mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-29 10:32:47 +00:00
d021bb8003
This is the third patch in a small series. It contains the CodeGen support for lowering the gc.statepoint intrinsic sequences (223078) to the STATEPOINT pseudo machine instruction (223085). The change also includes the set of helper routines and classes for working with gc.statepoints, gc.relocates, and gc.results since the lowering code uses them. With this change, gc.statepoints should be functionally complete. The documentation will follow in the fourth change, and there will likely be some cleanup changes, but interested parties can start experimenting now. I'm not particularly happy with the amount of code or complexity involved with the lowering step, but at least it's fairly well isolated. The statepoint lowering code is split into it's own files and anyone not working on the statepoint support itself should be able to ignore it. During the lowering process, we currently spill aggressively to stack. This is not entirely ideal (and we have plans to do better), but it's functional, relatively straight forward, and matches closely the implementations of the patchpoint intrinsics. Most of the complexity comes from trying to keep relocated copies of values in the same stack slots across statepoints. Doing so avoids the insertion of pointless load and store instructions to reshuffle the stack. The current implementation isn't as effective as I'd like, but it is functional and 'good enough' for many common use cases. In the long term, I'd like to figure out how to integrate the statepoint lowering with the register allocator. In principal, we shouldn't need to eagerly spill at all. The register allocator should do any spilling required and the statepoint should simply record that fact. Depending on how challenging that turns out to be, we may invest in a smarter global stack slot assignment mechanism as a stop gap measure. Reviewed by: atrick, ributzka git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@223137 91177308-0d34-0410-b5e6-96231b3b80d8
61 lines
3.5 KiB
LLVM
61 lines
3.5 KiB
LLVM
; RUN: llc < %s | FileCheck %s
|
|
|
|
target datalayout = "e-i64:64-f80:128-n8:16:32:64-S128"
|
|
target triple = "x86_64-pc-linux-gnu"
|
|
|
|
; This test is checking to make sure that we reuse the same stack slots
|
|
; for GC values spilled over two different call sites. Since the order
|
|
; of GC arguments differ, niave lowering code would insert loads and
|
|
; stores to rearrange items on the stack. We need to make sure (for
|
|
; performance) that this doesn't happen.
|
|
define i32 @back_to_back_calls(i32* %a, i32* %b, i32* %c) #1 {
|
|
; CHECK-LABEL: back_to_back_calls
|
|
; The exact stores don't matter, but there need to be three stack slots created
|
|
; CHECK: movq %rdx, 16(%rsp)
|
|
; CHECK: movq %rdi, 8(%rsp)
|
|
; CHECK: movq %rsi, (%rsp)
|
|
%safepoint_token = tail call i32 (void ()*, i32, i32, ...)* @llvm.experimental.gc.statepoint.p0f_isVoidf(void ()* undef, i32 0, i32 0, i32 5, i32 0, i32 -1, i32 0, i32 0, i32 0, i32* %a, i32* %b, i32* %c)
|
|
%a1 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token, i32 9, i32 9)
|
|
%b1 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token, i32 9, i32 10)
|
|
%c1 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token, i32 9, i32 11)
|
|
; CHECK: callq
|
|
; This is the key check. There should NOT be any memory moves here
|
|
; CHECK-NOT: movq
|
|
%safepoint_token2 = tail call i32 (void ()*, i32, i32, ...)* @llvm.experimental.gc.statepoint.p0f_isVoidf(void ()* undef, i32 0, i32 0, i32 5, i32 0, i32 -1, i32 0, i32 0, i32 0, i32* %c1, i32* %b1, i32* %a1)
|
|
%a2 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token2, i32 9, i32 11)
|
|
%b2 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token2, i32 9, i32 10)
|
|
%c2 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token2, i32 9, i32 9)
|
|
; CHECK: callq
|
|
ret i32 1
|
|
}
|
|
|
|
; This test simply checks that minor changes in vm state don't prevent slots
|
|
; being reused for gc values.
|
|
define i32 @reserve_first(i32* %a, i32* %b, i32* %c) #1 {
|
|
; CHECK-LABEL: reserve_first
|
|
; The exact stores don't matter, but there need to be three stack slots created
|
|
; CHECK: movq %rdx, 16(%rsp)
|
|
; CHECK: movq %rdi, 8(%rsp)
|
|
; CHECK: movq %rsi, (%rsp)
|
|
%safepoint_token = tail call i32 (void ()*, i32, i32, ...)* @llvm.experimental.gc.statepoint.p0f_isVoidf(void ()* undef, i32 0, i32 0, i32 5, i32 0, i32 -1, i32 0, i32 0, i32 0, i32* %a, i32* %b, i32* %c)
|
|
%a1 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token, i32 9, i32 9)
|
|
%b1 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token, i32 9, i32 10)
|
|
%c1 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token, i32 9, i32 11)
|
|
; CHECK: callq
|
|
; This is the key check. There should NOT be any memory moves here
|
|
; CHECK-NOT: movq
|
|
%safepoint_token2 = tail call i32 (void ()*, i32, i32, ...)* @llvm.experimental.gc.statepoint.p0f_isVoidf(void ()* undef, i32 0, i32 0, i32 5, i32* %a1, i32 0, i32* %c1, i32 0, i32 0, i32* %c1, i32* %b1, i32* %a1)
|
|
%a2 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token2, i32 9, i32 11)
|
|
%b2 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token2, i32 9, i32 10)
|
|
%c2 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token2, i32 9, i32 9)
|
|
; CHECK: callq
|
|
ret i32 1
|
|
}
|
|
|
|
; Function Attrs: nounwind
|
|
declare i32* @llvm.experimental.gc.relocate.p0i32(i32, i32, i32) #3
|
|
|
|
declare i32 @llvm.experimental.gc.statepoint.p0f_isVoidf(void ()*, i32, i32, ...)
|
|
|
|
attributes #1 = { uwtable }
|