[NFC][AArch64] Add cost model tests for extending loads

[david-arm]

• Added test cases for when loading into a legal type and extending it.

[MattDevereau]

llvm/test/Analysis/CostModel/AArch64/masked_ldst.ll

41

It's a bit weird that this file is called masked_ldst.ll when it doesn't have a single store in it, I'd consider renaming it

[david-arm]

• Rebase.

llvm/test/Analysis/CostModel/AArch64/masked_ldst.ll

entry:
   %v16i8 = call <16 x i8> @llvm.masked.load.v16i8.p0(ptr undef, i32 8, <16 x i1> undef, <16 x i8> undef)
   %v2i16 = call <2 x i16> @llvm.masked.load.v2i16.p0(ptr undef, i32 8, <2 x i1> undef, <2 x i16> undef)
   %v4i16 = call <4 x i16> @llvm.masked.load.v4i16.p0(ptr undef, i32 8, <4 x i1> undef, <4 x i16> undef)
   %v8i16 = call <8 x i16> @llvm.masked.load.v8i16.p0(ptr undef, i32 8, <8 x i1> undef, <8 x i16> undef)
   %v2i32 = call <2 x i32> @llvm.masked.load.v2i32.p0(ptr undef, i32 8, <2 x i1> undef, <2 x i32> undef)
   %v4i32 = call <4 x i32> @llvm.masked.load.v4i32.p0(ptr undef, i32 8, <4 x i1> undef, <4 x i32> undef)
   %v2i64 = call <2 x i64> @llvm.masked.load.v2i64.p0(ptr undef, i32 8, <2 x i1> undef, <2 x i64> undef)
 
   ; Legal fixed-width floating point types
   %v2f16 = call <2 x half> @llvm.masked.load.v2f16.p0(ptr undef, i32 8, <2 x i1> undef, <2 x half> undef)
   %v4f16 = call <4 x half> @llvm.masked.load.v4f16.p0(ptr undef, i32 8, <4 x i1> undef, <4 x half> undef)
   %v8f16 = call <8 x half> @llvm.masked.load.v8f16.p0(ptr undef, i32 8, <8 x i1> undef, <8 x half> undef)
   %v2f32 = call <2 x float> @llvm.masked.load.v2f32.p0(ptr undef, i32 8, <2 x i1> undef, <2 x float> undef)
   %v4f32 = call <4 x float> @llvm.masked.load.v4f32.p0(ptr undef, i32 8, <4 x i1> undef, <4 x float> undef)
   %v2f64 = call <2 x double> @llvm.masked.load.v2f64.p0(ptr undef, i32 8, <2 x i1> undef, <2 x double> undef)
 
   ; A couple of examples of illegal fixed-width types
entry:
   ; A couple of examples of illegal scalable types
   %nxv1i64 = call <vscale x 1 x i64> @llvm.masked.load.nxv1i64.p0(ptr undef, i32 8, <vscale x 1 x i1> undef, <vscale x 1 x i64> undef)
   %nxv4i64 = call <vscale x 4 x i64> @llvm.masked.load.nxv4i64.p0(ptr undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x i64> undef)
   %nxv32f16 = call <vscale x 32 x half> @llvm.masked.load.nxv32f16.p0(ptr undef, i32 8, <vscale x 32 x i1> undef, <vscale x 32 x half> undef)
 
   ret void
 }
 
+
+define void @scalable_ext_loads() {
+; CHECK-LABEL: 'scalable_ext_loads'
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %load.nxv8i8 = call <vscale x 8 x i8> @llvm.masked.load.nxv8i8.p0(ptr undef, i32 8, <vscale x 8 x i1> undef, <vscale x 8 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %zext.nxv8i8to16 = zext <vscale x 8 x i8> %load.nxv8i8 to <vscale x 8 x i16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %load.nxv4i8 = call <vscale x 4 x i8> @llvm.masked.load.nxv4i8.p0(ptr undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %zext.nxv4i8to32 = zext <vscale x 4 x i8> %load.nxv4i8 to <vscale x 4 x i32>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %load.nxv2i8 = call <vscale x 2 x i8> @llvm.masked.load.nxv2i8.p0(ptr undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %zext.nxv2i8to64 = zext <vscale x 2 x i8> %load.nxv2i8 to <vscale x 2 x i64>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %load.nxv4i16 = call <vscale x 4 x i16> @llvm.masked.load.nxv4i16.p0(ptr undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %zext.nxv4i16to32 = zext <vscale x 4 x i16> %load.nxv4i16 to <vscale x 4 x i32>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %load.nxv2i16 = call <vscale x 2 x i16> @llvm.masked.load.nxv2i16.p0(ptr undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %zext.nxv2i16to64 = zext <vscale x 2 x i16> %load.nxv2i16 to <vscale x 2 x i64>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %load.nxv2i32 = call <vscale x 2 x i32> @llvm.masked.load.nxv2i32.p0(ptr undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %zext.nxv2i32to64 = zext <vscale x 2 x i32> %load.nxv2i32 to <vscale x 2 x i64>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %load2.nxv8i8 = call <vscale x 8 x i8> @llvm.masked.load.nxv8i8.p0(ptr undef, i32 8, <vscale x 8 x i1> undef, <vscale x 8 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %sext.nxv8i8to16 = sext <vscale x 8 x i8> %load2.nxv8i8 to <vscale x 8 x i16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %load2.nxv4i8 = call <vscale x 4 x i8> @llvm.masked.load.nxv4i8.p0(ptr undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %sext.nxv4i8to32 = sext <vscale x 4 x i8> %load2.nxv4i8 to <vscale x 4 x i32>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %load2.nxv2i8 = call <vscale x 2 x i8> @llvm.masked.load.nxv2i8.p0(ptr undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %sext.nxv2i8to64 = sext <vscale x 2 x i8> %load2.nxv2i8 to <vscale x 2 x i64>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %load2.nxv4i16 = call <vscale x 4 x i16> @llvm.masked.load.nxv4i16.p0(ptr undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %sext.nxv4i16to32 = sext <vscale x 4 x i16> %load2.nxv4i16 to <vscale x 4 x i32>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %load2.nxv2i16 = call <vscale x 2 x i16> @llvm.masked.load.nxv2i16.p0(ptr undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %sext.nxv2i16to64 = sext <vscale x 2 x i16> %load2.nxv2i16 to <vscale x 2 x i64>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %load2.nxv2i32 = call <vscale x 2 x i32> @llvm.masked.load.nxv2i32.p0(ptr undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %sext.nxv2i32to64 = sext <vscale x 2 x i32> %load2.nxv2i32 to <vscale x 2 x i64>
+
+  %load.nxv8i8 = call <vscale x 8 x i8> @llvm.masked.load.nxv8i8.p0(ptr undef, i32 8, <vscale x 8 x i1> undef, <vscale x 8 x i8> undef)
+  %zext.nxv8i8to16 = zext <vscale x 8 x i8> %load.nxv8i8 to <vscale x 8 x i16>
+  %load.nxv4i8 = call <vscale x 4 x i8> @llvm.masked.load.nxv4i8.p0(ptr undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x i8> undef)
+  %zext.nxv4i8to32 = zext <vscale x 4 x i8> %load.nxv4i8 to <vscale x 4 x i32>
+  %load.nxv2i8 = call <vscale x 2 x i8> @llvm.masked.load.nxv2i8.p0(ptr undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x i8> undef)
+  %zext.nxv2i8to64 = zext <vscale x 2 x i8> %load.nxv2i8 to <vscale x 2 x i64>
+  %load.nxv4i16 = call <vscale x 4 x i16> @llvm.masked.load.nxv4i16.p0(ptr undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x i16> undef)
+  %zext.nxv4i16to32 = zext <vscale x 4 x i16> %load.nxv4i16 to <vscale x 4 x i32>
+  %load.nxv2i16 = call <vscale x 2 x i16> @llvm.masked.load.nxv2i16.p0(ptr undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x i16> undef)
+  %zext.nxv2i16to64 = zext <vscale x 2 x i16> %load.nxv2i16 to <vscale x 2 x i64>
+  %load.nxv2i32 = call <vscale x 2 x i32> @llvm.masked.load.nxv2i32.p0(ptr undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x i32> undef)
+  %zext.nxv2i32to64 = zext <vscale x 2 x i32> %load.nxv2i32 to <vscale x 2 x i64>
+
+  %load2.nxv8i8 = call <vscale x 8 x i8> @llvm.masked.load.nxv8i8.p0(ptr undef, i32 8, <vscale x 8 x i1> undef, <vscale x 8 x i8> undef)
+  %sext.nxv8i8to16 = sext <vscale x 8 x i8> %load2.nxv8i8 to <vscale x 8 x i16>
+  %load2.nxv4i8 = call <vscale x 4 x i8> @llvm.masked.load.nxv4i8.p0(ptr undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x i8> undef)
+  %sext.nxv4i8to32 = sext <vscale x 4 x i8> %load2.nxv4i8 to <vscale x 4 x i32>
+  %load2.nxv2i8 = call <vscale x 2 x i8> @llvm.masked.load.nxv2i8.p0(ptr undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x i8> undef)
+  %sext.nxv2i8to64 = sext <vscale x 2 x i8> %load2.nxv2i8 to <vscale x 2 x i64>
+  %load2.nxv4i16 = call <vscale x 4 x i16> @llvm.masked.load.nxv4i16.p0(ptr undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x i16> undef)
+  %sext.nxv4i16to32 = sext <vscale x 4 x i16> %load2.nxv4i16 to <vscale x 4 x i32>
+  %load2.nxv2i16 = call <vscale x 2 x i16> @llvm.masked.load.nxv2i16.p0(ptr undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x i16> undef)
+  %sext.nxv2i16to64 = sext <vscale x 2 x i16> %load2.nxv2i16 to <vscale x 2 x i64>
+  %load2.nxv2i32 = call <vscale x 2 x i32> @llvm.masked.load.nxv2i32.p0(ptr undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x i32> undef)
+  %sext.nxv2i32to64 = sext <vscale x 2 x i32> %load2.nxv2i32 to <vscale x 2 x i64>
+
+  ret void
+}
+
+
 declare <2 x i8> @llvm.masked.load.v2i8.p0(ptr, i32, <2 x i1>, <2 x i8>)
 declare <4 x i8> @llvm.masked.load.v4i8.p0(ptr, i32, <4 x i1>, <4 x i8>)
 declare <8 x i8> @llvm.masked.load.v8i8.p0(ptr, i32, <8 x i1>, <8 x i8>)
 declare <16 x i8> @llvm.masked.load.v16i8.p0(ptr, i32, <16 x i1>, <16 x i8>)
 declare <2 x i16> @llvm.masked.load.v2i16.p0(ptr, i32, <2 x i1>, <2 x i16>)
 declare <4 x i16> @llvm.masked.load.v4i16.p0(ptr, i32, <4 x i1>, <4 x i16>)
 declare <8 x i16> @llvm.masked.load.v8i16.p0(ptr, i32, <8 x i1>, <8 x i16>)
 declare <2 x i32> @llvm.masked.load.v2i32.p0(ptr, i32, <2 x i1>, <2 x i32>)

llvm/test/Analysis/CostModel/AArch64/sve-ldst.ll

 ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: store <vscale x 32 x i8>
 ; CHECK-NEXT: Cost Model: Invalid cost for instruction: store <vscale x 1 x i64>
   store <vscale x 8 x i8> undef, ptr undef
   store <vscale x 16 x i8> undef, ptr undef
   store <vscale x 32 x i8> undef, ptr undef
   store <vscale x 1 x i64> undef, ptr undef
   ret void
 }
+
+define void @scalable_ext_loads() {
+; CHECK-LABEL: 'scalable_ext_loads'
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %load.nxv8i8 = load <vscale x 8 x i8>, ptr undef, align 8
+; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction:   %zext.nxv8i8to16 = zext <vscale x 8 x i8> %load.nxv8i8 to <vscale x 8 x i16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %load.nxv4i8 = load <vscale x 4 x i8>, ptr undef, align 4
+; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction:   %zext.nxv4i8to32 = zext <vscale x 4 x i8> %load.nxv4i8 to <vscale x 4 x i32>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %load.nxv2i8 = load <vscale x 2 x i8>, ptr undef, align 2
+; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction:   %zext.nxv2i8to64 = zext <vscale x 2 x i8> %load.nxv2i8 to <vscale x 2 x i64>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %load.nxv4i16 = load <vscale x 4 x i16>, ptr undef, align 8
+; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction:   %zext.nxv4i16to32 = zext <vscale x 4 x i16> %load.nxv4i16 to <vscale x 4 x i32>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %load.nxv2i16 = load <vscale x 2 x i16>, ptr undef, align 4
+; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction:   %zext.nxv2i16to64 = zext <vscale x 2 x i16> %load.nxv2i16 to <vscale x 2 x i64>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %load.nxv2i32 = load <vscale x 2 x i32>, ptr undef, align 8
+; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction:   %zext.nxv2i32to64 = zext <vscale x 2 x i32> %load.nxv2i32 to <vscale x 2 x i64>
+
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %load2.nxv8i8 = load <vscale x 8 x i8>, ptr undef, align 8
+; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction:   %sext.nxv8i8to16 = sext <vscale x 8 x i8> %load2.nxv8i8 to <vscale x 8 x i16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %load2.nxv4i8 = load <vscale x 4 x i8>, ptr undef, align 4
+; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction:   %sext.nxv4i8to32 = sext <vscale x 4 x i8> %load2.nxv4i8 to <vscale x 4 x i32>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %load2.nxv2i8 = load <vscale x 2 x i8>, ptr undef, align 2
+; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction:   %sext.nxv2i8to64 = sext <vscale x 2 x i8> %load2.nxv2i8 to <vscale x 2 x i64>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %load2.nxv4i16 = load <vscale x 4 x i16>, ptr undef, align 8
+; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction:   %sext.nxv4i16to32 = sext <vscale x 4 x i16> %load2.nxv4i16 to <vscale x 4 x i32>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %load2.nxv2i16 = load <vscale x 2 x i16>, ptr undef, align 4
+; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction:   %sext.nxv2i16to64 = sext <vscale x 2 x i16> %load2.nxv2i16 to <vscale x 2 x i64>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %load2.nxv2i32 = load <vscale x 2 x i32>, ptr undef, align 8
+; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction:   %sext.nxv2i32to64 = sext <vscale x 2 x i32> %load2.nxv2i32 to <vscale x 2 x i64>
+  %load.nxv8i8 = load <vscale x 8 x i8>, ptr undef
+  %zext.nxv8i8to16 = zext <vscale x 8 x i8> %load.nxv8i8 to <vscale x 8 x i16>
+  %load.nxv4i8 = load <vscale x 4 x i8>, ptr undef
+  %zext.nxv4i8to32 = zext <vscale x 4 x i8> %load.nxv4i8 to <vscale x 4 x i32>
+  %load.nxv2i8 = load <vscale x 2 x i8>, ptr undef
+  %zext.nxv2i8to64 = zext <vscale x 2 x i8> %load.nxv2i8 to <vscale x 2 x i64>
+  %load.nxv4i16 = load <vscale x 4 x i16>, ptr undef
+  %zext.nxv4i16to32 = zext <vscale x 4 x i16> %load.nxv4i16 to <vscale x 4 x i32>
+  %load.nxv2i16 = load <vscale x 2 x i16>, ptr undef
+  %zext.nxv2i16to64 = zext <vscale x 2 x i16> %load.nxv2i16 to <vscale x 2 x i64>
+  %load.nxv2i32 = load <vscale x 2 x i32>, ptr undef
+  %zext.nxv2i32to64 = zext <vscale x 2 x i32> %load.nxv2i32 to <vscale x 2 x i64>
+
+  %load2.nxv8i8 = load <vscale x 8 x i8>, ptr undef
+  %sext.nxv8i8to16 = sext <vscale x 8 x i8> %load2.nxv8i8 to <vscale x 8 x i16>
+  %load2.nxv4i8 = load <vscale x 4 x i8>, ptr undef
+  %sext.nxv4i8to32 = sext <vscale x 4 x i8> %load2.nxv4i8 to <vscale x 4 x i32>
+  %load2.nxv2i8 = load <vscale x 2 x i8>, ptr undef
+  %sext.nxv2i8to64 = sext <vscale x 2 x i8> %load2.nxv2i8 to <vscale x 2 x i64>
+  %load2.nxv4i16 = load <vscale x 4 x i16>, ptr undef
+  %sext.nxv4i16to32 = sext <vscale x 4 x i16> %load2.nxv4i16 to <vscale x 4 x i32>
+  %load2.nxv2i16 = load <vscale x 2 x i16>, ptr undef
+  %sext.nxv2i16to64 = sext <vscale x 2 x i16> %load2.nxv2i16 to <vscale x 2 x i64>
+  %load2.nxv2i32 = load <vscale x 2 x i32>, ptr undef
+  %sext.nxv2i32to64 = sext <vscale x 2 x i32> %load2.nxv2i32 to <vscale x 2 x i64>
+  ret void
+}
+
+;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
+; CHECK: {{.*}}