mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-22 20:43:44 +02:00
277138a332
This is causing compilation timeouts on code with long sequences of local values and calls (i.e. foo(1); foo(2); foo(3); ...). It turns out that code coverage instrumentation is a great way to create sequences like this, which how our users ran into the issue in practice. Intel has a tool that detects these kinds of non-linear compile time issues, and Andy Kaylor reported it as PR37010. The current sinking code scans the whole basic block once per local value sink, which happens before emitting each call. In theory, local values should only be introduced to be used by instructions between the current flush point and the last flush point, so we should only need to scan those instructions. llvm-svn: 329822
33 lines
1.8 KiB
LLVM
33 lines
1.8 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -fast-isel-sink-local-values -O0 -mtriple=x86_64-unknown-linux-gnu < %s | FileCheck %s
|
|
|
|
define void @foo() {
|
|
; CHECK-LABEL: foo:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: # implicit-def: $rax
|
|
; CHECK-NEXT: jmpq *%rax
|
|
; CHECK-NEXT: .LBB0_1:
|
|
; CHECK-NEXT: xorps %xmm0, %xmm0
|
|
; CHECK-NEXT: pcmpeqd %xmm1, %xmm1
|
|
; CHECK-NEXT: # implicit-def: $rax
|
|
; CHECK-NEXT: movdqu %xmm1, (%rax)
|
|
; CHECK-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp) # 16-byte Spill
|
|
; CHECK-NEXT: .LBB0_2:
|
|
; CHECK-NEXT: retq
|
|
indirectbr i8* undef, [label %9, label %1]
|
|
|
|
; <label>:1: ; preds = %0
|
|
%2 = shufflevector <16 x i8> zeroinitializer, <16 x i8> <i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef>, <16 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
|
|
%3 = shufflevector <16 x i8> <i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0>, <16 x i8> zeroinitializer, <16 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
|
|
%4 = or <16 x i8> %3, %2
|
|
%5 = shufflevector <16 x i8> %4, <16 x i8> undef, <16 x i32> <i32 8, i32 5, i32 1, i32 13, i32 15, i32 10, i32 14, i32 0, i32 3, i32 2, i32 7, i32 4, i32 6, i32 9, i32 11, i32 12>
|
|
%6 = bitcast <16 x i8> %5 to <2 x i64>
|
|
%7 = xor <2 x i64> %6, zeroinitializer
|
|
%8 = xor <2 x i64> %7, <i64 -1, i64 -1>
|
|
store <2 x i64> %8, <2 x i64>* undef, align 1
|
|
unreachable
|
|
|
|
; <label>:9: ; preds = %0
|
|
ret void
|
|
}
|