mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-23 19:23:23 +01:00
d2570e78cd
Summary:
This is the last functional patch affecting the representation of DDG.
Here we try to simplify the DDG to reduce the number of nodes and edges by
iteratively merging pairs of nodes that satisfy the following conditions,
until no such pair can be identified. A pair of nodes consisting of a and b
can be merged if:
1. the only edge from a is a def-use edge to b and
2. the only edge to b is a def-use edge from a and
3. there is no cyclic edge from b to a and
4. all instructions in a and b belong to the same basic block and
5. both a and b are simple (single or multi instruction) nodes.
These criteria allow us to fold many uninteresting def-use edges that
commonly exist in the graph while avoiding the risk of introducing
dependencies that didn't exist before.
Authored By: bmahjour
Reviewer: Meinersbur, fhahn, myhsu, xtian, dmgreen, kbarton, jdoerfert
Reviewed By: Meinersbur
Subscribers: ychen, arphaman, simoll, a.elovikov, mgorny, hiraditya, jfb, wuzish, llvm-commits, jsji, Whitney, etiotto, ppc-slack
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D72350
198 lines
7.0 KiB
LLVM
198 lines
7.0 KiB
LLVM
; RUN: opt < %s -disable-output "-passes=print<ddg>" 2>&1 | FileCheck %s
|
|
|
|
; CHECK-LABEL: 'DDG' for loop 'test1.for.body':
|
|
|
|
; CHECK: Node Address:[[N1:0x[0-9a-f]*]]:pi-block
|
|
; CHECK-NEXT:--- start of nodes in pi-block ---
|
|
; CHECK: Node Address:[[N2:0x[0-9a-f]*]]:single-instruction
|
|
; CHECK-NEXT: Instructions:
|
|
; CHECK-NEXT: %i.02 = phi i64 [ %inc, %test1.for.body ], [ 1, %test1.for.body.preheader ]
|
|
; CHECK-NEXT: Edges:
|
|
; CHECK-NEXT: [def-use] to [[N3:0x[0-9a-f]*]]
|
|
|
|
; CHECK: Node Address:[[N3]]:single-instruction
|
|
; CHECK-NEXT: Instructions:
|
|
; CHECK-NEXT: %inc = add i64 %i.02, 1
|
|
; CHECK-NEXT: Edges:
|
|
; CHECK-NEXT: [def-use] to [[N2]]
|
|
; CHECK-NEXT:--- end of nodes in pi-block ---
|
|
; CHECK-NEXT: Edges:
|
|
; CHECK-NEXT: [def-use] to [[N4:0x[0-9a-f]*]]
|
|
; CHECK-NEXT: [def-use] to [[N5:0x[0-9a-f]*]]
|
|
; CHECK-NEXT: [def-use] to [[N6:0x[0-9a-f]*]]
|
|
; CHECK-NEXT: [def-use] to [[N7:0x[0-9a-f]*]]
|
|
|
|
; CHECK: Node Address:[[N7]]:multi-instruction
|
|
; CHECK-NEXT: Instructions:
|
|
; CHECK-NEXT: %cmp = icmp ult i64 %inc, %sub
|
|
; CHECK-NEXT: br i1 %cmp, label %test1.for.body, label %for.end.loopexit
|
|
; CHECK-NEXT: Edges:none!
|
|
|
|
; CHECK: Node Address:[[N6]]:single-instruction
|
|
; CHECK-NEXT: Instructions:
|
|
; CHECK-NEXT: %arrayidx3 = getelementptr inbounds float, float* %a, i64 %i.02
|
|
; CHECK-NEXT: Edges:
|
|
; CHECK-NEXT: [def-use] to [[N8:0x[0-9a-f]*]]
|
|
|
|
; CHECK: Node Address:[[N5]]:multi-instruction
|
|
; CHECK-NEXT: Instructions:
|
|
; CHECK-NEXT: %sub1 = add i64 %i.02, -1
|
|
; CHECK-NEXT: %arrayidx2 = getelementptr inbounds float, float* %a, i64 %sub1
|
|
; CHECK-NEXT: Edges:
|
|
; CHECK-NEXT: [def-use] to [[N8]]
|
|
|
|
; CHECK: Node Address:[[N4]]:multi-instruction
|
|
; CHECK-NEXT: Instructions:
|
|
; CHECK-NEXT: %arrayidx = getelementptr inbounds float, float* %b, i64 %i.02
|
|
; CHECK-NEXT: %0 = load float, float* %arrayidx, align 4
|
|
; CHECK-NEXT: Edges:
|
|
; CHECK-NEXT: [def-use] to [[N8]]
|
|
|
|
; CHECK: Node Address:[[N8]]:pi-block
|
|
; CHECK-NEXT: --- start of nodes in pi-block ---
|
|
; CHECK: Node Address:[[N9:0x[0-9a-f]*]]:single-instruction
|
|
; CHECK-NEXT: Instructions:
|
|
; CHECK-NEXT: %1 = load float, float* %arrayidx2, align 4
|
|
; CHECK-NEXT: Edges:
|
|
; CHECK-NEXT: [def-use] to [[N10:0x[0-9a-f]*]]
|
|
|
|
; CHECK: Node Address:[[N10]]:single-instruction
|
|
; CHECK-NEXT: Instructions:
|
|
; CHECK-NEXT: %add = fadd float %0, %1
|
|
; CHECK-NEXT: Edges:
|
|
; CHECK-NEXT: [def-use] to [[N11:0x[0-9a-f]*]]
|
|
|
|
; CHECK: Node Address:[[N11]]:single-instruction
|
|
; CHECK-NEXT: Instructions:
|
|
; CHECK-NEXT: store float %add, float* %arrayidx3, align 4
|
|
; CHECK-NEXT: Edges:
|
|
; CHECK-NEXT: [memory] to [[N9]]
|
|
; CHECK-NEXT:--- end of nodes in pi-block ---
|
|
; CHECK-NEXT: Edges:none!
|
|
|
|
|
|
|
|
;; Loop-carried dependence requiring edge-reversal to expose a cycle
|
|
;; in the graph.
|
|
;; void test(unsigned long n, float * restrict a, float * restrict b) {
|
|
;; for (unsigned long i = 1; i < n-1; i++)
|
|
;; a[i] = b[i] + a[i-1];
|
|
;; }
|
|
|
|
define void @test1(i64 %n, float* noalias %a, float* noalias %b) {
|
|
entry:
|
|
%sub = add i64 %n, -1
|
|
%cmp1 = icmp ult i64 1, %sub
|
|
br i1 %cmp1, label %test1.for.body, label %for.end
|
|
|
|
test1.for.body: ; preds = %entry, %test1.for.body
|
|
%i.02 = phi i64 [ %inc, %test1.for.body ], [ 1, %entry ]
|
|
%arrayidx = getelementptr inbounds float, float* %b, i64 %i.02
|
|
%0 = load float, float* %arrayidx, align 4
|
|
%sub1 = add i64 %i.02, -1
|
|
%arrayidx2 = getelementptr inbounds float, float* %a, i64 %sub1
|
|
%1 = load float, float* %arrayidx2, align 4
|
|
%add = fadd float %0, %1
|
|
%arrayidx3 = getelementptr inbounds float, float* %a, i64 %i.02
|
|
store float %add, float* %arrayidx3, align 4
|
|
%inc = add i64 %i.02, 1
|
|
%cmp = icmp ult i64 %inc, %sub
|
|
br i1 %cmp, label %test1.for.body, label %for.end
|
|
|
|
for.end: ; preds = %test1.for.body, %entry
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: 'DDG' for loop 'test2.for.body':
|
|
|
|
; CHECK: Node Address:[[N1:0x[0-9a-f]*]]:pi-block
|
|
; CHECK-NEXT:--- start of nodes in pi-block ---
|
|
|
|
; CHECK: Node Address:[[N2:0x[0-9a-f]*]]:single-instruction
|
|
; CHECK-NEXT: Instructions:
|
|
; CHECK-NEXT: %i.02 = phi i64 [ %inc, %test2.for.body ], [ 1, %test2.for.body.preheader ]
|
|
; CHECK-NEXT: Edges:
|
|
; CHECK-NEXT: [def-use] to [[N3:0x[0-9a-f]*]]
|
|
|
|
; CHECK: Node Address:[[N3]]:single-instruction
|
|
; CHECK-NEXT: Instructions:
|
|
; CHECK-NEXT: %inc = add i64 %i.02, 1
|
|
; CHECK-NEXT: Edges:
|
|
; CHECK-NEXT: [def-use] to [[N2]]
|
|
; CHECK-NEXT:--- end of nodes in pi-block ---
|
|
; CHECK-NEXT: Edges:
|
|
; CHECK-NEXT: [def-use] to [[N4:0x[0-9a-f]*]]
|
|
; CHECK-NEXT: [def-use] to [[N5:0x[0-9a-f]*]]
|
|
; CHECK-NEXT: [def-use] to [[N6:0x[0-9a-f]*]]
|
|
; CHECK-NEXT: [def-use] to [[N7:0x[0-9a-f]*]]
|
|
|
|
; CHECK: Node Address:[[N7]]:multi-instruction
|
|
; CHECK-NEXT: Instructions:
|
|
; CHECK-NEXT: %cmp = icmp ult i64 %inc, %sub
|
|
; CHECK-NEXT: br i1 %cmp, label %test2.for.body, label %for.end.loopexit
|
|
; CHECK-NEXT: Edges:none!
|
|
|
|
; CHECK: Node Address:[[N6]]:single-instruction
|
|
; CHECK-NEXT: Instructions:
|
|
; CHECK-NEXT: %arrayidx3 = getelementptr inbounds float, float* %a, i64 %i.02
|
|
; CHECK-NEXT: Edges:
|
|
; CHECK-NEXT: [def-use] to [[N8:0x[0-9a-f]*]]
|
|
|
|
; CHECK: Node Address:[[N5]]:multi-instruction
|
|
; CHECK-NEXT: Instructions:
|
|
; CHECK-NEXT: %add1 = add i64 %i.02, 1
|
|
; CHECK-NEXT: %arrayidx2 = getelementptr inbounds float, float* %a, i64 %add1
|
|
; CHECK-NEXT: %1 = load float, float* %arrayidx2, align 4
|
|
; CHECK-NEXT: Edges:
|
|
; CHECK-NEXT: [def-use] to [[N9:0x[0-9a-f]*]]
|
|
; CHECK-NEXT: [memory] to [[N8]]
|
|
|
|
; CHECK: Node Address:[[N4]]:multi-instruction
|
|
; CHECK-NEXT: Instructions:
|
|
; CHECK-NEXT: %arrayidx = getelementptr inbounds float, float* %b, i64 %i.02
|
|
; CHECK-NEXT: %0 = load float, float* %arrayidx, align 4
|
|
; CHECK-NEXT: Edges:
|
|
; CHECK-NEXT: [def-use] to [[N9]]
|
|
|
|
; CHECK: Node Address:[[N9]]:single-instruction
|
|
; CHECK-NEXT: Instructions:
|
|
; CHECK-NEXT: %add = fadd float %0, %1
|
|
; CHECK-NEXT: Edges:
|
|
; CHECK-NEXT: [def-use] to [[N8]]
|
|
|
|
; CHECK: Node Address:[[N8]]:single-instruction
|
|
; CHECK-NEXT: Instructions:
|
|
; CHECK-NEXT: store float %add, float* %arrayidx3, align 4
|
|
; CHECK-NEXT: Edges:none!
|
|
|
|
|
|
;; Forward loop-carried dependence *not* causing a cycle.
|
|
;; void test2(unsigned long n, float * restrict a, float * restrict b) {
|
|
;; for (unsigned long i = 1; i < n-1; i++)
|
|
;; a[i] = b[i] + a[i+1];
|
|
;; }
|
|
|
|
define void @test2(i64 %n, float* noalias %a, float* noalias %b) {
|
|
entry:
|
|
%sub = add i64 %n, -1
|
|
%cmp1 = icmp ult i64 1, %sub
|
|
br i1 %cmp1, label %test2.for.body, label %for.end
|
|
|
|
test2.for.body: ; preds = %entry, %test2.for.body
|
|
%i.02 = phi i64 [ %inc, %test2.for.body ], [ 1, %entry ]
|
|
%arrayidx = getelementptr inbounds float, float* %b, i64 %i.02
|
|
%0 = load float, float* %arrayidx, align 4
|
|
%add1 = add i64 %i.02, 1
|
|
%arrayidx2 = getelementptr inbounds float, float* %a, i64 %add1
|
|
%1 = load float, float* %arrayidx2, align 4
|
|
%add = fadd float %0, %1
|
|
%arrayidx3 = getelementptr inbounds float, float* %a, i64 %i.02
|
|
store float %add, float* %arrayidx3, align 4
|
|
%inc = add i64 %i.02, 1
|
|
%cmp = icmp ult i64 %inc, %sub
|
|
br i1 %cmp, label %test2.for.body, label %for.end
|
|
|
|
for.end: ; preds = %test2.for.body, %entry
|
|
ret void
|
|
}
|