mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-23 19:23:23 +01:00
17ea6ea969
Currently, isTruncateFree() and isZExtFree() callbacks return false
as they are not implemented in BPF backend. This may cause suboptimal
code generation. For example, if the load in the context of zero extension
has more than one use, the pattern zextload{i8,i16,i32} will
not be generated. Rather, the load will be matched first and
then the result is zero extended.
For example, in the test together with this commit, we have
I1: %0 = load i32, i32* %data_end1, align 4, !tbaa !2
I2: %conv = zext i32 %0 to i64
...
I3: %2 = load i32, i32* %data, align 4, !tbaa !7
I4: %conv2 = zext i32 %2 to i64
...
I5: %4 = trunc i64 %sub.ptr.lhs.cast to i32
I6: %conv13 = sub i32 %4, %2
...
The I1 and I2 will match to one zextloadi32 DAG node, where SUBREG_TO_REG is
used to convert a 32bit register to 64bit one. During code generation,
SUBREG_TO_REG is a noop.
The %2 in I3 is used in both I4 and I6. If isTruncateFree() is false,
the current implementation will generate a SLL_ri and SRL_ri
for the zext part during lowering.
This patch implement isTruncateFree() in the BPF backend, so for the
above example, I3 and I4 will generate a zextloadi32 DAG node with
SUBREG_TO_REG is generated during lowering to Machine IR.
isZExtFree() is also implemented as it should help code gen as well.
This patch also enables the change in https://reviews.llvm.org/D73985
since it won't kick in generates MOV_32_64 machine instruction.
Differential Revision: https://reviews.llvm.org/D74101
27 lines
1.1 KiB
LLVM
27 lines
1.1 KiB
LLVM
; RUN: llc -march=bpfel -mattr=+alu32 < %s | FileCheck %s
|
|
; Source:
|
|
; unsigned test(unsigned long x, unsigned long y) {
|
|
; return x & y;
|
|
; }
|
|
; Compilation flag:
|
|
; clang -target bpf -O2 -emit-llvm -S test.c
|
|
|
|
; Function Attrs: norecurse nounwind readnone
|
|
define dso_local i32 @test(i64 %x, i64 %y) local_unnamed_addr #0 {
|
|
entry:
|
|
%and = and i64 %y, %x
|
|
%conv = trunc i64 %and to i32
|
|
ret i32 %conv
|
|
}
|
|
|
|
; CHECK: r[[REG1:[0-9]+]] = r{{[0-9]+}}
|
|
; CHECK: w[[REG1]] &= w{{[0-9]+}}
|
|
|
|
attributes #0 = { norecurse nounwind readnone "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "frame-pointer"="all" "less-precise-fpmad"="false" "min-legal-vector-width"="0" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
|
|
|
|
!llvm.module.flags = !{!0}
|
|
!llvm.ident = !{!1}
|
|
|
|
!0 = !{i32 1, !"wchar_size", i32 4}
|
|
!1 = !{!"clang version 11.0.0 (https://github.com/llvm/llvm-project.git b3ab5b2e7ffe9964ddf75a92fd7a444fe5aaa426)"}
|