[Hexagon] Add HVX patterns for vector arithmetic

This patch Introduces instruction selection patterns to generate the
vsub, vadd, vmpy, vmin, and vmax HVX vector instructions.
These patterns match on standard IR-level vector operations and lower
them to the corresponding Hexagon HVX intrinsics.

Patch By: Fateme Hosseini

Co-authored-by: Jyotsna Verma <[email protected]>

Author: fhossein-quic

llvm/lib/Target/Hexagon/HexagonPatterns.td

@@ -380,6 +380,7 @@ multiclass NopCast_pat<ValueType Ty1, ValueType Ty2, RegisterClass RC> {
 def Add: pf2<add>;    def And: pf2<and>;    def Sra: pf2<sra>;
 def Sub: pf2<sub>;    def Or:  pf2<or>;     def Srl: pf2<srl>;
 def Mul: pf2<mul>;    def Xor: pf2<xor>;    def Shl: pf2<shl>;
+def Sext: pf1<sext>;  def Zext: pf1<zext>;
 
 def Smin: pf2<smin>;  def Smax: pf2<smax>;
 def Umin: pf2<umin>;  def Umax: pf2<umax>;

llvm/lib/Target/Hexagon/HexagonPatternsHVX.td

@@ -76,6 +76,12 @@ def VSxth: OutPatFrag<(ops node:$Vs), (V6_vunpackh  $Vs)>;
 def VZxtb: OutPatFrag<(ops node:$Vs), (V6_vunpackub $Vs)>;
 def VZxth: OutPatFrag<(ops node:$Vs), (V6_vunpackuh $Vs)>;
 
+def VShuff: OutPatFrag<(ops node:$Vs, node:$S),
+                       (V6_vshuffvdd (HiVec $Vs), (LoVec $Vs), (A2_tfrsi $S))>;
+
+def VDeal: OutPatFrag<(ops node:$Vs, node:$S),
+                      (V6_vdealvdd (HiVec $Vs), (LoVec $Vs), (A2_tfrsi $S))>;
+
 class VSubi<InstHexagon VSub, InstHexagon VSplati>:
   OutPatFrag<(ops node:$Imm, node:$Vs), (VSub (VSplati (i32 $Imm)), $Vs)>;
 
@@ -402,6 +408,64 @@ class Vneg1<ValueType VecTy>
 class Vnot<ValueType VecTy>
   : PatFrag<(ops node:$Vs), (xor $Vs, Vneg1<VecTy>)>;
 
+class ExtOp_pat<InstHexagon MI, PatFrag Op, PatFrag Ext, ValueType ResType,
+                 PatFrag VPred, int Shuff>
+  : Pat<(ResType (Op (Ext VPred:$Vs), (Ext VPred:$Vt))),
+        (VShuff (MI VPred:$Vs, VPred:$Vt), Shuff)>;
+
+class VOpAcc_pat<InstHexagon MI, PatFrag Op, PatFrag Ext, ValueType ResType,
+                  PatFrag VxPred, PatFrag VsPred, int Shuff>
+  : Pat<(ResType (add VxPred:$Vx, (Op (Ext VsPred:$Vs), (Ext VsPred:$Vt)))),
+        (VShuff (MI (VDeal $Vx, Shuff), VsPred:$Vs, VsPred:$Vt), Shuff)>;
+
+let Predicates = [UseHVX] in {
+  let AddedComplexity = 200 in {
+    def : ExtOp_pat<V6_vaddubh, Add, Zext, VecPI16, HVI8, -2>;
+    def : ExtOp_pat<V6_vadduhw, Add, Zext, VecPI32, HVI16, -4>;
+    def : ExtOp_pat<V6_vaddhw, Add, Sext, VecPI32, HVI16, -4>;
+
+    def : ExtOp_pat<V6_vsububh, Sub, Zext, VecPI16, HVI8, -2>;
+    def : ExtOp_pat<V6_vsubuhw, Sub, Zext, VecPI32, HVI16, -4>;
+    def : ExtOp_pat<V6_vsubhw, Sub, Sext, VecPI32, HVI16, -4>;
+
+    def : ExtOp_pat<V6_vmpybv, Mul, Sext, VecPI16, HVI8, -2>;
+    def : ExtOp_pat<V6_vmpyhv, Mul, Sext, VecPI32, HVI16, -4>;
+    def : ExtOp_pat<V6_vmpyubv, Mul, Zext, VecPI16, HVI8, -2>;
+    def : ExtOp_pat<V6_vmpyuhv, Mul, Zext, VecPI32, HVI16, -4>;
+
+    // The first operand in V6_vmpybusv is unsigned.
+    def : Pat<(VecPI16 (mul (VecPI16 (zext HVI8:$Vs)),
+                            (VecPI16 (sext HVI8:$Vv)))),
+              (VShuff (V6_vmpybusv HVI8:$Vs, HVI8:$Vv), -2)>;
+
+    // The second operand in V6_vmpyhus is unsigned.
+    def : Pat<(VecPI32 (mul (VecPI32 (sext HVI16:$Vs)),
+                            (VecPI32 (zext HVI16:$Vv)))),
+              (VShuff (V6_vmpyhus HVI16:$Vs, HVI16:$Vv), -4)>;
+
+    def : VOpAcc_pat<V6_vaddubh_acc, Add, Zext, VecPI16, HWI16, HVI8, -2>;
+    def : VOpAcc_pat<V6_vadduhw_acc, Add, Zext, VecPI32, HWI32, HVI16, -4>;
+    def : VOpAcc_pat<V6_vaddhw_acc, Add, Sext, VecPI32, HWI32, HVI16, -4>;
+
+    def : VOpAcc_pat<V6_vmpybv_acc, Mul, Sext, VecPI16, HWI16, HVI8, -2>;
+    def : VOpAcc_pat<V6_vmpyubv_acc, Mul, Zext, VecPI16, HWI16, HVI8, -2>;
+    def : VOpAcc_pat<V6_vmpyhv_acc, Mul, Sext, VecPI32, HWI32, HVI16, -4>;
+    def : VOpAcc_pat<V6_vmpyuhv_acc, Mul, Zext, VecPI32, HWI32, HVI16, -4>;
+
+    // The second operand in V6_vmpybusv_acc is unsigned.
+    def : Pat<(VecPI16 (add HWI16:$Vx , (mul (VecPI16 (zext HVI8:$Vs)),
+                                             (VecPI16 (sext HVI8:$Vt))))),
+              (VShuff (V6_vmpybusv_acc (VDeal $Vx, -2),
+                                       HVI8:$Vs, HVI8:$Vt), -2)>;
+
+    // The third operand in V6_vmpyhus_acc is unsigned.
+    def : Pat<(add HWI32:$Vx, (mul (VecPI32 (sext HVI16:$Vs)),
+                                   (VecPI32 (zext HVI16:$Vt)))),
+              (VShuff (V6_vmpyhus_acc (VDeal $Vx, -4),
+                                      HVI16:$Vs, HVI16:$Vt), -4)>;
+  }
+}
+
 let Predicates = [UseHVX] in {
   let AddedComplexity = 200 in {
     def: Pat<(Vnot<VecI8>   HVI8:$Vs), (V6_vnot HvxVR:$Vs)>;

llvm/test/CodeGen/Hexagon/autohvx/arith.ll

@@ -132,141 +132,5 @@ define <32 x i32> @xorw_128(<32 x i32> %v0, <32 x i32> %v1) #1 {
   ret <32 x i32> %p
 }
 
-; --- add
-
-; CHECK-LABEL: addb_64:
-; CHECK: vadd(v0.b,v1.b)
-define <64 x i8> @addb_64(<64 x i8> %v0, <64 x i8> %v1) #0 {
-  %p = add <64 x i8> %v0, %v1
-  ret <64 x i8> %p
-}
-
-; CHECK-LABEL: addb_128:
-; CHECK: vadd(v0.b,v1.b)
-define <128 x i8> @addb_128(<128 x i8> %v0, <128 x i8> %v1) #1 {
-  %p = add <128 x i8> %v0, %v1
-  ret <128 x i8> %p
-}
-
-; CHECK-LABEL: addh_64:
-; CHECK: vadd(v0.h,v1.h)
-define <32 x i16> @addh_64(<32 x i16> %v0, <32 x i16> %v1) #0 {
-  %p = add <32 x i16> %v0, %v1
-  ret <32 x i16> %p
-}
-
-; CHECK-LABEL: addh_128:
-; CHECK: vadd(v0.h,v1.h)
-define <64 x i16> @addh_128(<64 x i16> %v0, <64 x i16> %v1) #1 {
-  %p = add <64 x i16> %v0, %v1
-  ret <64 x i16> %p
-}
-
-; CHECK-LABEL: addw_64:
-; CHECK: vadd(v0.w,v1.w)
-define <16 x i32> @addw_64(<16 x i32> %v0, <16 x i32> %v1) #0 {
-  %p = add <16 x i32> %v0, %v1
-  ret <16 x i32> %p
-}
-
-; CHECK-LABEL: addw_128:
-; CHECK: vadd(v0.w,v1.w)
-define <32 x i32> @addw_128(<32 x i32> %v0, <32 x i32> %v1) #1 {
-  %p = add <32 x i32> %v0, %v1
-  ret <32 x i32> %p
-}
-
-; --- sub
-
-; CHECK-LABEL: subb_64:
-; CHECK: vsub(v0.b,v1.b)
-define <64 x i8> @subb_64(<64 x i8> %v0, <64 x i8> %v1) #0 {
-  %p = sub <64 x i8> %v0, %v1
-  ret <64 x i8> %p
-}
-
-; CHECK-LABEL: subb_128:
-; CHECK: vsub(v0.b,v1.b)
-define <128 x i8> @subb_128(<128 x i8> %v0, <128 x i8> %v1) #1 {
-  %p = sub <128 x i8> %v0, %v1
-  ret <128 x i8> %p
-}
-
-; CHECK-LABEL: subh_64:
-; CHECK: vsub(v0.h,v1.h)
-define <32 x i16> @subh_64(<32 x i16> %v0, <32 x i16> %v1) #0 {
-  %p = sub <32 x i16> %v0, %v1
-  ret <32 x i16> %p
-}
-
-; CHECK-LABEL: subh_128:
-; CHECK: vsub(v0.h,v1.h)
-define <64 x i16> @subh_128(<64 x i16> %v0, <64 x i16> %v1) #1 {
-  %p = sub <64 x i16> %v0, %v1
-  ret <64 x i16> %p
-}
-
-; CHECK-LABEL: subw_64:
-; CHECK: vsub(v0.w,v1.w)
-define <16 x i32> @subw_64(<16 x i32> %v0, <16 x i32> %v1) #0 {
-  %p = sub <16 x i32> %v0, %v1
-  ret <16 x i32> %p
-}
-
-; CHECK-LABEL: subw_128:
-; CHECK: vsub(v0.w,v1.w)
-define <32 x i32> @subw_128(<32 x i32> %v0, <32 x i32> %v1) #1 {
-  %p = sub <32 x i32> %v0, %v1
-  ret <32 x i32> %p
-}
-
-; --- mul
-
-; CHECK-LABEL: mpyb_64:
-; CHECK: v[[H0:[0-9]+]]:[[L0:[0-9]+]].h = vmpy(v0.b,v1.b)
-; CHECK: vshuffe(v[[H0]].b,v[[L0]].b)
-define <64 x i8> @mpyb_64(<64 x i8> %v0, <64 x i8> %v1) #0 {
-  %p = mul <64 x i8> %v0, %v1
-  ret <64 x i8> %p
-}
-
-; CHECK-LABEL: mpyb_128:
-; CHECK: v[[H0:[0-9]+]]:[[L0:[0-9]+]].h = vmpy(v0.b,v1.b)
-; CHECK: vshuffe(v[[H0]].b,v[[L0]].b)
-define <128 x i8> @mpyb_128(<128 x i8> %v0, <128 x i8> %v1) #1 {
-  %p = mul <128 x i8> %v0, %v1
-  ret <128 x i8> %p
-}
-
-; CHECK-LABEL: mpyh_64:
-; CHECK: vmpyi(v0.h,v1.h)
-define <32 x i16> @mpyh_64(<32 x i16> %v0, <32 x i16> %v1) #0 {
-  %p = mul <32 x i16> %v0, %v1
-  ret <32 x i16> %p
-}
-
-; CHECK-LABEL: mpyh_128:
-; CHECK: vmpyi(v0.h,v1.h)
-define <64 x i16> @mpyh_128(<64 x i16> %v0, <64 x i16> %v1) #1 {
-  %p = mul <64 x i16> %v0, %v1
-  ret <64 x i16> %p
-}
-
-; CHECK-LABEL: mpyw_64:
-; CHECK: v[[V0:[0-9]+]].w = vmpyieo(v0.h,v1.h)
-; CHECK: v[[V0]].w += vmpyie(v0.w,v1.uh)
-define <16 x i32> @mpyw_64(<16 x i32> %v0, <16 x i32> %v1) #0 {
-  %p = mul <16 x i32> %v0, %v1
-  ret <16 x i32> %p
-}
-
-; CHECK-LABEL: mpyw_128:
-; CHECK: v[[V0:[0-9]+]].w = vmpyieo(v0.h,v1.h)
-; CHECK: v[[V0]].w += vmpyie(v0.w,v1.uh)
-define <32 x i32> @mpyw_128(<32 x i32> %v0, <32 x i32> %v1) #1 {
-  %p = mul <32 x i32> %v0, %v1
-  ret <32 x i32> %p
-}
-
-attributes #0 = { nounwind "target-cpu"="hexagonv60" "target-features"="+hvx,+hvx-length64b" }
-attributes #1 = { nounwind "target-cpu"="hexagonv60" "target-features"="+hvx,+hvx-length128b" }
+attributes #0 = { nounwind "target-cpu"="hexagonv73" "target-features"="+hvxv73,+hvx-length64b" }
+attributes #1 = { nounwind "target-cpu"="hexagonv73" "target-features"="+hvxv73,+hvx-length128b" }

llvm/test/CodeGen/Hexagon/autohvx/vector-compare-128b.ll

@@ -573,4 +573,137 @@ define <32 x i32> @test_2i(<32 x i32> %v0, <32 x i32> %v1, <32 x i32> %v2) #0 {
   ret <32 x i32> %t1
 }
 
-attributes #0 = { nounwind readnone "target-cpu"="hexagonv60" "target-features"="+hvx,+hvx-length128b" }
+; --- Float32
+
+; CHECK-LABEL: test_2j:
+; CHECK: q[[Q2J0:[0-3]]] = vcmp.eq(v0.w,v1.w)
+; CHECK: v0 = vmux(q[[Q2J0]],v0,v1)
+define <32 x float> @test_2j(<32 x float> %v0, <32 x float> %v1) #1 {
+  %t0 = fcmp oeq <32 x float> %v0, %v1
+  %t1 = select <32 x i1> %t0, <32 x float> %v0, <32 x float> %v1
+  ret <32 x float> %t1
+}
+
+; CHECK-LABEL: test_2k:
+; CHECK: q[[Q2K0:[0-3]]] = vcmp.eq(v0.w,v1.w)
+; CHECK: v0 = vmux(q[[Q2K0]],v1,v0)
+define <32 x float> @test_2k(<32 x float> %v0, <32 x float> %v1) #1 {
+  %t0 = fcmp one <32 x float> %v0, %v1
+  %t1 = select <32 x i1> %t0, <32 x float> %v0, <32 x float> %v1
+  ret <32 x float> %t1
+}
+
+; CHECK-LABEL: test_2l:
+; CHECK: v0.sf = vmin(v1.sf,v0.sf)
+define <32 x float> @test_2l(<32 x float> %v0, <32 x float> %v1) #1 {
+  %t0 = fcmp olt <32 x float> %v0, %v1
+  %t1 = select <32 x i1> %t0, <32 x float> %v0, <32 x float> %v1
+  ret <32 x float> %t1
+}
+
+; CHECK-LABEL: test_2m:
+; CHECK: q[[Q2M0:[0-3]]] = vcmp.gt(v0.sf,v1.sf)
+; CHECK: v0 = vmux(q[[Q2M0]],v1,v0)
+define <32 x float> @test_2m(<32 x float> %v0, <32 x float> %v1) #1 {
+  %t0 = fcmp ole <32 x float> %v0, %v1
+  %t1 = select <32 x i1> %t0, <32 x float> %v0, <32 x float> %v1
+  ret <32 x float> %t1
+}
+
+; CHECK-LABEL: test_2n:
+; CHECK: v0.sf = vmax(v0.sf,v1.sf)
+define <32 x float> @test_2n(<32 x float> %v0, <32 x float> %v1) #1 {
+  %t0 = fcmp ogt <32 x float> %v0, %v1
+  %t1 = select <32 x i1> %t0, <32 x float> %v0, <32 x float> %v1
+  ret <32 x float> %t1
+}
+
+; CHECK-LABEL: test_2o:
+; CHECK: q[[Q2O0:[0-3]]] = vcmp.gt(v1.sf,v0.sf)
+; CHECK: v0 = vmux(q[[Q2O0]],v1,v0)
+define <32 x float> @test_2o(<32 x float> %v0, <32 x float> %v1) #1 {
+  %t0 = fcmp oge <32 x float> %v0, %v1
+  %t1 = select <32 x i1> %t0, <32 x float> %v0, <32 x float> %v1
+  ret <32 x float> %t1
+}
+
+; CHECK-LABEL: test_2p:
+; CHECK: r[[R2P0:[0-9]*]] = ##16843009
+; CHECK: q[[Q2P1:[0-3]]] = vand(v2,r[[R2P0]])
+; CHECK: q[[Q2P1:[0-3]]] &= vcmp.eq(v0.w,v1.w)
+; CHECK: v0 = vmux(q[[Q2P1]],v0,v1)
+define <32 x float> @test_2p(<32 x float> %v0, <32 x float> %v1, <32 x i32> %v2) #1 {
+  %q0 = fcmp oeq <32 x float> %v0, %v1
+  %q1 = trunc <32 x i32> %v2 to <32 x i1>
+  %q2 = and <32 x i1> %q0, %q1
+  %t1 = select <32 x i1> %q2, <32 x float> %v0, <32 x float> %v1
+  ret <32 x float> %t1
+}
+
+; CHECK-LABEL: test_2q:
+; CHECK: r[[R2Q0:[0-9]*]] = ##16843009
+; CHECK: q[[Q2Q1:[0-3]]] = vand(v2,r[[R2Q0]])
+; CHECK: q[[Q2Q1:[0-3]]] |= vcmp.eq(v0.w,v1.w)
+; CHECK: v0 = vmux(q[[Q2Q1]],v0,v1)
+define <32 x float> @test_2q(<32 x float> %v0, <32 x float> %v1, <32 x i32> %v2) #1 {
+  %q0 = fcmp oeq <32 x float> %v0, %v1
+  %q1 = trunc <32 x i32> %v2 to <32 x i1>
+  %q2 = or <32 x i1> %q0, %q1
+  %t1 = select <32 x i1> %q2, <32 x float> %v0, <32 x float> %v1
+  ret <32 x float> %t1
+}
+
+; CHECK-LABEL: test_2r:
+; CHECK: r[[R2R0:[0-9]*]] = ##16843009
+; CHECK: q[[Q2R1:[0-3]]] = vand(v2,r[[R2R0]])
+; CHECK: q[[Q2R1:[0-3]]] ^= vcmp.eq(v0.w,v1.w)
+; CHECK: v0 = vmux(q[[Q2R1]],v0,v1)
+define <32 x float> @test_2r(<32 x float> %v0, <32 x float> %v1, <32 x i32> %v2) #1 {
+  %q0 = fcmp oeq <32 x float> %v0, %v1
+  %q1 = trunc <32 x i32> %v2 to <32 x i1>
+  %q2 = xor <32 x i1> %q0, %q1
+  %t1 = select <32 x i1> %q2, <32 x float> %v0, <32 x float> %v1
+  ret <32 x float> %t1
+}
+
+; CHECK-LABEL: test_2s:
+; CHECK: r[[R2S0:[0-9]*]] = ##16843009
+; CHECK: q[[Q2S1:[0-3]]] = vand(v2,r[[R2S0]])
+; CHECK: q[[Q2S1:[0-3]]] &= vcmp.gt(v0.sf,v1.sf)
+; CHECK: v0 = vmux(q[[Q2R1]],v0,v1)
+define <32 x float> @test_2s(<32 x float> %v0, <32 x float> %v1, <32 x i32> %v2) #1 {
+  %q0 = fcmp ogt <32 x float> %v0, %v1
+  %q1 = trunc <32 x i32> %v2 to <32 x i1>
+  %q2 = and <32 x i1> %q0, %q1
+  %t1 = select <32 x i1> %q2, <32 x float> %v0, <32 x float> %v1
+  ret <32 x float> %t1
+}
+
+; CHECK-LABEL: test_2t:
+; CHECK: r[[R2T0:[0-9]*]] = ##16843009
+; CHECK: q[[Q2T1:[0-3]]] = vand(v2,r[[R2T0]])
+; CHECK: q[[Q2T1:[0-3]]] |= vcmp.gt(v0.sf,v1.sf)
+; CHECK: v0 = vmux(q[[Q2T1]],v0,v1)
+define <32 x float> @test_2t(<32 x float> %v0, <32 x float> %v1, <32 x i32> %v2) #1 {
+  %q0 = fcmp ogt <32 x float> %v0, %v1
+  %q1 = trunc <32 x i32> %v2 to <32 x i1>
+  %q2 = or <32 x i1> %q0, %q1
+  %t1 = select <32 x i1> %q2, <32 x float> %v0, <32 x float> %v1
+  ret <32 x float> %t1
+}
+
+; CHECK-LABEL: test_2u:
+; CHECK: r[[R2U0:[0-9]*]] = ##16843009
+; CHECK: q[[Q2U1:[0-3]]] = vand(v2,r[[R2U0]])
+; CHECK: q[[Q2U1:[0-3]]] ^= vcmp.gt(v0.sf,v1.sf)
+; CHECK: v0 = vmux(q[[Q2U1]],v0,v1)
+define <32 x float> @test_2u(<32 x float> %v0, <32 x float> %v1, <32 x i32> %v2) #1 {
+  %q0 = fcmp ogt <32 x float> %v0, %v1
+  %q1 = trunc <32 x i32> %v2 to <32 x i1>
+  %q2 = xor <32 x i1> %q0, %q1
+  %t1 = select <32 x i1> %q2, <32 x float> %v0, <32 x float> %v1
+  ret <32 x float> %t1
+}
+
+attributes #0 = { nounwind readnone "target-cpu"="hexagonv73" "target-features"="+hvxv73,+hvx-length128b" }
+attributes #1 = { nounwind readnone "target-cpu"="hexagonv68" "target-features"="+hvxv68,+hvx-length128b,+hvx-qfloat" }

llvm/test/CodeGen/Hexagon/autohvx/vector-compare-64b.ll

@@ -574,4 +574,4 @@ define <16 x i32> @test_2i(<16 x i32> %v0, <16 x i32> %v1, <16 x i32> %v2) #0 {
   ret <16 x i32> %t1
 }
 
-attributes #0 = { nounwind readnone "target-cpu"="hexagonv60" "target-features"="+hvx,+hvx-length64b" }
+attributes #0 = { nounwind readnone "target-cpu"="hexagonv73" "target-features"="+hvxv73,+hvx-length64b" }