| ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py |
| ; RUN: opt < %s -mtriple=aarch64-unknown-linux-gnu -cost-model -cost-kind=throughput -analyze | FileCheck %s --check-prefixes=CHECK,CHECK-NOF16 |
| ; RUN: opt < %s -mtriple=aarch64-unknown-linux-gnu -mattr=+fullfp16 -cost-model -cost-kind=throughput -analyze | FileCheck %s --check-prefixes=CHECK,CHECK-F16 |
| |
| define void @reduce_umin() { |
| ; CHECK-LABEL: 'reduce_umin' |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1i8 = call i8 @llvm.vector.reduce.umin.v1i8(<1 x i8> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V3i8 = call i8 @llvm.vector.reduce.umin.v3i8(<3 x i8> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i8 = call i8 @llvm.vector.reduce.umin.v4i8(<4 x i8> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8i8 = call i8 @llvm.vector.reduce.umin.v8i8(<8 x i8> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16i8 = call i8 @llvm.vector.reduce.umin.v16i8(<16 x i8> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32i8 = call i8 @llvm.vector.reduce.umin.v32i8(<32 x i8> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V64i8 = call i8 @llvm.vector.reduce.umin.v64i8(<64 x i8> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i16 = call i16 @llvm.vector.reduce.umin.v2i16(<2 x i16> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i16 = call i16 @llvm.vector.reduce.umin.v4i16(<4 x i16> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8i16 = call i16 @llvm.vector.reduce.umin.v8i16(<8 x i16> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V16i16 = call i16 @llvm.vector.reduce.umin.v16i16(<16 x i16> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i32 = call i32 @llvm.vector.reduce.umin.v2i32(<2 x i32> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i32 = call i32 @llvm.vector.reduce.umin.v4i32(<4 x i32> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8i32 = call i32 @llvm.vector.reduce.umin.v8i32(<8 x i32> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = call i64 @llvm.vector.reduce.umin.v2i64(<2 x i64> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = call i64 @llvm.vector.reduce.umin.v4i64(<4 x i64> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void |
| ; |
| %V1i8 = call i8 @llvm.vector.reduce.umin.v1i8(<1 x i8> undef) |
| %V3i8 = call i8 @llvm.vector.reduce.umin.v3i8(<3 x i8> undef) |
| %V4i8 = call i8 @llvm.vector.reduce.umin.v4i8(<4 x i8> undef) |
| %V8i8 = call i8 @llvm.vector.reduce.umin.v8i8(<8 x i8> undef) |
| %V16i8 = call i8 @llvm.vector.reduce.umin.v16i8(<16 x i8> undef) |
| %V32i8 = call i8 @llvm.vector.reduce.umin.v32i8(<32 x i8> undef) |
| %V64i8 = call i8 @llvm.vector.reduce.umin.v64i8(<64 x i8> undef) |
| %V2i16 = call i16 @llvm.vector.reduce.umin.v2i16(<2 x i16> undef) |
| %V4i16 = call i16 @llvm.vector.reduce.umin.v4i16(<4 x i16> undef) |
| %V8i16 = call i16 @llvm.vector.reduce.umin.v8i16(<8 x i16> undef) |
| %V16i16 = call i16 @llvm.vector.reduce.umin.v16i16(<16 x i16> undef) |
| %V2i32 = call i32 @llvm.vector.reduce.umin.v2i32(<2 x i32> undef) |
| %V4i32 = call i32 @llvm.vector.reduce.umin.v4i32(<4 x i32> undef) |
| %V8i32 = call i32 @llvm.vector.reduce.umin.v8i32(<8 x i32> undef) |
| %V2i64 = call i64 @llvm.vector.reduce.umin.v2i64(<2 x i64> undef) |
| %V4i64 = call i64 @llvm.vector.reduce.umin.v4i64(<4 x i64> undef) |
| ret void |
| } |
| |
| define void @reduce_umax() { |
| ; CHECK-LABEL: 'reduce_umax' |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1i8 = call i8 @llvm.vector.reduce.umax.v1i8(<1 x i8> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V3i8 = call i8 @llvm.vector.reduce.umax.v3i8(<3 x i8> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i8 = call i8 @llvm.vector.reduce.umax.v4i8(<4 x i8> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8i8 = call i8 @llvm.vector.reduce.umax.v8i8(<8 x i8> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16i8 = call i8 @llvm.vector.reduce.umax.v16i8(<16 x i8> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32i8 = call i8 @llvm.vector.reduce.umax.v32i8(<32 x i8> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V64i8 = call i8 @llvm.vector.reduce.umax.v64i8(<64 x i8> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i16 = call i16 @llvm.vector.reduce.umax.v2i16(<2 x i16> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i16 = call i16 @llvm.vector.reduce.umax.v4i16(<4 x i16> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8i16 = call i16 @llvm.vector.reduce.umax.v8i16(<8 x i16> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V16i16 = call i16 @llvm.vector.reduce.umax.v16i16(<16 x i16> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i32 = call i32 @llvm.vector.reduce.umax.v2i32(<2 x i32> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i32 = call i32 @llvm.vector.reduce.umax.v4i32(<4 x i32> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8i32 = call i32 @llvm.vector.reduce.umax.v8i32(<8 x i32> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = call i64 @llvm.vector.reduce.umax.v2i64(<2 x i64> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = call i64 @llvm.vector.reduce.umax.v4i64(<4 x i64> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void |
| ; |
| %V1i8 = call i8 @llvm.vector.reduce.umax.v1i8(<1 x i8> undef) |
| %V3i8 = call i8 @llvm.vector.reduce.umax.v3i8(<3 x i8> undef) |
| %V4i8 = call i8 @llvm.vector.reduce.umax.v4i8(<4 x i8> undef) |
| %V8i8 = call i8 @llvm.vector.reduce.umax.v8i8(<8 x i8> undef) |
| %V16i8 = call i8 @llvm.vector.reduce.umax.v16i8(<16 x i8> undef) |
| %V32i8 = call i8 @llvm.vector.reduce.umax.v32i8(<32 x i8> undef) |
| %V64i8 = call i8 @llvm.vector.reduce.umax.v64i8(<64 x i8> undef) |
| %V2i16 = call i16 @llvm.vector.reduce.umax.v2i16(<2 x i16> undef) |
| %V4i16 = call i16 @llvm.vector.reduce.umax.v4i16(<4 x i16> undef) |
| %V8i16 = call i16 @llvm.vector.reduce.umax.v8i16(<8 x i16> undef) |
| %V16i16 = call i16 @llvm.vector.reduce.umax.v16i16(<16 x i16> undef) |
| %V2i32 = call i32 @llvm.vector.reduce.umax.v2i32(<2 x i32> undef) |
| %V4i32 = call i32 @llvm.vector.reduce.umax.v4i32(<4 x i32> undef) |
| %V8i32 = call i32 @llvm.vector.reduce.umax.v8i32(<8 x i32> undef) |
| %V2i64 = call i64 @llvm.vector.reduce.umax.v2i64(<2 x i64> undef) |
| %V4i64 = call i64 @llvm.vector.reduce.umax.v4i64(<4 x i64> undef) |
| ret void |
| } |
| |
| define void @reduce_smin() { |
| ; CHECK-LABEL: 'reduce_smin' |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1i8 = call i8 @llvm.vector.reduce.smin.v1i8(<1 x i8> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V3i8 = call i8 @llvm.vector.reduce.smin.v3i8(<3 x i8> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i8 = call i8 @llvm.vector.reduce.smin.v4i8(<4 x i8> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8i8 = call i8 @llvm.vector.reduce.smin.v8i8(<8 x i8> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16i8 = call i8 @llvm.vector.reduce.smin.v16i8(<16 x i8> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32i8 = call i8 @llvm.vector.reduce.smin.v32i8(<32 x i8> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V64i8 = call i8 @llvm.vector.reduce.smin.v64i8(<64 x i8> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i16 = call i16 @llvm.vector.reduce.smin.v2i16(<2 x i16> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i16 = call i16 @llvm.vector.reduce.smin.v4i16(<4 x i16> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8i16 = call i16 @llvm.vector.reduce.smin.v8i16(<8 x i16> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V16i16 = call i16 @llvm.vector.reduce.smin.v16i16(<16 x i16> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i32 = call i32 @llvm.vector.reduce.smin.v2i32(<2 x i32> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i32 = call i32 @llvm.vector.reduce.smin.v4i32(<4 x i32> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8i32 = call i32 @llvm.vector.reduce.smin.v8i32(<8 x i32> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = call i64 @llvm.vector.reduce.smin.v2i64(<2 x i64> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = call i64 @llvm.vector.reduce.smin.v4i64(<4 x i64> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void |
| ; |
| %V1i8 = call i8 @llvm.vector.reduce.smin.v1i8(<1 x i8> undef) |
| %V3i8 = call i8 @llvm.vector.reduce.smin.v3i8(<3 x i8> undef) |
| %V4i8 = call i8 @llvm.vector.reduce.smin.v4i8(<4 x i8> undef) |
| %V8i8 = call i8 @llvm.vector.reduce.smin.v8i8(<8 x i8> undef) |
| %V16i8 = call i8 @llvm.vector.reduce.smin.v16i8(<16 x i8> undef) |
| %V32i8 = call i8 @llvm.vector.reduce.smin.v32i8(<32 x i8> undef) |
| %V64i8 = call i8 @llvm.vector.reduce.smin.v64i8(<64 x i8> undef) |
| %V2i16 = call i16 @llvm.vector.reduce.smin.v2i16(<2 x i16> undef) |
| %V4i16 = call i16 @llvm.vector.reduce.smin.v4i16(<4 x i16> undef) |
| %V8i16 = call i16 @llvm.vector.reduce.smin.v8i16(<8 x i16> undef) |
| %V16i16 = call i16 @llvm.vector.reduce.smin.v16i16(<16 x i16> undef) |
| %V2i32 = call i32 @llvm.vector.reduce.smin.v2i32(<2 x i32> undef) |
| %V4i32 = call i32 @llvm.vector.reduce.smin.v4i32(<4 x i32> undef) |
| %V8i32 = call i32 @llvm.vector.reduce.smin.v8i32(<8 x i32> undef) |
| %V2i64 = call i64 @llvm.vector.reduce.smin.v2i64(<2 x i64> undef) |
| %V4i64 = call i64 @llvm.vector.reduce.smin.v4i64(<4 x i64> undef) |
| ret void |
| } |
| |
| define void @reduce_smax() { |
| ; CHECK-LABEL: 'reduce_smax' |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1i8 = call i8 @llvm.vector.reduce.smax.v1i8(<1 x i8> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V3i8 = call i8 @llvm.vector.reduce.smax.v3i8(<3 x i8> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i8 = call i8 @llvm.vector.reduce.smax.v4i8(<4 x i8> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8i8 = call i8 @llvm.vector.reduce.smax.v8i8(<8 x i8> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16i8 = call i8 @llvm.vector.reduce.smax.v16i8(<16 x i8> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32i8 = call i8 @llvm.vector.reduce.smax.v32i8(<32 x i8> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V64i8 = call i8 @llvm.vector.reduce.smax.v64i8(<64 x i8> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i16 = call i16 @llvm.vector.reduce.smax.v2i16(<2 x i16> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i16 = call i16 @llvm.vector.reduce.smax.v4i16(<4 x i16> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8i16 = call i16 @llvm.vector.reduce.smax.v8i16(<8 x i16> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V16i16 = call i16 @llvm.vector.reduce.smax.v16i16(<16 x i16> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i32 = call i32 @llvm.vector.reduce.smax.v2i32(<2 x i32> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i32 = call i32 @llvm.vector.reduce.smax.v4i32(<4 x i32> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8i32 = call i32 @llvm.vector.reduce.smax.v8i32(<8 x i32> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = call i64 @llvm.vector.reduce.smax.v2i64(<2 x i64> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = call i64 @llvm.vector.reduce.smax.v4i64(<4 x i64> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void |
| ; |
| %V1i8 = call i8 @llvm.vector.reduce.smax.v1i8(<1 x i8> undef) |
| %V3i8 = call i8 @llvm.vector.reduce.smax.v3i8(<3 x i8> undef) |
| %V4i8 = call i8 @llvm.vector.reduce.smax.v4i8(<4 x i8> undef) |
| %V8i8 = call i8 @llvm.vector.reduce.smax.v8i8(<8 x i8> undef) |
| %V16i8 = call i8 @llvm.vector.reduce.smax.v16i8(<16 x i8> undef) |
| %V32i8 = call i8 @llvm.vector.reduce.smax.v32i8(<32 x i8> undef) |
| %V64i8 = call i8 @llvm.vector.reduce.smax.v64i8(<64 x i8> undef) |
| %V2i16 = call i16 @llvm.vector.reduce.smax.v2i16(<2 x i16> undef) |
| %V4i16 = call i16 @llvm.vector.reduce.smax.v4i16(<4 x i16> undef) |
| %V8i16 = call i16 @llvm.vector.reduce.smax.v8i16(<8 x i16> undef) |
| %V16i16 = call i16 @llvm.vector.reduce.smax.v16i16(<16 x i16> undef) |
| %V2i32 = call i32 @llvm.vector.reduce.smax.v2i32(<2 x i32> undef) |
| %V4i32 = call i32 @llvm.vector.reduce.smax.v4i32(<4 x i32> undef) |
| %V8i32 = call i32 @llvm.vector.reduce.smax.v8i32(<8 x i32> undef) |
| %V2i64 = call i64 @llvm.vector.reduce.smax.v2i64(<2 x i64> undef) |
| %V4i64 = call i64 @llvm.vector.reduce.smax.v4i64(<4 x i64> undef) |
| ret void |
| } |
| |
| define void @reduce_fmin16() { |
| ; CHECK-NOF16-LABEL: 'reduce_fmin16' |
| ; CHECK-NOF16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V2f16 = call half @llvm.vector.reduce.fmin.v2f16(<2 x half> undef) |
| ; CHECK-NOF16-NEXT: Cost Model: Found an estimated cost of 58 for instruction: %V4f16 = call half @llvm.vector.reduce.fmin.v4f16(<4 x half> undef) |
| ; CHECK-NOF16-NEXT: Cost Model: Found an estimated cost of 198 for instruction: %V8f16 = call half @llvm.vector.reduce.fmin.v8f16(<8 x half> undef) |
| ; CHECK-NOF16-NEXT: Cost Model: Found an estimated cost of 298 for instruction: %V16f16 = call half @llvm.vector.reduce.fmin.v16f16(<16 x half> undef) |
| ; CHECK-NOF16-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void |
| ; |
| ; CHECK-F16-LABEL: 'reduce_fmin16' |
| ; CHECK-F16-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2f16 = call half @llvm.vector.reduce.fmin.v2f16(<2 x half> undef) |
| ; CHECK-F16-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4f16 = call half @llvm.vector.reduce.fmin.v4f16(<4 x half> undef) |
| ; CHECK-F16-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8f16 = call half @llvm.vector.reduce.fmin.v8f16(<8 x half> undef) |
| ; CHECK-F16-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V16f16 = call half @llvm.vector.reduce.fmin.v16f16(<16 x half> undef) |
| ; CHECK-F16-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void |
| ; |
| %V2f16 = call half @llvm.vector.reduce.fmin.v2f16(<2 x half> undef) |
| %V4f16 = call half @llvm.vector.reduce.fmin.v4f16(<4 x half> undef) |
| %V8f16 = call half @llvm.vector.reduce.fmin.v8f16(<8 x half> undef) |
| %V16f16 = call half @llvm.vector.reduce.fmin.v16f16(<16 x half> undef) |
| ret void |
| } |
| |
| define void @reduce_fmax16() { |
| ; CHECK-NOF16-LABEL: 'reduce_fmax16' |
| ; CHECK-NOF16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V2f16 = call half @llvm.vector.reduce.fmax.v2f16(<2 x half> undef) |
| ; CHECK-NOF16-NEXT: Cost Model: Found an estimated cost of 58 for instruction: %V4f16 = call half @llvm.vector.reduce.fmax.v4f16(<4 x half> undef) |
| ; CHECK-NOF16-NEXT: Cost Model: Found an estimated cost of 198 for instruction: %V8f16 = call half @llvm.vector.reduce.fmax.v8f16(<8 x half> undef) |
| ; CHECK-NOF16-NEXT: Cost Model: Found an estimated cost of 298 for instruction: %V16f16 = call half @llvm.vector.reduce.fmax.v16f16(<16 x half> undef) |
| ; CHECK-NOF16-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void |
| ; |
| ; CHECK-F16-LABEL: 'reduce_fmax16' |
| ; CHECK-F16-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2f16 = call half @llvm.vector.reduce.fmax.v2f16(<2 x half> undef) |
| ; CHECK-F16-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4f16 = call half @llvm.vector.reduce.fmax.v4f16(<4 x half> undef) |
| ; CHECK-F16-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8f16 = call half @llvm.vector.reduce.fmax.v8f16(<8 x half> undef) |
| ; CHECK-F16-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V16f16 = call half @llvm.vector.reduce.fmax.v16f16(<16 x half> undef) |
| ; CHECK-F16-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void |
| ; |
| %V2f16 = call half @llvm.vector.reduce.fmax.v2f16(<2 x half> undef) |
| %V4f16 = call half @llvm.vector.reduce.fmax.v4f16(<4 x half> undef) |
| %V8f16 = call half @llvm.vector.reduce.fmax.v8f16(<8 x half> undef) |
| %V16f16 = call half @llvm.vector.reduce.fmax.v16f16(<16 x half> undef) |
| ret void |
| } |
| |
| define void @reduce_fmin() { |
| ; CHECK-LABEL: 'reduce_fmin' |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2f32 = call float @llvm.vector.reduce.fmin.v2f32(<2 x float> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4f32 = call float @llvm.vector.reduce.fmin.v4f32(<4 x float> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8f32 = call float @llvm.vector.reduce.fmin.v8f32(<8 x float> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2f64 = call double @llvm.vector.reduce.fmin.v2f64(<2 x double> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4f64 = call double @llvm.vector.reduce.fmin.v4f64(<4 x double> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void |
| ; |
| %V2f32 = call float @llvm.vector.reduce.fmin.v2f32(<2 x float> undef) |
| %V4f32 = call float @llvm.vector.reduce.fmin.v4f32(<4 x float> undef) |
| %V8f32 = call float @llvm.vector.reduce.fmin.v8f32(<8 x float> undef) |
| %V2f64 = call double @llvm.vector.reduce.fmin.v2f64(<2 x double> undef) |
| %V4f64 = call double @llvm.vector.reduce.fmin.v4f64(<4 x double> undef) |
| ret void |
| } |
| |
| define void @reduce_fmax() { |
| ; CHECK-LABEL: 'reduce_fmax' |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2f32 = call float @llvm.vector.reduce.fmax.v2f32(<2 x float> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4f32 = call float @llvm.vector.reduce.fmax.v4f32(<4 x float> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8f32 = call float @llvm.vector.reduce.fmax.v8f32(<8 x float> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2f64 = call double @llvm.vector.reduce.fmax.v2f64(<2 x double> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4f64 = call double @llvm.vector.reduce.fmax.v4f64(<4 x double> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void |
| ; |
| %V2f32 = call float @llvm.vector.reduce.fmax.v2f32(<2 x float> undef) |
| %V4f32 = call float @llvm.vector.reduce.fmax.v4f32(<4 x float> undef) |
| %V8f32 = call float @llvm.vector.reduce.fmax.v8f32(<8 x float> undef) |
| %V2f64 = call double @llvm.vector.reduce.fmax.v2f64(<2 x double> undef) |
| %V4f64 = call double @llvm.vector.reduce.fmax.v4f64(<4 x double> undef) |
| ret void |
| } |
| |
| declare i8 @llvm.vector.reduce.umin.v1i8(<1 x i8>) |
| declare i8 @llvm.vector.reduce.umin.v3i8(<3 x i8>) |
| declare i8 @llvm.vector.reduce.umin.v4i8(<4 x i8>) |
| declare i8 @llvm.vector.reduce.umin.v8i8(<8 x i8>) |
| declare i8 @llvm.vector.reduce.umin.v16i8(<16 x i8>) |
| declare i8 @llvm.vector.reduce.umin.v32i8(<32 x i8>) |
| declare i8 @llvm.vector.reduce.umin.v64i8(<64 x i8>) |
| declare i16 @llvm.vector.reduce.umin.v2i16(<2 x i16>) |
| declare i16 @llvm.vector.reduce.umin.v4i16(<4 x i16>) |
| declare i16 @llvm.vector.reduce.umin.v8i16(<8 x i16>) |
| declare i16 @llvm.vector.reduce.umin.v16i16(<16 x i16>) |
| declare i32 @llvm.vector.reduce.umin.v2i32(<2 x i32>) |
| declare i32 @llvm.vector.reduce.umin.v4i32(<4 x i32>) |
| declare i32 @llvm.vector.reduce.umin.v8i32(<8 x i32>) |
| declare i64 @llvm.vector.reduce.umin.v2i64(<2 x i64>) |
| declare i64 @llvm.vector.reduce.umin.v4i64(<4 x i64>) |
| |
| declare i8 @llvm.vector.reduce.umax.v1i8(<1 x i8>) |
| declare i8 @llvm.vector.reduce.umax.v3i8(<3 x i8>) |
| declare i8 @llvm.vector.reduce.umax.v4i8(<4 x i8>) |
| declare i8 @llvm.vector.reduce.umax.v8i8(<8 x i8>) |
| declare i8 @llvm.vector.reduce.umax.v16i8(<16 x i8>) |
| declare i8 @llvm.vector.reduce.umax.v32i8(<32 x i8>) |
| declare i8 @llvm.vector.reduce.umax.v64i8(<64 x i8>) |
| declare i16 @llvm.vector.reduce.umax.v2i16(<2 x i16>) |
| declare i16 @llvm.vector.reduce.umax.v4i16(<4 x i16>) |
| declare i16 @llvm.vector.reduce.umax.v8i16(<8 x i16>) |
| declare i16 @llvm.vector.reduce.umax.v16i16(<16 x i16>) |
| declare i32 @llvm.vector.reduce.umax.v2i32(<2 x i32>) |
| declare i32 @llvm.vector.reduce.umax.v4i32(<4 x i32>) |
| declare i32 @llvm.vector.reduce.umax.v8i32(<8 x i32>) |
| declare i64 @llvm.vector.reduce.umax.v2i64(<2 x i64>) |
| declare i64 @llvm.vector.reduce.umax.v4i64(<4 x i64>) |
| |
| declare i8 @llvm.vector.reduce.smin.v1i8(<1 x i8>) |
| declare i8 @llvm.vector.reduce.smin.v3i8(<3 x i8>) |
| declare i8 @llvm.vector.reduce.smin.v4i8(<4 x i8>) |
| declare i8 @llvm.vector.reduce.smin.v8i8(<8 x i8>) |
| declare i8 @llvm.vector.reduce.smin.v16i8(<16 x i8>) |
| declare i8 @llvm.vector.reduce.smin.v32i8(<32 x i8>) |
| declare i8 @llvm.vector.reduce.smin.v64i8(<64 x i8>) |
| declare i16 @llvm.vector.reduce.smin.v2i16(<2 x i16>) |
| declare i16 @llvm.vector.reduce.smin.v4i16(<4 x i16>) |
| declare i16 @llvm.vector.reduce.smin.v8i16(<8 x i16>) |
| declare i16 @llvm.vector.reduce.smin.v16i16(<16 x i16>) |
| declare i32 @llvm.vector.reduce.smin.v2i32(<2 x i32>) |
| declare i32 @llvm.vector.reduce.smin.v4i32(<4 x i32>) |
| declare i32 @llvm.vector.reduce.smin.v8i32(<8 x i32>) |
| declare i64 @llvm.vector.reduce.smin.v2i64(<2 x i64>) |
| declare i64 @llvm.vector.reduce.smin.v4i64(<4 x i64>) |
| |
| declare i8 @llvm.vector.reduce.smax.v1i8(<1 x i8>) |
| declare i8 @llvm.vector.reduce.smax.v3i8(<3 x i8>) |
| declare i8 @llvm.vector.reduce.smax.v4i8(<4 x i8>) |
| declare i8 @llvm.vector.reduce.smax.v8i8(<8 x i8>) |
| declare i8 @llvm.vector.reduce.smax.v16i8(<16 x i8>) |
| declare i8 @llvm.vector.reduce.smax.v32i8(<32 x i8>) |
| declare i8 @llvm.vector.reduce.smax.v64i8(<64 x i8>) |
| declare i16 @llvm.vector.reduce.smax.v2i16(<2 x i16>) |
| declare i16 @llvm.vector.reduce.smax.v4i16(<4 x i16>) |
| declare i16 @llvm.vector.reduce.smax.v8i16(<8 x i16>) |
| declare i16 @llvm.vector.reduce.smax.v16i16(<16 x i16>) |
| declare i32 @llvm.vector.reduce.smax.v2i32(<2 x i32>) |
| declare i32 @llvm.vector.reduce.smax.v4i32(<4 x i32>) |
| declare i32 @llvm.vector.reduce.smax.v8i32(<8 x i32>) |
| declare i64 @llvm.vector.reduce.smax.v2i64(<2 x i64>) |
| declare i64 @llvm.vector.reduce.smax.v4i64(<4 x i64>) |
| |
| declare half @llvm.vector.reduce.fmin.v2f16(<2 x half>) |
| declare half @llvm.vector.reduce.fmin.v4f16(<4 x half>) |
| declare half @llvm.vector.reduce.fmin.v8f16(<8 x half>) |
| declare half @llvm.vector.reduce.fmin.v16f16(<16 x half>) |
| declare float @llvm.vector.reduce.fmin.v2f32(<2 x float>) |
| declare float @llvm.vector.reduce.fmin.v4f32(<4 x float>) |
| declare float @llvm.vector.reduce.fmin.v8f32(<8 x float>) |
| declare double @llvm.vector.reduce.fmin.v2f64(<2 x double>) |
| declare double @llvm.vector.reduce.fmin.v4f64(<4 x double>) |
| |
| declare half @llvm.vector.reduce.fmax.v2f16(<2 x half>) |
| declare half @llvm.vector.reduce.fmax.v4f16(<4 x half>) |
| declare half @llvm.vector.reduce.fmax.v8f16(<8 x half>) |
| declare half @llvm.vector.reduce.fmax.v16f16(<16 x half>) |
| declare float @llvm.vector.reduce.fmax.v2f32(<2 x float>) |
| declare float @llvm.vector.reduce.fmax.v4f32(<4 x float>) |
| declare float @llvm.vector.reduce.fmax.v8f32(<8 x float>) |
| declare double @llvm.vector.reduce.fmax.v2f64(<2 x double>) |
| declare double @llvm.vector.reduce.fmax.v4f64(<4 x double>) |