From b085e51d818a39c7e2ea659ebbefd1943689c642 Mon Sep 17 00:00:00 2001
From: Cameron McInally <cameron.mcinally@nyu.edu>
Date: Thu, 14 May 2020 16:07:59 -0500
Subject: [PATCH] [AArch64][SVE] Add some integer DestructiveBinaryComm*
 patterns

Add DestructiveBinaryComm* patterns for ADD, SUB, and SUBR.

Differential Revision: https://reviews.llvm.org/D76711
---
 .../lib/Target/AArch64/AArch64SVEInstrInfo.td |  10 +-
 llvm/lib/Target/AArch64/SVEInstrFormats.td    |  19 +-
 .../sve-intrinsics-int-arith-merging.ll       | 172 ++++++++++++++++++
 3 files changed, 193 insertions(+), 8 deletions(-)
 create mode 100644 llvm/test/CodeGen/AArch64/sve-intrinsics-int-arith-merging.ll

diff --git a/llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td b/llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td
index 363d451b2c07..8c0c95bd124a 100644
--- a/llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td
+++ b/llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td
@@ -199,9 +199,13 @@ let Predicates = [HasSVE] in {
   defm EOR_ZZZ : sve_int_bin_cons_log<0b10, "eor", xor>;
   defm BIC_ZZZ : sve_int_bin_cons_log<0b11, "bic", null_frag>;
 
-  defm ADD_ZPmZ   : sve_int_bin_pred_arit_0<0b000, "add", int_aarch64_sve_add>;
-  defm SUB_ZPmZ   : sve_int_bin_pred_arit_0<0b001, "sub", int_aarch64_sve_sub>;
-  defm SUBR_ZPmZ  : sve_int_bin_pred_arit_0<0b011, "subr", int_aarch64_sve_subr>;
+  defm ADD_ZPmZ  : sve_int_bin_pred_arit_0<0b000, "add",  "ADD_ZPZZ", int_aarch64_sve_add, DestructiveBinaryComm>;
+  defm SUB_ZPmZ  : sve_int_bin_pred_arit_0<0b001, "sub",  "SUB_ZPZZ", int_aarch64_sve_sub, DestructiveBinaryCommWithRev, "SUBR_ZPmZ", 1>;
+  defm SUBR_ZPmZ : sve_int_bin_pred_arit_0<0b011, "subr", "SUBR_ZPZZ", int_aarch64_sve_subr, DestructiveBinaryCommWithRev, "SUB_ZPmZ", 0>;
+
+  defm ADD_ZPZZ  : sve_int_bin_pred_zx<int_aarch64_sve_add>;
+  defm SUB_ZPZZ  : sve_int_bin_pred_zx<int_aarch64_sve_sub>;
+  defm SUBR_ZPZZ : sve_int_bin_pred_zx<int_aarch64_sve_subr>;
 
   defm ORR_ZPmZ : sve_int_bin_pred_log<0b000, "orr", int_aarch64_sve_orr>;
   defm EOR_ZPmZ : sve_int_bin_pred_log<0b001, "eor", int_aarch64_sve_eor>;
diff --git a/llvm/lib/Target/AArch64/SVEInstrFormats.td b/llvm/lib/Target/AArch64/SVEInstrFormats.td
index 5624e78b65ac..48b3d8a3199a 100644
--- a/llvm/lib/Target/AArch64/SVEInstrFormats.td
+++ b/llvm/lib/Target/AArch64/SVEInstrFormats.td
@@ -2341,11 +2341,20 @@ multiclass sve_int_bin_pred_log<bits<3> opc, string asm, SDPatternOperator op> {
   def : SVE_3_Op_Pat<nxv2i64, op, nxv2i1, nxv2i64, nxv2i64, !cast<Instruction>(NAME # _D)>;
 }
 
-multiclass sve_int_bin_pred_arit_0<bits<3> opc, string asm, SDPatternOperator op> {
-  def _B : sve_int_bin_pred_arit_log<0b00, 0b00, opc, asm, ZPR8>;
-  def _H : sve_int_bin_pred_arit_log<0b01, 0b00, opc, asm, ZPR16>;
-  def _S : sve_int_bin_pred_arit_log<0b10, 0b00, opc, asm, ZPR32>;
-  def _D : sve_int_bin_pred_arit_log<0b11, 0b00, opc, asm, ZPR64>;
+multiclass sve_int_bin_pred_arit_0<bits<3> opc, string asm, string Ps,
+                                   SDPatternOperator op,
+                                   DestructiveInstTypeEnum flags,
+                                   string revname="", bit isOrig=0> {
+  let DestructiveInstType = flags in {
+  def _B : sve_int_bin_pred_arit_log<0b00, 0b00, opc, asm, ZPR8>,
+             SVEPseudo2Instr<Ps # _B, 1>, SVEInstr2Rev<NAME # _B, revname # _B, isOrig>;
+  def _H : sve_int_bin_pred_arit_log<0b01, 0b00, opc, asm, ZPR16>,
+             SVEPseudo2Instr<Ps # _H, 1>, SVEInstr2Rev<NAME # _H, revname # _H, isOrig>;
+  def _S : sve_int_bin_pred_arit_log<0b10, 0b00, opc, asm, ZPR32>,
+             SVEPseudo2Instr<Ps # _S, 1>, SVEInstr2Rev<NAME # _S, revname # _S, isOrig>;
+  def _D : sve_int_bin_pred_arit_log<0b11, 0b00, opc, asm, ZPR64>,
+             SVEPseudo2Instr<Ps # _D, 1>, SVEInstr2Rev<NAME # _D, revname # _D, isOrig>;
+  }
 
   def : SVE_3_Op_Pat<nxv16i8, op, nxv16i1, nxv16i8, nxv16i8, !cast<Instruction>(NAME # _B)>;
   def : SVE_3_Op_Pat<nxv8i16, op, nxv8i1, nxv8i16, nxv8i16, !cast<Instruction>(NAME # _H)>;
diff --git a/llvm/test/CodeGen/AArch64/sve-intrinsics-int-arith-merging.ll b/llvm/test/CodeGen/AArch64/sve-intrinsics-int-arith-merging.ll
new file mode 100644
index 000000000000..984ebd17322f
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/sve-intrinsics-int-arith-merging.ll
@@ -0,0 +1,172 @@
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s
+
+;
+; ADD
+;
+
+define <vscale x 16 x i8> @add_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: add_i8:
+; CHECK:      movprfx z0.b, p0/z, z0.b
+; CHECK-NEXT: add z0.b, p0/m, z0.b, z1.b
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> zeroinitializer
+  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.add.nxv16i8(<vscale x 16 x i1> %pg,
+                                                               <vscale x 16 x i8> %a_z,
+                                                               <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %out
+}
+
+define <vscale x 8 x i16> @add_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: add_i16:
+; CHECK:      movprfx z0.h, p0/z, z0.h
+; CHECK-NEXT: add z0.h, p0/m, z0.h, z1.h
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> zeroinitializer
+  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.add.nxv8i16(<vscale x 8 x i1> %pg,
+                                                               <vscale x 8 x i16> %a_z,
+                                                               <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %out
+}
+
+define <vscale x 4 x i32> @add_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: add_i32:
+; CHECK:      movprfx z0.s, p0/z, z0.s
+; CHECK-NEXT: add z0.s, p0/m, z0.s, z1.s
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> zeroinitializer
+  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.add.nxv4i32(<vscale x 4 x i1> %pg,
+                                                               <vscale x 4 x i32> %a_z,
+                                                               <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %out
+}
+
+define <vscale x 2 x i64> @add_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: add_i64:
+; CHECK:      movprfx z0.d, p0/z, z0.d
+; CHECK-NEXT: add z0.d, p0/m, z0.d, z1.d
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> zeroinitializer
+  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.add.nxv2i64(<vscale x 2 x i1> %pg,
+                                                               <vscale x 2 x i64> %a_z,
+                                                               <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %out
+}
+
+;
+; SUB
+;
+
+define <vscale x 16 x i8> @sub_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: sub_i8:
+; CHECK:      movprfx z0.b, p0/z, z0.b
+; CHECK-NEXT: sub z0.b, p0/m, z0.b, z1.b
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> zeroinitializer
+  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.sub.nxv16i8(<vscale x 16 x i1> %pg,
+                                                               <vscale x 16 x i8> %a_z,
+                                                               <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %out
+}
+
+define <vscale x 8 x i16> @sub_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: sub_i16:
+; CHECK:      movprfx z0.h, p0/z, z0.h
+; CHECK-NEXT: sub z0.h, p0/m, z0.h, z1.h
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> zeroinitializer
+  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.sub.nxv8i16(<vscale x 8 x i1> %pg,
+                                                               <vscale x 8 x i16> %a_z,
+                                                               <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %out
+}
+
+define <vscale x 4 x i32> @sub_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: sub_i32:
+; CHECK:      movprfx z0.s, p0/z, z0.s
+; CHECK-NEXT: sub z0.s, p0/m, z0.s, z1.s
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> zeroinitializer
+  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.sub.nxv4i32(<vscale x 4 x i1> %pg,
+                                                               <vscale x 4 x i32> %a_z,
+                                                               <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %out
+}
+
+define <vscale x 2 x i64> @sub_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: sub_i64:
+; CHECK:      movprfx z0.d, p0/z, z0.d
+; CHECK-NEXT: sub z0.d, p0/m, z0.d, z1.d
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> zeroinitializer
+  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.sub.nxv2i64(<vscale x 2 x i1> %pg,
+                                                               <vscale x 2 x i64> %a_z,
+                                                               <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %out
+}
+
+;
+; SUBR
+;
+
+define <vscale x 16 x i8> @subr_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: subr_i8:
+; CHECK:      movprfx z0.b, p0/z, z0.b
+; CHECK-NEXT: subr z0.b, p0/m, z0.b, z1.b
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> zeroinitializer
+  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.subr.nxv16i8(<vscale x 16 x i1> %pg,
+                                                                <vscale x 16 x i8> %a_z,
+                                                                <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %out
+}
+
+define <vscale x 8 x i16> @subr_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: subr_i16:
+; CHECK:      movprfx z0.h, p0/z, z0.h
+; CHECK-NEXT: subr z0.h, p0/m, z0.h, z1.h
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> zeroinitializer
+  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.subr.nxv8i16(<vscale x 8 x i1> %pg,
+                                                                <vscale x 8 x i16> %a_z,
+                                                                <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %out
+}
+
+define <vscale x 4 x i32> @subr_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: subr_i32:
+; CHECK:      movprfx z0.s, p0/z, z0.s
+; CHECK-NEXT: subr z0.s, p0/m, z0.s, z1.s
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> zeroinitializer
+  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.subr.nxv4i32(<vscale x 4 x i1> %pg,
+                                                                <vscale x 4 x i32> %a_z,
+                                                                <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %out
+}
+
+define <vscale x 2 x i64> @subr_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: subr_i64:
+; CHECK:      movprfx z0.d, p0/z, z0.d
+; CHECK-NEXT: subr z0.d, p0/m, z0.d, z1.d
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> zeroinitializer
+  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.subr.nxv2i64(<vscale x 2 x i1> %pg,
+                                                                <vscale x 2 x i64> %a_z,
+                                                                <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %out
+}
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.add.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>)
+declare <vscale x 8 x i16> @llvm.aarch64.sve.add.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
+declare <vscale x 4 x i32> @llvm.aarch64.sve.add.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>)
+declare <vscale x 2 x i64> @llvm.aarch64.sve.add.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>)
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.sub.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>)
+declare <vscale x 8 x i16> @llvm.aarch64.sve.sub.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
+declare <vscale x 4 x i32> @llvm.aarch64.sve.sub.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>)
+declare <vscale x 2 x i64> @llvm.aarch64.sve.sub.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>)
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.subr.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>)
+declare <vscale x 8 x i16> @llvm.aarch64.sve.subr.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
+declare <vscale x 4 x i32> @llvm.aarch64.sve.subr.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>)
+declare <vscale x 2 x i64> @llvm.aarch64.sve.subr.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>)