; RUN: llc < %s -march=x86-64 -mcpu=core2 -mattr=+sse2 | FileCheck %s
+; RUN: llc < %s -march=x86-64 -mcpu=core2 -mattr=+sse2 -x86-experimental-vector-widening-legalization | FileCheck %s --check-prefix=CHECK-WIDE
define double @test1(double %A) {
}
; 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.
-
+; pshufd+paddq+pshufd. This is fixed with the widening legalization.
+;
; CHECK-LABEL: test1
; CHECK-NOT: movsd
; CHECK: pshufd
; CHECK-NEXT: paddd
; CHECK-NEXT: pshufd
; CHECK-NEXT: ret
+;
+; CHECK-WIDE-LABEL: test1
+; CHECK-WIDE-NOT: movsd
+; CHECK-WIDE: paddd
+; CHECK-WIDE-NEXT: ret
define double @test2(double %A, double %B) {
; CHECK-NOT: movsd
; CHECK: paddd
; CHECK-NEXT: ret
+;
+; CHECK-WIDE-LABEL: test2
+; CHECK-WIDE-NOT: movsd
+; CHECK-WIDE: paddd
+; CHECK-WIDE-NEXT: ret
define i64 @test3(i64 %A) {
; CHECK: addps
; CHECK-NOT: pshufd
; CHECK: ret
+;
+; CHECK-WIDE-LABEL: test3
+; CHECK-WIDE-NOT: pshufd
+; CHECK-WIDE: addps
+; CHECK-WIDE-NOT: pshufd
+; CHECK-WIDE: ret
define i64 @test4(i64 %A) {
%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.
-
+; FIXME: At the moment we still produce the sequence pshufd+paddd+pshufd.
+; Ideally, we should fold that sequence into a single paddd. This is fixed with
+; the widening legalization.
+;
; CHECK-LABEL: test4
; CHECK: pshufd
-; CHECK-NEXT: paddq
+; CHECK-NEXT: paddd
; CHECK-NEXT: pshufd
; CHECK: ret
+;
+; CHECK-WIDE-LABEL: test4
+; CHECK-WIDE: movd %{{rdi|rcx}},
+; CHECK-WIDE-NEXT: paddd
+; CHECK-WIDE-NEXT: movd {{.*}}, %rax
+; CHECK-WIDE: ret
define double @test5(double %A) {
; CHECK-LABEL: test5
; CHECK: addps
; CHECK-NEXT: ret
+;
+; CHECK-WIDE-LABEL: test5
+; CHECK-WIDE: addps
+; CHECK-WIDE-NEXT: ret
define double @test6(double %A) {
ret double %2
}
; FIXME: Ideally we should be able to fold the entire body of @test6 into a
-; single paddw instruction.
-
+; single paddw instruction. This is fixed with the widening legalization.
+;
; CHECK-LABEL: test6
; CHECK-NOT: movsd
; CHECK: punpcklwd
; CHECK-NEXT: paddw
; CHECK-NEXT: pshufb
; CHECK-NEXT: ret
+;
+; CHECK-WIDE-LABEL: test6
+; CHECK-WIDE-NOT: mov
+; CHECK-WIDE-NOT: punpcklwd
+; CHECK-WIDE: paddw
+; CHECK-WIDE-NEXT: ret
define double @test7(double %A, double %B) {
; CHECK-NOT: punpcklwd
; CHECK: paddw
; CHECK-NEXT: ret
+;
+; CHECK-WIDE-LABEL: test7
+; CHECK-WIDE-NOT: movsd
+; CHECK-WIDE-NOT: punpcklwd
+; CHECK-WIDE: paddw
+; CHECK-WIDE-NEXT: ret
define double @test8(double %A) {
}
; 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.
-
+; pshufd+paddw+pshufd. This is fixed with the widening legalization.
+;
; CHECK-LABEL: test8
; CHECK-NOT: movsd
; CHECK: punpcklbw
; CHECK-NEXT: paddb
; CHECK-NEXT: pshufb
; CHECK-NEXT: ret
+;
+; CHECK-WIDE-LABEL: test8
+; CHECK-WIDE-NOT: movsd
+; CHECK-WIDE-NOT: punpcklbw
+; CHECK-WIDE: paddb
+; CHECK-WIDE-NEXT: ret
define double @test9(double %A, double %B) {
; CHECK-NOT: punpcklbw
; CHECK: paddb
; CHECK-NEXT: ret
+;
+; CHECK-WIDE-LABEL: test9
+; CHECK-WIDE-NOT: movsd
+; CHECK-WIDE-NOT: punpcklbw
+; CHECK-WIDE: paddb
+; CHECK-WIDE-NEXT: ret