4698bf145d
This reverts commit41784bed01. Since the original revisionead815924e, this revision fixes three issues: - This revision fixes the Windows build. My original patch improperly copied EH pads on Windows. This patch disregards jump threading opportunities having to do with EH pads. - This revision fixes jump threading to a wrong destination. Specifically, my original patch treated any Constant other than 0 as 1 while evaluating the branch condition. This bug led to treating constant expressions like: icmp ugt i8* null, inttoptr (i64 4 to i8*) to "true". This patch fixes the bug by calling isOneValue. - This revision fixes the cost calculation of two basic blocks being threaded through. Note that getJumpThreadDuplicationCost returns "(unsigned)~0" for those basic blocks that cannot be duplicated. If we sum of two return values from getJumpThreadDuplicationCost, we could have an unsigned overflow like: (unsigned)~0 + 5 = 4 and mistakenly determine that it's safe and profitable to proceed with the jump threading opportunity. The patch fixes the bug by checking each return value before summing them up. [JumpThreading] Thread jumps through two basic blocks Summary: This patch teaches JumpThreading.cpp to thread through two basic blocks like: bb3: %var = phi i32* [ null, %bb1 ], [ @a, %bb2 ] %tobool = icmp eq i32 %cond, 0 br i1 %tobool, label %bb4, label ... bb4: %cmp = icmp eq i32* %var, null br i1 %cmp, label bb5, label bb6 by duplicating basic blocks like bb3 above. Once we duplicate bb3 as bb3.dup and redirect edge bb2->bb3 to bb2->bb3.dup, we have: bb3: %var = phi i32* [ @a, %bb2 ] %tobool = icmp eq i32 %cond, 0 br i1 %tobool, label %bb4, label ... bb3.dup: %var = phi i32* [ null, %bb1 ] %tobool = icmp eq i32 %cond, 0 br i1 %tobool, label %bb4, label ... bb4: %cmp = icmp eq i32* %var, null br i1 %cmp, label bb5, label bb6 Then the existing code in JumpThreading.cpp can thread edge bb3.dup->bb4 through bb4 and eventually create bb3.dup->bb5. Reviewers: wmi Subscribers: hiraditya, jfb, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D70247
63 lines
1.2 KiB
LLVM
63 lines
1.2 KiB
LLVM
; RUN: opt < %s -jump-threading -S -verify | FileCheck %s
|
|
|
|
target datalayout = "e-i64:64-i128:128-v16:16-v32:32-n16:32:64"
|
|
target triple = "nvptx64-nvidia-cuda"
|
|
|
|
$wrapped_tid = comdat any
|
|
|
|
$foo = comdat any
|
|
|
|
define i32 @wrapped_tid() #0 comdat align 32 {
|
|
%1 = call i32 @tid()
|
|
ret i32 %1
|
|
}
|
|
|
|
declare void @llvm.nvvm.barrier0() #1
|
|
|
|
; We had a bug where we duplicated basic blocks containing convergent
|
|
; functions like @llvm.nvvm.barrier0 below. Verify that we don't do
|
|
; that.
|
|
define void @foo() local_unnamed_addr #2 comdat align 32 {
|
|
; CHECK-LABEL: @foo
|
|
%1 = call i32 @tid()
|
|
%2 = urem i32 %1, 7
|
|
br label %3
|
|
|
|
3:
|
|
%4 = icmp eq i32 %1, 0
|
|
br i1 %4, label %5, label %6
|
|
|
|
5:
|
|
call void @bar()
|
|
br label %6
|
|
|
|
6:
|
|
; CHECK: call void @llvm.nvvm.barrier0()
|
|
; CHECK-NOT: call void @llvm.nvvm.barrier0()
|
|
call void @llvm.nvvm.barrier0()
|
|
%7 = icmp eq i32 %2, 0
|
|
br i1 %7, label %11, label %8
|
|
|
|
8:
|
|
%9 = icmp ult i32 %1, 49
|
|
br i1 %9, label %10, label %11
|
|
|
|
10:
|
|
call void @llvm.trap()
|
|
unreachable
|
|
|
|
11:
|
|
br label %3
|
|
}
|
|
|
|
declare i32 @tid() #2
|
|
|
|
declare void @bar()
|
|
|
|
declare void @llvm.trap() #3
|
|
|
|
attributes #1 = { convergent }
|
|
attributes #2 = { readnone }
|
|
attributes #3 = { noreturn }
|
|
attributes #4 = { convergent }
|