Skip to content

[NFC][AArch64] Tests for guarding unrolling with scalable vec ins/ext #81132

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Feb 19, 2024
Merged

[NFC][AArch64] Tests for guarding unrolling with scalable vec ins/ext #81132

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
d25b58f
[NFC][AArch64] Precommit tests for guarding unrolling with scalable s…
huntergr-arm Feb 7, 2024
4047162
Add direct cost model tests, remove negative case from unroll test
huntergr-arm Feb 9, 2024
c734bdc
Add tests with predicate types, change vector params to undef
huntergr-arm Feb 14, 2024
e939d4b
Add a test to extract a fixed width predicate from a scalable predicate
huntergr-arm Feb 15, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
57 changes: 57 additions & 0 deletions llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,61 @@ declare <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v16i32(<vscale x 4 x i32>
declare <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv16i32(<vscale x 16 x i32>, i64)
declare <vscale x 16 x i32> @llvm.vector.insert.nxv16i32.nxv4i32(<vscale x 16 x i32>, <vscale x 4 x i32>, i64)

define void @vector_insert_extract_idxzero_128b() #1 {
; CHECK-LABEL: 'vector_insert_extract_idxzero_128b'
; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %insert_legal_fixed_into_scalable = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v4f32(<vscale x 4 x float> undef, <4 x float> undef, i64 0)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %extract_legal_fixed_from_scalable = call <2 x double> @llvm.vector.extract.v2f64.nxv2f64(<vscale x 2 x double> undef, i64 0)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.nxv2i1(<vscale x 16 x i1> undef, <vscale x 2 x i1> undef, i64 0)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> undef, i64 0)
; CHECK-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> undef, i64 0)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; TYPE_BASED_ONLY-LABEL: 'vector_insert_extract_idxzero_128b'
; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %insert_legal_fixed_into_scalable = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v4f32(<vscale x 4 x float> undef, <4 x float> undef, i64 0)
; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %extract_legal_fixed_from_scalable = call <2 x double> @llvm.vector.extract.v2f64.nxv2f64(<vscale x 2 x double> undef, i64 0)
; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.nxv2i1(<vscale x 16 x i1> undef, <vscale x 2 x i1> undef, i64 0)
; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> undef, i64 0)
; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> undef, i64 0)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%insert_legal_fixed_into_scalable = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v4f32(<vscale x 4 x float> undef, <4 x float> undef, i64 0)
%extract_legal_fixed_from_scalable = call <2 x double> @llvm.vector.extract.v2f64.nxv2f64(<vscale x 2 x double> undef, i64 0)
%insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.v2i1(<vscale x 16 x i1> undef, <vscale x 2 x i1> undef, i64 0)
%extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> undef, i64 0)
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

nit: Could you also add a test-case of extracting a fixed-length predicate from a scalable predicate, e.g. <8 x i1> from a <vscale x 8 x i1> ?

%extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> undef, i64 0)
ret void
}
declare <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v4f32(<vscale x 4 x float>, <4 x float>, i64)
declare <2 x double> @llvm.vector.extract.v2f64.nxv2f64(<vscale x 2 x double>, i64)
declare <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.v2i1(<vscale x 16 x i1>, <vscale x 2 x i1>, i64)
declare <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1>, i64)

define void @vector_insert_extract_idxzero_256b() #2 {
; CHECK-LABEL: 'vector_insert_extract_idxzero_256b'
; CHECK-NEXT: Cost Model: Found an estimated cost of 60 for instruction: %insert_legal_fixed_into_scalable = call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v16i16(<vscale x 8 x i16> undef, <16 x i16> undef, i64 0)
; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %extract_legal_fixed_from_scalable = call <8 x float> @llvm.vector.extract.v8f32.nxv4f32(<vscale x 4 x float> undef, i64 0)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.nxv2i1(<vscale x 16 x i1> undef, <vscale x 2 x i1> undef, i64 0)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> undef, i64 0)
; CHECK-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> undef, i64 0)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; TYPE_BASED_ONLY-LABEL: 'vector_insert_extract_idxzero_256b'
; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %insert_legal_fixed_into_scalable = call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v16i16(<vscale x 8 x i16> undef, <16 x i16> undef, i64 0)
; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %extract_legal_fixed_from_scalable = call <8 x float> @llvm.vector.extract.v8f32.nxv4f32(<vscale x 4 x float> undef, i64 0)
; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.nxv2i1(<vscale x 16 x i1> undef, <vscale x 2 x i1> undef, i64 0)
; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> undef, i64 0)
; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> undef, i64 0)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%insert_legal_fixed_into_scalable = call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v16i16(<vscale x 8 x i16> undef, <16 x i16> undef, i64 0)
%extract_legal_fixed_from_scalable = call <8 x float> @llvm.vector.extract.v8f32.nx4f32(<vscale x 4 x float> undef, i64 0)
%insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.v2i1(<vscale x 16 x i1> undef, <vscale x 2 x i1> undef, i64 0)
%extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> undef, i64 0)
%extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> undef, i64 0)
ret void
}
declare <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v16i16(<vscale x 8 x i16>, <16 x i16>, i64)
declare <8 x float> @llvm.vector.extract.v8f32.nxv4f32(<vscale x 4 x float>, i64)

define void @reductions(<vscale x 4 x i32> %v0, <vscale x 4 x i64> %v1, <vscale x 4 x float> %v2, <vscale x 4 x double> %v3) {
; CHECK-LABEL: 'reductions'
Expand Down Expand Up @@ -864,3 +919,5 @@ declare void @llvm.masked.scatter.v4i32(<4 x i32> %data, <4 x ptr> %ptrs, i32 %a
declare void @llvm.masked.scatter.v1i128.v1p0(<1 x i128> %data, <1 x ptr> %ptrs, i32 %align, <1 x i1> %masks)

attributes #0 = { "target-features"="+sve,+bf16" }
attributes #1 = { "target-features"="+sve" vscale_range(1,16) }
attributes #2 = { "target-features"="+sve" vscale_range(2, 16) }
63 changes: 63 additions & 0 deletions llvm/test/Transforms/LoopUnroll/AArch64/scalable-vec-ins-ext.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,63 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 3
; RUN: opt -passes=loop-unroll,simplifycfg -S -mtriple aarch64 %s | FileCheck %s

;; This test contains IR similar to what would be generated when SVE ACLE
;; routines are used with fixed-width vector types -- lots of subvector inserts
;; and extracts that are effectively just bitcasts since the types are the
;; same at a given SVE bit size. We want to make sure that they are not a
;; barrier to unrolling simple loops with a fixed trip count which could be
;; further optimized.

define void @test_ins_ext_cost(ptr readonly %a, ptr readonly %b, ptr readonly %c, ptr noalias %d) #0 {
; CHECK-LABEL: define void @test_ins_ext_cost(
; CHECK-SAME: ptr readonly [[A:%.*]], ptr readonly [[B:%.*]], ptr readonly [[C:%.*]], ptr noalias [[D:%.*]]) #[[ATTR0:[0-9]+]] {
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[EXIT_COND:%.*]] = phi i1 [ true, [[ENTRY:%.*]] ], [ false, [[FOR_BODY]] ]
; CHECK-NEXT: [[IV:%.*]] = phi i64 [ 0, [[ENTRY]] ], [ 1, [[FOR_BODY]] ]
; CHECK-NEXT: [[GEP_A:%.*]] = getelementptr inbounds <8 x float>, ptr [[A]], i64 [[IV]]
; CHECK-NEXT: [[LOAD_A:%.*]] = load <8 x float>, ptr [[GEP_A]], align 16
; CHECK-NEXT: [[GEP_B:%.*]] = getelementptr inbounds <8 x float>, ptr [[B]], i64 [[IV]]
; CHECK-NEXT: [[LOAD_B:%.*]] = load <8 x float>, ptr [[GEP_B]], align 16
; CHECK-NEXT: [[GEP_C:%.*]] = getelementptr inbounds <8 x float>, ptr [[C]], i64 [[IV]]
; CHECK-NEXT: [[LOAD_C:%.*]] = load <8 x float>, ptr [[GEP_C]], align 16
; CHECK-NEXT: [[CAST_SCALABLE_B:%.*]] = tail call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v8f32(<vscale x 4 x float> undef, <8 x float> [[LOAD_B]], i64 0)
; CHECK-NEXT: [[CAST_SCALABLE_C:%.*]] = tail call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v8f32(<vscale x 4 x float> undef, <8 x float> [[LOAD_C]], i64 0)
; CHECK-NEXT: [[ADD:%.*]] = fadd <vscale x 4 x float> [[CAST_SCALABLE_B]], [[CAST_SCALABLE_C]]
; CHECK-NEXT: [[CAST_SCALABLE_A:%.*]] = tail call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v8f32(<vscale x 4 x float> undef, <8 x float> [[LOAD_A]], i64 0)
; CHECK-NEXT: [[MUL:%.*]] = fmul <vscale x 4 x float> [[CAST_SCALABLE_A]], [[ADD]]
; CHECK-NEXT: [[CAST_FIXED_D:%.*]] = tail call <8 x float> @llvm.vector.extract.v8f32.nxv4f32(<vscale x 4 x float> [[MUL]], i64 0)
; CHECK-NEXT: [[GEP_D:%.*]] = getelementptr inbounds <8 x float>, ptr [[D]], i64 0, i64 [[IV]]
; CHECK-NEXT: store <8 x float> [[CAST_FIXED_D]], ptr [[GEP_D]], align 16
; CHECK-NEXT: br i1 [[EXIT_COND]], label [[FOR_BODY]], label [[EXIT:%.*]]
; CHECK: exit:
; CHECK-NEXT: ret void
;
entry:
br label %for.body

for.body:
%exit.cond = phi i1 [ true, %entry ], [ false, %for.body ]
%iv = phi i64 [ 0, %entry ], [ 1, %for.body ]
%gep.a = getelementptr inbounds <8 x float>, ptr %a, i64 %iv
%load.a = load <8 x float>, ptr %gep.a, align 16
%gep.b = getelementptr inbounds <8 x float>, ptr %b, i64 %iv
%load.b = load <8 x float>, ptr %gep.b, align 16
%gep.c = getelementptr inbounds <8 x float>, ptr %c, i64 %iv
%load.c = load <8 x float>, ptr %gep.c, align 16
%cast.scalable.b = tail call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v8f32(<vscale x 4 x float> undef, <8 x float> %load.b, i64 0)
%cast.scalable.c = tail call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v8f32(<vscale x 4 x float> undef, <8 x float> %load.c, i64 0)
%add = fadd <vscale x 4 x float> %cast.scalable.b, %cast.scalable.c
%cast.scalable.a = tail call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v8f32(<vscale x 4 x float> undef, <8 x float> %load.a, i64 0)
%mul = fmul <vscale x 4 x float> %cast.scalable.a, %add
%cast.fixed.d = tail call <8 x float> @llvm.vector.extract.v8f32.nxv4f32(<vscale x 4 x float> %mul, i64 0)
%gep.d = getelementptr inbounds <8 x float>, ptr %d, i64 0, i64 %iv
store <8 x float> %cast.fixed.d, ptr %gep.d, align 16
br i1 %exit.cond, label %for.body, label %exit

exit:
ret void
}

attributes #0 = { "target-features"="+sve" vscale_range(2, 16) }