Doomhowl-Interactive/llvm-project
0
0
Fork 0
Code Issues Pull Requests Actions 5 Packages Projects Releases Wiki Activity
Files
main
llvm-project/llvm/test/Transforms/LoopVectorize/minimumnum-maximumnum-reductions.ll
David Sherwood ba91dd14b9 [LV][NFC] Remove unneeded LLVM intrinsic declarations (#190993) 
We no longer need to declare LLVM intrinsics in .ll files as the
intrinsics are populated automatically in the module. Remove the
declarations from tests to reduce test noise and size.

This came from a suggestion on PR #190786.
2026-04-09 11:41:18 +01:00

189 lines
9.7 KiB
LLVM
Raw Permalink Blame History

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
; RUN: opt -passes=loop-vectorize -force-vector-width=2 -force-vector-interleave=2 -S %s | FileCheck %s
; RUN: opt -passes=loop-vectorize -force-vector-width=2 -force-vector-interleave=2 -prefer-inloop-reductions -S %s | FileCheck %s
define float @maximumnum_intrinsic(ptr readonly %x) {
; CHECK-LABEL: define float @maximumnum_intrinsic(
; CHECK-SAME: ptr readonly [[X:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: br label %[[VECTOR_PH:.*]]
; CHECK: [[VECTOR_PH]]:
; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
; CHECK: [[VECTOR_BODY]]:
; CHECK-NEXT: [[IV:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <2 x float> [ zeroinitializer, %[[VECTOR_PH]] ], [ [[TMP3:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_PHI1:%.*]] = phi <2 x float> [ zeroinitializer, %[[VECTOR_PH]] ], [ [[TMP4:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds float, ptr [[X]], i32 [[IV]]
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds float, ptr [[GEP]], i64 2
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <2 x float>, ptr [[GEP]], align 4
; CHECK-NEXT: [[WIDE_LOAD2:%.*]] = load <2 x float>, ptr [[TMP2]], align 4
; CHECK-NEXT: [[TMP3]] = call <2 x float> @llvm.maximumnum.v2f32(<2 x float> [[VEC_PHI]], <2 x float> [[WIDE_LOAD]])
; CHECK-NEXT: [[TMP4]] = call <2 x float> @llvm.maximumnum.v2f32(<2 x float> [[VEC_PHI1]], <2 x float> [[WIDE_LOAD2]])
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[IV]], 4
; CHECK-NEXT: [[TMP5:%.*]] = icmp eq i32 [[INDEX_NEXT]], 1024
; CHECK-NEXT: br i1 [[TMP5]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[RDX_MINMAX:%.*]] = call <2 x float> @llvm.maximumnum.v2f32(<2 x float> [[TMP3]], <2 x float> [[TMP4]])
; CHECK-NEXT: [[TMP6:%.*]] = call float @llvm.vector.reduce.fmax.v2f32(<2 x float> [[RDX_MINMAX]])
; CHECK-NEXT: br label %[[EXIT:.*]]
; CHECK: [[EXIT]]:
; CHECK-NEXT: ret float [[TMP6]]
;
entry:
br label %loop
loop:
%iv = phi i32 [ 0, %entry ], [ %inc, %loop ]
%red = phi float [ 0.000000e+00, %entry ], [ %red.next, %loop ]
%gep = getelementptr inbounds float, ptr %x, i32 %iv
%l = load float, ptr %gep, align 4
%red.next = tail call float @llvm.maximumnum.f32(float %red, float %l)
%inc = add nuw nsw i32 %iv, 1
%ec = icmp eq i32 %inc, 1024
br i1 %ec, label %exit, label %loop
exit:
ret float %red.next
}
define float @maximumnum_intrinsic_fast(ptr readonly %x) {
; CHECK-LABEL: define float @maximumnum_intrinsic_fast(
; CHECK-SAME: ptr readonly [[X:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: br label %[[VECTOR_PH:.*]]
; CHECK: [[VECTOR_PH]]:
; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
; CHECK: [[VECTOR_BODY]]:
; CHECK-NEXT: [[IV:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <2 x float> [ zeroinitializer, %[[VECTOR_PH]] ], [ [[TMP3:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_PHI1:%.*]] = phi <2 x float> [ zeroinitializer, %[[VECTOR_PH]] ], [ [[TMP4:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds float, ptr [[X]], i32 [[IV]]
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds float, ptr [[GEP]], i64 2
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <2 x float>, ptr [[GEP]], align 4
; CHECK-NEXT: [[WIDE_LOAD2:%.*]] = load <2 x float>, ptr [[TMP2]], align 4
; CHECK-NEXT: [[TMP3]] = call fast <2 x float> @llvm.maximumnum.v2f32(<2 x float> [[VEC_PHI]], <2 x float> [[WIDE_LOAD]])
; CHECK-NEXT: [[TMP4]] = call fast <2 x float> @llvm.maximumnum.v2f32(<2 x float> [[VEC_PHI1]], <2 x float> [[WIDE_LOAD2]])
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[IV]], 4
; CHECK-NEXT: [[TMP5:%.*]] = icmp eq i32 [[INDEX_NEXT]], 1024
; CHECK-NEXT: br i1 [[TMP5]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[RDX_MINMAX:%.*]] = call fast <2 x float> @llvm.maximumnum.v2f32(<2 x float> [[TMP3]], <2 x float> [[TMP4]])
; CHECK-NEXT: [[TMP6:%.*]] = call fast float @llvm.vector.reduce.fmax.v2f32(<2 x float> [[RDX_MINMAX]])
; CHECK-NEXT: br label %[[EXIT:.*]]
; CHECK: [[EXIT]]:
; CHECK-NEXT: ret float [[TMP6]]
;
entry:
br label %loop
loop:
%iv = phi i32 [ 0, %entry ], [ %inc, %loop ]
%red = phi float [ 0.000000e+00, %entry ], [ %red.next, %loop ]
%gep = getelementptr inbounds float, ptr %x, i32 %iv
%l = load float, ptr %gep, align 4
%red.next = tail call fast float @llvm.maximumnum.f32(float %red, float %l)
%inc = add nuw nsw i32 %iv, 1
%ec = icmp eq i32 %inc, 1024
br i1 %ec, label %exit, label %loop
exit:
ret float %red.next
}
define float @minimumnum_intrinsic(ptr readonly %x) {
; CHECK-LABEL: define float @minimumnum_intrinsic(
; CHECK-SAME: ptr readonly [[X:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: br label %[[VECTOR_PH:.*]]
; CHECK: [[VECTOR_PH]]:
; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
; CHECK: [[VECTOR_BODY]]:
; CHECK-NEXT: [[IV:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <2 x float> [ zeroinitializer, %[[VECTOR_PH]] ], [ [[TMP3:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_PHI1:%.*]] = phi <2 x float> [ zeroinitializer, %[[VECTOR_PH]] ], [ [[TMP4:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds float, ptr [[X]], i32 [[IV]]
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds float, ptr [[GEP]], i64 2
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <2 x float>, ptr [[GEP]], align 4
; CHECK-NEXT: [[WIDE_LOAD2:%.*]] = load <2 x float>, ptr [[TMP2]], align 4
; CHECK-NEXT: [[TMP3]] = call <2 x float> @llvm.minimumnum.v2f32(<2 x float> [[VEC_PHI]], <2 x float> [[WIDE_LOAD]])
; CHECK-NEXT: [[TMP4]] = call <2 x float> @llvm.minimumnum.v2f32(<2 x float> [[VEC_PHI1]], <2 x float> [[WIDE_LOAD2]])
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[IV]], 4
; CHECK-NEXT: [[TMP5:%.*]] = icmp eq i32 [[INDEX_NEXT]], 1024
; CHECK-NEXT: br i1 [[TMP5]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[RDX_MINMAX:%.*]] = call <2 x float> @llvm.minimumnum.v2f32(<2 x float> [[TMP3]], <2 x float> [[TMP4]])
; CHECK-NEXT: [[TMP6:%.*]] = call float @llvm.vector.reduce.fmin.v2f32(<2 x float> [[RDX_MINMAX]])
; CHECK-NEXT: br label %[[EXIT:.*]]
; CHECK: [[EXIT]]:
; CHECK-NEXT: ret float [[TMP6]]
;
entry:
br label %loop
loop:
%iv = phi i32 [ 0, %entry ], [ %inc, %loop ]
%red = phi float [ 0.000000e+00, %entry ], [ %red.next, %loop ]
%gep = getelementptr inbounds float, ptr %x, i32 %iv
%l = load float, ptr %gep, align 4
%red.next = tail call float @llvm.minimumnum.f32(float %red, float %l)
%inc = add nuw nsw i32 %iv, 1
%ec = icmp eq i32 %inc, 1024
br i1 %ec, label %exit, label %loop
exit:
ret float %red.next
}
define float @minimumnum_intrinsic_fast(ptr readonly %x) {
; CHECK-LABEL: define float @minimumnum_intrinsic_fast(
; CHECK-SAME: ptr readonly [[X:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: br label %[[VECTOR_PH:.*]]
; CHECK: [[VECTOR_PH]]:
; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
; CHECK: [[VECTOR_BODY]]:
; CHECK-NEXT: [[IV:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <2 x float> [ zeroinitializer, %[[VECTOR_PH]] ], [ [[TMP3:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_PHI1:%.*]] = phi <2 x float> [ zeroinitializer, %[[VECTOR_PH]] ], [ [[TMP4:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds float, ptr [[X]], i32 [[IV]]
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds float, ptr [[GEP]], i64 2
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <2 x float>, ptr [[GEP]], align 4
; CHECK-NEXT: [[WIDE_LOAD2:%.*]] = load <2 x float>, ptr [[TMP2]], align 4
; CHECK-NEXT: [[TMP3]] = call fast <2 x float> @llvm.minimumnum.v2f32(<2 x float> [[VEC_PHI]], <2 x float> [[WIDE_LOAD]])
; CHECK-NEXT: [[TMP4]] = call fast <2 x float> @llvm.minimumnum.v2f32(<2 x float> [[VEC_PHI1]], <2 x float> [[WIDE_LOAD2]])
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[IV]], 4
; CHECK-NEXT: [[TMP5:%.*]] = icmp eq i32 [[INDEX_NEXT]], 1024
; CHECK-NEXT: br i1 [[TMP5]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[RDX_MINMAX:%.*]] = call fast <2 x float> @llvm.minimumnum.v2f32(<2 x float> [[TMP3]], <2 x float> [[TMP4]])
; CHECK-NEXT: [[TMP6:%.*]] = call fast float @llvm.vector.reduce.fmin.v2f32(<2 x float> [[RDX_MINMAX]])
; CHECK-NEXT: br label %[[EXIT:.*]]
; CHECK: [[EXIT]]:
; CHECK-NEXT: ret float [[TMP6]]
;
entry:
br label %loop
loop:
%iv = phi i32 [ 0, %entry ], [ %inc, %loop ]
%red = phi float [ 0.000000e+00, %entry ], [ %red.next, %loop ]
%gep = getelementptr inbounds float, ptr %x, i32 %iv
%l = load float, ptr %gep, align 4
%red.next = tail call fast float @llvm.minimumnum.f32(float %red, float %l)
%inc = add nuw nsw i32 %iv, 1
%ec = icmp eq i32 %inc, 1024
br i1 %ec, label %exit, label %loop
exit:
ret float %red.next
}
;.
; CHECK: [[LOOP0]] = distinct !{[[LOOP0]], [[META1:![0-9]+]], [[META2:![0-9]+]]}
; CHECK: [[META1]] = !{!"llvm.loop.isvectorized", i32 1}
; CHECK: [[META2]] = !{!"llvm.loop.unroll.runtime.disable"}
; CHECK: [[LOOP3]] = distinct !{[[LOOP3]], [[META1]], [[META2]]}
; CHECK: [[LOOP4]] = distinct !{[[LOOP4]], [[META1]], [[META2]]}
; CHECK: [[LOOP5]] = distinct !{[[LOOP5]], [[META1]], [[META2]]}
;.
Reference in New Issue View Git Blame Copy Permalink