[DAG] Fold trunc(avg(x,y)) for avgceil/floor u/s nodes if they have sufficient leading zero/sign bits-4

Author: houngkoungting

llvm/test/CodeGen/AArch64/trunc-avg-fold.ll

@@ -1,15 +1,13 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
 ; RUN: llc -mtriple=aarch64-- -O2 -mattr=+neon < %s | FileCheck %s
 
-
 define <8 x i8> @test_avgceil_u(<8 x i16> %a, <8 x i16> %b) {
 ; CHECK-LABEL: test_avgceil_u:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    xtn v0.8b, v0.8h
 ; CHECK-NEXT:    xtn v1.8b, v1.8h
 ; CHECK-NEXT:    uhadd v0.8b, v0.8b, v1.8b
 ; CHECK-NEXT:    ret
-
   %mask = insertelement <8 x i16> poison, i16 255, i32 0
   %mask.splat = shufflevector <8 x i16> %mask, <8 x i16> poison, <8 x i32> zeroinitializer
   %ta16 = and <8 x i16> %a, %mask.splat
@@ -20,80 +18,67 @@ define <8 x i8> @test_avgceil_u(<8 x i16> %a, <8 x i16> %b) {
   ret <8 x i8> %res
 }
 
-
 define <8 x i8> @test_avgceil_s(<8 x i16> %a, <8 x i16> %b) {
 ; CHECK-LABEL: test_avgceil_s:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sqxtn v0.8b, v0.8h
 ; CHECK-NEXT:    sqxtn v1.8b, v1.8h
 ; CHECK-NEXT:    shadd v0.8b, v0.8b, v1.8b
 ; CHECK-NEXT:    ret
-
-  %smin = insertelement <8 x i16> poison, i16 -128, i32 0
-  %smax = insertelement <8 x i16> poison, i16 127, i32 0
-  %min = shufflevector <8 x i16> %smin, <8 x i16> poison, <8 x i32> zeroinitializer
-  %max = shufflevector <8 x i16> %smax, <8 x i16> poison, <8 x i32> zeroinitializer
-
-  %ta16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> %a, <8 x i16> %max)
-  %ta16.clamped = call <8 x i16> @llvm.smax.v8i16(<8 x i16> %ta16, <8 x i16> %min)
-  %tb16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> %b, <8 x i16> %max)
-  %tb16.clamped = call <8 x i16> @llvm.smax.v8i16(<8 x i16> %tb16, <8 x i16> %min)
-
+  %min = insertelement <8 x i16> poison, i16 -128, i32 0
+  %min.splat = shufflevector <8 x i16> %min, <8 x i16> poison, <8 x i32> zeroinitializer
+  %max = insertelement <8 x i16> poison, i16 127, i32 0
+  %max.splat = shufflevector <8 x i16> %max, <8 x i16> poison, <8 x i32> zeroinitializer
+  %ta16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> %a, <8 x i16> %max.splat)
+  %ta16.clamped = call <8 x i16> @llvm.smax.v8i16(<8 x i16> %ta16, <8 x i16> %min.splat)
+  %tb16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> %b, <8 x i16> %max.splat)
+  %tb16.clamped = call <8 x i16> @llvm.smax.v8i16(<8 x i16> %tb16, <8 x i16> %min.splat)
   %ta8 = trunc <8 x i16> %ta16.clamped to <8 x i8>
   %tb8 = trunc <8 x i16> %tb16.clamped to <8 x i8>
   %res = call <8 x i8> @llvm.aarch64.neon.shadd.v8i8(<8 x i8> %ta8, <8 x i8> %tb8)
   ret <8 x i8> %res
 }
 
-
 define <8 x i8> @test_avgfloor_u(<8 x i16> %a, <8 x i16> %b) {
 ; CHECK-LABEL: test_avgfloor_u:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    xtn v0.8b, v0.8h
 ; CHECK-NEXT:    xtn v1.8b, v1.8h
-; CHECK-NEXT:    urhadd v0.8b, v0.8b, v1.8b
+; CHECK-NEXT:    uhadd v0.8b, v0.8b, v1.8b
 ; CHECK-NEXT:    ret
-
-  %mask = insertelement <8 x i16> undef, i16 255, i32 0
-  %mask.splat = shufflevector <8 x i16> %mask, <8 x i16> undef, <8 x i32> zeroinitializer
+  %mask = insertelement <8 x i16> poison, i16 255, i32 0
+  %mask.splat = shufflevector <8 x i16> %mask, <8 x i16> poison, <8 x i32> zeroinitializer
   %ta16 = and <8 x i16> %a, %mask.splat
   %tb16 = and <8 x i16> %b, %mask.splat
   %ta8 = trunc <8 x i16> %ta16 to <8 x i8>
   %tb8 = trunc <8 x i16> %tb16 to <8 x i8>
-  %res = call <8 x i8> @llvm.aarch64.neon.urhadd.v8i8(<8 x i8> %ta8, <8 x i8> %tb8)
+  %res = call <8 x i8> @llvm.aarch64.neon.uhadd.v8i8(<8 x i8> %ta8, <8 x i8> %tb8)
   ret <8 x i8> %res
 }
 
-
 define <8 x i8> @test_avgfloor_s(<8 x i16> %a, <8 x i16> %b) {
 ; CHECK-LABEL: test_avgfloor_s:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sqxtn v0.8b, v0.8h
 ; CHECK-NEXT:    sqxtn v1.8b, v1.8h
-; CHECK-NEXT:    srhadd v0.8b, v0.8b, v1.8b
+; CHECK-NEXT:    shadd v0.8b, v0.8b, v1.8b
 ; CHECK-NEXT:    ret
-
-  %smin = insertelement <8 x i16> poison, i16 -128, i32 0
-  %smax = insertelement <8 x i16> poison, i16 127, i32 0
-  %min = shufflevector <8 x i16> %smin, <8 x i16> poison, <8 x i32> zeroinitializer
-  %max = shufflevector <8 x i16> %smax, <8 x i16> poison, <8 x i32> zeroinitializer
-
-  %ta16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> %a, <8 x i16> %max)
-  %ta16.clamped = call <8 x i16> @llvm.smax.v8i16(<8 x i16> %ta16, <8 x i16> %min)
-  %tb16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> %b, <8 x i16> %max)
-  %tb16.clamped = call <8 x i16> @llvm.smax.v8i16(<8 x i16> %tb16, <8 x i16> %min)
-
+  %min = insertelement <8 x i16> poison, i16 -128, i32 0
+  %min.splat = shufflevector <8 x i16> %min, <8 x i16> poison, <8 x i32> zeroinitializer
+  %max = insertelement <8 x i16> poison, i16 127, i32 0
+  %max.splat = shufflevector <8 x i16> %max, <8 x i16> poison, <8 x i32> zeroinitializer
+  %ta16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> %a, <8 x i16> %max.splat)
+  %ta16.clamped = call <8 x i16> @llvm.smax.v8i16(<8 x i16> %ta16, <8 x i16> %min.splat)
+  %tb16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> %b, <8 x i16> %max.splat)
+  %tb16.clamped = call <8 x i16> @llvm.smax.v8i16(<8 x i16> %tb16, <8 x i16> %min.splat)
   %ta8 = trunc <8 x i16> %ta16.clamped to <8 x i8>
   %tb8 = trunc <8 x i16> %tb16.clamped to <8 x i8>
-  %res = call <8 x i8> @llvm.aarch64.neon.srhadd.v8i8(<8 x i8> %ta8, <8 x i8> %tb8)
+  %res = call <8 x i8> @llvm.aarch64.neon.shadd.v8i8(<8 x i8> %ta8, <8 x i8> %tb8)
   ret <8 x i8> %res
 }
 
 declare <8 x i8> @llvm.aarch64.neon.uhadd.v8i8(<8 x i8>, <8 x i8>)
 declare <8 x i8> @llvm.aarch64.neon.shadd.v8i8(<8 x i8>, <8 x i8>)
-declare <8 x i8> @llvm.aarch64.neon.urhadd.v8i8(<8 x i8>, <8 x i8>)
-declare <8 x i8> @llvm.aarch64.neon.srhadd.v8i8(<8 x i8>, <8 x i8>)
-
 declare <8 x i16> @llvm.smin.v8i16(<8 x i16>, <8 x i16>)
 declare <8 x i16> @llvm.smax.v8i16(<8 x i16>, <8 x i16>)