mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2025-01-22 10:33:23 +00:00
1726e2ff15
This patch teaches the backend how to simplify/canonicalize dag node
sequences normally introduced by the backend when promoting certain dag nodes
with illegal vector type.
This patch adds two new combine rules:
1) fold (shuffle (bitcast (BINOP A, B)), Undef, <Mask>) ->
(shuffle (BINOP (bitcast A), (bitcast B)), Undef, <Mask>)
2) fold (BINOP (shuffle (A, Undef, <Mask>)), (shuffle (B, Undef, <Mask>))) ->
(shuffle (BINOP A, B), Undef, <Mask>).
Both rules are only triggered on the type-legalized DAG.
In particular, rule 1. is a target specific combine rule that attempts
to sink a bitconvert into the operands of a binary operation.
Rule 2. is a target independet rule that attempts to move a shuffle
immediately after a binary operation.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@209930 91177308-0d34-0410-b5e6-96231b3b80d8
137 lines
3.1 KiB
LLVM
137 lines
3.1 KiB
LLVM
; RUN: llc < %s -march=x86-64 -mcpu=core2 -mattr=+sse2 | FileCheck %s
|
|
|
|
|
|
define double @test1(double %A) {
|
|
%1 = bitcast double %A to <2 x i32>
|
|
%add = add <2 x i32> %1, <i32 3, i32 5>
|
|
%2 = bitcast <2 x i32> %add to double
|
|
ret double %2
|
|
}
|
|
; FIXME: Ideally we should be able to fold the entire body of @test1 into a
|
|
; single paddd instruction. At the moment we produce the sequence
|
|
; pshufd+paddq+pshufd.
|
|
|
|
; CHECK-LABEL: test1
|
|
; CHECK-NOT: movsd
|
|
; CHECK: pshufd
|
|
; CHECK-NEXT: paddd
|
|
; CHECK-NEXT: pshufd
|
|
; CHECK-NEXT: ret
|
|
|
|
|
|
define double @test2(double %A, double %B) {
|
|
%1 = bitcast double %A to <2 x i32>
|
|
%2 = bitcast double %B to <2 x i32>
|
|
%add = add <2 x i32> %1, %2
|
|
%3 = bitcast <2 x i32> %add to double
|
|
ret double %3
|
|
}
|
|
; CHECK-LABEL: test2
|
|
; CHECK-NOT: movsd
|
|
; CHECK: paddd
|
|
; CHECK-NEXT: ret
|
|
|
|
|
|
define i64 @test3(i64 %A) {
|
|
%1 = bitcast i64 %A to <2 x float>
|
|
%add = fadd <2 x float> %1, <float 3.0, float 5.0>
|
|
%2 = bitcast <2 x float> %add to i64
|
|
ret i64 %2
|
|
}
|
|
; CHECK-LABEL: test3
|
|
; CHECK-NOT: pshufd
|
|
; CHECK: addps
|
|
; CHECK-NOT: pshufd
|
|
; CHECK: ret
|
|
|
|
|
|
define i64 @test4(i64 %A) {
|
|
%1 = bitcast i64 %A to <2 x i32>
|
|
%add = add <2 x i32> %1, <i32 3, i32 5>
|
|
%2 = bitcast <2 x i32> %add to i64
|
|
ret i64 %2
|
|
}
|
|
; FIXME: At the moment we still produce the sequence pshufd+paddq+pshufd.
|
|
; Ideally, we should fold that sequence into a single paddd.
|
|
|
|
; CHECK-LABEL: test4
|
|
; CHECK: pshufd
|
|
; CHECK-NEXT: paddq
|
|
; CHECK-NEXT: pshufd
|
|
; CHECK: ret
|
|
|
|
|
|
define double @test5(double %A) {
|
|
%1 = bitcast double %A to <2 x float>
|
|
%add = fadd <2 x float> %1, <float 3.0, float 5.0>
|
|
%2 = bitcast <2 x float> %add to double
|
|
ret double %2
|
|
}
|
|
; CHECK-LABEL: test5
|
|
; CHECK: addps
|
|
; CHECK-NEXT: ret
|
|
|
|
|
|
define double @test6(double %A) {
|
|
%1 = bitcast double %A to <4 x i16>
|
|
%add = add <4 x i16> %1, <i16 3, i16 4, i16 5, i16 6>
|
|
%2 = bitcast <4 x i16> %add to double
|
|
ret double %2
|
|
}
|
|
; FIXME: Ideally we should be able to fold the entire body of @test6 into a
|
|
; single paddw instruction.
|
|
|
|
; CHECK-LABEL: test6
|
|
; CHECK-NOT: movsd
|
|
; CHECK: punpcklwd
|
|
; CHECK-NEXT: paddw
|
|
; CHECK-NEXT: pshufb
|
|
; CHECK-NEXT: ret
|
|
|
|
|
|
define double @test7(double %A, double %B) {
|
|
%1 = bitcast double %A to <4 x i16>
|
|
%2 = bitcast double %B to <4 x i16>
|
|
%add = add <4 x i16> %1, %2
|
|
%3 = bitcast <4 x i16> %add to double
|
|
ret double %3
|
|
}
|
|
; CHECK-LABEL: test7
|
|
; CHECK-NOT: movsd
|
|
; CHECK-NOT: punpcklwd
|
|
; CHECK: paddw
|
|
; CHECK-NEXT: ret
|
|
|
|
|
|
define double @test8(double %A) {
|
|
%1 = bitcast double %A to <8 x i8>
|
|
%add = add <8 x i8> %1, <i8 3, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10>
|
|
%2 = bitcast <8 x i8> %add to double
|
|
ret double %2
|
|
}
|
|
; FIXME: Ideally we should be able to fold the entire body of @test8 into a
|
|
; single paddb instruction. At the moment we produce the sequence
|
|
; pshufd+paddw+pshufd.
|
|
|
|
; CHECK-LABEL: test8
|
|
; CHECK-NOT: movsd
|
|
; CHECK: punpcklbw
|
|
; CHECK-NEXT: paddb
|
|
; CHECK-NEXT: pshufb
|
|
; CHECK-NEXT: ret
|
|
|
|
|
|
define double @test9(double %A, double %B) {
|
|
%1 = bitcast double %A to <8 x i8>
|
|
%2 = bitcast double %B to <8 x i8>
|
|
%add = add <8 x i8> %1, %2
|
|
%3 = bitcast <8 x i8> %add to double
|
|
ret double %3
|
|
}
|
|
; CHECK-LABEL: test9
|
|
; CHECK-NOT: movsd
|
|
; CHECK-NOT: punpcklbw
|
|
; CHECK: paddb
|
|
; CHECK-NEXT: ret
|
|
|