Add Loop Sink pass to reverse the LICM based of basic block frequency.
Summary: LICM may hoist instructions to preheader speculatively. Before code generation, we need to sink down the hoisted instructions inside to loop if it's beneficial. This pass is a reverse of LICM: looking at instructions in preheader and sinks the instruction to basic blocks inside the loop body if basic block frequency is smaller than the preheader frequency.
Reviewers: hfinkel, davidxl, chandlerc
Subscribers: anna, modocache, mgorny, beanz, reames, dberlin, chandlerc, mcrosier, junbuml, sanjoy, mzolotukhin, llvm-commits
Differential Revision: https://reviews.llvm.org/D22778
llvm-svn: 285308
2016-10-28 00:30:08 +08:00
|
|
|
; RUN: opt -S -licm < %s | FileCheck %s --check-prefix=CHECK-LICM
|
|
|
|
|
; RUN: opt -S -licm < %s | opt -S -loop-sink | FileCheck %s --check-prefix=CHECK-SINK
|
|
|
|
|
|
|
|
|
|
; Original source code:
|
|
|
|
|
; int g;
|
|
|
|
|
; int foo(int p, int x) {
|
|
|
|
|
; for (int i = 0; i != x; i++)
|
|
|
|
|
; if (__builtin_expect(i == p, 0)) {
|
|
|
|
|
; x += g; x *= g;
|
|
|
|
|
; }
|
|
|
|
|
; return x;
|
|
|
|
|
; }
|
|
|
|
|
;
|
|
|
|
|
; Load of global value g should not be hoisted to preheader.
|
|
|
|
|
|
|
|
|
|
@g = global i32 0, align 4
|
|
|
|
|
|
2016-11-09 08:58:19 +08:00
|
|
|
define i32 @foo(i32, i32) #0 !prof !2 {
|
Add Loop Sink pass to reverse the LICM based of basic block frequency.
Summary: LICM may hoist instructions to preheader speculatively. Before code generation, we need to sink down the hoisted instructions inside to loop if it's beneficial. This pass is a reverse of LICM: looking at instructions in preheader and sinks the instruction to basic blocks inside the loop body if basic block frequency is smaller than the preheader frequency.
Reviewers: hfinkel, davidxl, chandlerc
Subscribers: anna, modocache, mgorny, beanz, reames, dberlin, chandlerc, mcrosier, junbuml, sanjoy, mzolotukhin, llvm-commits
Differential Revision: https://reviews.llvm.org/D22778
llvm-svn: 285308
2016-10-28 00:30:08 +08:00
|
|
|
%3 = icmp eq i32 %1, 0
|
|
|
|
|
br i1 %3, label %._crit_edge, label %.lr.ph.preheader
|
|
|
|
|
|
|
|
|
|
.lr.ph.preheader:
|
|
|
|
|
br label %.lr.ph
|
|
|
|
|
|
|
|
|
|
; CHECK-LICM: .lr.ph.preheader:
|
|
|
|
|
; CHECK-LICM: load i32, i32* @g
|
|
|
|
|
; CHECK-LICM: br label %.lr.ph
|
|
|
|
|
|
|
|
|
|
.lr.ph:
|
|
|
|
|
%.03 = phi i32 [ %8, %.combine ], [ 0, %.lr.ph.preheader ]
|
|
|
|
|
%.012 = phi i32 [ %.1, %.combine ], [ %1, %.lr.ph.preheader ]
|
|
|
|
|
%4 = icmp eq i32 %.03, %0
|
|
|
|
|
br i1 %4, label %.then, label %.combine, !prof !1
|
|
|
|
|
|
|
|
|
|
.then:
|
|
|
|
|
%5 = load i32, i32* @g, align 4
|
|
|
|
|
%6 = add nsw i32 %5, %.012
|
|
|
|
|
%7 = mul nsw i32 %6, %5
|
|
|
|
|
br label %.combine
|
|
|
|
|
|
|
|
|
|
; CHECK-SINK: .then:
|
|
|
|
|
; CHECK-SINK: load i32, i32* @g
|
|
|
|
|
; CHECK-SINK: br label %.combine
|
|
|
|
|
|
|
|
|
|
.combine:
|
|
|
|
|
%.1 = phi i32 [ %7, %.then ], [ %.012, %.lr.ph ]
|
|
|
|
|
%8 = add nuw nsw i32 %.03, 1
|
|
|
|
|
%9 = icmp eq i32 %8, %.1
|
|
|
|
|
br i1 %9, label %._crit_edge.loopexit, label %.lr.ph
|
|
|
|
|
|
|
|
|
|
._crit_edge.loopexit:
|
|
|
|
|
%.1.lcssa = phi i32 [ %.1, %.combine ]
|
|
|
|
|
br label %._crit_edge
|
|
|
|
|
|
|
|
|
|
._crit_edge:
|
|
|
|
|
%.01.lcssa = phi i32 [ 0, %2 ], [ %.1.lcssa, %._crit_edge.loopexit ]
|
|
|
|
|
ret i32 %.01.lcssa
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
!1 = !{!"branch_weights", i32 1, i32 2000}
|
2016-11-09 08:58:19 +08:00
|
|
|
!2 = !{!"function_entry_count", i64 1}
|
