a5891fa4d2
This patch starts initial modeling of VF * UF in VPlan. Initially, introduce a dedicated VFxUF VPValue, which is then populated during VPlan::prepareToExecute. Initially, the VF * UF applies only to the main vector loop region. Once we extend the scope of VPlan in the future, we may want to associate different VFxUFs with different vector loop regions (e.g. the epilogue vector loop) This allows explicitly parameterizing recipes that rely on the VF * UF, like the canonical induction increment. At the moment, this mainly helps to avoid generating some duplicated calls to vscale with scalable vectors. It should also allow using EVL as induction increments explicitly in D99750. Referring to VF * UF is also needed in other places that we plan to migrate to VPlan, like the minimum trip count check during skeleton creation. The first version creates the value for VF * UF directly in prepareToExecute to limit the scope of the patch. A follow-on patch will model VF * UF computation explicitly in VPlan using recipes. Moved from Phabricator (https://reviews.llvm.org/D157322)
61 lines
3.0 KiB
LLVM
61 lines
3.0 KiB
LLVM
; REQUIRES: asserts
|
|
|
|
; RUN: opt -passes=loop-vectorize -debug-only=loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -vplan-print-in-dot-format -disable-output %s 2>&1 | FileCheck %s
|
|
|
|
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
|
|
|
|
; Verify that -vplan-print-in-dot-format option works.
|
|
|
|
define void @print_call_and_memory(i64 %n, ptr noalias %y, ptr noalias %x) nounwind uwtable {
|
|
; CHECK: digraph VPlan {
|
|
; CHECK-NEXT: graph [labelloc=t, fontsize=30; label="Vectorization Plan\nInitial VPlan for VF=\{4\},UF\>=1\nLive-in vp\<[[VFxUF:%.+]]\> = VF * UF\nLive-in vp\<[[VEC_TC:%.+]]\> = vector-trip-count\nLive-in ir\<%n\> = original trip-count\n"]
|
|
; CHECK-NEXT: node [shape=rect, fontname=Courier, fontsize=30]
|
|
; CHECK-NEXT: edge [fontname=Courier, fontsize=30]
|
|
; CHECK-NEXT: compound=true
|
|
; CHECK-NEXT: N0 [label =
|
|
; CHECK-NEXT: "ph:\l" +
|
|
; CHECK-NEXT: "No successors\l"
|
|
; CHECK-NEXT: ]
|
|
; CHECK-NEXT: N1 [label =
|
|
; CHECK-NEXT: "vector.ph:\l" +
|
|
; CHECK-NEXT: "Successor(s): vector loop\l"
|
|
; CHECK-NEXT: ]
|
|
; CHECK-NEXT: N1 -> N2 [ label="" lhead=cluster_N3]
|
|
; CHECK-NEXT: subgraph cluster_N3 {
|
|
; CHECK-NEXT: fontname=Courier
|
|
; CHECK-NEXT: label="\<x1\> vector loop"
|
|
; CHECK-NEXT: N2 [label =
|
|
; CHECK-NEXT: "vector.body:\l" +
|
|
; CHECK-NEXT: " EMIT vp\<[[CAN_IV:%.+]]\> = CANONICAL-INDUCTION ir\<0\>, vp\<[[CAN_IV_NEXT:%.+]]\>\l" +
|
|
; CHECK-NEXT: " vp\<[[STEPS:%.+]]\> = SCALAR-STEPS vp\<[[CAN_IV]]\>, ir\<1\>\l" +
|
|
; CHECK-NEXT: " CLONE ir\<%arrayidx\> = getelementptr inbounds ir\<%y\>, vp\<[[STEPS]]\>\l" +
|
|
; CHECK-NEXT: " WIDEN ir\<%lv\> = load ir\<%arrayidx\>\l" +
|
|
; CHECK-NEXT: " WIDEN-CALL ir\<%call\> = call @llvm.sqrt.f32(ir\<%lv\>) (using vector intrinsic)\l" +
|
|
; CHECK-NEXT: " CLONE ir\<%arrayidx2\> = getelementptr inbounds ir\<%x\>, vp\<[[STEPS]]\>\l" +
|
|
; CHECK-NEXT: " WIDEN store ir\<%arrayidx2\>, ir\<%call\>\l" +
|
|
; CHECK-NEXT: " EMIT vp\<[[CAN_IV_NEXT]]\> = add nuw vp\<[[CAN_IV]]\>, vp\<[[VFxUF]]\>\l" +
|
|
; CHECK-NEXT: " EMIT branch-on-count vp\<[[CAN_IV_NEXT]]\>, vp\<[[VEC_TC]]\>\l" +
|
|
; CHECK-NEXT: "No successors\l"
|
|
; CHECK-NEXT: ]
|
|
;
|
|
entry:
|
|
%cmp6 = icmp sgt i64 %n, 0
|
|
br i1 %cmp6, label %for.body, label %for.end
|
|
|
|
for.body: ; preds = %entry, %for.body
|
|
%iv = phi i64 [ %iv.next, %for.body ], [ 0, %entry ]
|
|
%arrayidx = getelementptr inbounds float, ptr %y, i64 %iv
|
|
%lv = load float, ptr %arrayidx, align 4
|
|
%call = tail call float @llvm.sqrt.f32(float %lv) nounwind readnone
|
|
%arrayidx2 = getelementptr inbounds float, ptr %x, i64 %iv
|
|
store float %call, ptr %arrayidx2, align 4
|
|
%iv.next = add i64 %iv, 1
|
|
%exitcond = icmp eq i64 %iv.next, %n
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
for.end: ; preds = %for.body, %entry
|
|
ret void
|
|
}
|
|
|
|
declare float @llvm.sqrt.f32(float) nounwind readnone
|