2015-11-24 05:33:58 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
2017-06-27 02:20:46 +08:00
; RUN: llc < %s -mtriple=i386-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=X86
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=X64
2009-08-16 01:28:09 +08:00
; Tests for SSE2 and below, without SSE3+.
2008-05-24 08:10:02 +08:00
2010-08-29 11:19:04 +08:00
define void @test1 ( < 2 x double > * %r , < 2 x double > * %A , double %B ) nounwind {
2017-06-27 02:20:46 +08:00
; X86-LABEL: test1:
; X86: # BB#0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movapd (%ecx), %xmm0
; X86-NEXT: movlpd {{.*#+}} xmm0 = mem[0],xmm0[1]
; X86-NEXT: movapd %xmm0, (%eax)
; X86-NEXT: retl
;
; X64-LABEL: test1:
; X64: # BB#0:
; X64-NEXT: movapd (%rsi), %xmm1
; X64-NEXT: movsd {{.*#+}} xmm1 = xmm0[0],xmm1[1]
; X64-NEXT: movapd %xmm1, (%rdi)
; X64-NEXT: retq
2015-02-28 05:17:42 +08:00
%tmp3 = load < 2 x double > , < 2 x double > * %A , align 16
2008-05-24 08:10:02 +08:00
%tmp7 = insertelement < 2 x double > undef , double %B , i32 0
%tmp9 = shufflevector < 2 x double > %tmp3 , < 2 x double > %tmp7 , < 2 x i32 > < i32 2 , i32 1 >
store < 2 x double > %tmp9 , < 2 x double > * %r , align 16
ret void
}
2010-08-29 11:19:04 +08:00
define void @test2 ( < 2 x double > * %r , < 2 x double > * %A , double %B ) nounwind {
2017-06-27 02:20:46 +08:00
; X86-LABEL: test2:
; X86: # BB#0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movapd (%ecx), %xmm0
; X86-NEXT: movhpd {{.*#+}} xmm0 = xmm0[0],mem[0]
; X86-NEXT: movapd %xmm0, (%eax)
; X86-NEXT: retl
;
; X64-LABEL: test2:
; X64: # BB#0:
2017-09-18 11:29:54 +08:00
; X64-NEXT: movaps (%rsi), %xmm1
2017-09-18 12:40:58 +08:00
; X64-NEXT: movlhps {{.*#+}} xmm1 = xmm1[0],xmm0[0]
2017-09-18 11:29:54 +08:00
; X64-NEXT: movaps %xmm1, (%rdi)
2017-06-27 02:20:46 +08:00
; X64-NEXT: retq
2015-02-28 05:17:42 +08:00
%tmp3 = load < 2 x double > , < 2 x double > * %A , align 16
2008-05-24 08:10:02 +08:00
%tmp7 = insertelement < 2 x double > undef , double %B , i32 0
%tmp9 = shufflevector < 2 x double > %tmp3 , < 2 x double > %tmp7 , < 2 x i32 > < i32 0 , i32 2 >
store < 2 x double > %tmp9 , < 2 x double > * %r , align 16
ret void
}
2010-08-29 11:19:04 +08:00
define void @test3 ( < 4 x float > * %res , < 4 x float > * %A , < 4 x float > * %B ) nounwind {
2017-06-27 02:20:46 +08:00
; X86-LABEL: test3:
; X86: # BB#0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: movaps (%edx), %xmm0
; X86-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],mem[0],xmm0[1],mem[1]
; X86-NEXT: movaps %xmm0, (%eax)
; X86-NEXT: retl
;
; X64-LABEL: test3:
; X64: # BB#0:
; X64-NEXT: movaps (%rsi), %xmm0
; X64-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],mem[0],xmm0[1],mem[1]
; X64-NEXT: movaps %xmm0, (%rdi)
; X64-NEXT: retq
2015-02-28 05:17:42 +08:00
%tmp = load < 4 x float > , < 4 x float > * %B ; <<4 x float>> [#uses=2]
%tmp3 = load < 4 x float > , < 4 x float > * %A ; <<4 x float>> [#uses=2]
2010-08-29 11:19:04 +08:00
%tmp.upgrd.1 = extractelement < 4 x float > %tmp3 , i32 0 ; <float> [#uses=1]
%tmp7 = extractelement < 4 x float > %tmp , i32 0 ; <float> [#uses=1]
%tmp8 = extractelement < 4 x float > %tmp3 , i32 1 ; <float> [#uses=1]
%tmp9 = extractelement < 4 x float > %tmp , i32 1 ; <float> [#uses=1]
%tmp10 = insertelement < 4 x float > undef , float %tmp.upgrd.1 , i32 0 ; <<4 x float>> [#uses=1]
%tmp11 = insertelement < 4 x float > %tmp10 , float %tmp7 , i32 1 ; <<4 x float>> [#uses=1]
%tmp12 = insertelement < 4 x float > %tmp11 , float %tmp8 , i32 2 ; <<4 x float>> [#uses=1]
%tmp13 = insertelement < 4 x float > %tmp12 , float %tmp9 , i32 3 ; <<4 x float>> [#uses=1]
store < 4 x float > %tmp13 , < 4 x float > * %res
ret void
}
define void @test4 ( < 4 x float > %X , < 4 x float > * %res ) nounwind {
2017-06-27 02:20:46 +08:00
; X86-LABEL: test4:
; X86: # BB#0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: shufps {{.*#+}} xmm0 = xmm0[2,1,3,3]
; X86-NEXT: movaps %xmm0, (%eax)
; X86-NEXT: retl
;
; X64-LABEL: test4:
; X64: # BB#0:
; X64-NEXT: shufps {{.*#+}} xmm0 = xmm0[2,1,3,3]
; X64-NEXT: movaps %xmm0, (%rdi)
; X64-NEXT: retq
2010-08-29 11:19:04 +08:00
%tmp5 = shufflevector < 4 x float > %X , < 4 x float > undef , < 4 x i32 > < i32 2 , i32 6 , i32 3 , i32 7 > ; <<4 x float>> [#uses=1]
store < 4 x float > %tmp5 , < 4 x float > * %res
ret void
}
define < 4 x i32 > @test5 ( i8 * * %ptr ) nounwind {
2017-06-27 02:20:46 +08:00
; X86-LABEL: test5:
; X86: # BB#0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl (%eax), %eax
; X86-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
; X86-NEXT: pxor %xmm0, %xmm0
; X86-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
; X86-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; X86-NEXT: retl
;
; X64-LABEL: test5:
; X64: # BB#0:
; X64-NEXT: movq (%rdi), %rax
; X64-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
; X64-NEXT: pxor %xmm0, %xmm0
; X64-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
; X64-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; X64-NEXT: retq
2015-02-28 05:17:42 +08:00
%tmp = load i8 * , i8 * * %ptr ; <i8*> [#uses=1]
2010-08-29 11:19:04 +08:00
%tmp.upgrd.1 = bitcast i8 * %tmp to float * ; <float*> [#uses=1]
2015-02-28 05:17:42 +08:00
%tmp.upgrd.2 = load float , float * %tmp.upgrd.1 ; <float> [#uses=1]
2010-08-29 11:19:04 +08:00
%tmp.upgrd.3 = insertelement < 4 x float > undef , float %tmp.upgrd.2 , i32 0 ; <<4 x float>> [#uses=1]
%tmp9 = insertelement < 4 x float > %tmp.upgrd.3 , float 0.000000e+00 , i32 1 ; <<4 x float>> [#uses=1]
%tmp10 = insertelement < 4 x float > %tmp9 , float 0.000000e+00 , i32 2 ; <<4 x float>> [#uses=1]
%tmp11 = insertelement < 4 x float > %tmp10 , float 0.000000e+00 , i32 3 ; <<4 x float>> [#uses=1]
%tmp21 = bitcast < 4 x float > %tmp11 to < 16 x i8 > ; <<16 x i8>> [#uses=1]
%tmp22 = shufflevector < 16 x i8 > %tmp21 , < 16 x i8 > zeroinitializer , < 16 x i32 > < i32 0 , i32 16 , i32 1 , i32 17 , i32 2 , i32 18 , i32 3 , i32 19 , i32 4 , i32 20 , i32 5 , i32 21 , i32 6 , i32 22 , i32 7 , i32 23 > ; <<16 x i8>> [#uses=1]
%tmp31 = bitcast < 16 x i8 > %tmp22 to < 8 x i16 > ; <<8 x i16>> [#uses=1]
%tmp.upgrd.4 = shufflevector < 8 x i16 > zeroinitializer , < 8 x i16 > %tmp31 , < 8 x i32 > < i32 0 , i32 8 , i32 1 , i32 9 , i32 2 , i32 10 , i32 3 , i32 11 > ; <<8 x i16>> [#uses=1]
%tmp36 = bitcast < 8 x i16 > %tmp.upgrd.4 to < 4 x i32 > ; <<4 x i32>> [#uses=1]
ret < 4 x i32 > %tmp36
}
define void @test6 ( < 4 x float > * %res , < 4 x float > * %A ) nounwind {
2017-06-27 02:20:46 +08:00
; X86-LABEL: test6:
; X86: # BB#0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movaps (%ecx), %xmm0
; X86-NEXT: movaps %xmm0, (%eax)
; X86-NEXT: retl
;
; X64-LABEL: test6:
; X64: # BB#0:
; X64-NEXT: movaps (%rsi), %xmm0
; X64-NEXT: movaps %xmm0, (%rdi)
; X64-NEXT: retq
2015-02-28 05:17:42 +08:00
%tmp1 = load < 4 x float > , < 4 x float > * %A ; <<4 x float>> [#uses=1]
2014-10-03 09:37:58 +08:00
%tmp2 = shufflevector < 4 x float > %tmp1 , < 4 x float > undef , < 4 x i32 > < i32 0 , i32 5 , i32 6 , i32 7 > ; <<4 x float>> [#uses=1]
store < 4 x float > %tmp2 , < 4 x float > * %res
ret void
2010-08-29 11:19:04 +08:00
}
define void @test7 ( ) nounwind {
2017-06-27 02:20:46 +08:00
; X86-LABEL: test7:
; X86: # BB#0:
; X86-NEXT: xorps %xmm0, %xmm0
; X86-NEXT: movaps %xmm0, 0
; X86-NEXT: retl
;
; X64-LABEL: test7:
; X64: # BB#0:
; X64-NEXT: xorps %xmm0, %xmm0
; X64-NEXT: movaps %xmm0, 0
; X64-NEXT: retq
2014-10-03 09:37:58 +08:00
bitcast < 4 x i32 > zeroinitializer to < 4 x float > ; <<4 x float>>:1 [#uses=1]
shufflevector < 4 x float > %1 , < 4 x float > zeroinitializer , < 4 x i32 > zeroinitializer ; <<4 x float>>:2 [#uses=1]
store < 4 x float > %2 , < 4 x float > * null
ret void
2010-08-29 11:19:04 +08:00
}
@x = external global [ 4 x i32 ]
define < 2 x i64 > @test8 ( ) nounwind {
2017-06-27 02:20:46 +08:00
; X86-LABEL: test8:
; X86: # BB#0:
; X86-NEXT: movups x, %xmm0
; X86-NEXT: retl
;
; X64-LABEL: test8:
; X64: # BB#0:
; X64-NEXT: movups {{.*}}(%rip), %xmm0
; X64-NEXT: retq
2015-03-14 02:20:45 +08:00
%tmp = load i32 , i32 * getelementptr ( [ 4 x i32 ] , [ 4 x i32 ] * @x , i32 0 , i32 0 ) ; <i32> [#uses=1]
%tmp3 = load i32 , i32 * getelementptr ( [ 4 x i32 ] , [ 4 x i32 ] * @x , i32 0 , i32 1 ) ; <i32> [#uses=1]
%tmp5 = load i32 , i32 * getelementptr ( [ 4 x i32 ] , [ 4 x i32 ] * @x , i32 0 , i32 2 ) ; <i32> [#uses=1]
%tmp7 = load i32 , i32 * getelementptr ( [ 4 x i32 ] , [ 4 x i32 ] * @x , i32 0 , i32 3 ) ; <i32> [#uses=1]
2010-08-29 11:19:04 +08:00
%tmp.upgrd.1 = insertelement < 4 x i32 > undef , i32 %tmp , i32 0 ; <<4 x i32>> [#uses=1]
%tmp13 = insertelement < 4 x i32 > %tmp.upgrd.1 , i32 %tmp3 , i32 1 ; <<4 x i32>> [#uses=1]
%tmp14 = insertelement < 4 x i32 > %tmp13 , i32 %tmp5 , i32 2 ; <<4 x i32>> [#uses=1]
%tmp15 = insertelement < 4 x i32 > %tmp14 , i32 %tmp7 , i32 3 ; <<4 x i32>> [#uses=1]
%tmp16 = bitcast < 4 x i32 > %tmp15 to < 2 x i64 > ; <<2 x i64>> [#uses=1]
ret < 2 x i64 > %tmp16
}
define < 4 x float > @test9 ( i32 %dummy , float %a , float %b , float %c , float %d ) nounwind {
2017-06-27 02:20:46 +08:00
; X86-LABEL: test9:
; X86: # BB#0:
; X86-NEXT: movups {{[0-9]+}}(%esp), %xmm0
; X86-NEXT: retl
;
; X64-LABEL: test9:
; X64: # BB#0:
; X64-NEXT: unpcklps {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1]
; X64-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
2017-09-18 12:40:58 +08:00
; X64-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm2[0]
2017-06-27 02:20:46 +08:00
; X64-NEXT: retq
2010-08-29 11:19:04 +08:00
%tmp = insertelement < 4 x float > undef , float %a , i32 0 ; <<4 x float>> [#uses=1]
%tmp11 = insertelement < 4 x float > %tmp , float %b , i32 1 ; <<4 x float>> [#uses=1]
%tmp12 = insertelement < 4 x float > %tmp11 , float %c , i32 2 ; <<4 x float>> [#uses=1]
%tmp13 = insertelement < 4 x float > %tmp12 , float %d , i32 3 ; <<4 x float>> [#uses=1]
ret < 4 x float > %tmp13
}
define < 4 x float > @test10 ( float %a , float %b , float %c , float %d ) nounwind {
2017-06-27 02:20:46 +08:00
; X86-LABEL: test10:
; X86: # BB#0:
; X86-NEXT: movups {{[0-9]+}}(%esp), %xmm0
; X86-NEXT: retl
;
; X64-LABEL: test10:
; X64: # BB#0:
; X64-NEXT: unpcklps {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1]
; X64-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
2017-09-18 12:40:58 +08:00
; X64-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm2[0]
2017-06-27 02:20:46 +08:00
; X64-NEXT: retq
2010-08-29 11:19:04 +08:00
%tmp = insertelement < 4 x float > undef , float %a , i32 0 ; <<4 x float>> [#uses=1]
%tmp11 = insertelement < 4 x float > %tmp , float %b , i32 1 ; <<4 x float>> [#uses=1]
%tmp12 = insertelement < 4 x float > %tmp11 , float %c , i32 2 ; <<4 x float>> [#uses=1]
%tmp13 = insertelement < 4 x float > %tmp12 , float %d , i32 3 ; <<4 x float>> [#uses=1]
ret < 4 x float > %tmp13
}
define < 2 x double > @test11 ( double %a , double %b ) nounwind {
2017-06-27 02:20:46 +08:00
; X86-LABEL: test11:
; X86: # BB#0:
; X86-NEXT: movups {{[0-9]+}}(%esp), %xmm0
; X86-NEXT: retl
;
; X64-LABEL: test11:
; X64: # BB#0:
2017-09-18 12:40:58 +08:00
; X64-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm1[0]
2017-06-27 02:20:46 +08:00
; X64-NEXT: retq
2010-08-29 11:19:04 +08:00
%tmp = insertelement < 2 x double > undef , double %a , i32 0 ; <<2 x double>> [#uses=1]
%tmp7 = insertelement < 2 x double > %tmp , double %b , i32 1 ; <<2 x double>> [#uses=1]
ret < 2 x double > %tmp7
}
define void @test12 ( ) nounwind {
2017-06-27 02:20:46 +08:00
; X86-LABEL: test12:
; X86: # BB#0:
; X86-NEXT: movapd 0, %xmm0
; X86-NEXT: movapd {{.*#+}} xmm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
; X86-NEXT: movsd {{.*#+}} xmm1 = xmm0[0],xmm1[1]
; X86-NEXT: xorps %xmm2, %xmm2
; X86-NEXT: movhlps {{.*#+}} xmm2 = xmm0[1],xmm2[1]
; X86-NEXT: addps %xmm1, %xmm2
; X86-NEXT: movaps %xmm2, 0
; X86-NEXT: retl
;
; X64-LABEL: test12:
; X64: # BB#0:
; X64-NEXT: movapd 0, %xmm0
; X64-NEXT: movapd {{.*#+}} xmm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
; X64-NEXT: movsd {{.*#+}} xmm1 = xmm0[0],xmm1[1]
; X64-NEXT: xorps %xmm2, %xmm2
; X64-NEXT: movhlps {{.*#+}} xmm2 = xmm0[1],xmm2[1]
; X64-NEXT: addps %xmm1, %xmm2
; X64-NEXT: movaps %xmm2, 0
; X64-NEXT: retq
2015-02-28 05:17:42 +08:00
%tmp1 = load < 4 x float > , < 4 x float > * null ; <<4 x float>> [#uses=2]
2014-10-03 09:37:58 +08:00
%tmp2 = shufflevector < 4 x float > %tmp1 , < 4 x float > < float 1.000000e+00 , float 1.000000e+00 , float 1.000000e+00 , float 1.000000e+00 > , < 4 x i32 > < i32 0 , i32 1 , i32 6 , i32 7 > ; <<4 x float>> [#uses=1]
%tmp3 = shufflevector < 4 x float > %tmp1 , < 4 x float > zeroinitializer , < 4 x i32 > < i32 2 , i32 3 , i32 6 , i32 7 > ; <<4 x float>> [#uses=1]
%tmp4 = fadd < 4 x float > %tmp2 , %tmp3 ; <<4 x float>> [#uses=1]
store < 4 x float > %tmp4 , < 4 x float > * null
ret void
2010-08-29 11:19:04 +08:00
}
define void @test13 ( < 4 x float > * %res , < 4 x float > * %A , < 4 x float > * %B , < 4 x float > * %C ) nounwind {
2017-06-27 02:20:46 +08:00
; X86-LABEL: test13:
; X86: # BB#0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: movaps (%edx), %xmm0
; X86-NEXT: shufps {{.*#+}} xmm0 = xmm0[1,1],mem[0,1]
; X86-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,2,1,3]
; X86-NEXT: movaps %xmm0, (%eax)
; X86-NEXT: retl
;
; X64-LABEL: test13:
; X64: # BB#0:
; X64-NEXT: movaps (%rdx), %xmm0
; X64-NEXT: shufps {{.*#+}} xmm0 = xmm0[1,1],mem[0,1]
; X64-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,2,1,3]
; X64-NEXT: movaps %xmm0, (%rdi)
; X64-NEXT: retq
2015-02-28 05:17:42 +08:00
%tmp3 = load < 4 x float > , < 4 x float > * %B ; <<4 x float>> [#uses=1]
%tmp5 = load < 4 x float > , < 4 x float > * %C ; <<4 x float>> [#uses=1]
2014-10-03 09:37:58 +08:00
%tmp11 = shufflevector < 4 x float > %tmp3 , < 4 x float > %tmp5 , < 4 x i32 > < i32 1 , i32 4 , i32 1 , i32 5 > ; <<4 x float>> [#uses=1]
store < 4 x float > %tmp11 , < 4 x float > * %res
ret void
2010-08-29 11:19:04 +08:00
}
define < 4 x float > @test14 ( < 4 x float > * %x , < 4 x float > * %y ) nounwind {
2017-06-27 02:20:46 +08:00
; X86-LABEL: test14:
; X86: # BB#0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movaps (%ecx), %xmm1
; X86-NEXT: movaps (%eax), %xmm2
; X86-NEXT: movaps %xmm2, %xmm0
; X86-NEXT: addps %xmm1, %xmm0
; X86-NEXT: subps %xmm1, %xmm2
2017-09-18 12:40:58 +08:00
; X86-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm2[0]
2017-06-27 02:20:46 +08:00
; X86-NEXT: retl
;
; X64-LABEL: test14:
; X64: # BB#0:
; X64-NEXT: movaps (%rsi), %xmm1
; X64-NEXT: movaps (%rdi), %xmm2
; X64-NEXT: movaps %xmm2, %xmm0
; X64-NEXT: addps %xmm1, %xmm0
; X64-NEXT: subps %xmm1, %xmm2
2017-09-18 12:40:58 +08:00
; X64-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm2[0]
2017-06-27 02:20:46 +08:00
; X64-NEXT: retq
2015-02-28 05:17:42 +08:00
%tmp = load < 4 x float > , < 4 x float > * %y ; <<4 x float>> [#uses=2]
%tmp5 = load < 4 x float > , < 4 x float > * %x ; <<4 x float>> [#uses=2]
2014-10-03 09:37:58 +08:00
%tmp9 = fadd < 4 x float > %tmp5 , %tmp ; <<4 x float>> [#uses=1]
%tmp21 = fsub < 4 x float > %tmp5 , %tmp ; <<4 x float>> [#uses=1]
%tmp27 = shufflevector < 4 x float > %tmp9 , < 4 x float > %tmp21 , < 4 x i32 > < i32 0 , i32 1 , i32 4 , i32 5 > ; <<4 x float>> [#uses=1]
ret < 4 x float > %tmp27
2010-08-29 11:19:04 +08:00
}
define < 4 x float > @test15 ( < 4 x float > * %x , < 4 x float > * %y ) nounwind {
2017-06-27 02:20:46 +08:00
; X86-LABEL: test15:
; X86: # BB#0: # %entry
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
2017-09-18 11:29:54 +08:00
; X86-NEXT: movaps (%ecx), %xmm0
2017-06-27 02:20:46 +08:00
; X86-NEXT: unpckhpd {{.*#+}} xmm0 = xmm0[1],mem[1]
; X86-NEXT: retl
;
; X64-LABEL: test15:
; X64: # BB#0: # %entry
2017-09-18 11:29:54 +08:00
; X64-NEXT: movaps (%rdi), %xmm0
2017-06-27 02:20:46 +08:00
; X64-NEXT: unpckhpd {{.*#+}} xmm0 = xmm0[1],mem[1]
; X64-NEXT: retq
2014-10-03 09:37:58 +08:00
entry:
2015-02-28 05:17:42 +08:00
%tmp = load < 4 x float > , < 4 x float > * %y ; <<4 x float>> [#uses=1]
%tmp3 = load < 4 x float > , < 4 x float > * %x ; <<4 x float>> [#uses=1]
2014-10-03 09:37:58 +08:00
%tmp4 = shufflevector < 4 x float > %tmp3 , < 4 x float > %tmp , < 4 x i32 > < i32 2 , i32 3 , i32 6 , i32 7 > ; <<4 x float>> [#uses=1]
ret < 4 x float > %tmp4
2010-08-29 11:19:04 +08:00
}
2011-01-06 06:28:46 +08:00
; PR8900
define < 2 x double > @test16 ( < 4 x double > * nocapture %srcA , < 2 x double > * nocapture %dst ) {
2017-06-27 02:20:46 +08:00
; X86-LABEL: test16:
; X86: # BB#0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
2017-09-18 11:29:54 +08:00
; X86-NEXT: movaps 96(%eax), %xmm0
2017-06-27 02:20:46 +08:00
; X86-NEXT: unpcklpd {{.*#+}} xmm0 = xmm0[0],mem[0]
; X86-NEXT: retl
;
; X64-LABEL: test16:
; X64: # BB#0:
2017-09-18 11:29:54 +08:00
; X64-NEXT: movaps 96(%rdi), %xmm0
2017-06-27 02:20:46 +08:00
; X64-NEXT: unpcklpd {{.*#+}} xmm0 = xmm0[0],mem[0]
; X64-NEXT: retq
[opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction
One of several parallel first steps to remove the target type of pointers,
replacing them with a single opaque pointer type.
This adds an explicit type parameter to the gep instruction so that when the
first parameter becomes an opaque pointer type, the type to gep through is
still available to the instructions.
* This doesn't modify gep operators, only instructions (operators will be
handled separately)
* Textual IR changes only. Bitcode (including upgrade) and changing the
in-memory representation will be in separate changes.
* geps of vectors are transformed as:
getelementptr <4 x float*> %x, ...
->getelementptr float, <4 x float*> %x, ...
Then, once the opaque pointer type is introduced, this will ultimately look
like:
getelementptr float, <4 x ptr> %x
with the unambiguous interpretation that it is a vector of pointers to float.
* address spaces remain on the pointer, not the type:
getelementptr float addrspace(1)* %x
->getelementptr float, float addrspace(1)* %x
Then, eventually:
getelementptr float, ptr addrspace(1) %x
Importantly, the massive amount of test case churn has been automated by
same crappy python code. I had to manually update a few test cases that
wouldn't fit the script's model (r228970,r229196,r229197,r229198). The
python script just massages stdin and writes the result to stdout, I
then wrapped that in a shell script to handle replacing files, then
using the usual find+xargs to migrate all the files.
update.py:
import fileinput
import sys
import re
ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
def conv(match, line):
if not match:
return line
line = match.groups()[0]
if len(match.groups()[5]) == 0:
line += match.groups()[2]
line += match.groups()[3]
line += ", "
line += match.groups()[1]
line += "\n"
return line
for line in sys.stdin:
if line.find("getelementptr ") == line.find("getelementptr inbounds"):
if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("):
line = conv(re.match(ibrep, line), line)
elif line.find("getelementptr ") != line.find("getelementptr ("):
line = conv(re.match(normrep, line), line)
sys.stdout.write(line)
apply.sh:
for name in "$@"
do
python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name"
rm -f "$name.tmp"
done
The actual commands:
From llvm/src:
find test/ -name *.ll | xargs ./apply.sh
From llvm/src/tools/clang:
find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}"
From llvm/src/tools/polly:
find test/ -name *.ll | xargs ./apply.sh
After that, check-all (with llvm, clang, clang-tools-extra, lld,
compiler-rt, and polly all checked out).
The extra 'rm' in the apply.sh script is due to a few files in clang's test
suite using interesting unicode stuff that my python script was throwing
exceptions on. None of those files needed to be migrated, so it seemed
sufficient to ignore those cases.
Reviewers: rafael, dexonsmith, grosser
Differential Revision: http://reviews.llvm.org/D7636
llvm-svn: 230786
2015-02-28 03:29:02 +08:00
%i5 = getelementptr inbounds < 4 x double > , < 4 x double > * %srcA , i32 3
2015-02-28 05:17:42 +08:00
%i6 = load < 4 x double > , < 4 x double > * %i5 , align 32
2011-01-06 06:28:46 +08:00
%i7 = shufflevector < 4 x double > %i6 , < 4 x double > undef , < 2 x i32 > < i32 0 , i32 2 >
ret < 2 x double > %i7
}
2011-01-24 11:42:46 +08:00
; PR9009
define fastcc void @test17 ( ) nounwind {
2017-06-27 02:20:46 +08:00
; X86-LABEL: test17:
; X86: # BB#0: # %entry
; X86-NEXT: movaps {{.*#+}} xmm0 = <u,u,32768,32768>
; X86-NEXT: movaps %xmm0, (%eax)
; X86-NEXT: retl
;
; X64-LABEL: test17:
; X64: # BB#0: # %entry
; X64-NEXT: movaps {{.*#+}} xmm0 = <u,u,32768,32768>
; X64-NEXT: movaps %xmm0, (%rax)
; X64-NEXT: retq
2011-01-24 11:42:46 +08:00
entry:
%0 = insertelement < 4 x i32 > undef , i32 undef , i32 1
%1 = shufflevector < 4 x i32 > < i32 undef , i32 undef , i32 32768 , i32 32768 > , < 4 x i32 > %0 , < 4 x i32 > < i32 4 , i32 5 , i32 2 , i32 3 >
%2 = bitcast < 4 x i32 > %1 to < 4 x float >
store < 4 x float > %2 , < 4 x float > * undef
ret void
}
2011-02-14 14:30:45 +08:00
; PR9210
define < 4 x float > @f ( < 4 x double > ) nounwind {
2017-06-27 02:20:46 +08:00
; X86-LABEL: f:
; X86: # BB#0: # %entry
; X86-NEXT: cvtpd2ps %xmm1, %xmm1
; X86-NEXT: cvtpd2ps %xmm0, %xmm0
; X86-NEXT: unpcklpd {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; X86-NEXT: retl
;
; X64-LABEL: f:
; X64: # BB#0: # %entry
; X64-NEXT: cvtpd2ps %xmm1, %xmm1
; X64-NEXT: cvtpd2ps %xmm0, %xmm0
; X64-NEXT: unpcklpd {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; X64-NEXT: retq
2011-02-14 14:30:45 +08:00
entry:
%double2float.i = fptrunc < 4 x double > %0 to < 4 x float >
ret < 4 x float > %double2float.i
}
2014-05-09 07:16:08 +08:00
define < 2 x i64 > @test_insert_64_zext ( < 2 x i64 > %i ) {
2017-06-27 02:20:46 +08:00
; X86-LABEL: test_insert_64_zext:
; X86: # BB#0:
; X86-NEXT: movq {{.*#+}} xmm0 = xmm0[0],zero
; X86-NEXT: retl
;
; X64-LABEL: test_insert_64_zext:
; X64: # BB#0:
; X64-NEXT: movq {{.*#+}} xmm0 = xmm0[0],zero
; X64-NEXT: retq
2014-05-09 07:16:08 +08:00
%1 = shufflevector < 2 x i64 > %i , < 2 x i64 > < i64 0 , i64 undef > , < 2 x i32 > < i32 0 , i32 2 >
ret < 2 x i64 > %1
}
2014-05-12 21:12:08 +08:00
define < 4 x i32 > @PR19721 ( < 4 x i32 > %i ) {
2017-06-27 02:20:46 +08:00
; X86-LABEL: PR19721:
; X86: # BB#0:
; X86-NEXT: andps {{\.LCPI.*}}, %xmm0
; X86-NEXT: retl
;
; X64-LABEL: PR19721:
; X64: # BB#0:
; X64-NEXT: movq %xmm0, %rax
; X64-NEXT: movabsq $-4294967296, %rcx # imm = 0xFFFFFFFF00000000
; X64-NEXT: andq %rax, %rcx
; X64-NEXT: movq %rcx, %xmm1
; X64-NEXT: movsd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
; X64-NEXT: retq
2014-05-12 21:12:08 +08:00
%bc = bitcast < 4 x i32 > %i to i128
%insert = and i128 %bc , -4294967296
%bc2 = bitcast i128 %insert to < 4 x i32 >
ret < 4 x i32 > %bc2
2014-10-03 09:37:58 +08:00
}
2014-05-12 21:12:08 +08:00
2014-10-03 09:37:58 +08:00
define < 4 x i32 > @test_mul ( < 4 x i32 > %x , < 4 x i32 > %y ) {
2017-06-27 02:20:46 +08:00
; X86-LABEL: test_mul:
; X86: # BB#0:
; X86-NEXT: pshufd {{.*#+}} xmm2 = xmm0[1,1,3,3]
; X86-NEXT: pmuludq %xmm1, %xmm0
; X86-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; X86-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,3,3]
; X86-NEXT: pmuludq %xmm2, %xmm1
; X86-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; X86-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; X86-NEXT: retl
;
; X64-LABEL: test_mul:
; X64: # BB#0:
; X64-NEXT: pshufd {{.*#+}} xmm2 = xmm0[1,1,3,3]
; X64-NEXT: pmuludq %xmm1, %xmm0
; X64-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; X64-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,3,3]
; X64-NEXT: pmuludq %xmm2, %xmm1
; X64-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; X64-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; X64-NEXT: retq
2014-10-03 09:37:58 +08:00
%m = mul < 4 x i32 > %x , %y
ret < 4 x i32 > %m
2014-05-12 21:12:08 +08:00
}
