2016-02-02 05:46:12 +08:00
|
|
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
|
|
; RUN: llc < %s -mtriple=i686-unknown -mattr=+sse2 | FileCheck %s --check-prefix=X32-SSE2
|
|
|
|
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+ssse3 | FileCheck %s --check-prefix=X64-SSSE3
|
|
|
|
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+avx | FileCheck %s --check-prefix=X64-AVX
|
2008-05-13 16:35:03 +08:00
|
|
|
|
2014-08-27 19:22:16 +08:00
|
|
|
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
|
|
|
|
|
2008-05-13 16:35:03 +08:00
|
|
|
define i32 @t(<2 x i64>* %val) nounwind {
|
2016-02-02 05:46:12 +08:00
|
|
|
; X32-SSE2-LABEL: t:
|
2017-12-05 01:18:51 +08:00
|
|
|
; X32-SSE2: # %bb.0:
|
2016-02-02 05:46:12 +08:00
|
|
|
; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
|
|
; X32-SSE2-NEXT: movl 8(%eax), %eax
|
|
|
|
; X32-SSE2-NEXT: retl
|
|
|
|
;
|
|
|
|
; X64-SSSE3-LABEL: t:
|
2017-12-05 01:18:51 +08:00
|
|
|
; X64-SSSE3: # %bb.0:
|
2016-02-02 05:46:12 +08:00
|
|
|
; X64-SSSE3-NEXT: movl 8(%rdi), %eax
|
|
|
|
; X64-SSSE3-NEXT: retq
|
|
|
|
;
|
|
|
|
; X64-AVX-LABEL: t:
|
2017-12-05 01:18:51 +08:00
|
|
|
; X64-AVX: # %bb.0:
|
2016-02-02 05:46:12 +08:00
|
|
|
; X64-AVX-NEXT: movl 8(%rdi), %eax
|
|
|
|
; X64-AVX-NEXT: retq
|
|
|
|
%tmp2 = load <2 x i64>, <2 x i64>* %val, align 16 ; <<2 x i64>> [#uses=1]
|
|
|
|
%tmp3 = bitcast <2 x i64> %tmp2 to <4 x i32> ; <<4 x i32>> [#uses=1]
|
|
|
|
%tmp4 = extractelement <4 x i32> %tmp3, i32 2 ; <i32> [#uses=1]
|
|
|
|
ret i32 %tmp4
|
2008-05-13 16:35:03 +08:00
|
|
|
}
|
2011-07-26 06:25:42 +08:00
|
|
|
|
|
|
|
; Case where extractelement of load ends up as undef.
|
|
|
|
; (Making sure this doesn't crash.)
|
|
|
|
define i32 @t2(<8 x i32>* %xp) {
|
2016-02-02 05:46:12 +08:00
|
|
|
; X32-SSE2-LABEL: t2:
|
2017-12-05 01:18:51 +08:00
|
|
|
; X32-SSE2: # %bb.0:
|
2016-02-02 05:46:12 +08:00
|
|
|
; X32-SSE2-NEXT: retl
|
|
|
|
;
|
|
|
|
; X64-SSSE3-LABEL: t2:
|
2017-12-05 01:18:51 +08:00
|
|
|
; X64-SSSE3: # %bb.0:
|
2016-02-02 05:46:12 +08:00
|
|
|
; X64-SSSE3-NEXT: retq
|
|
|
|
;
|
|
|
|
; X64-AVX-LABEL: t2:
|
2017-12-05 01:18:51 +08:00
|
|
|
; X64-AVX: # %bb.0:
|
2016-02-02 05:46:12 +08:00
|
|
|
; X64-AVX-NEXT: retq
|
2015-02-28 05:17:42 +08:00
|
|
|
%x = load <8 x i32>, <8 x i32>* %xp
|
2016-02-02 05:46:12 +08:00
|
|
|
%Shuff68 = shufflevector <8 x i32> %x, <8 x i32> undef, <8 x i32> <i32 undef, i32 7, i32 9, i32 undef, i32 13, i32 15, i32 1, i32 3>
|
2011-07-26 06:25:42 +08:00
|
|
|
%y = extractelement <8 x i32> %Shuff68, i32 0
|
|
|
|
ret i32 %y
|
|
|
|
}
|
2014-08-27 19:22:16 +08:00
|
|
|
|
|
|
|
; This case could easily end up inf-looping in the DAG combiner due to an
|
|
|
|
; low alignment load of the vector which prevents us from reliably forming a
|
|
|
|
; narrow load.
|
2014-12-11 00:58:54 +08:00
|
|
|
|
|
|
|
; The expected codegen is identical for the AVX case except
|
|
|
|
; load/store instructions will have a leading 'v', so we don't
|
|
|
|
; need to special-case the checks.
|
|
|
|
|
2014-08-27 19:22:16 +08:00
|
|
|
define void @t3() {
|
2016-02-02 05:46:12 +08:00
|
|
|
; X32-SSE2-LABEL: t3:
|
2017-12-05 01:18:51 +08:00
|
|
|
; X32-SSE2: # %bb.0: # %bb
|
2016-02-02 05:46:12 +08:00
|
|
|
; X32-SSE2-NEXT: movupd (%eax), %xmm0
|
|
|
|
; X32-SSE2-NEXT: movhpd %xmm0, (%eax)
|
|
|
|
;
|
|
|
|
; X64-SSSE3-LABEL: t3:
|
2017-12-05 01:18:51 +08:00
|
|
|
; X64-SSSE3: # %bb.0: # %bb
|
2016-03-02 19:43:05 +08:00
|
|
|
; X64-SSSE3-NEXT: movddup {{.*#+}} xmm0 = mem[0,0]
|
|
|
|
; X64-SSSE3-NEXT: movlpd %xmm0, (%rax)
|
2016-02-02 05:46:12 +08:00
|
|
|
;
|
|
|
|
; X64-AVX-LABEL: t3:
|
2017-12-05 01:18:51 +08:00
|
|
|
; X64-AVX: # %bb.0: # %bb
|
2016-03-02 19:43:05 +08:00
|
|
|
; X64-AVX-NEXT: vmovddup {{.*#+}} xmm0 = mem[0,0]
|
|
|
|
; X64-AVX-NEXT: vmovlpd %xmm0, (%rax)
|
2014-08-27 19:22:16 +08:00
|
|
|
bb:
|
2015-02-28 05:17:42 +08:00
|
|
|
%tmp13 = load <2 x double>, <2 x double>* undef, align 1
|
2014-08-27 19:22:16 +08:00
|
|
|
%.sroa.3.24.vec.extract = extractelement <2 x double> %tmp13, i32 1
|
|
|
|
store double %.sroa.3.24.vec.extract, double* undef, align 8
|
|
|
|
unreachable
|
|
|
|
}
|
2014-10-25 05:04:41 +08:00
|
|
|
|
|
|
|
; Case where a load is unary shuffled, then bitcast (to a type with the same
|
|
|
|
; number of elements) before extractelement.
|
|
|
|
; This is testing for an assertion - the extraction was assuming that the undef
|
|
|
|
; second shuffle operand was a post-bitcast type instead of a pre-bitcast type.
|
|
|
|
define i64 @t4(<2 x double>* %a) {
|
2016-02-02 05:46:12 +08:00
|
|
|
; X32-SSE2-LABEL: t4:
|
2017-12-05 01:18:51 +08:00
|
|
|
; X32-SSE2: # %bb.0:
|
2016-02-02 05:46:12 +08:00
|
|
|
; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
|
|
; X32-SSE2-NEXT: movapd (%eax), %xmm0
|
|
|
|
; X32-SSE2-NEXT: shufpd {{.*#+}} xmm0 = xmm0[1,0]
|
|
|
|
; X32-SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
|
|
; X32-SSE2-NEXT: movd %xmm1, %eax
|
2016-12-18 22:26:02 +08:00
|
|
|
; X32-SSE2-NEXT: shufps {{.*#+}} xmm0 = xmm0[3,1,2,3]
|
2016-02-02 05:46:12 +08:00
|
|
|
; X32-SSE2-NEXT: movd %xmm0, %edx
|
|
|
|
; X32-SSE2-NEXT: retl
|
|
|
|
;
|
|
|
|
; X64-SSSE3-LABEL: t4:
|
2017-12-05 01:18:51 +08:00
|
|
|
; X64-SSSE3: # %bb.0:
|
2016-02-02 05:46:12 +08:00
|
|
|
; X64-SSSE3-NEXT: movq (%rdi), %rax
|
|
|
|
; X64-SSSE3-NEXT: retq
|
|
|
|
;
|
|
|
|
; X64-AVX-LABEL: t4:
|
2017-12-05 01:18:51 +08:00
|
|
|
; X64-AVX: # %bb.0:
|
2016-02-02 05:46:12 +08:00
|
|
|
; X64-AVX-NEXT: movq (%rdi), %rax
|
|
|
|
; X64-AVX-NEXT: retq
|
2015-02-28 05:17:42 +08:00
|
|
|
%b = load <2 x double>, <2 x double>* %a, align 16
|
2014-10-25 05:04:41 +08:00
|
|
|
%c = shufflevector <2 x double> %b, <2 x double> %b, <2 x i32> <i32 1, i32 0>
|
|
|
|
%d = bitcast <2 x double> %c to <2 x i64>
|
|
|
|
%e = extractelement <2 x i64> %d, i32 1
|
|
|
|
ret i64 %e
|
|
|
|
}
|
|
|
|
|