[llvm] b7c3de8 - [ARM] MVE min/max cost tests. NFC
David Green via llvm-commits
llvm-commits at lists.llvm.org
Sat Feb 13 03:12:24 PST 2021
Author: David Green
Date: 2021-02-13T11:12:12Z
New Revision: b7c3de8d5a3d10dd976de796d73fc3f395a832e0
URL: https://github.com/llvm/llvm-project/commit/b7c3de8d5a3d10dd976de796d73fc3f395a832e0
DIFF: https://github.com/llvm/llvm-project/commit/b7c3de8d5a3d10dd976de796d73fc3f395a832e0.diff
LOG: [ARM] MVE min/max cost tests. NFC
Added:
llvm/test/Analysis/CostModel/ARM/mve-minmax.ll
Modified:
Removed:
################################################################################
diff --git a/llvm/test/Analysis/CostModel/ARM/mve-minmax.ll b/llvm/test/Analysis/CostModel/ARM/mve-minmax.ll
new file mode 100644
index 000000000000..87007e234016
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/ARM/mve-minmax.ll
@@ -0,0 +1,659 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt -cost-model -analyze -mtriple=thumbv8.1m.main-none-eabi -mattr=+mve < %s | FileCheck %s --check-prefixes=MVE-RECIP,MVEI-RECIP
+; RUN: opt -cost-model -analyze -cost-kind=code-size -mtriple=thumbv8.1m.main-none-eabi -mattr=+mve < %s | FileCheck %s --check-prefixes=MVE-SIZE,MVEI-SIZE
+; RUN: opt -cost-model -analyze -mtriple=thumbv8.1m.-none-eabimain -mattr=+mve.fp < %s | FileCheck %s --check-prefixes=MVE-RECIP,MVEF-RECIP
+; RUN: opt -cost-model -analyze -cost-kind=code-size -mtriple=thumbv8.1m.main-none-eabi -mattr=+mve.fp < %s | FileCheck %s --check-prefixes=MVE-SIZE,MVEF-SIZE
+
+declare i64 @llvm.smin.i64(i64, i64)
+declare <2 x i64> @llvm.smin.v2i64(<2 x i64>, <2 x i64>)
+declare <4 x i64> @llvm.smin.v4i64(<4 x i64>, <4 x i64>)
+declare <8 x i64> @llvm.smin.v8i64(<8 x i64>, <8 x i64>)
+
+declare i32 @llvm.smin.i32(i32, i32)
+declare <2 x i32> @llvm.smin.v2i32(<2 x i32>, <2 x i32>)
+declare <4 x i32> @llvm.smin.v4i32(<4 x i32>, <4 x i32>)
+declare <8 x i32> @llvm.smin.v8i32(<8 x i32>, <8 x i32>)
+declare <16 x i32> @llvm.smin.v16i32(<16 x i32>, <16 x i32>)
+
+declare i16 @llvm.smin.i16(i16, i16)
+declare <2 x i16> @llvm.smin.v2i16(<2 x i16>, <2 x i16>)
+declare <4 x i16> @llvm.smin.v4i16(<4 x i16>, <4 x i16>)
+declare <8 x i16> @llvm.smin.v8i16(<8 x i16>, <8 x i16>)
+declare <16 x i16> @llvm.smin.v16i16(<16 x i16>, <16 x i16>)
+declare <32 x i16> @llvm.smin.v32i16(<32 x i16>, <32 x i16>)
+
+declare i8 @llvm.smin.i8(i8, i8)
+declare <2 x i8> @llvm.smin.v2i8(<2 x i8>, <2 x i8>)
+declare <4 x i8> @llvm.smin.v4i8(<4 x i8>, <4 x i8>)
+declare <8 x i8> @llvm.smin.v8i8(<8 x i8>, <8 x i8>)
+declare <16 x i8> @llvm.smin.v16i8(<16 x i8>, <16 x i8>)
+declare <32 x i8> @llvm.smin.v32i8(<32 x i8>, <32 x i8>)
+declare <64 x i8> @llvm.smin.v64i8(<64 x i8>, <64 x i8>)
+
+define i32 @smin(i32 %arg) {
+; MVE-RECIP-LABEL: 'smin'
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 304 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I32 = call <2 x i32> @llvm.smin.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I16 = call <2 x i16> @llvm.smin.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I16 = call <4 x i16> @llvm.smin.v4i16(<4 x i16> undef, <4 x i16> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I8 = call <2 x i8> @llvm.smin.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.smin.v4i8(<4 x i8> undef, <4 x i8> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I8 = call <8 x i8> @llvm.smin.v8i8(<8 x i8> undef, <8 x i8> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; MVE-SIZE-LABEL: 'smin'
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I32 = call <2 x i32> @llvm.smin.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I16 = call <2 x i16> @llvm.smin.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I16 = call <4 x i16> @llvm.smin.v4i16(<4 x i16> undef, <4 x i16> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I8 = call <2 x i8> @llvm.smin.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I8 = call <4 x i8> @llvm.smin.v4i8(<4 x i8> undef, <4 x i8> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I8 = call <8 x i8> @llvm.smin.v8i8(<8 x i8> undef, <8 x i8> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
+ %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
+ %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
+ %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
+
+ %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
+ %V2I32 = call <2 x i32> @llvm.smin.v2i32(<2 x i32> undef, <2 x i32> undef)
+ %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
+ %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
+ %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
+
+ %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
+ %V2I16 = call <2 x i16> @llvm.smin.v2i16(<2 x i16> undef, <2 x i16> undef)
+ %V4I16 = call <4 x i16> @llvm.smin.v4i16(<4 x i16> undef, <4 x i16> undef)
+ %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
+ %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
+ %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
+
+ %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
+ %V2I8 = call <2 x i8> @llvm.smin.v2i8(<2 x i8> undef, <2 x i8> undef)
+ %V4I8 = call <4 x i8> @llvm.smin.v4i8(<4 x i8> undef, <4 x i8> undef)
+ %V8I8 = call <8 x i8> @llvm.smin.v8i8(<8 x i8> undef, <8 x i8> undef)
+ %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
+ %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
+ %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
+
+ ret i32 undef
+}
+
+
+declare i64 @llvm.smax.i64(i64, i64)
+declare <2 x i64> @llvm.smax.v2i64(<2 x i64>, <2 x i64>)
+declare <4 x i64> @llvm.smax.v4i64(<4 x i64>, <4 x i64>)
+declare <8 x i64> @llvm.smax.v8i64(<8 x i64>, <8 x i64>)
+
+declare i32 @llvm.smax.i32(i32, i32)
+declare <2 x i32> @llvm.smax.v2i32(<2 x i32>, <2 x i32>)
+declare <4 x i32> @llvm.smax.v4i32(<4 x i32>, <4 x i32>)
+declare <8 x i32> @llvm.smax.v8i32(<8 x i32>, <8 x i32>)
+declare <16 x i32> @llvm.smax.v16i32(<16 x i32>, <16 x i32>)
+
+declare i16 @llvm.smax.i16(i16, i16)
+declare <2 x i16> @llvm.smax.v2i16(<2 x i16>, <2 x i16>)
+declare <4 x i16> @llvm.smax.v4i16(<4 x i16>, <4 x i16>)
+declare <8 x i16> @llvm.smax.v8i16(<8 x i16>, <8 x i16>)
+declare <16 x i16> @llvm.smax.v16i16(<16 x i16>, <16 x i16>)
+declare <32 x i16> @llvm.smax.v32i16(<32 x i16>, <32 x i16>)
+
+declare i8 @llvm.smax.i8(i8, i8)
+declare <2 x i8> @llvm.smax.v2i8(<2 x i8>, <2 x i8>)
+declare <4 x i8> @llvm.smax.v4i8(<4 x i8>, <4 x i8>)
+declare <8 x i8> @llvm.smax.v8i8(<8 x i8>, <8 x i8>)
+declare <16 x i8> @llvm.smax.v16i8(<16 x i8>, <16 x i8>)
+declare <32 x i8> @llvm.smax.v32i8(<32 x i8>, <32 x i8>)
+declare <64 x i8> @llvm.smax.v64i8(<64 x i8>, <64 x i8>)
+
+define i32 @smax(i32 %arg) {
+; MVE-RECIP-LABEL: 'smax'
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 304 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I32 = call <2 x i32> @llvm.smax.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I16 = call <2 x i16> @llvm.smax.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I16 = call <4 x i16> @llvm.smax.v4i16(<4 x i16> undef, <4 x i16> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I8 = call <2 x i8> @llvm.smax.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.smax.v4i8(<4 x i8> undef, <4 x i8> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I8 = call <8 x i8> @llvm.smax.v8i8(<8 x i8> undef, <8 x i8> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; MVE-SIZE-LABEL: 'smax'
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I32 = call <2 x i32> @llvm.smax.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I16 = call <2 x i16> @llvm.smax.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I16 = call <4 x i16> @llvm.smax.v4i16(<4 x i16> undef, <4 x i16> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I8 = call <2 x i8> @llvm.smax.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I8 = call <4 x i8> @llvm.smax.v4i8(<4 x i8> undef, <4 x i8> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I8 = call <8 x i8> @llvm.smax.v8i8(<8 x i8> undef, <8 x i8> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
+ %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
+ %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
+ %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
+
+ %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
+ %V2I32 = call <2 x i32> @llvm.smax.v2i32(<2 x i32> undef, <2 x i32> undef)
+ %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
+ %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
+ %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
+
+ %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
+ %V2I16 = call <2 x i16> @llvm.smax.v2i16(<2 x i16> undef, <2 x i16> undef)
+ %V4I16 = call <4 x i16> @llvm.smax.v4i16(<4 x i16> undef, <4 x i16> undef)
+ %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
+ %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
+ %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
+
+ %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
+ %V2I8 = call <2 x i8> @llvm.smax.v2i8(<2 x i8> undef, <2 x i8> undef)
+ %V4I8 = call <4 x i8> @llvm.smax.v4i8(<4 x i8> undef, <4 x i8> undef)
+ %V8I8 = call <8 x i8> @llvm.smax.v8i8(<8 x i8> undef, <8 x i8> undef)
+ %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
+ %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
+ %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
+
+ ret i32 undef
+}
+
+
+
+declare i64 @llvm.umin.i64(i64, i64)
+declare <2 x i64> @llvm.umin.v2i64(<2 x i64>, <2 x i64>)
+declare <4 x i64> @llvm.umin.v4i64(<4 x i64>, <4 x i64>)
+declare <8 x i64> @llvm.umin.v8i64(<8 x i64>, <8 x i64>)
+
+declare i32 @llvm.umin.i32(i32, i32)
+declare <2 x i32> @llvm.umin.v2i32(<2 x i32>, <2 x i32>)
+declare <4 x i32> @llvm.umin.v4i32(<4 x i32>, <4 x i32>)
+declare <8 x i32> @llvm.umin.v8i32(<8 x i32>, <8 x i32>)
+declare <16 x i32> @llvm.umin.v16i32(<16 x i32>, <16 x i32>)
+
+declare i16 @llvm.umin.i16(i16, i16)
+declare <2 x i16> @llvm.umin.v2i16(<2 x i16>, <2 x i16>)
+declare <4 x i16> @llvm.umin.v4i16(<4 x i16>, <4 x i16>)
+declare <8 x i16> @llvm.umin.v8i16(<8 x i16>, <8 x i16>)
+declare <16 x i16> @llvm.umin.v16i16(<16 x i16>, <16 x i16>)
+declare <32 x i16> @llvm.umin.v32i16(<32 x i16>, <32 x i16>)
+
+declare i8 @llvm.umin.i8(i8, i8)
+declare <2 x i8> @llvm.umin.v2i8(<2 x i8>, <2 x i8>)
+declare <4 x i8> @llvm.umin.v4i8(<4 x i8>, <4 x i8>)
+declare <8 x i8> @llvm.umin.v8i8(<8 x i8>, <8 x i8>)
+declare <16 x i8> @llvm.umin.v16i8(<16 x i8>, <16 x i8>)
+declare <32 x i8> @llvm.umin.v32i8(<32 x i8>, <32 x i8>)
+declare <64 x i8> @llvm.umin.v64i8(<64 x i8>, <64 x i8>)
+
+define i32 @umin(i32 %arg) {
+; MVE-RECIP-LABEL: 'umin'
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 304 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I32 = call <2 x i32> @llvm.umin.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I16 = call <2 x i16> @llvm.umin.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I16 = call <4 x i16> @llvm.umin.v4i16(<4 x i16> undef, <4 x i16> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I8 = call <2 x i8> @llvm.umin.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.umin.v4i8(<4 x i8> undef, <4 x i8> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I8 = call <8 x i8> @llvm.umin.v8i8(<8 x i8> undef, <8 x i8> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; MVE-SIZE-LABEL: 'umin'
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I32 = call <2 x i32> @llvm.umin.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I16 = call <2 x i16> @llvm.umin.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I16 = call <4 x i16> @llvm.umin.v4i16(<4 x i16> undef, <4 x i16> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I8 = call <2 x i8> @llvm.umin.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I8 = call <4 x i8> @llvm.umin.v4i8(<4 x i8> undef, <4 x i8> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I8 = call <8 x i8> @llvm.umin.v8i8(<8 x i8> undef, <8 x i8> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
+ %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
+ %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
+ %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
+
+ %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
+ %V2I32 = call <2 x i32> @llvm.umin.v2i32(<2 x i32> undef, <2 x i32> undef)
+ %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
+ %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
+ %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
+
+ %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
+ %V2I16 = call <2 x i16> @llvm.umin.v2i16(<2 x i16> undef, <2 x i16> undef)
+ %V4I16 = call <4 x i16> @llvm.umin.v4i16(<4 x i16> undef, <4 x i16> undef)
+ %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
+ %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
+ %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
+
+ %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
+ %V2I8 = call <2 x i8> @llvm.umin.v2i8(<2 x i8> undef, <2 x i8> undef)
+ %V4I8 = call <4 x i8> @llvm.umin.v4i8(<4 x i8> undef, <4 x i8> undef)
+ %V8I8 = call <8 x i8> @llvm.umin.v8i8(<8 x i8> undef, <8 x i8> undef)
+ %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
+ %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
+ %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
+
+ ret i32 undef
+}
+
+
+declare i64 @llvm.umax.i64(i64, i64)
+declare <2 x i64> @llvm.umax.v2i64(<2 x i64>, <2 x i64>)
+declare <4 x i64> @llvm.umax.v4i64(<4 x i64>, <4 x i64>)
+declare <8 x i64> @llvm.umax.v8i64(<8 x i64>, <8 x i64>)
+
+declare i32 @llvm.umax.i32(i32, i32)
+declare <2 x i32> @llvm.umax.v2i32(<2 x i32>, <2 x i32>)
+declare <4 x i32> @llvm.umax.v4i32(<4 x i32>, <4 x i32>)
+declare <8 x i32> @llvm.umax.v8i32(<8 x i32>, <8 x i32>)
+declare <16 x i32> @llvm.umax.v16i32(<16 x i32>, <16 x i32>)
+
+declare i16 @llvm.umax.i16(i16, i16)
+declare <2 x i16> @llvm.umax.v2i16(<2 x i16>, <2 x i16>)
+declare <4 x i16> @llvm.umax.v4i16(<4 x i16>, <4 x i16>)
+declare <8 x i16> @llvm.umax.v8i16(<8 x i16>, <8 x i16>)
+declare <16 x i16> @llvm.umax.v16i16(<16 x i16>, <16 x i16>)
+declare <32 x i16> @llvm.umax.v32i16(<32 x i16>, <32 x i16>)
+
+declare i8 @llvm.umax.i8(i8, i8)
+declare <2 x i8> @llvm.umax.v2i8(<2 x i8>, <2 x i8>)
+declare <4 x i8> @llvm.umax.v4i8(<4 x i8>, <4 x i8>)
+declare <8 x i8> @llvm.umax.v8i8(<8 x i8>, <8 x i8>)
+declare <16 x i8> @llvm.umax.v16i8(<16 x i8>, <16 x i8>)
+declare <32 x i8> @llvm.umax.v32i8(<32 x i8>, <32 x i8>)
+declare <64 x i8> @llvm.umax.v64i8(<64 x i8>, <64 x i8>)
+
+define i32 @sub(i32 %arg) {
+; MVE-RECIP-LABEL: 'sub'
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 304 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I32 = call <2 x i32> @llvm.umax.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I16 = call <2 x i16> @llvm.umax.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I16 = call <4 x i16> @llvm.umax.v4i16(<4 x i16> undef, <4 x i16> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I8 = call <2 x i8> @llvm.umax.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.umax.v4i8(<4 x i8> undef, <4 x i8> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I8 = call <8 x i8> @llvm.umax.v8i8(<8 x i8> undef, <8 x i8> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
+; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; MVE-SIZE-LABEL: 'sub'
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I32 = call <2 x i32> @llvm.umax.v2i32(<2 x i32> undef, <2 x i32> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I16 = call <2 x i16> @llvm.umax.v2i16(<2 x i16> undef, <2 x i16> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I16 = call <4 x i16> @llvm.umax.v4i16(<4 x i16> undef, <4 x i16> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I8 = call <2 x i8> @llvm.umax.v2i8(<2 x i8> undef, <2 x i8> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I8 = call <4 x i8> @llvm.umax.v4i8(<4 x i8> undef, <4 x i8> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I8 = call <8 x i8> @llvm.umax.v8i8(<8 x i8> undef, <8 x i8> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
+; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
+ %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
+ %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
+ %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
+
+ %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
+ %V2I32 = call <2 x i32> @llvm.umax.v2i32(<2 x i32> undef, <2 x i32> undef)
+ %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
+ %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
+ %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
+
+ %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
+ %V2I16 = call <2 x i16> @llvm.umax.v2i16(<2 x i16> undef, <2 x i16> undef)
+ %V4I16 = call <4 x i16> @llvm.umax.v4i16(<4 x i16> undef, <4 x i16> undef)
+ %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
+ %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
+ %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
+
+ %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
+ %V2I8 = call <2 x i8> @llvm.umax.v2i8(<2 x i8> undef, <2 x i8> undef)
+ %V4I8 = call <4 x i8> @llvm.umax.v4i8(<4 x i8> undef, <4 x i8> undef)
+ %V8I8 = call <8 x i8> @llvm.umax.v8i8(<8 x i8> undef, <8 x i8> undef)
+ %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
+ %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
+ %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
+
+ ret i32 undef
+}
+
+
+
+declare double @llvm.minnum.f64(double, double)
+declare <2 x double> @llvm.minnum.v2f64(<2 x double>, <2 x double>)
+declare <4 x double> @llvm.minnum.v4f64(<4 x double>, <4 x double>)
+declare <8 x double> @llvm.minnum.v8f64(<8 x double>, <8 x double>)
+
+declare float @llvm.minnum.f32(float, float)
+declare <2 x float> @llvm.minnum.v2f32(<2 x float>, <2 x float>)
+declare <4 x float> @llvm.minnum.v4f32(<4 x float>, <4 x float>)
+declare <8 x float> @llvm.minnum.v8f32(<8 x float>, <8 x float>)
+declare <16 x float> @llvm.minnum.v16f32(<16 x float>, <16 x float>)
+
+declare half @llvm.minnum.f16(half, half)
+declare <2 x half> @llvm.minnum.v2f16(<2 x half>, <2 x half>)
+declare <4 x half> @llvm.minnum.v4f16(<4 x half>, <4 x half>)
+declare <8 x half> @llvm.minnum.v8f16(<8 x half>, <8 x half>)
+declare <16 x half> @llvm.minnum.v16f16(<16 x half>, <16 x half>)
+declare <32 x half> @llvm.minnum.v32f16(<32 x half>, <32 x half>)
+
+define float @minnum(float %arg) {
+; MVEI-RECIP-LABEL: 'minnum'
+; MVEI-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %F64 = call double @llvm.minnum.f64(double undef, double undef)
+; MVEI-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2F64 = call <2 x double> @llvm.minnum.v2f64(<2 x double> undef, <2 x double> undef)
+; MVEI-RECIP-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V4F64 = call <4 x double> @llvm.minnum.v4f64(<4 x double> undef, <4 x double> undef)
+; MVEI-RECIP-NEXT: Cost Model: Found an estimated cost of 144 for instruction: %V8F64 = call <8 x double> @llvm.minnum.v8f64(<8 x double> undef, <8 x double> undef)
+; MVEI-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %F32 = call float @llvm.minnum.f32(float undef, float undef)
+; MVEI-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2F32 = call <2 x float> @llvm.minnum.v2f32(<2 x float> undef, <2 x float> undef)
+; MVEI-RECIP-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V4F32 = call <4 x float> @llvm.minnum.v4f32(<4 x float> undef, <4 x float> undef)
+; MVEI-RECIP-NEXT: Cost Model: Found an estimated cost of 144 for instruction: %V8F32 = call <8 x float> @llvm.minnum.v8f32(<8 x float> undef, <8 x float> undef)
+; MVEI-RECIP-NEXT: Cost Model: Found an estimated cost of 416 for instruction: %V16F32 = call <16 x float> @llvm.minnum.v16f32(<16 x float> undef, <16 x float> undef)
+; MVEI-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %F16 = call half @llvm.minnum.f16(half undef, half undef)
+; MVEI-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2F16 = call <2 x half> @llvm.minnum.v2f16(<2 x half> undef, <2 x half> undef)
+; MVEI-RECIP-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V4F16 = call <4 x half> @llvm.minnum.v4f16(<4 x half> undef, <4 x half> undef)
+; MVEI-RECIP-NEXT: Cost Model: Found an estimated cost of 144 for instruction: %V8F16 = call <8 x half> @llvm.minnum.v8f16(<8 x half> undef, <8 x half> undef)
+; MVEI-RECIP-NEXT: Cost Model: Found an estimated cost of 416 for instruction: %V16F16 = call <16 x half> @llvm.minnum.v16f16(<16 x half> undef, <16 x half> undef)
+; MVEI-RECIP-NEXT: Cost Model: Found an estimated cost of 1344 for instruction: %V32F16 = call <32 x half> @llvm.minnum.v32f16(<32 x half> undef, <32 x half> undef)
+; MVEI-RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float undef
+;
+; MVEI-SIZE-LABEL: 'minnum'
+; MVEI-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.minnum.f64(double undef, double undef)
+; MVEI-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2F64 = call <2 x double> @llvm.minnum.v2f64(<2 x double> undef, <2 x double> undef)
+; MVEI-SIZE-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4F64 = call <4 x double> @llvm.minnum.v4f64(<4 x double> undef, <4 x double> undef)
+; MVEI-SIZE-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %V8F64 = call <8 x double> @llvm.minnum.v8f64(<8 x double> undef, <8 x double> undef)
+; MVEI-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.minnum.f32(float undef, float undef)
+; MVEI-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2F32 = call <2 x float> @llvm.minnum.v2f32(<2 x float> undef, <2 x float> undef)
+; MVEI-SIZE-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4F32 = call <4 x float> @llvm.minnum.v4f32(<4 x float> undef, <4 x float> undef)
+; MVEI-SIZE-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %V8F32 = call <8 x float> @llvm.minnum.v8f32(<8 x float> undef, <8 x float> undef)
+; MVEI-SIZE-NEXT: Cost Model: Found an estimated cost of 272 for instruction: %V16F32 = call <16 x float> @llvm.minnum.v16f32(<16 x float> undef, <16 x float> undef)
+; MVEI-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F16 = call half @llvm.minnum.f16(half undef, half undef)
+; MVEI-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2F16 = call <2 x half> @llvm.minnum.v2f16(<2 x half> undef, <2 x half> undef)
+; MVEI-SIZE-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4F16 = call <4 x half> @llvm.minnum.v4f16(<4 x half> undef, <4 x half> undef)
+; MVEI-SIZE-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %V8F16 = call <8 x half> @llvm.minnum.v8f16(<8 x half> undef, <8 x half> undef)
+; MVEI-SIZE-NEXT: Cost Model: Found an estimated cost of 272 for instruction: %V16F16 = call <16 x half> @llvm.minnum.v16f16(<16 x half> undef, <16 x half> undef)
+; MVEI-SIZE-NEXT: Cost Model: Found an estimated cost of 1056 for instruction: %V32F16 = call <32 x half> @llvm.minnum.v32f16(<32 x half> undef, <32 x half> undef)
+; MVEI-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret float undef
+;
+; MVEF-RECIP-LABEL: 'minnum'
+; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %F64 = call double @llvm.minnum.f64(double undef, double undef)
+; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2F64 = call <2 x double> @llvm.minnum.v2f64(<2 x double> undef, <2 x double> undef)
+; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V4F64 = call <4 x double> @llvm.minnum.v4f64(<4 x double> undef, <4 x double> undef)
+; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 144 for instruction: %V8F64 = call <8 x double> @llvm.minnum.v8f64(<8 x double> undef, <8 x double> undef)
+; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.minnum.f32(float undef, float undef)
+; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = call <2 x float> @llvm.minnum.v2f32(<2 x float> undef, <2 x float> undef)
+; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.minnum.v4f32(<4 x float> undef, <4 x float> undef)
+; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.minnum.v8f32(<8 x float> undef, <8 x float> undef)
+; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16F32 = call <16 x float> @llvm.minnum.v16f32(<16 x float> undef, <16 x float> undef)
+; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F16 = call half @llvm.minnum.f16(half undef, half undef)
+; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F16 = call <2 x half> @llvm.minnum.v2f16(<2 x half> undef, <2 x half> undef)
+; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F16 = call <4 x half> @llvm.minnum.v4f16(<4 x half> undef, <4 x half> undef)
+; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F16 = call <8 x half> @llvm.minnum.v8f16(<8 x half> undef, <8 x half> undef)
+; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = call <16 x half> @llvm.minnum.v16f16(<16 x half> undef, <16 x half> undef)
+; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32F16 = call <32 x half> @llvm.minnum.v32f16(<32 x half> undef, <32 x half> undef)
+; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float undef
+;
+; MVEF-SIZE-LABEL: 'minnum'
+; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.minnum.f64(double undef, double undef)
+; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2F64 = call <2 x double> @llvm.minnum.v2f64(<2 x double> undef, <2 x double> undef)
+; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4F64 = call <4 x double> @llvm.minnum.v4f64(<4 x double> undef, <4 x double> undef)
+; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %V8F64 = call <8 x double> @llvm.minnum.v8f64(<8 x double> undef, <8 x double> undef)
+; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.minnum.f32(float undef, float undef)
+; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = call <2 x float> @llvm.minnum.v2f32(<2 x float> undef, <2 x float> undef)
+; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.minnum.v4f32(<4 x float> undef, <4 x float> undef)
+; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.minnum.v8f32(<8 x float> undef, <8 x float> undef)
+; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16F32 = call <16 x float> @llvm.minnum.v16f32(<16 x float> undef, <16 x float> undef)
+; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F16 = call half @llvm.minnum.f16(half undef, half undef)
+; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F16 = call <2 x half> @llvm.minnum.v2f16(<2 x half> undef, <2 x half> undef)
+; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F16 = call <4 x half> @llvm.minnum.v4f16(<4 x half> undef, <4 x half> undef)
+; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F16 = call <8 x half> @llvm.minnum.v8f16(<8 x half> undef, <8 x half> undef)
+; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = call <16 x half> @llvm.minnum.v16f16(<16 x half> undef, <16 x half> undef)
+; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32F16 = call <32 x half> @llvm.minnum.v32f16(<32 x half> undef, <32 x half> undef)
+; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret float undef
+;
+ %F64 = call double @llvm.minnum.f64(double undef, double undef)
+ %V2F64 = call <2 x double> @llvm.minnum.v2f64(<2 x double> undef, <2 x double> undef)
+ %V4F64 = call <4 x double> @llvm.minnum.v4f64(<4 x double> undef, <4 x double> undef)
+ %V8F64 = call <8 x double> @llvm.minnum.v8f64(<8 x double> undef, <8 x double> undef)
+
+ %F32 = call float @llvm.minnum.f32(float undef, float undef)
+ %V2F32 = call <2 x float> @llvm.minnum.v2f32(<2 x float> undef, <2 x float> undef)
+ %V4F32 = call <4 x float> @llvm.minnum.v4f32(<4 x float> undef, <4 x float> undef)
+ %V8F32 = call <8 x float> @llvm.minnum.v8f32(<8 x float> undef, <8 x float> undef)
+ %V16F32 = call <16 x float> @llvm.minnum.v16f32(<16 x float> undef, <16 x float> undef)
+
+ %F16 = call half @llvm.minnum.f16(half undef, half undef)
+ %V2F16 = call <2 x half> @llvm.minnum.v2f16(<2 x half> undef, <2 x half> undef)
+ %V4F16 = call <4 x half> @llvm.minnum.v4f16(<4 x half> undef, <4 x half> undef)
+ %V8F16 = call <8 x half> @llvm.minnum.v8f16(<8 x half> undef, <8 x half> undef)
+ %V16F16 = call <16 x half> @llvm.minnum.v16f16(<16 x half> undef, <16 x half> undef)
+ %V32F16 = call <32 x half> @llvm.minnum.v32f16(<32 x half> undef, <32 x half> undef)
+
+ ret float undef
+}
+
+declare double @llvm.maxnum.f64(double, double)
+declare <2 x double> @llvm.maxnum.v2f64(<2 x double>, <2 x double>)
+declare <4 x double> @llvm.maxnum.v4f64(<4 x double>, <4 x double>)
+declare <8 x double> @llvm.maxnum.v8f64(<8 x double>, <8 x double>)
+
+declare float @llvm.maxnum.f32(float, float)
+declare <2 x float> @llvm.maxnum.v2f32(<2 x float>, <2 x float>)
+declare <4 x float> @llvm.maxnum.v4f32(<4 x float>, <4 x float>)
+declare <8 x float> @llvm.maxnum.v8f32(<8 x float>, <8 x float>)
+declare <16 x float> @llvm.maxnum.v16f32(<16 x float>, <16 x float>)
+
+declare half @llvm.maxnum.f16(half, half)
+declare <2 x half> @llvm.maxnum.v2f16(<2 x half>, <2 x half>)
+declare <4 x half> @llvm.maxnum.v4f16(<4 x half>, <4 x half>)
+declare <8 x half> @llvm.maxnum.v8f16(<8 x half>, <8 x half>)
+declare <16 x half> @llvm.maxnum.v16f16(<16 x half>, <16 x half>)
+declare <32 x half> @llvm.maxnum.v32f16(<32 x half>, <32 x half>)
+
+define float @maxnum(float %arg) {
+; MVEI-RECIP-LABEL: 'maxnum'
+; MVEI-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %F64 = call double @llvm.maxnum.f64(double undef, double undef)
+; MVEI-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2F64 = call <2 x double> @llvm.maxnum.v2f64(<2 x double> undef, <2 x double> undef)
+; MVEI-RECIP-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V4F64 = call <4 x double> @llvm.maxnum.v4f64(<4 x double> undef, <4 x double> undef)
+; MVEI-RECIP-NEXT: Cost Model: Found an estimated cost of 144 for instruction: %V8F64 = call <8 x double> @llvm.maxnum.v8f64(<8 x double> undef, <8 x double> undef)
+; MVEI-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %F32 = call float @llvm.maxnum.f32(float undef, float undef)
+; MVEI-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2F32 = call <2 x float> @llvm.maxnum.v2f32(<2 x float> undef, <2 x float> undef)
+; MVEI-RECIP-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V4F32 = call <4 x float> @llvm.maxnum.v4f32(<4 x float> undef, <4 x float> undef)
+; MVEI-RECIP-NEXT: Cost Model: Found an estimated cost of 144 for instruction: %V8F32 = call <8 x float> @llvm.maxnum.v8f32(<8 x float> undef, <8 x float> undef)
+; MVEI-RECIP-NEXT: Cost Model: Found an estimated cost of 416 for instruction: %V16F32 = call <16 x float> @llvm.maxnum.v16f32(<16 x float> undef, <16 x float> undef)
+; MVEI-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %F16 = call half @llvm.maxnum.f16(half undef, half undef)
+; MVEI-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2F16 = call <2 x half> @llvm.maxnum.v2f16(<2 x half> undef, <2 x half> undef)
+; MVEI-RECIP-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V4F16 = call <4 x half> @llvm.maxnum.v4f16(<4 x half> undef, <4 x half> undef)
+; MVEI-RECIP-NEXT: Cost Model: Found an estimated cost of 144 for instruction: %V8F16 = call <8 x half> @llvm.maxnum.v8f16(<8 x half> undef, <8 x half> undef)
+; MVEI-RECIP-NEXT: Cost Model: Found an estimated cost of 416 for instruction: %V16F16 = call <16 x half> @llvm.maxnum.v16f16(<16 x half> undef, <16 x half> undef)
+; MVEI-RECIP-NEXT: Cost Model: Found an estimated cost of 1344 for instruction: %V32F16 = call <32 x half> @llvm.maxnum.v32f16(<32 x half> undef, <32 x half> undef)
+; MVEI-RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float undef
+;
+; MVEI-SIZE-LABEL: 'maxnum'
+; MVEI-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.maxnum.f64(double undef, double undef)
+; MVEI-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2F64 = call <2 x double> @llvm.maxnum.v2f64(<2 x double> undef, <2 x double> undef)
+; MVEI-SIZE-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4F64 = call <4 x double> @llvm.maxnum.v4f64(<4 x double> undef, <4 x double> undef)
+; MVEI-SIZE-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %V8F64 = call <8 x double> @llvm.maxnum.v8f64(<8 x double> undef, <8 x double> undef)
+; MVEI-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.maxnum.f32(float undef, float undef)
+; MVEI-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2F32 = call <2 x float> @llvm.maxnum.v2f32(<2 x float> undef, <2 x float> undef)
+; MVEI-SIZE-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4F32 = call <4 x float> @llvm.maxnum.v4f32(<4 x float> undef, <4 x float> undef)
+; MVEI-SIZE-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %V8F32 = call <8 x float> @llvm.maxnum.v8f32(<8 x float> undef, <8 x float> undef)
+; MVEI-SIZE-NEXT: Cost Model: Found an estimated cost of 272 for instruction: %V16F32 = call <16 x float> @llvm.maxnum.v16f32(<16 x float> undef, <16 x float> undef)
+; MVEI-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F16 = call half @llvm.maxnum.f16(half undef, half undef)
+; MVEI-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2F16 = call <2 x half> @llvm.maxnum.v2f16(<2 x half> undef, <2 x half> undef)
+; MVEI-SIZE-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4F16 = call <4 x half> @llvm.maxnum.v4f16(<4 x half> undef, <4 x half> undef)
+; MVEI-SIZE-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %V8F16 = call <8 x half> @llvm.maxnum.v8f16(<8 x half> undef, <8 x half> undef)
+; MVEI-SIZE-NEXT: Cost Model: Found an estimated cost of 272 for instruction: %V16F16 = call <16 x half> @llvm.maxnum.v16f16(<16 x half> undef, <16 x half> undef)
+; MVEI-SIZE-NEXT: Cost Model: Found an estimated cost of 1056 for instruction: %V32F16 = call <32 x half> @llvm.maxnum.v32f16(<32 x half> undef, <32 x half> undef)
+; MVEI-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret float undef
+;
+; MVEF-RECIP-LABEL: 'maxnum'
+; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %F64 = call double @llvm.maxnum.f64(double undef, double undef)
+; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2F64 = call <2 x double> @llvm.maxnum.v2f64(<2 x double> undef, <2 x double> undef)
+; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V4F64 = call <4 x double> @llvm.maxnum.v4f64(<4 x double> undef, <4 x double> undef)
+; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 144 for instruction: %V8F64 = call <8 x double> @llvm.maxnum.v8f64(<8 x double> undef, <8 x double> undef)
+; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.maxnum.f32(float undef, float undef)
+; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = call <2 x float> @llvm.maxnum.v2f32(<2 x float> undef, <2 x float> undef)
+; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.maxnum.v4f32(<4 x float> undef, <4 x float> undef)
+; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.maxnum.v8f32(<8 x float> undef, <8 x float> undef)
+; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16F32 = call <16 x float> @llvm.maxnum.v16f32(<16 x float> undef, <16 x float> undef)
+; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F16 = call half @llvm.maxnum.f16(half undef, half undef)
+; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F16 = call <2 x half> @llvm.maxnum.v2f16(<2 x half> undef, <2 x half> undef)
+; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F16 = call <4 x half> @llvm.maxnum.v4f16(<4 x half> undef, <4 x half> undef)
+; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F16 = call <8 x half> @llvm.maxnum.v8f16(<8 x half> undef, <8 x half> undef)
+; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = call <16 x half> @llvm.maxnum.v16f16(<16 x half> undef, <16 x half> undef)
+; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32F16 = call <32 x half> @llvm.maxnum.v32f16(<32 x half> undef, <32 x half> undef)
+; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float undef
+;
+; MVEF-SIZE-LABEL: 'maxnum'
+; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.maxnum.f64(double undef, double undef)
+; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2F64 = call <2 x double> @llvm.maxnum.v2f64(<2 x double> undef, <2 x double> undef)
+; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4F64 = call <4 x double> @llvm.maxnum.v4f64(<4 x double> undef, <4 x double> undef)
+; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %V8F64 = call <8 x double> @llvm.maxnum.v8f64(<8 x double> undef, <8 x double> undef)
+; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.maxnum.f32(float undef, float undef)
+; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = call <2 x float> @llvm.maxnum.v2f32(<2 x float> undef, <2 x float> undef)
+; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.maxnum.v4f32(<4 x float> undef, <4 x float> undef)
+; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.maxnum.v8f32(<8 x float> undef, <8 x float> undef)
+; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16F32 = call <16 x float> @llvm.maxnum.v16f32(<16 x float> undef, <16 x float> undef)
+; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F16 = call half @llvm.maxnum.f16(half undef, half undef)
+; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F16 = call <2 x half> @llvm.maxnum.v2f16(<2 x half> undef, <2 x half> undef)
+; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F16 = call <4 x half> @llvm.maxnum.v4f16(<4 x half> undef, <4 x half> undef)
+; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F16 = call <8 x half> @llvm.maxnum.v8f16(<8 x half> undef, <8 x half> undef)
+; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = call <16 x half> @llvm.maxnum.v16f16(<16 x half> undef, <16 x half> undef)
+; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32F16 = call <32 x half> @llvm.maxnum.v32f16(<32 x half> undef, <32 x half> undef)
+; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret float undef
+;
+ %F64 = call double @llvm.maxnum.f64(double undef, double undef)
+ %V2F64 = call <2 x double> @llvm.maxnum.v2f64(<2 x double> undef, <2 x double> undef)
+ %V4F64 = call <4 x double> @llvm.maxnum.v4f64(<4 x double> undef, <4 x double> undef)
+ %V8F64 = call <8 x double> @llvm.maxnum.v8f64(<8 x double> undef, <8 x double> undef)
+
+ %F32 = call float @llvm.maxnum.f32(float undef, float undef)
+ %V2F32 = call <2 x float> @llvm.maxnum.v2f32(<2 x float> undef, <2 x float> undef)
+ %V4F32 = call <4 x float> @llvm.maxnum.v4f32(<4 x float> undef, <4 x float> undef)
+ %V8F32 = call <8 x float> @llvm.maxnum.v8f32(<8 x float> undef, <8 x float> undef)
+ %V16F32 = call <16 x float> @llvm.maxnum.v16f32(<16 x float> undef, <16 x float> undef)
+
+ %F16 = call half @llvm.maxnum.f16(half undef, half undef)
+ %V2F16 = call <2 x half> @llvm.maxnum.v2f16(<2 x half> undef, <2 x half> undef)
+ %V4F16 = call <4 x half> @llvm.maxnum.v4f16(<4 x half> undef, <4 x half> undef)
+ %V8F16 = call <8 x half> @llvm.maxnum.v8f16(<8 x half> undef, <8 x half> undef)
+ %V16F16 = call <16 x half> @llvm.maxnum.v16f16(<16 x half> undef, <16 x half> undef)
+ %V32F16 = call <32 x half> @llvm.maxnum.v32f16(<32 x half> undef, <32 x half> undef)
+
+ ret float undef
+}
More information about the llvm-commits
mailing list