], [llvm_v16i8_ty, llvm_i32_ty],
+                         [IntrNoMem]>;
 }
 
 // Vector average.
 def int_ppc_altivec_vavgsb : PowerPC_Vec_BBB_Intrinsic<"vavgsb">;
 def int_ppc_altivec_vavgsh : PowerPC_Vec_HHH_Intrinsic<"vavgsh">;
 def int_ppc_altivec_vavgsw : PowerPC_Vec_WWW_Intrinsic<"vavgsw">;
 def int_ppc_altivec_vavgub : PowerPC_Vec_BBB_Intrinsic<"vavgub">;
 def int_ppc_altivec_vavguh : PowerPC_Vec_HHH_Intrinsic<"vavguh">;

llvm/lib/Target/PowerPC/PPCInstrPrefix.td

def VPEXTD : VXForm_1<1421, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
                          [(set v2i64:$vD,
                          (int_ppc_altivec_vpextd v2i64:$vA, v2i64:$vB))]>;
    def PDEPD : XForm_6<31, 156, (outs g8rc:$rA), (ins g8rc:$rS, g8rc:$rB),
                        "pdepd $rA, $rS, $rB", IIC_IntGeneral,
                        [(set i64:$rA, (int_ppc_pdepd i64:$rS, i64:$rB))]>;
    def PEXTD : XForm_6<31, 188, (outs g8rc:$rA), (ins g8rc:$rS, g8rc:$rB),
                        "pextd $rA, $rS, $rB", IIC_IntGeneral,
                        [(set i64:$rA, (int_ppc_pextd i64:$rS, i64:$rB))]>;
+   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))]>;
 }

llvm/test/CodeGen/PowerPC/p10-string-ops.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
+
+; These test cases aim to test the vector string isolate builtins on Power10.
+
+declare <16 x i8> @llvm.ppc.altivec.vclrlb(<16 x i8>, i32)
+declare <16 x i8> @llvm.ppc.altivec.vclrrb(<16 x i8>, i32)
+
+define <16 x i8> @test_vclrlb(<16 x i8> %a, i32 %n) {
+; CHECK-LABEL: test_vclrlb:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vclrlb v2, v2, r5
+; CHECK-NEXT:    blr
+entry:
+  %tmp = tail call <16 x i8> @llvm.ppc.altivec.vclrlb(<16 x i8> %a, i32 %n)
+  ret <16 x i8> %tmp
+}
+
+define <16 x i8> @test_vclrrb(<16 x i8> %a, i32 %n) {
+; CHECK-LABEL: test_vclrrb:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vclrrb v2, v2, r5
+; CHECK-NEXT:    blr
+entry:
+  %tmp = tail call <16 x i8> @llvm.ppc.altivec.vclrrb(<16 x i8> %a, i32 %n)
+  ret <16 x i8> %tmp
+}

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

 # RUN: llvm-mc --disassemble %s -triple powerpc64-unknown-linux-gnu \
 # RUN:   -mcpu=pwr10 | FileCheck %s
 
 # CHECK: vpdepd 1, 2, 0
 0x10 0x22 0x05 0xcd
 
 # CHECK: vpextd 1, 2, 0
 0x10 0x22 0x05 0x8d
 
 # CHECK: pdepd 1, 2, 4
 0x7c 0x41 0x21 0x38
 
 # CHECK: pextd 1, 2, 4
 0x7c 0x41 0x21 0x78
+
+# CHECK: vclrlb 1, 4, 3
+0x10 0x24 0x19 0x8d
+
+# CHECK: vclrrb 1, 4, 3
+0x10 0x24 0x19 0xcd

llvm/test/MC/PowerPC/p10.s

 # CHECK-LE: vpextd 1, 2, 0                        # encoding: [0x8d,0x05,0x22,0x10]
             vpextd 1, 2, 0
 # CHECK-BE: pdepd 1, 2, 4                         # encoding: [0x7c,0x41,0x21,0x38]
 # CHECK-LE: pdepd 1, 2, 4                         # encoding: [0x38,0x21,0x41,0x7c]
             pdepd 1, 2, 4
 # CHECK-BE: pextd 1, 2, 4                         # encoding: [0x7c,0x41,0x21,0x78]
 # CHECK-LE: pextd 1, 2, 4                         # encoding: [0x78,0x21,0x41,0x7c]
             pextd 1, 2, 4
+# 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