8f997b4f01
We just removed a broken duplicate elimination algorithm in D75964, and after landed that it occurred to me that duplicate elimination is simply CSE. SelectionDAG has a build in CSE, so why wasn't that triggering? Well, it turns out we were overly conservative in the memory states for our reloads and CSE (rightly) considers the incoming memory state for a load part of the identity of the load. By loosening the chain and allowing reordering, we also allow CSE. As shown in the test case, doing iterative CSE as we go is enough to eliminate duplicate stores in later statepoints as well. We key our (block local) slot map by SDValue, so commoning a previous pair of loads at construction time means we also common following stores. Differential Revision: https://reviews.llvm.org/D76013
78 lines
3.7 KiB
LLVM
78 lines
3.7 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -verify-machineinstrs < %s | FileCheck %s
|
|
|
|
; Check that we can export values of "duplicated" gc.relocates without a crash
|
|
; "duplicate" here means maps to same SDValue. We previously had an
|
|
; optimization which tried to reduce number of spills/stackmap entries in such
|
|
; cases, but it incorrectly handled exports across basis block boundaries
|
|
; leading to a crash in this case.
|
|
|
|
target triple = "x86_64-pc-linux-gnu"
|
|
|
|
declare void @func()
|
|
|
|
define i1 @test() gc "statepoint-example" {
|
|
; CHECK-LABEL: test:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: pushq %rax
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: callq func
|
|
; CHECK-NEXT: .Ltmp0:
|
|
; CHECK-NEXT: callq func
|
|
; CHECK-NEXT: .Ltmp1:
|
|
; CHECK-NEXT: movb $1, %al
|
|
; CHECK-NEXT: popq %rcx
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 8
|
|
; CHECK-NEXT: retq
|
|
entry:
|
|
%safepoint_token = call token (i64, i32, void ()*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_isVoidf(i64 0, i32 0, void ()* @func, i32 0, i32 0, i32 0, i32 0, i32 addrspace(1)* null, i32 addrspace(1)* null)
|
|
%base = call i32 addrspace(1)* @llvm.experimental.gc.relocate.p1i32(token %safepoint_token, i32 7, i32 7)
|
|
%derived = call i32 addrspace(1)* @llvm.experimental.gc.relocate.p1i32(token %safepoint_token, i32 7, i32 8)
|
|
%safepoint_token2 = call token (i64, i32, void ()*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_isVoidf(i64 0, i32 0, void ()* @func, i32 0, i32 0, i32 0, i32 0, i32 addrspace(1)* %base, i32 addrspace(1)* %derived)
|
|
br label %next
|
|
|
|
next:
|
|
%base_reloc = call i32 addrspace(1)* @llvm.experimental.gc.relocate.p1i32(token %safepoint_token2, i32 7, i32 7)
|
|
%derived_reloc = call i32 addrspace(1)* @llvm.experimental.gc.relocate.p1i32(token %safepoint_token2, i32 7, i32 8)
|
|
%cmp1 = icmp eq i32 addrspace(1)* %base_reloc, null
|
|
%cmp2 = icmp eq i32 addrspace(1)* %derived_reloc, null
|
|
%cmp = and i1 %cmp1, %cmp2
|
|
ret i1 %cmp
|
|
}
|
|
|
|
; Showing redundant fill on first statepoint and spill/fill on second one
|
|
define i1 @test2(i32 addrspace(1)* %arg) gc "statepoint-example" {
|
|
; CHECK-LABEL: test2:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: pushq %rax
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: movq %rdi, (%rsp)
|
|
; CHECK-NEXT: callq func
|
|
; CHECK-NEXT: .Ltmp2:
|
|
; CHECK-NEXT: callq func
|
|
; CHECK-NEXT: .Ltmp3:
|
|
; CHECK-NEXT: cmpq $0, (%rsp)
|
|
; CHECK-NEXT: sete %al
|
|
; CHECK-NEXT: popq %rcx
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 8
|
|
; CHECK-NEXT: retq
|
|
entry:
|
|
%safepoint_token = call token (i64, i32, void ()*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_isVoidf(i64 0, i32 0, void ()* @func, i32 0, i32 0, i32 0, i32 0, i32 addrspace(1)* %arg, i32 addrspace(1)* %arg)
|
|
%base = call i32 addrspace(1)* @llvm.experimental.gc.relocate.p1i32(token %safepoint_token, i32 7, i32 7)
|
|
%derived = call i32 addrspace(1)* @llvm.experimental.gc.relocate.p1i32(token %safepoint_token, i32 7, i32 8)
|
|
%safepoint_token2 = call token (i64, i32, void ()*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_isVoidf(i64 0, i32 0, void ()* @func, i32 0, i32 0, i32 0, i32 0, i32 addrspace(1)* %base, i32 addrspace(1)* %derived)
|
|
br label %next
|
|
|
|
next:
|
|
%base_reloc = call i32 addrspace(1)* @llvm.experimental.gc.relocate.p1i32(token %safepoint_token2, i32 7, i32 7)
|
|
%derived_reloc = call i32 addrspace(1)* @llvm.experimental.gc.relocate.p1i32(token %safepoint_token2, i32 7, i32 8)
|
|
%cmp1 = icmp eq i32 addrspace(1)* %base_reloc, null
|
|
%cmp2 = icmp eq i32 addrspace(1)* %derived_reloc, null
|
|
%cmp = and i1 %cmp1, %cmp2
|
|
ret i1 %cmp
|
|
}
|
|
|
|
|
|
declare token @llvm.experimental.gc.statepoint.p0f_isVoidf(i64, i32, void ()*, i32, i32, ...)
|
|
declare i32 addrspace(1)* @llvm.experimental.gc.relocate.p1i32(token, i32, i32)
|