mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-25 12:12:47 +01:00
8d4bf186a4
Local values are constants or addresses that can't be folded into the instruction that uses them. FastISel materializes these in a "local value" area that always dominates the current insertion point, to try to avoid materializing these values more than once (per block). https://reviews.llvm.org/D43093 added code to sink these local value instructions to their first use, which has two beneficial effects. One, it is likely to avoid some unnecessary spills and reloads; two, it allows us to attach the debug location of the user to the local value instruction. The latter effect can improve the debugging experience for debuggers with a "set next statement" feature, such as the Visual Studio debugger and PS4 debugger, because instructions to set up constants for a given statement will be associated with the appropriate source line. There are also some constants (primarily addresses) that could be produced by no-op casts or GEP instructions; the main difference from "local value" instructions is that these are values from separate IR instructions, and therefore could have multiple users across multiple basic blocks. D43093 avoided sinking these, even though they were emitted to the same "local value" area as the other instructions. The patch comment for D43093 states: Local values may also be used by no-op casts, which adds the register to the RegFixups table. Without reversing the RegFixups map direction, we don't have enough information to sink these instructions. This patch undoes most of D43093, and instead flushes the local value map after(*) every IR instruction, using that instruction's debug location. This avoids sometimes incorrect locations used previously, and emits instructions in a more natural order. In addition, constants materialized due to PHI instructions are not assigned a debug location immediately; instead, when the local value map is flushed, if the first local value instruction has no debug location, it is given the same location as the first non-local-value-map instruction. This prevents PHIs from introducing unattributed instructions, which would either be implicitly attributed to the location for the preceding IR instruction, or given line 0 if they are at the beginning of a machine basic block. Neither of those consequences is good for debugging. This does mean materialized values are not re-used across IR instruction boundaries; however, only about 5% of those values were reused in an experimental self-build of clang. (*) Actually, just prior to the next instruction. It seems like it would be cleaner the other way, but I was having trouble getting that to work. This reapplies commits cf1c774d and dc35368c, and adds the modification to PHI handling, which should avoid problems with debugging under gdb. Differential Revision: https://reviews.llvm.org/D91734
51 lines
2.5 KiB
LLVM
51 lines
2.5 KiB
LLVM
; RUN: llc < %s -mtriple=aarch64-none-linux-gnu | FileCheck %s
|
|
|
|
@.str = private unnamed_addr constant [11 x i8] c"val = %ld\0A\00", align 1
|
|
|
|
; Function Attrs: noinline optnone
|
|
define dso_local void @set_large(i64 %val) #0 {
|
|
entry:
|
|
%val.addr = alloca i64, align 8
|
|
%large = alloca [268435456 x i64], align 8
|
|
%i = alloca i32, align 4
|
|
store i64 %val, i64* %val.addr, align 8
|
|
%0 = load i64, i64* %val.addr, align 8
|
|
%arrayidx = getelementptr inbounds [268435456 x i64], [268435456 x i64]* %large, i64 0, i64 %0
|
|
store i64 1, i64* %arrayidx, align 8
|
|
%1 = load i64, i64* %val.addr, align 8
|
|
%arrayidx1 = getelementptr inbounds [268435456 x i64], [268435456 x i64]* %large, i64 0, i64 %1
|
|
%2 = load i64, i64* %arrayidx1, align 8
|
|
%call = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([11 x i8], [11 x i8]* @.str, i64 0, i64 0), i64 %2)
|
|
ret void
|
|
}
|
|
|
|
declare dso_local i32 @printf(i8*, ...)
|
|
|
|
attributes #0 = { noinline optnone "frame-pointer"="all" }
|
|
|
|
; CHECK: stp x[[SPILL_REG1:[0-9]+]], x[[SPILL_REG2:[0-9]+]], [sp, #-[[SPILL_OFFSET1:[0-9]+]]]
|
|
; CHECK-NEXT: str x[[SPILL_REG3:[0-9]+]], [sp, #[[SPILL_OFFSET2:[0-9]+]]]
|
|
; CHECK-NEXT: mov x[[FRAME:[0-9]+]], sp
|
|
; CHECK-COUNT-128: sub sp, sp, #[[STACK1:[0-9]+]], lsl #12
|
|
; CHECK-NEXT: sub sp, sp, #[[STACK2:[0-9]+]], lsl #12
|
|
; CHECK-NEXT: sub sp, sp, #[[STACK3:[0-9]+]]
|
|
; CHECK: sub x[[INDEX:[0-9]+]], x[[FRAME]], #8
|
|
; CHECK-NEXT: str x0, [x[[INDEX]]]
|
|
; CHECK-NEXT: ldr x[[VAL1:[0-9]+]], [x[[INDEX]]]
|
|
; CHECK-NEXT: add x[[VAL3:[0-9]+]], sp, #8
|
|
; CHECK-NEXT: mov x[[VAL2:[0-9]+]], #8
|
|
; CHECK-NEXT: madd x[[VAL1]], x[[VAL1]], x[[VAL2]], x[[VAL3]]
|
|
; CHECK-NEXT: mov x[[TMP1:[0-9]+]], #1
|
|
; CHECK-NEXT: str x[[TMP1]], [x[[VAL1]]]
|
|
; CHECK-NEXT: ldr x[[INDEX]], [x[[INDEX]]]
|
|
; CHECK-NEXT: add x[[VAL3:[0-9]+]], sp, #8
|
|
; CHECK-NEXT: mov x[[VAL4:[0-9]+]], #8
|
|
; CHECK-NEXT: madd x[[INDEX]], x[[INDEX]], x[[VAL4]], x[[VAL3]]
|
|
; CHECK-NEXT: ldr x1, [x[[INDEX]]
|
|
; CHECK: bl printf
|
|
; CHECK-COUNT-128: add sp, sp, #[[STACK1]], lsl #12
|
|
; CHECK-NEXT: add sp, sp, #[[STACK2]], lsl #12
|
|
; CHECK-NEXT: add sp, sp, #[[STACK3]]
|
|
; CHECK-NEXT: ldr x[[SPILL_REG3]], [sp, #[[SPILL_OFFSET2]]]
|
|
; CHECK-NEXT: ldp x[[SPILL_REG1]], x[[SPILL_REG2]], [sp], #[[SPILL_OFFSET1]]
|