maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

Revert "In visitSTORE, always use FindBetterChain, rather than only when UseAA is enabled." 

This reverts commit r296252 until 256-bit operations are more efficiently generated in X86.

llvm-svn: 296279
This commit is contained in:
Nirav Dave 2017-02-26 01:27:32 +00:00
parent 19ce92e20c
commit 73cd0194cf
74 changed files with 3132 additions and 3085 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
llvm/include/llvm/Target/TargetLowering.h
View File

@ -363,9 +363,6 @@ public:
return false;
}
/// Returns if it's reasonable to merge stores to MemVT size.
virtual bool canMergeStoresTo(EVT MemVT) const { return true; }
/// \brief Return true if it is cheap to speculate a call to intrinsic cttz.
virtual bool isCheapToSpeculateCttz() const {
return false;

742
llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
View File

File diff suppressed because it is too large Load Diff

2
llvm/lib/CodeGen/TargetLoweringBase.cpp
View File

@ -850,7 +850,7 @@ TargetLoweringBase::TargetLoweringBase(const TargetMachine &tm) : TM(tm) {
MinFunctionAlignment = 0;
PrefFunctionAlignment = 0;
PrefLoopAlignment = 0;
GatherAllAliasesMaxDepth = 18;
GatherAllAliasesMaxDepth = 6;
MinStackArgumentAlignment = 1;
// TODO: the default will be switched to 0 in the next commit, along
// with the Target-specific changes necessary.

2
llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
View File

@ -9254,7 +9254,7 @@ static SDValue performSTORECombine(SDNode *N,
return SDValue();
}
/// This function handles the log2-shuffle pattern produced by the
/// This function handles the log2-shuffle pattern produced by the
/// LoopVectorizer for the across vector reduction. It consists of
/// log2(NumVectorElements) steps and, in each step, 2^(s) elements
/// are reduced, where s is an induction variable from 0 to

5
llvm/lib/Target/ARM/ARMISelLowering.h
View File

@ -500,11 +500,6 @@ class InstrItineraryData;
bool canCombineStoreAndExtract(Type *VectorTy, Value *Idx,
unsigned &Cost) const override;
bool canMergeStoresTo(EVT MemVT) const override {
// Do not merge to larger than i32.
return (MemVT.getSizeInBits() <= 32);
}
bool isCheapToSpeculateCttz() const override;
bool isCheapToSpeculateCtlz() const override;

4
llvm/test/CodeGen/AArch64/argument-blocks.ll
View File

@ -59,10 +59,10 @@ define i64 @test_hfa_ignores_gprs([7 x float], [2 x float] %in, i64, i64 %res) {
}
; [2 x float] should not be promoted to double by the Darwin varargs handling,
; but should go in an 8-byte aligned slot and can be merged as integer stores.
; but should go in an 8-byte aligned slot.
define void @test_varargs_stackalign() {
; CHECK-LABEL: test_varargs_stackalign:
; CHECK-DARWINPCS: str {{x[0-9]+}}, [sp, #16]
; CHECK-DARWINPCS: stp {{w[0-9]+}}, {{w[0-9]+}}, [sp, #16]
call void(...) @callee([3 x float] undef, [2 x float] [float 1.0, float 2.0])
ret void

5
llvm/test/CodeGen/AArch64/arm64-abi.ll
View File

@ -205,7 +205,10 @@ declare i32 @args_i32(i32, i32, i32, i32, i32, i32, i32, i32, i16 signext, i32,
define i32 @test8(i32 %argc, i8** nocapture %argv) nounwind {
entry:
; CHECK-LABEL: test8
; CHECK: str w8, [sp]
; CHECK: strb {{w[0-9]+}}, [sp, #3]
; CHECK: strb wzr, [sp, #2]
; CHECK: strb {{w[0-9]+}}, [sp, #1]
; CHECK: strb wzr, [sp]
; CHECK: bl
; FAST-LABEL: test8
; FAST: strb {{w[0-9]+}}, [sp]

4
llvm/test/CodeGen/AArch64/arm64-memset-inline.ll
View File

@ -13,8 +13,8 @@ define void @t2() nounwind ssp {
entry:
; CHECK-LABEL: t2:
; CHECK: strh wzr, [sp, #32]
; CHECK: stp xzr, xzr, [sp, #8]
; CHECK: str xzr, [sp, #24]
; CHECK: stp xzr, xzr, [sp, #16]
; CHECK: str xzr, [sp, #8]
%buf = alloca [26 x i8], align 1
%0 = getelementptr inbounds [26 x i8], [26 x i8]* %buf, i32 0, i32 0
call void @llvm.memset.p0i8.i32(i8* %0, i8 0, i32 26, i32 1, i1 false)

2
llvm/test/CodeGen/AArch64/arm64-variadic-aapcs.ll
View File

@ -99,7 +99,7 @@ define void @test_nospare([8 x i64], [8 x float], ...) {
; __stack field should point just past them.
define void @test_offsetstack([8 x i64], [2 x i64], [3 x float], ...) {
; CHECK-LABEL: test_offsetstack:
; CHECK: stp {{q[0-9]+}}, {{q[0-9]+}}, [sp, #-80]!
; CHECK: sub sp, sp, #80
; CHECK: add [[STACK_TOP:x[0-9]+]], sp, #96
; CHECK: add x[[VAR:[0-9]+]], {{x[0-9]+}}, :lo12:var
; CHECK: str [[STACK_TOP]], [x[[VAR]]]

3
llvm/test/CodeGen/AArch64/merge-store.ll
View File

@ -4,7 +4,8 @@
@g0 = external global <3 x float>, align 16
@g1 = external global <3 x float>, align 4
; CHECK: ldr q[[R0:[0-9]+]], {{\[}}[[R1:x[0-9]+]], :lo12:g0
; CHECK: ldr s[[R0:[0-9]+]], {{\[}}[[R1:x[0-9]+]]{{\]}}, #4
; CHECK: ld1{{\.?s?}} { v[[R0]]{{\.?s?}} }[1], {{\[}}[[R1]]{{\]}}
; CHECK: str d[[R0]]
define void @blam() {

3
llvm/test/CodeGen/AArch64/vector_merge_dep_check.ll
View File

@ -1,4 +1,5 @@
; RUN: llc < %s | FileCheck %s
; RUN: llc --combiner-alias-analysis=false < %s | FileCheck %s
; RUN: llc --combiner-alias-analysis=true < %s | FileCheck %s
; This test checks that we do not merge stores together which have
; dependencies through their non-chain operands (e.g. one store is the

24
llvm/test/CodeGen/AMDGPU/debugger-insert-nops.ll
View File

@ -1,21 +1,13 @@
; RUN: llc -O0 -mtriple=amdgcn--amdhsa -mcpu=fiji -mattr=+amdgpu-debugger-insert-nops -verify-machineinstrs < %s | FileCheck %s --check-prefix=CHECK
; RUN: llc -O0 -mtriple=amdgcn--amdhsa -mcpu=fiji -mattr=+amdgpu-debugger-insert-nops -verify-machineinstrs < %s | FileCheck %s --check-prefix=CHECKNOP
; RUN: llc -O0 -mtriple=amdgcn--amdhsa -mcpu=fiji -mattr=+amdgpu-debugger-insert-nops -verify-machineinstrs < %s | FileCheck %s
; This test expects that we have one instance for each line in some order with "s_nop 0" instances after each.
; CHECK: test01.cl:2:{{[0-9]+}}
; CHECK-NEXT: s_nop 0
; Check that each line appears at least once
; CHECK-DAG: test01.cl:2:3
; CHECK-DAG: test01.cl:3:3
; CHECK-DAG: test01.cl:4:3
; CHECK: test01.cl:3:{{[0-9]+}}
; CHECK-NEXT: s_nop 0
; Check that each of each of the lines consists of the line output, followed by "s_nop 0"
; CHECKNOP: test01.cl:{{[234]}}:3
; CHECKNOP-NEXT: s_nop 0
; CHECKNOP: test01.cl:{{[234]}}:3
; CHECKNOP-NEXT: s_nop 0
; CHECKNOP: test01.cl:{{[234]}}:3
; CHECKNOP-NEXT: s_nop 0
; CHECK: test01.cl:4:{{[0-9]+}}
; CHECK-NEXT: s_nop 0
; CHECK: test01.cl:5:{{[0-9]+}}
; CHECK-NEXT: s_nop 0
@ -29,7 +21,7 @@ entry:
call void @llvm.dbg.declare(metadata i32 addrspace(1)** %A.addr, metadata !17, metadata !18), !dbg !19
%0 = load i32 addrspace(1)*, i32 addrspace(1)** %A.addr, align 4, !dbg !20
%arrayidx = getelementptr inbounds i32, i32 addrspace(1)* %0, i32 0, !dbg !20
store i32 1, i32 addrspace(1)* %arrayidx, align 4, !dbg !20
store i32 1, i32 addrspace(1)* %arrayidx, align 4, !dbg !21
%1 = load i32 addrspace(1)*, i32 addrspace(1)** %A.addr, align 4, !dbg !22
%arrayidx1 = getelementptr inbounds i32, i32 addrspace(1)* %1, i32 1, !dbg !22
store i32 2, i32 addrspace(1)* %arrayidx1, align 4, !dbg !23

6
llvm/test/CodeGen/AMDGPU/insert_vector_elt.ll
View File

@ -255,9 +255,11 @@ define void @dynamic_insertelement_v2i8(<2 x i8> addrspace(1)* %out, <2 x i8> %a
; GCN: buffer_load_ubyte v{{[0-9]+}}, off
; GCN: buffer_load_ubyte v{{[0-9]+}}, off
; GCN-DAG: buffer_store_byte v{{[0-9]+}}, off, s{{\[[0-9]+:[0-9]+\]}}, s{{[0-9]+}} offset:4
; GCN-DAG: buffer_store_byte v{{[0-9]+}}, off, s{{\[[0-9]+:[0-9]+\]}}, s{{[0-9]+}} offset:5
; GCN-DAG: buffer_store_byte v{{[0-9]+}}, off, s{{\[[0-9]+:[0-9]+\]}}, s{{[0-9]+}} offset:6
; GCN-DAG: buffer_store_byte v{{[0-9]+}}, off, s{{\[[0-9]+:[0-9]+\]}}, s{{[0-9]+}} offset:5
; GCN-DAG: buffer_store_byte v{{[0-9]+}}, off, s{{\[[0-9]+:[0-9]+\]}}, s{{[0-9]+}} offset:4
; GCN: buffer_store_byte v{{[0-9]+}}, v{{[0-9]+}}, s{{\[[0-9]+:[0-9]+\]}}, s{{[0-9]+}} offen{{$}}
; GCN: buffer_load_ubyte
; GCN: buffer_load_ubyte

24
llvm/test/CodeGen/AMDGPU/merge-stores.ll
View File

@ -1,5 +1,8 @@
; RUN: llc -march=amdgcn -verify-machineinstrs -amdgpu-load-store-vectorizer=0 < %s | FileCheck -check-prefix=SI -check-prefix=GCN -check-prefix=GCN-AA %s
; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs -amdgpu-load-store-vectorizer=0 < %s | FileCheck -check-prefix=SI -check-prefix=GCN -check-prefix=GCN-AA %s
; RUN: llc -march=amdgcn -verify-machineinstrs -amdgpu-load-store-vectorizer=0 < %s | FileCheck -check-prefix=SI -check-prefix=GCN -check-prefix=GCN-NOAA %s
; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs -amdgpu-load-store-vectorizer=0 < %s | FileCheck -check-prefix=SI -check-prefix=GCN -check-prefix=GCN-NOAA %s
; RUN: llc -march=amdgcn -verify-machineinstrs -combiner-alias-analysis -amdgpu-load-store-vectorizer=0 < %s | FileCheck -check-prefix=SI -check-prefix=GCN -check-prefix=GCN-AA %s
; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs -combiner-alias-analysis -amdgpu-load-store-vectorizer=0 < %s | FileCheck -check-prefix=SI -check-prefix=GCN -check-prefix=GCN-AA %s
; This test is mostly to test DAG store merging, so disable the vectorizer.
; Run with devices with different unaligned load restrictions.
@ -147,7 +150,12 @@ define void @merge_global_store_4_constants_f32(float addrspace(1)* %out) #0 {
}
; GCN-LABEL: {{^}}merge_global_store_4_constants_mixed_i32_f32:
; GCN-AA: buffer_store_dwordx4 v
; GCN-NOAA: buffer_store_dwordx4 v
; GCN-AA: buffer_store_dwordx2
; GCN-AA: buffer_store_dword v
; GCN-AA: buffer_store_dword v
; GCN: s_endpgm
define void @merge_global_store_4_constants_mixed_i32_f32(float addrspace(1)* %out) #0 {
%out.gep.1 = getelementptr float, float addrspace(1)* %out, i32 1
@ -466,9 +474,17 @@ define void @merge_global_store_4_adjacent_loads_i8_natural_align(i8 addrspace(1
ret void
}
; This works once AA is enabled on the subtarget
; GCN-LABEL: {{^}}merge_global_store_4_vector_elts_loads_v4i32:
; GCN: buffer_load_dwordx4 [[LOAD:v\[[0-9]+:[0-9]+\]]]
; GCN: buffer_store_dwordx4 [[LOAD]]
; GCN-NOAA: buffer_store_dword v
; GCN-NOAA: buffer_store_dword v
; GCN-NOAA: buffer_store_dword v
; GCN-NOAA: buffer_store_dword v
; GCN-AA: buffer_store_dwordx4 [[LOAD]]
; GCN: s_endpgm
define void @merge_global_store_4_vector_elts_loads_v4i32(i32 addrspace(1)* %out, <4 x i32> addrspace(1)* %in) #0 {
%out.gep.1 = getelementptr i32, i32 addrspace(1)* %out, i32 1

12
llvm/test/CodeGen/AMDGPU/private-element-size.ll
View File

@ -32,10 +32,10 @@
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], s9 offset:40{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], s9 offset:44{{$}}
; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen{{$}}
; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:4{{$}}
; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:8{{$}}
; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:12{{$}}
; HSA-ELT4: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen{{$}}
; HSA-ELT4: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:4{{$}}
; HSA-ELT4: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:8{{$}}
; HSA-ELT4: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:12{{$}}
define void @private_elt_size_v4i32(<4 x i32> addrspace(1)* %out, i32 addrspace(1)* %index.array) #0 {
entry:
%tid = call i32 @llvm.amdgcn.workitem.id.x()
@ -130,8 +130,8 @@ entry:
; HSA-ELT8: private_element_size = 2
; HSA-ELT4: private_element_size = 1
; HSA-ELTGE8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, {{off|v[0-9]}}, s[0:3], s9 offset:1
; HSA-ELTGE8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, {{off|v[0-9]}}, s[0:3], s9 offset:2
; HSA-ELTGE8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], s9 offset:16
; HSA-ELTGE8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], s9 offset:24
; HSA-ELTGE8: buffer_load_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen

17
llvm/test/CodeGen/AMDGPU/si-triv-disjoint-mem-access.ll
View File

@ -157,8 +157,9 @@ define void @reorder_global_load_local_store_global_load(i32 addrspace(1)* %out,
; FUNC-LABEL: @reorder_local_offsets
; CI: ds_read2_b32 {{v\[[0-9]+:[0-9]+\]}}, {{v[0-9]+}} offset0:100 offset1:102
; CI-DAG: ds_write2_b32 {{v[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} offset0:3 offset1:100
; CI-DAG: ds_write_b32 {{v[0-9]+}}, {{v[0-9]+}} offset:408
; CI: ds_write2_b32 {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}} offset0:3 offset1:100
; CI: ds_read_b32 {{v[0-9]+}}, {{v[0-9]+}} offset:12
; CI: ds_write_b32 {{v[0-9]+}}, {{v[0-9]+}} offset:408
; CI: buffer_store_dword
; CI: s_endpgm
define void @reorder_local_offsets(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* noalias nocapture readnone %gptr, i32 addrspace(3)* noalias nocapture %ptr0) #0 {
@ -180,12 +181,12 @@ define void @reorder_local_offsets(i32 addrspace(1)* nocapture %out, i32 addrspa
}
; FUNC-LABEL: @reorder_global_offsets
; CI-DAG: buffer_load_dword {{v[0-9]+}}, off, {{s\[[0-9]+:[0-9]+\]}}, 0 offset:400
; CI-DAG: buffer_load_dword {{v[0-9]+}}, off, {{s\[[0-9]+:[0-9]+\]}}, 0 offset:408
; CI-DAG: buffer_store_dword {{v[0-9]+}}, off, {{s\[[0-9]+:[0-9]+\]}}, 0 offset:12
; CI-DAG: buffer_store_dword {{v[0-9]+}}, off, {{s\[[0-9]+:[0-9]+\]}}, 0 offset:400
; CI-DAG: buffer_store_dword {{v[0-9]+}}, off, {{s\[[0-9]+:[0-9]+\]}}, 0 offset:408
; CI: buffer_store_dword
; CI: buffer_load_dword {{v[0-9]+}}, off, {{s\[[0-9]+:[0-9]+\]}}, 0 offset:400
; CI: buffer_load_dword {{v[0-9]+}}, off, {{s\[[0-9]+:[0-9]+\]}}, 0 offset:408
; CI: buffer_store_dword {{v[0-9]+}}, off, {{s\[[0-9]+:[0-9]+\]}}, 0 offset:12
; CI: buffer_store_dword {{v[0-9]+}}, off, {{s\[[0-9]+:[0-9]+\]}}, 0 offset:400
; CI: buffer_store_dword {{v[0-9]+}}, off, {{s\[[0-9]+:[0-9]+\]}}, 0 offset:408
; CI: buffer_load_dword {{v[0-9]+}}, off, {{s\[[0-9]+:[0-9]+\]}}, 0 offset:12
; CI: s_endpgm
define void @reorder_global_offsets(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* noalias nocapture readnone %gptr, i32 addrspace(1)* noalias nocapture %ptr0) #0 {
%ptr1 = getelementptr inbounds i32, i32 addrspace(1)* %ptr0, i32 3

3
llvm/test/CodeGen/ARM/2012-10-04-AAPCS-byval-align8.ll
View File

@ -12,8 +12,7 @@ define void @test_byval_8_bytes_alignment(i32 %i, ...) {
entry:
; CHECK: sub sp, sp, #12
; CHECK: sub sp, sp, #4
; CHECK: add r0, sp, #4
; CHECK: stm sp, {r0, r1, r2, r3}
; CHECK: stmib sp, {r1, r2, r3}
%g = alloca i8*
%g1 = bitcast i8** %g to i8*
call void @llvm.va_start(i8* %g1)

100
llvm/test/CodeGen/ARM/alloc-no-stack-realign.ll
View File

@ -1,4 +1,5 @@
; RUN: llc < %s -mtriple=armv7-apple-ios -O0 | FileCheck %s
; RUN: llc < %s -mtriple=armv7-apple-ios -O0 | FileCheck %s -check-prefix=NO-REALIGN
; RUN: llc < %s -mtriple=armv7-apple-ios -O0 | FileCheck %s -check-prefix=REALIGN
; rdar://12713765
; When realign-stack is set to false, make sure we are not creating stack
@ -7,31 +8,29 @@
define void @test1(<16 x float>* noalias sret %agg.result) nounwind ssp "no-realign-stack" {
entry:
; CHECK-LABEL: test1
; CHECK: ldr r[[R1:[0-9]+]], [pc, r1]
; CHECK: add r[[R2:[0-9]+]], r1, #48
; CHECK: vld1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
; CHECK: mov r[[R2:[0-9]+]], r[[R1]]
; CHECK: vld1.32 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]!
; CHECK: vld1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
; CHECK: add r[[R1:[0-9]+]], r[[R1]], #32
; CHECK: vld1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R1]]:128]
; CHECK: mov r[[R1:[0-9]+]], sp
; CHECK: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R1]]:128]
; CHECK: add r[[R2:[0-9]+]], r[[R1]], #32
; CHECK: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
; CHECK: vld1.32 {{{d[0-9]+, d[0-9]+}}}, [r[[R1]]:128]!
; CHECK: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R1]]:128]
; CHECK: vld1.32 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]!
; CHECK: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
; CHECK: vld1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R1]]:128]
; CHECK: vld1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
; CHECK: add r[[R1:[0-9]+]], r0, #48
; CHECK: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R1]]:128]
; CHECK: add r[[R1:[0-9]+]], r0, #32
; CHECK: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R1]]:128]
; CHECK: vst1.32 {{{d[0-9]+, d[0-9]+}}}, [r0:128]!
; CHECK: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r0:128]
; NO-REALIGN-LABEL: test1
; NO-REALIGN: mov r[[R2:[0-9]+]], r[[R1:[0-9]+]]
; NO-REALIGN: vld1.32 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]!
; NO-REALIGN: vld1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
; NO-REALIGN: add r[[R2:[0-9]+]], r[[R1]], #32
; NO-REALIGN: vld1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
; NO-REALIGN: add r[[R2:[0-9]+]], r[[R1]], #48
; NO-REALIGN: vld1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
; NO-REALIGN: add r[[R2:[0-9]+]], r[[R1:[0-9]+]], #48
; NO-REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
; NO-REALIGN: add r[[R2:[0-9]+]], r[[R1]], #32
; NO-REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
; NO-REALIGN: mov r[[R3:[0-9]+]], r[[R1]]
; NO-REALIGN: vst1.32 {{{d[0-9]+, d[0-9]+}}}, [r[[R3]]:128]!
; NO-REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R3]]:128]
; NO-REALIGN: add r[[R2:[0-9]+]], r[[R0:0]], #48
; NO-REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
; NO-REALIGN: add r[[R2:[0-9]+]], r[[R0]], #32
; NO-REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
; NO-REALIGN: vst1.32 {{{d[0-9]+, d[0-9]+}}}, [r[[R0]]:128]!
; NO-REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R0]]:128]
%retval = alloca <16 x float>, align 16
%0 = load <16 x float>, <16 x float>* @T3_retval, align 16
store <16 x float> %0, <16 x float>* %retval
@ -42,33 +41,32 @@ entry:
define void @test2(<16 x float>* noalias sret %agg.result) nounwind ssp {
entry:
; CHECK: ldr r[[R1:[0-9]+]], [pc, r1]
; CHECK: add r[[R2:[0-9]+]], r[[R1]], #48
; CHECK: vld1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
; CHECK: mov r[[R2:[0-9]+]], r[[R1]]
; CHECK: vld1.32 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]!
; CHECK: vld1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
; CHECK: add r[[R1:[0-9]+]], r[[R1]], #32
; CHECK: vld1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R1]]:128]
; CHECK: mov r[[R1:[0-9]+]], sp
; CHECK: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R1]]:128]
; CHECK: orr r[[R2:[0-9]+]], r[[R1]], #32
; CHECK: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
; CHECK: vld1.32 {{{d[0-9]+, d[0-9]+}}}, [r[[R1]]:128]!
; CHECK: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R1]]:128]
; CHECK: vld1.32 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]!
; CHECK: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
; CHECK: vld1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R1]]:128]
; CHECK: vld1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
; CHECK: add r[[R1:[0-9]+]], r0, #48
; CHECK: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R1]]:128]
; CHECK: add r[[R1:[0-9]+]], r0, #32
; CHECK: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R1]]:128]
; CHECK: vst1.32 {{{d[0-9]+, d[0-9]+}}}, [r0:128]!
; CHECK: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r0:128]
; REALIGN-LABEL: test2
; REALIGN: bfc sp, #0, #6
; REALIGN: mov r[[R2:[0-9]+]], r[[R1:[0-9]+]]
; REALIGN: vld1.32 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]!
; REALIGN: vld1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
; REALIGN: add r[[R2:[0-9]+]], r[[R1]], #32
; REALIGN: vld1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
; REALIGN: add r[[R2:[0-9]+]], r[[R1]], #48
; REALIGN: vld1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
%retval = alloca <16 x float>, align 16
; REALIGN: orr r[[R2:[0-9]+]], r[[R1:[0-9]+]], #48
; REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
; REALIGN: orr r[[R2:[0-9]+]], r[[R1]], #32
; REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
; REALIGN: orr r[[R2:[0-9]+]], r[[R1]], #16
; REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
; REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R1]]:128]
; REALIGN: add r[[R1:[0-9]+]], r[[R0:0]], #48
; REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R1]]:128]
; REALIGN: add r[[R1:[0-9]+]], r[[R0]], #32
; REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R1]]:128]
; REALIGN: vst1.32 {{{d[0-9]+, d[0-9]+}}}, [r[[R0]]:128]!
; REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R0]]:128]
%retval = alloca <16 x float>, align 16
%0 = load <16 x float>, <16 x float>* @T3_retval, align 16
store <16 x float> %0, <16 x float>* %retval
%1 = load <16 x float>, <16 x float>* %retval

18
llvm/test/CodeGen/ARM/gpr-paired-spill.ll
View File

@ -16,22 +16,22 @@ define void @foo(i64* %addr) {
; an LDMIA was created with both a FrameIndex and an offset, which
; is not allowed.
; CHECK-WITH-LDRD-DAG: strd {{r[0-9]+}}, {{r[0-9]+}}, [sp, #8]
; CHECK-WITH-LDRD-DAG: strd {{r[0-9]+}}, {{r[0-9]+}}, [sp]
; CHECK-WITH-LDRD: strd {{r[0-9]+}}, {{r[0-9]+}}, [sp, #8]
; CHECK-WITH-LDRD: strd {{r[0-9]+}}, {{r[0-9]+}}, [sp]
; CHECK-WITH-LDRD-DAG: ldrd {{r[0-9]+}}, {{r[0-9]+}}, [sp, #8]
; CHECK-WITH-LDRD-DAG: ldrd {{r[0-9]+}}, {{r[0-9]+}}, [sp]
; CHECK-WITH-LDRD: ldrd {{r[0-9]+}}, {{r[0-9]+}}, [sp, #8]
; CHECK-WITH-LDRD: ldrd {{r[0-9]+}}, {{r[0-9]+}}, [sp]
; We also want to ensure the register scavenger is working (i.e. an
; offset from sp can be generated), so we need two spills.
; CHECK-WITHOUT-LDRD-DAG: add [[ADDRREG:[a-z0-9]+]], sp, #{{[0-9]+}}
; CHECK-WITHOUT-LDRD-DAG: stm [[ADDRREG]], {r{{[0-9]+}}, r{{[0-9]+}}}
; CHECK-WITHOUT-LDRD-DAG: stm sp, {r{{[0-9]+}}, r{{[0-9]+}}}
; CHECK-WITHOUT-LDRD: add [[ADDRREG:[a-z0-9]+]], sp, #{{[0-9]+}}
; CHECK-WITHOUT-LDRD: stm [[ADDRREG]], {r{{[0-9]+}}, r{{[0-9]+}}}
; CHECK-WITHOUT-LDRD: stm sp, {r{{[0-9]+}}, r{{[0-9]+}}}
; In principle LLVM may have to recalculate the offset. At the moment
; it reuses the original though.
; CHECK-WITHOUT-LDRD-DAG: ldm [[ADDRREG]], {r{{[0-9]+}}, r{{[0-9]+}}}
; CHECK-WITHOUT-LDRD-DAG: ldm sp, {r{{[0-9]+}}, r{{[0-9]+}}}
; CHECK-WITHOUT-LDRD: ldm [[ADDRREG]], {r{{[0-9]+}}, r{{[0-9]+}}}
; CHECK-WITHOUT-LDRD: ldm sp, {r{{[0-9]+}}, r{{[0-9]+}}}
store volatile i64 %val1, i64* %addr
store volatile i64 %val2, i64* %addr

2
llvm/test/CodeGen/ARM/ifcvt10.ll
View File

@ -9,6 +9,8 @@ entry:
; CHECK-LABEL: t:
; CHECK: vpop {d8}
; CHECK-NOT: vpopne
; CHECK: pop {r7, pc}
; CHECK: vpop {d8}
; CHECK: pop {r7, pc}
br i1 undef, label %if.else, label %if.then

54
llvm/test/CodeGen/ARM/illegal-bitfield-loadstore.ll
View File

@ -6,7 +6,9 @@ define void @i24_or(i24* %a) {
; LE-LABEL: i24_or:
; LE: @ BB#0:
; LE-NEXT: ldrh r1, [r0]
; LE-NEXT: ldrb r2, [r0, #2]
; LE-NEXT: orr r1, r1, #384
; LE-NEXT: strb r2, [r0, #2]
; LE-NEXT: strh r1, [r0]
; LE-NEXT: mov pc, lr
;
@ -112,9 +114,14 @@ define void @i24_insert_bit(i24* %a, i1 zeroext %bit) {
define void @i56_or(i56* %a) {
; LE-LABEL: i56_or:
; LE: @ BB#0:
; LE-NEXT: ldr r1, [r0]
; LE-NEXT: orr r1, r1, #384
; LE-NEXT: mov r2, r0
; LE-NEXT: ldr r12, [r0]
; LE-NEXT: ldrh r3, [r2, #4]!
; LE-NEXT: ldrb r1, [r2, #2]
; LE-NEXT: strb r1, [r2, #2]
; LE-NEXT: orr r1, r12, #384
; LE-NEXT: str r1, [r0]
; LE-NEXT: strh r3, [r2]
; LE-NEXT: mov pc, lr
;
; BE-LABEL: i56_or:
@ -142,29 +149,36 @@ define void @i56_or(i56* %a) {
define void @i56_and_or(i56* %a) {
; LE-LABEL: i56_and_or:
; LE: @ BB#0:
; LE-NEXT: mov r2, r0
; LE-NEXT: ldr r1, [r0]
; LE-NEXT: ldrh r12, [r2, #4]!
; LE-NEXT: orr r1, r1, #384
; LE-NEXT: ldrb r3, [r2, #2]
; LE-NEXT: bic r1, r1, #127
; LE-NEXT: strb r3, [r2, #2]
; LE-NEXT: str r1, [r0]
; LE-NEXT: strh r12, [r2]
; LE-NEXT: mov pc, lr
;
; BE-LABEL: i56_and_or:
; BE: @ BB#0:
; BE-NEXT: mov r1, r0
; BE-NEXT: .save {r11, lr}
; BE-NEXT: push {r11, lr}
; BE-NEXT: mov r2, r0
; BE-NEXT: ldr lr, [r0]
; BE-NEXT: mov r3, #128
; BE-NEXT: ldrh r2, [r1, #4]!
; BE-NEXT: strb r3, [r1, #2]
; BE-NEXT: lsl r2, r2, #8
; BE-NEXT: ldr r12, [r0]
; BE-NEXT: orr r2, r2, r12, lsl #24
; BE-NEXT: orr r2, r2, #384
; BE-NEXT: lsr r3, r2, #8
; BE-NEXT: strh r3, [r1]
; BE-NEXT: bic r1, r12, #255
; BE-NEXT: orr r1, r1, r2, lsr #24
; BE-NEXT: ldrh r12, [r2, #4]!
; BE-NEXT: strb r3, [r2, #2]
; BE-NEXT: lsl r3, r12, #8
; BE-NEXT: orr r3, r3, lr, lsl #24
; BE-NEXT: orr r3, r3, #384
; BE-NEXT: lsr r1, r3, #8
; BE-NEXT: strh r1, [r2]
; BE-NEXT: bic r1, lr, #255
; BE-NEXT: orr r1, r1, r3, lsr #24
; BE-NEXT: str r1, [r0]
; BE-NEXT: pop {r11, lr}
; BE-NEXT: mov pc, lr
%b = load i56, i56* %a, align 1
%c = and i56 %b, -128
%d = or i56 %c, 384
@ -175,10 +189,18 @@ define void @i56_and_or(i56* %a) {
define void @i56_insert_bit(i56* %a, i1 zeroext %bit) {
; LE-LABEL: i56_insert_bit:
; LE: @ BB#0:
; LE-NEXT: ldr r2, [r0]
; LE-NEXT: bic r2, r2, #8192
; LE-NEXT: .save {r11, lr}
; LE-NEXT: push {r11, lr}
; LE-NEXT: mov r3, r0
; LE-NEXT: ldr lr, [r0]
; LE-NEXT: ldrh r12, [r3, #4]!
; LE-NEXT: ldrb r2, [r3, #2]
; LE-NEXT: strb r2, [r3, #2]
; LE-NEXT: bic r2, lr, #8192
; LE-NEXT: orr r1, r2, r1, lsl #13
; LE-NEXT: str r1, [r0]
; LE-NEXT: strh r12, [r3]
; LE-NEXT: pop {r11, lr}
; LE-NEXT: mov pc, lr
;
; BE-LABEL: i56_insert_bit:

6
llvm/test/CodeGen/ARM/static-addr-hoisting.ll
View File

@ -6,9 +6,9 @@ define void @multiple_store() {
; CHECK: movs [[VAL:r[0-9]+]], #42
; CHECK: movt r[[BASE1]], #15
; CHECK-DAG: str [[VAL]], [r[[BASE1]]]
; CHECK-DAG: str [[VAL]], [r[[BASE1]], #24]
; CHECK-DAG: str.w [[VAL]], [r[[BASE1]], #42]
; CHECK: str [[VAL]], [r[[BASE1]]]
; CHECK: str [[VAL]], [r[[BASE1]], #24]
; CHECK: str.w [[VAL]], [r[[BASE1]], #42]
; CHECK: movw r[[BASE2:[0-9]+]], #20394
; CHECK: movt r[[BASE2]], #18

65
llvm/test/CodeGen/BPF/undef.ll
View File

@ -13,55 +13,50 @@
; Function Attrs: nounwind uwtable
define i32 @ebpf_filter(%struct.__sk_buff* nocapture readnone %ebpf_packet) #0 section "socket1" {
; CHECK: r2 = r10
; CHECK: r2 += -2
; CHECK: r1 = 0
; CHECK: *(u16 *)(r2 + 6) = r1
; CHECK: *(u16 *)(r2 + 4) = r1
; CHECK: *(u16 *)(r2 + 2) = r1
; CHECK: r2 = 6
; CHECK: *(u8 *)(r10 - 7) = r2
; CHECK: r2 = 5
; CHECK: *(u8 *)(r10 - 8) = r2
; CHECK: r2 = 7
; CHECK: *(u8 *)(r10 - 6) = r2
; CHECK: r2 = 8
; CHECK: *(u8 *)(r10 - 5) = r2
; CHECK: r2 = 9
; CHECK: *(u8 *)(r10 - 4) = r2
; CHECK: r2 = 10
; CHECK: *(u8 *)(r10 - 3) = r2
; CHECK: *(u16 *)(r10 + 24) = r1
; CHECK: *(u16 *)(r10 + 22) = r1
; CHECK: *(u16 *)(r10 + 20) = r1
; CHECK: *(u16 *)(r10 + 18) = r1
; CHECK: *(u16 *)(r10 + 16) = r1
; CHECK: *(u16 *)(r10 + 14) = r1
; CHECK: *(u16 *)(r10 + 12) = r1
; CHECK: *(u16 *)(r10 + 10) = r1
; CHECK: *(u16 *)(r10 + 8) = r1
; CHECK: *(u16 *)(r10 + 6) = r1
; CHECK: *(u16 *)(r10 - 2) = r1
; CHECK: *(u16 *)(r10 + 26) = r1
; CHECK: r2 = r10
; CHECK: r2 += -8
; CHECK: r1 = <MCOperand Expr:(routing)>ll
; CHECK: call bpf_map_lookup_elem
; CHECK: exit
%key = alloca %struct.routing_key_2, align 1
%1 = getelementptr inbounds %struct.routing_key_2, %struct.routing_key_2* %key, i64 0, i32 0, i64 0
; CHECK: r1 = 5
; CHECK: *(u8 *)(r10 - 8) = r1
store i8 5, i8* %1, align 1
%2 = getelementptr inbounds %struct.routing_key_2, %struct.routing_key_2* %key, i64 0, i32 0, i64 1
; CHECK: r1 = 6
; CHECK: *(u8 *)(r10 - 7) = r1
store i8 6, i8* %2, align 1
%3 = getelementptr inbounds %struct.routing_key_2, %struct.routing_key_2* %key, i64 0, i32 0, i64 2
; CHECK: r1 = 7
; CHECK: *(u8 *)(r10 - 6) = r1
store i8 7, i8* %3, align 1
%4 = getelementptr inbounds %struct.routing_key_2, %struct.routing_key_2* %key, i64 0, i32 0, i64 3
; CHECK: r1 = 8
; CHECK: *(u8 *)(r10 - 5) = r1
store i8 8, i8* %4, align 1
%5 = getelementptr inbounds %struct.routing_key_2, %struct.routing_key_2* %key, i64 0, i32 0, i64 4
; CHECK: r1 = 9
; CHECK: *(u8 *)(r10 - 4) = r1
store i8 9, i8* %5, align 1
%6 = getelementptr inbounds %struct.routing_key_2, %struct.routing_key_2* %key, i64 0, i32 0, i64 5
; CHECK: r1 = 10
; CHECK: *(u8 *)(r10 - 3) = r1
store i8 10, i8* %6, align 1
%7 = getelementptr inbounds %struct.routing_key_2, %struct.routing_key_2* %key, i64 1, i32 0, i64 0
; CHECK: r1 = r10
; CHECK: r1 += -2
; CHECK: r2 = 0
; CHECK: *(u16 *)(r1 + 6) = r2
; CHECK: *(u16 *)(r1 + 4) = r2
; CHECK: *(u16 *)(r1 + 2) = r2
; CHECK: *(u16 *)(r10 + 24) = r2
; CHECK: *(u16 *)(r10 + 22) = r2
; CHECK: *(u16 *)(r10 + 20) = r2
; CHECK: *(u16 *)(r10 + 18) = r2
; CHECK: *(u16 *)(r10 + 16) = r2
; CHECK: *(u16 *)(r10 + 14) = r2
; CHECK: *(u16 *)(r10 + 12) = r2
; CHECK: *(u16 *)(r10 + 10) = r2
; CHECK: *(u16 *)(r10 + 8) = r2
; CHECK: *(u16 *)(r10 + 6) = r2
; CHECK: *(u16 *)(r10 - 2) = r2
; CHECK: *(u16 *)(r10 + 26) = r2
call void @llvm.memset.p0i8.i64(i8* %7, i8 0, i64 30, i32 1, i1 false)
%8 = call i32 (%struct.bpf_map_def*, %struct.routing_key_2*, ...) bitcast (i32 (...)* @bpf_map_lookup_elem to i32 (%struct.bpf_map_def*, %struct.routing_key_2*, ...)*)(%struct.bpf_map_def* nonnull @routing, %struct.routing_key_2* nonnull %key) #3
ret i32 undef

2
llvm/test/CodeGen/MSP430/Inst16mm.ll
View File

@ -1,4 +1,4 @@
; RUN: llc -march=msp430 < %s | FileCheck %s
; RUN: llc -march=msp430 -combiner-alias-analysis < %s | FileCheck %s
target datalayout = "e-p:16:8:8-i8:8:8-i16:8:8-i32:8:8"
target triple = "msp430-generic-generic"
@foo = common global i16 0, align 2

24
llvm/test/CodeGen/Mips/cconv/arguments-float.ll
View File

@ -63,39 +63,39 @@ entry:
; NEW-DAG: sd $5, 16([[R2]])
; O32 has run out of argument registers and starts using the stack
; O32-DAG: lw [[R3:\$([0-9]+|gp)]], 16($sp)
; O32-DAG: lw [[R4:\$([0-9]+|gp)]], 20($sp)
; O32-DAG: lw [[R3:\$([0-9]+|gp)]], 24($sp)
; O32-DAG: lw [[R4:\$([0-9]+|gp)]], 28($sp)
; O32-DAG: sw [[R3]], 24([[R2]])
; O32-DAG: sw [[R4]], 28([[R2]])
; NEW-DAG: sd $6, 24([[R2]])
; O32-DAG: lw [[R3:\$([0-9]+|gp)]], 24($sp)
; O32-DAG: lw [[R4:\$([0-9]+|gp)]], 28($sp)
; O32-DAG: lw [[R3:\$([0-9]+|gp)]], 32($sp)
; O32-DAG: lw [[R4:\$([0-9]+|gp)]], 36($sp)
; O32-DAG: sw [[R3]], 32([[R2]])
; O32-DAG: sw [[R4]], 36([[R2]])
; NEW-DAG: sd $7, 32([[R2]])
; O32-DAG: lw [[R3:\$([0-9]+|gp)]], 32($sp)
; O32-DAG: lw [[R4:\$([0-9]+|gp)]], 36($sp)
; O32-DAG: lw [[R3:\$([0-9]+|gp)]], 40($sp)
; O32-DAG: lw [[R4:\$([0-9]+|gp)]], 44($sp)
; O32-DAG: sw [[R3]], 40([[R2]])
; O32-DAG: sw [[R4]], 44([[R2]])
; NEW-DAG: sd $8, 40([[R2]])
; O32-DAG: lw [[R3:\$([0-9]+|gp)]], 40($sp)
; O32-DAG: lw [[R4:\$([0-9]+|gp)]], 44($sp)
; O32-DAG: lw [[R3:\$([0-9]+|gp)]], 48($sp)
; O32-DAG: lw [[R4:\$([0-9]+|gp)]], 52($sp)
; O32-DAG: sw [[R3]], 48([[R2]])
; O32-DAG: sw [[R4]], 52([[R2]])
; NEW-DAG: sd $9, 48([[R2]])
; O32-DAG: lw [[R3:\$([0-9]+|gp)]], 48($sp)
; O32-DAG: lw [[R4:\$([0-9]+|gp)]], 52($sp)
; O32-DAG: lw [[R3:\$([0-9]+|gp)]], 56($sp)
; O32-DAG: lw [[R4:\$([0-9]+|gp)]], 60($sp)
; O32-DAG: sw [[R3]], 56([[R2]])
; O32-DAG: sw [[R4]], 60([[R2]])
; NEW-DAG: sd $10, 56([[R2]])
; N32/N64 have run out of registers and starts using the stack too
; O32-DAG: lw [[R3:\$[0-9]+]], 56($sp)
; O32-DAG: lw [[R4:\$[0-9]+]], 60($sp)
; O32-DAG: lw [[R3:\$[0-9]+]], 64($sp)
; O32-DAG: lw [[R4:\$[0-9]+]], 68($sp)
; O32-DAG: sw [[R3]], 64([[R2]])
; O32-DAG: sw [[R4]], 68([[R2]])
; NEW-DAG: ld [[R3:\$[0-9]+]], 0($sp)

44
llvm/test/CodeGen/Mips/cconv/arguments-varargs.ll
View File

@ -315,11 +315,12 @@ entry:
; Big-endian mode for N32/N64 must add an additional 4 to the offset due to byte
; order.
; O32-DAG: addiu [[GV:\$[0-9]+]], ${{[0-9]+}}, %lo(dwords)
; O32-DAG: lw [[ARG1:\$[0-9]+]], 0([[VA_TMP2]])
; O32-DAG: lw [[ARG1:\$[0-9]+]], 0([[VA]])
; O32-DAG: sw [[ARG1]], 8([[GV]])
; O32-DAG: addiu [[VA3:\$[0-9]+]], [[VA2]], 4
; O32-DAG: sw [[VA3]], 0([[SP]])
; O32-DAG: lw [[ARG1:\$[0-9]+]], 4([[VA_TMP2]])
; O32-DAG: lw [[VA:\$[0-9]+]], 0([[SP]])
; O32-DAG: addiu [[VA2:\$[0-9]+]], [[VA]], 4
; O32-DAG: sw [[VA2]], 0([[SP]])
; O32-DAG: lw [[ARG1:\$[0-9]+]], 0([[VA]])
; O32-DAG: sw [[ARG1]], 12([[GV]])
; N32-DAG: addiu [[GV:\$[0-9]+]], ${{[0-9]+}}, %lo(dwords)
@ -348,9 +349,10 @@ entry:
; Load the second argument from the variable portion and copy it to the global.
; O32-DAG: lw [[ARG2:\$[0-9]+]], 0([[VA]])
; O32-DAG: sw [[ARG2]], 16([[GV]])
; O32-DAG: addiu [[VA3:\$[0-9]+]], [[VA2]], 4
; O32-DAG: sw [[VA3]], 0([[SP]])
; O32-DAG: lw [[ARG2:\$[0-9]+]], 4([[VA_TMP2]])
; O32-DAG: lw [[VA:\$[0-9]+]], 0([[SP]])
; O32-DAG: addiu [[VA2:\$[0-9]+]], [[VA]], 4
; O32-DAG: sw [[VA2]], 0([[SP]])
; O32-DAG: lw [[ARG2:\$[0-9]+]], 0([[VA]])
; O32-DAG: sw [[ARG2]], 20([[GV]])
; NEW-DAG: ld [[ARG2:\$[0-9]+]], 0([[VA2]])
@ -676,11 +678,12 @@ entry:
; Big-endian mode for N32/N64 must add an additional 4 to the offset due to byte
; order.
; O32-DAG: addiu [[GV:\$[0-9]+]], ${{[0-9]+}}, %lo(dwords)
; O32-DAG: lw [[ARG1:\$[0-9]+]], 0([[VA_TMP2]])
; O32-DAG: lw [[ARG1:\$[0-9]+]], 0([[VA]])
; O32-DAG: sw [[ARG1]], 8([[GV]])
; O32-DAG: addiu [[VA3:\$[0-9]+]], [[VA2]], 4
; O32-DAG: sw [[VA3]], 0([[SP]])
; O32-DAG: lw [[ARG1:\$[0-9]+]], 4([[VA_TMP2]])
; O32-DAG: lw [[VA:\$[0-9]+]], 0([[SP]])
; O32-DAG: addiu [[VA2:\$[0-9]+]], [[VA]], 4
; O32-DAG: sw [[VA2]], 0([[SP]])
; O32-DAG: lw [[ARG1:\$[0-9]+]], 0([[VA]])
; O32-DAG: sw [[ARG1]], 12([[GV]])
; N32-DAG: addiu [[GV:\$[0-9]+]], ${{[0-9]+}}, %lo(dwords)
@ -709,9 +712,10 @@ entry:
; Load the second argument from the variable portion and copy it to the global.
; O32-DAG: lw [[ARG2:\$[0-9]+]], 0([[VA]])
; O32-DAG: sw [[ARG2]], 16([[GV]])
; O32-DAG: addiu [[VA3:\$[0-9]+]], [[VA2]], 4
; O32-DAG: lw [[VA:\$[0-9]+]], 0([[SP]])
; O32-DAG: addiu [[VA2:\$[0-9]+]], [[VA]], 4
; O32-DAG: sw [[VA2]], 0([[SP]])
; O32-DAG: lw [[ARG2:\$[0-9]+]], 4([[VA_TMP2]])
; O32-DAG: lw [[ARG2:\$[0-9]+]], 0([[VA]])
; O32-DAG: sw [[ARG2]], 20([[GV]])
; NEW-DAG: ld [[ARG2:\$[0-9]+]], 0([[VA2]])
@ -1036,9 +1040,10 @@ entry:
; O32-DAG: addiu [[GV:\$[0-9]+]], ${{[0-9]+}}, %lo(dwords)
; O32-DAG: lw [[ARG1:\$[0-9]+]], 0([[VA]])
; O32-DAG: sw [[ARG1]], 8([[GV]])
; O32-DAG: addiu [[VA3:\$[0-9]+]], [[VA2]], 4
; O32-DAG: sw [[VA3]], 0([[SP]])
; O32-DAG: lw [[ARG1:\$[0-9]+]], 4([[VA_TMP2]])
; O32-DAG: lw [[VA:\$[0-9]+]], 0([[SP]])
; O32-DAG: addiu [[VA2:\$[0-9]+]], [[VA]], 4
; O32-DAG: sw [[VA2]], 0([[SP]])
; O32-DAG: lw [[ARG1:\$[0-9]+]], 0([[VA]])
; O32-DAG: sw [[ARG1]], 12([[GV]])
; N32-DAG: addiu [[GV:\$[0-9]+]], ${{[0-9]+}}, %lo(dwords)
@ -1067,9 +1072,10 @@ entry:
; Load the second argument from the variable portion and copy it to the global.
; O32-DAG: lw [[ARG2:\$[0-9]+]], 0([[VA]])
; O32-DAG: sw [[ARG2]], 16([[GV]])
; O32-DAG: addiu [[VA3:\$[0-9]+]], [[VA2]], 4
; O32-DAG: sw [[VA3]], 0([[SP]])
; O32-DAG: lw [[ARG2:\$[0-9]+]], 4([[VA_TMP2]])
; O32-DAG: lw [[VA:\$[0-9]+]], 0([[SP]])
; O32-DAG: addiu [[VA2:\$[0-9]+]], [[VA]], 4
; O32-DAG: sw [[VA2]], 0([[SP]])
; O32-DAG: lw [[ARG2:\$[0-9]+]], 0([[VA]])
; O32-DAG: sw [[ARG2]], 20([[GV]])
; NEW-DAG: ld [[ARG2:\$[0-9]+]], 0([[VA2]])

76
llvm/test/CodeGen/Mips/fastcc.ll
View File

@ -132,19 +132,20 @@ entry:
define internal fastcc void @callee0(i32 %a0, i32 %a1, i32 %a2, i32 %a3, i32 %a4, i32 %a5, i32 %a6, i32 %a7, i32 %a8, i32 %a9, i32 %a10, i32 %a11, i32 %a12, i32 %a13, i32 %a14, i32 %a15, i32 %a16) nounwind noinline {
entry:
; CHECK: callee0
; CHECK-DAG: sw $4
; CHECK-DAG: sw $5
; CHECK-DAG: sw $7
; CHECK-DAG: sw $8
; CHECK-DAG: sw $9
; CHECK-DAG: sw $10
; CHECK-DAG: sw $11
; CHECK-DAG: sw $12
; CHECK-DAG: sw $13
; CHECK-DAG: sw $14
; CHECK-DAG: sw $15
; CHECK-DAG: sw $24
; CHECK-DAG: sw $3
; CHECK: sw $4
; CHECK: sw $5
; CHECK: sw $6
; CHECK: sw $7
; CHECK: sw $8
; CHECK: sw $9
; CHECK: sw $10
; CHECK: sw $11
; CHECK: sw $12
; CHECK: sw $13
; CHECK: sw $14
; CHECK: sw $15
; CHECK: sw $24
; CHECK: sw $3
; t6, t7 and t8 are reserved in NaCl and cannot be used for fastcc.
; CHECK-NACL-NOT: sw $14
@ -222,27 +223,27 @@ entry:
define internal fastcc void @callee1(float %a0, float %a1, float %a2, float %a3, float %a4, float %a5, float %a6, float %a7, float %a8, float %a9, float %a10, float %a11, float %a12, float %a13, float %a14, float %a15, float %a16, float %a17, float %a18, float %a19, float %a20) nounwind noinline {
entry:
; CHECK-LABEL: callee1:
; CHECK-DAG: swc1 $f0
; CHECK-DAG: swc1 $f1
; CHECK-DAG: swc1 $f2
; CHECK-DAG: swc1 $f3
; CHECK-DAG: swc1 $f4
; CHECK-DAG: swc1 $f5
; CHECK-DAG: swc1 $f6
; CHECK-DAG: swc1 $f7
; CHECK-DAG: swc1 $f8
; CHECK-DAG: swc1 $f9
; CHECK-DAG: swc1 $f10
; CHECK-DAG: swc1 $f11
; CHECK-DAG: swc1 $f12
; CHECK-DAG: swc1 $f13
; CHECK-DAG: swc1 $f14
; CHECK-DAG: swc1 $f15
; CHECK-DAG: swc1 $f16
; CHECK-DAG: swc1 $f17
; CHECK-DAG: swc1 $f18
; CHECK-DAG: swc1 $f19
; CHECK: callee1
; CHECK: swc1 $f0
; CHECK: swc1 $f1
; CHECK: swc1 $f2
; CHECK: swc1 $f3
; CHECK: swc1 $f4
; CHECK: swc1 $f5
; CHECK: swc1 $f6
; CHECK: swc1 $f7
; CHECK: swc1 $f8
; CHECK: swc1 $f9
; CHECK: swc1 $f10
; CHECK: swc1 $f11
; CHECK: swc1 $f12
; CHECK: swc1 $f13
; CHECK: swc1 $f14
; CHECK: swc1 $f15
; CHECK: swc1 $f16
; CHECK: swc1 $f17
; CHECK: swc1 $f18
; CHECK: swc1 $f19
store float %a0, float* @gf0, align 4
store float %a1, float* @gf1, align 4
@ -315,6 +316,8 @@ entry:
; NOODDSPREG-LABEL: callee2:
; NOODDSPREG: addiu $sp, $sp, -[[OFFSET:[0-9]+]]
; Check that first 10 arguments are received in even float registers
; f0, f2, ... , f18. Check that 11th argument is received on stack.
@ -330,7 +333,7 @@ entry:
; NOODDSPREG-DAG: swc1 $f16, 32($[[R0]])
; NOODDSPREG-DAG: swc1 $f18, 36($[[R0]])
; NOODDSPREG-DAG: lwc1 $[[F0:f[0-9]*[02468]]], 0($sp)
; NOODDSPREG-DAG: lwc1 $[[F0:f[0-9]*[02468]]], [[OFFSET]]($sp)
; NOODDSPREG-DAG: swc1 $[[F0]], 40($[[R0]])
store float %a0, float* getelementptr ([11 x float], [11 x float]* @fa, i32 0, i32 0), align 4
@ -394,6 +397,7 @@ entry:
; FP64-NOODDSPREG-LABEL: callee3:
; FP64-NOODDSPREG: addiu $sp, $sp, -[[OFFSET:[0-9]+]]
; Check that first 10 arguments are received in even float registers
; f0, f2, ... , f18. Check that 11th argument is received on stack.
@ -410,7 +414,7 @@ entry:
; FP64-NOODDSPREG-DAG: sdc1 $f16, 64($[[R0]])
; FP64-NOODDSPREG-DAG: sdc1 $f18, 72($[[R0]])
; FP64-NOODDSPREG-DAG: ldc1 $[[F0:f[0-9]*[02468]]], 0($sp)
; FP64-NOODDSPREG-DAG: ldc1 $[[F0:f[0-9]*[02468]]], [[OFFSET]]($sp)
; FP64-NOODDSPREG-DAG: sdc1 $[[F0]], 80($[[R0]])
store double %a0, double* getelementptr ([11 x double], [11 x double]* @da, i32 0, i32 0), align 8

126
llvm/test/CodeGen/Mips/load-store-left-right.ll
View File

@ -250,18 +250,12 @@ entry:
; MIPS64-EB: ld $[[PTR:[0-9]+]], %got_disp(struct_s0)(
; MIPS64R6: ld $[[PTR:[0-9]+]], %got_disp(struct_s0)(
; MIPS32-DAG: lbu $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS32-DAG: sb $[[R1]], 2($[[PTR]])
; MIPS32-DAG: lbu $[[R2:[0-9]+]], 1($[[PTR]])
; MIPS32-DAG: sb $[[R2]], 3($[[PTR]])
; MIPS32R6: lhu $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS32R6: sh $[[R1]], 2($[[PTR]])
; MIPS64-DAG: lbu $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS64-DAG: sb $[[R1]], 2($[[PTR]])
; MIPS64-DAG: lbu $[[R2:[0-9]+]], 1($[[PTR]])
; MIPS64-DAG: sb $[[R2]], 3($[[PTR]])
; FIXME: We should be able to do better than this on MIPS32r6/MIPS64r6 since
; we have unaligned halfword load/store available
; ALL-DAG: lbu $[[R1:[0-9]+]], 0($[[PTR]])
; ALL-DAG: sb $[[R1]], 2($[[PTR]])
; ALL-DAG: lbu $[[R1:[0-9]+]], 1($[[PTR]])
; ALL-DAG: sb $[[R1]], 3($[[PTR]])
%0 = load %struct.S0, %struct.S0* getelementptr inbounds (%struct.S0, %struct.S0* @struct_s0, i32 0), align 1
store %struct.S0 %0, %struct.S0* getelementptr inbounds (%struct.S0, %struct.S0* @struct_s0, i32 1), align 1
@ -274,54 +268,37 @@ entry:
; MIPS32-EL: lw $[[PTR:[0-9]+]], %got(struct_s1)(
; MIPS32-EB: lw $[[PTR:[0-9]+]], %got(struct_s1)(
; MIPS32-EL-DAG: lwl $[[R1:[0-9]+]], 3($[[PTR]])
; MIPS32-EL-DAG: lwr $[[R1]], 0($[[PTR]])
; MIPS32-EL-DAG: swl $[[R1]], 7($[[PTR]])
; MIPS32-EL-DAG: swr $[[R1]], 4($[[PTR]])
; MIPS32-EB-DAG: lwl $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS32-EB-DAG: lwr $[[R1]], 3($[[PTR]])
; MIPS32-EB-DAG: swl $[[R1]], 4($[[PTR]])
; MIPS32-EB-DAG: swr $[[R1]], 7($[[PTR]])
; MIPS32-NOLEFTRIGHT-DAG: lbu $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS32-NOLEFTRIGHT-DAG: sb $[[R1]], 4($[[PTR]])
; MIPS32-NOLEFTRIGHT-DAG: lbu $[[R1:[0-9]+]], 1($[[PTR]])
; MIPS32-NOLEFTRIGHT-DAG: sb $[[R1]], 5($[[PTR]])
; MIPS32-NOLEFTRIGHT-DAG: lbu $[[R1:[0-9]+]], 2($[[PTR]])
; MIPS32-NOLEFTRIGHT-DAG: sb $[[R1]], 6($[[PTR]])
; MIPS32-NOLEFTRIGHT-DAG: lbu $[[R1:[0-9]+]], 3($[[PTR]])
; MIPS32-NOLEFTRIGHT-DAG: sb $[[R1]], 7($[[PTR]])
; MIPS32-DAG: lbu $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS32-DAG: sb $[[R1]], 4($[[PTR]])
; MIPS32-DAG: lbu $[[R1:[0-9]+]], 1($[[PTR]])
; MIPS32-DAG: sb $[[R1]], 5($[[PTR]])
; MIPS32-DAG: lbu $[[R1:[0-9]+]], 2($[[PTR]])
; MIPS32-DAG: sb $[[R1]], 6($[[PTR]])
; MIPS32-DAG: lbu $[[R1:[0-9]+]], 3($[[PTR]])
; MIPS32-DAG: sb $[[R1]], 7($[[PTR]])
; MIPS32R6: lw $[[PTR:[0-9]+]], %got(struct_s1)(
; MIPS32R6-DAG: lw $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS32R6-DAG: sw $[[R1]], 4($[[PTR]])
; MIPS32R6-DAG: lhu $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS32R6-DAG: sh $[[R1]], 4($[[PTR]])
; MIPS32R6-DAG: lhu $[[R1:[0-9]+]], 2($[[PTR]])
; MIPS32R6-DAG: sh $[[R1]], 6($[[PTR]])
; MIPS64-EL: ld $[[PTR:[0-9]+]], %got_disp(struct_s1)(
; MIPS64-EB: ld $[[PTR:[0-9]+]], %got_disp(struct_s1)(
; MIPS64-EL-DAG: lwl $[[R1:[0-9]+]], 3($[[PTR]])
; MIPS64-EL-DAG: lwr $[[R1]], 0($[[PTR]])
; MIPS64-EL-DAG: swl $[[R1]], 7($[[PTR]])
; MIPS64-EL-DAG: swr $[[R1]], 4($[[PTR]])
; MIPS64-EB-DAG: lwl $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS64-EB-DAG: lwr $[[R1]], 3($[[PTR]])
; MIPS64-EB-DAG: swl $[[R1]], 4($[[PTR]])
; MIPS64-EB-DAG: swr $[[R1]], 7($[[PTR]])
; MIPS64-NOLEFTRIGHT-DAG: lbu $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS64-NOLEFTRIGHT-DAG: sb $[[R1]], 4($[[PTR]])
; MIPS64-NOLEFTRIGHT-DAG: lbu $[[R1:[0-9]+]], 1($[[PTR]])
; MIPS64-NOLEFTRIGHT-DAG: sb $[[R1]], 5($[[PTR]])
; MIPS64-NOLEFTRIGHT-DAG: lbu $[[R1:[0-9]+]], 2($[[PTR]])
; MIPS64-NOLEFTRIGHT-DAG: sb $[[R1]], 6($[[PTR]])
; MIPS64-NOLEFTRIGHT-DAG: lbu $[[R1:[0-9]+]], 3($[[PTR]])
; MIPS64-NOLEFTRIGHT-DAG: sb $[[R1]], 7($[[PTR]])
; MIPS64-DAG: lbu $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS64-DAG: sb $[[R1]], 4($[[PTR]])
; MIPS64-DAG: lbu $[[R1:[0-9]+]], 1($[[PTR]])
; MIPS64-DAG: sb $[[R1]], 5($[[PTR]])
; MIPS64-DAG: lbu $[[R1:[0-9]+]], 2($[[PTR]])
; MIPS64-DAG: sb $[[R1]], 6($[[PTR]])
; MIPS64-DAG: lbu $[[R1:[0-9]+]], 3($[[PTR]])
; MIPS64-DAG: sb $[[R1]], 7($[[PTR]])
; MIPS64R6: ld $[[PTR:[0-9]+]], %got_disp(struct_s1)(
; MIPS64R6-DAG: lw $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS64R6-DAG: sw $[[R1]], 4($[[PTR]])
; MIPS64R6-DAG: lhu $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS64R6-DAG: sh $[[R1]], 4($[[PTR]])
; MIPS64R6-DAG: lhu $[[R1:[0-9]+]], 2($[[PTR]])
; MIPS64R6-DAG: sh $[[R1]], 6($[[PTR]])
%0 = load %struct.S1, %struct.S1* getelementptr inbounds (%struct.S1, %struct.S1* @struct_s1, i32 0), align 1
store %struct.S1 %0, %struct.S1* getelementptr inbounds (%struct.S1, %struct.S1* @struct_s1, i32 1), align 1
@ -359,21 +336,30 @@ entry:
; MIPS32R6-DAG: sw $[[R1]], 12($[[PTR]])
; MIPS64-EL: ld $[[PTR:[0-9]+]], %got_disp(struct_s2)(
; MIPS64-EL-DAG: ldl $[[R1:[0-9]+]], 7($[[PTR]])
; MIPS64-EL-DAG: ldr $[[R1]], 0($[[PTR]])
; MIPS64-EL-DAG: sdl $[[R1]], 15($[[PTR]])
; MIPS64-EL-DAG: sdr $[[R1]], 8($[[PTR]])
; MIPS64-EL-DAG: lwl $[[R1:[0-9]+]], 3($[[PTR]])
; MIPS64-EL-DAG: lwr $[[R1]], 0($[[PTR]])
; MIPS64-EL-DAG: swl $[[R1]], 11($[[PTR]])
; MIPS64-EL-DAG: swr $[[R1]], 8($[[PTR]])
; MIPS64-EL-DAG: lwl $[[R1:[0-9]+]], 7($[[PTR]])
; MIPS64-EL-DAG: lwr $[[R1]], 4($[[PTR]])
; MIPS64-EL-DAG: swl $[[R1]], 15($[[PTR]])
; MIPS64-EL-DAG: swr $[[R1]], 12($[[PTR]])
; MIPS64-EB: ld $[[PTR:[0-9]+]], %got_disp(struct_s2)(
; MIPS64-EB-DAG: ldl $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS64-EB-DAG: ldr $[[R1]], 7($[[PTR]])
; MIPS64-EB-DAG: sdl $[[R1]], 8($[[PTR]])
; MIPS64-EB-DAG: sdr $[[R1]], 15($[[PTR]])
; MIPS64-EB-DAG: lwl $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS64-EB-DAG: lwr $[[R1]], 3($[[PTR]])
; MIPS64-EB-DAG: swl $[[R1]], 8($[[PTR]])
; MIPS64-EB-DAG: swr $[[R1]], 11($[[PTR]])
; MIPS64-EB-DAG: lwl $[[R1:[0-9]+]], 4($[[PTR]])
; MIPS64-EB-DAG: lwr $[[R1]], 7($[[PTR]])
; MIPS64-EB-DAG: swl $[[R1]], 12($[[PTR]])
; MIPS64-EB-DAG: swr $[[R1]], 15($[[PTR]])
; MIPS64R6: ld $[[PTR:[0-9]+]], %got_disp(struct_s2)(
; MIPS64R6-DAG: ld $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS64R6-DAG: sd $[[R1]], 8($[[PTR]])
; MIPS64R6-DAG: lw $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS64R6-DAG: sw $[[R1]], 8($[[PTR]])
; MIPS64R6-DAG: lw $[[R1:[0-9]+]], 4($[[PTR]])
; MIPS64R6-DAG: sw $[[R1]], 12($[[PTR]])
%0 = load %struct.S2, %struct.S2* getelementptr inbounds (%struct.S2, %struct.S2* @struct_s2, i32 0), align 1
store %struct.S2 %0, %struct.S2* getelementptr inbounds (%struct.S2, %struct.S2* @struct_s2, i32 1), align 1
@ -430,17 +416,17 @@ entry:
; MIPS64-EL-DAG: lwl $[[R1:[0-9]+]], 3($[[PTR]])
; MIPS64-EL-DAG: lwr $[[R1]], 0($[[PTR]])
; MIPS64-EB: ld $[[SPTR:[0-9]+]], %got_disp(arr)(
; MIPS64-EB: ld $[[SPTR:[0-9]+]], %got_disp(arr)(
; MIPS64-EB-DAG: lwl $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS64-EB-DAG: lwr $[[R1]], 3($[[PTR]])
; MIPS64-EB-DAG: dsll $[[R1]], $[[R1]], 32
; MIPS64-EB-DAG: lbu $[[R2:[0-9]+]], 5($[[PTR]])
; MIPS64-EB-DAG: lbu $[[R3:[0-9]+]], 4($[[PTR]])
; MIPS64-EB-DAG: dsll $[[T0:[0-9]+]], $[[R3]], 8
; MIPS64-EB-DAG: or $[[T1:[0-9]+]], $[[T0]], $[[R2]]
; MIPS64-EB-DAG: lbu $[[R4:[0-9]+]], 6($[[PTR]])
; MIPS64-EB-DAG: dsll $[[T1]], $[[T1]], 16
; MIPS64-EB-DAG: lwl $[[R1:[0-9]+]], 0($[[PTR]])
; MIPS64-EB-DAG: lwr $[[R1]], 3($[[PTR]])
; MIPS64-EB-DAG: dsll $[[R5:[0-9]+]], $[[R1]], 32
; MIPS64-EB-DAG: or $[[T3:[0-9]+]], $[[R5]], $[[T1]]
; MIPS64-EB-DAG: or $[[T3:[0-9]+]], $[[R1]], $[[T1]]
; MIPS64-EB-DAG: lbu $[[R4:[0-9]+]], 6($[[PTR]])
; MIPS64-EB-DAG: dsll $[[T4:[0-9]+]], $[[R4]], 8
; MIPS64-EB-DAG: or $4, $[[T3]], $[[T4]]

2
llvm/test/CodeGen/Mips/micromips-li.ll
View File

@ -13,6 +13,6 @@ entry:
ret i32 0
}
; CHECK: addiu ${{[0-9]+}}, $zero, 2148
; CHECK: li16 ${{[2-7]|16|17}}, 1
; CHECK: addiu ${{[0-9]+}}, $zero, 2148
; CHECK: ori ${{[0-9]+}}, $zero, 33332

15
llvm/test/CodeGen/Mips/mips64-f128-call.ll
View File

@ -4,8 +4,8 @@
@gld1 = external global fp128
; CHECK: foo0
; CHECK-DAG: sdc1 $f12, %lo(gld0)(${{[0-9]+}})
; CHECK-DAG: sdc1 $f13, 8(${{[0-9]+}})
; CHECK: sdc1 $f12, %lo(gld0)(${{[0-9]+}})
; CHECK: sdc1 $f13, 8(${{[0-9]+}})
define void @foo0(fp128 %a0) {
entry:
@ -14,8 +14,8 @@ entry:
}
; CHECK: foo1
; CHECK-DAG: ldc1 $f12, %lo(gld0)(${{[0-9]+}})
; CHECK-DAG: ldc1 $f13, 8(${{[0-9]+}})
; CHECK: ldc1 $f12, %lo(gld0)(${{[0-9]+}})
; CHECK: ldc1 $f13, 8(${{[0-9]+}})
define void @foo1() {
entry:
@ -26,11 +26,11 @@ entry:
declare void @foo2(fp128)
; CHECK: foo3:
; CHECK: daddiu $[[R2:[0-9]+]], $[[R1:[0-9]+]], %lo(gld0)
; CHECK: daddiu $[[R0:[0-9]+]], ${{[0-9]+}}, %hi(gld0)
; CHECK: dsll $[[R1:[0-9]+]], $[[R0]], 16
; CHECK: sdc1 $f0, %lo(gld0)($[[R1]])
; CHECK: daddiu $[[R2:[0-9]]], $[[R1]], %lo(gld0)
; CHECK: sdc1 $f2, 8($[[R2]])
; CHECK: daddiu $[[R3:[0-9]+]], ${{[0-9]+}}, %hi(gld1)
; CHECK: dsll $[[R4:[0-9]+]], $[[R3]], 16
@ -39,6 +39,7 @@ declare void @foo2(fp128)
; CHECK: ldc1 $f2, 8($[[R5]])
define fp128 @foo3() {
entry:
%call = tail call fp128 @foo4()

2
llvm/test/CodeGen/Mips/mips64-f128.ll
View File

@ -577,10 +577,10 @@ entry:
; ALL-LABEL: store_LD_LD:
; ALL: ld $[[R0:[0-9]+]], %got_disp(gld1)
; ALL: ld $[[R1:[0-9]+]], 0($[[R0]])
; ALL: ld $[[R2:[0-9]+]], 8($[[R0]])
; ALL: ld $[[R3:[0-9]+]], %got_disp(gld0)
; ALL: sd $[[R2]], 8($[[R3]])
; ALL: ld $[[R1:[0-9]+]], 0($[[R0]])
; ALL: sd $[[R1]], 0($[[R3]])
define void @store_LD_LD() {

46
llvm/test/CodeGen/Mips/mno-ldc1-sdc1.ll
View File

@ -130,12 +130,12 @@
; MM-MNO-PIC: addiu $[[R1:[0-9]+]], $[[R0]], %lo(_gp_disp)
; MM-MNO-PIC: addu $[[R2:[0-9]+]], $[[R1]], $25
; MM-MNO-PIC: lw $[[R3:[0-9]+]], %got(g0)($[[R2]])
; MM-MNO-PIC-DAG: lw16 $[[R4:[0-9]+]], 0($[[R3]])
; MM-MNO-PIC-DAG: lw16 $[[R5:[0-9]+]], 4($[[R3]])
; MM-MNO-LE-PIC-DAG: mtc1 $[[R4]], $f0
; MM-MNO-LE-PIC-DAG: mthc1 $[[R5]], $f0
; MM-MNO-BE-PIC-DAG: mtc1 $[[R5]], $f0
; MM-MNO-BE-PIC-DAG: mthc1 $[[R4]], $f0
; MM-MNO-PIC: lw16 $[[R4:[0-9]+]], 0($[[R3]])
; MM-MNO-PIC: lw16 $[[R5:[0-9]+]], 4($[[R3]])
; MM-MNO-LE-PIC: mtc1 $[[R4]], $f0
; MM-MNO-LE-PIC: mthc1 $[[R5]], $f0
; MM-MNO-BE-PIC: mtc1 $[[R5]], $f0
; MM-MNO-BE-PIC: mthc1 $[[R4]], $f0
; MM-STATIC-PIC: lui $[[R0:[0-9]+]], %hi(g0)
; MM-STATIC-PIC: ldc1 $f0, %lo(g0)($[[R0]])
@ -214,13 +214,13 @@ entry:
; MM-MNO-PIC: lui $[[R0:[0-9]+]], %hi(_gp_disp)
; MM-MNO-PIC: addiu $[[R1:[0-9]+]], $[[R0]], %lo(_gp_disp)
; MM-MNO-PIC: addu $[[R2:[0-9]+]], $[[R1]], $25
; MM-MNO-LE-PIC-DAG: mfc1 $[[R3:[0-9]+]], $f12
; MM-MNO-BE-PIC-DAG: mfhc1 $[[R3:[0-9]+]], $f12
; MM-MNO-PIC-DAG: lw $[[R4:[0-9]+]], %got(g0)($[[R2]])
; MM-MNO-PIC-DAG: sw16 $[[R3]], 0($[[R4]])
; MM-MNO-LE-PIC-DAG: mfhc1 $[[R5:[0-9]+]], $f12
; MM-MNO-BE-PIC-DAG: mfc1 $[[R5:[0-9]+]], $f12
; MM-MNO-PIC-DAG: sw16 $[[R5]], 4($[[R4]])
; MM-MNO-LE-PIC: mfc1 $[[R3:[0-9]+]], $f12
; MM-MNO-BE-PIC: mfhc1 $[[R3:[0-9]+]], $f12
; MM-MNO-PIC: lw $[[R4:[0-9]+]], %got(g0)($[[R2]])
; MM-MNO-PIC: sw16 $[[R3]], 0($[[R4]])
; MM-MNO-LE-PIC: mfhc1 $[[R5:[0-9]+]], $f12
; MM-MNO-BE-PIC: mfc1 $[[R5:[0-9]+]], $f12
; MM-MNO-PIC: sw16 $[[R5]], 4($[[R4]])
; MM-STATIC-PIC: lui $[[R0:[0-9]+]], %hi(g0)
; MM-STATIC-PIC: sdc1 $f12, %lo(g0)($[[R0]])
@ -267,8 +267,8 @@ entry:
; MM-MNO-PIC: sll16 $[[R0:[0-9]+]], $5, 3
; MM-MNO-PIC: addu16 $[[R1:[0-9]+]], $4, $[[R0]]
; MM-MNO-PIC-DAG: lw16 $[[R2:[0-9]+]], 0($[[R1]])
; MM-MNO-PIC-DAG: lw16 $[[R3:[0-9]+]], 4($[[R1]])
; MM-MNO-PIC: lw16 $[[R2:[0-9]+]], 0($[[R1]])
; MM-MNO-PIC: lw16 $[[R3:[0-9]+]], 4($[[R1]])
; MM-MNO-LE-PIC: mtc1 $[[R2]], $f0
; MM-MNO-LE-PIC: mthc1 $[[R3]], $f0
; MM-MNO-BE-PIC: mtc1 $[[R3]], $f0
@ -313,14 +313,14 @@ entry:
; MM: addu16 $[[R1:[0-9]+]], $6, $[[R0]]
; MM: sdc1 $f12, 0($[[R1]])
; MM-MNO-PIC: sll16 $[[R0:[0-9]+]], $7, 3
; MM-MNO-PIC: addu16 $[[R1:[0-9]+]], $6, $[[R0]]
; MM-MNO-LE-PIC-DAG: mfc1 $[[R2:[0-9]+]], $f12
; MM-MNO-BE-PIC-DAG: mfhc1 $[[R2:[0-9]+]], $f12
; MM-MNO-PIC-DAG: sw16 $[[R2]], 0($[[R1]])
; MM-MNO-LE-PIC-DAG: mfhc1 $[[R3:[0-9]+]], $f12
; MM-MNO-BE-PIC-DAG: mfc1 $[[R3:[0-9]+]], $f12
; MM-MNO-PIC-DAG: sw16 $[[R3]], 4($[[R1]])
; MM-MNO-PIC: sll16 $[[R0:[0-9]+]], $7, 3
; MM-MNO-PIC: addu16 $[[R1:[0-9]+]], $6, $[[R0]]
; MM-MNO-LE-PIC: mfc1 $[[R2:[0-9]+]], $f12
; MM-MNO-BE-PIC: mfhc1 $[[R2:[0-9]+]], $f12
; MM-MNO-PIC: sw16 $[[R2]], 0($[[R1]])
; MM-MNO-LE-PIC: mfhc1 $[[R3:[0-9]+]], $f12
; MM-MNO-BE-PIC: mfc1 $[[R3:[0-9]+]], $f12
; MM-MNO-PIC: sw16 $[[R3]], 4($[[R1]])
; MM-STATIC-PIC: sll16 $[[R0:[0-9]+]], $7, 3
; MM-STATIC-PIC: addu16 $[[R1:[0-9]+]], $6, $[[R0]]

14
llvm/test/CodeGen/Mips/msa/f16-llvm-ir.ll
View File

@ -234,15 +234,15 @@ entry:
; MIPS32: insert.w $w[[W0]][1], $[[R1]]
; MIPS32: insert.w $w[[W0]][3], $[[R1]]
; MIPS64-N64-DAG: ld $[[R3:[0-9]+]], %got_disp(h)
; MIPS64-N32-DAG: lw $[[R3:[0-9]+]], %got_disp(h)
; MIPS64-DAG: dmfc1 $[[R1:[0-9]+]], $f[[F2]]
; MIPS64-DAG: fill.d $w[[W0:[0-9]+]], $[[R1]]
; MIPS64-N64: ld $[[R3:[0-9]+]], %got_disp(h)
; MIPS64-N32: lw $[[R3:[0-9]+]], %got_disp(h)
; MIPS64: dmfc1 $[[R1:[0-9]+]], $f[[F2]]
; MIPS64: fill.d $w[[W0:[0-9]+]], $[[R1]]
; ALL-DAG: fexdo.w $w[[W1:[0-9]+]], $w[[W0]], $w[[W0]]
; ALL-DAG: fexdo.h $w[[W2:[0-9]+]], $w[[W1]], $w[[W1]]
; ALL: fexdo.w $w[[W1:[0-9]+]], $w[[W0]], $w[[W0]]
; ALL: fexdo.h $w[[W2:[0-9]+]], $w[[W1]], $w[[W1]]
; MIPS32-DAG: lw $[[R3:[0-9]+]], %got(h)
; MIPS32: lw $[[R3:[0-9]+]], %got(h)
; ALL: copy_u.h $[[R2:[0-9]+]], $w[[W2]]
; ALL: sh $[[R2]], 0($[[R3]])

32
llvm/test/CodeGen/Mips/msa/i5_ld_st.ll
View File

@ -336,8 +336,8 @@ entry:
; CHECK: llvm_mips_st_b_valid_range_tests:
; CHECK: ld.b
; CHECK-DAG: st.b [[R1:\$w[0-9]+]], -512(
; CHECK-DAG: st.b [[R1:\$w[0-9]+]], 511(
; CHECK: st.b [[R1:\$w[0-9]+]], -512(
; CHECK: st.b [[R1:\$w[0-9]+]], 511(
; CHECK: .size llvm_mips_st_b_valid_range_tests
;
@ -351,10 +351,10 @@ entry:
}
; CHECK: llvm_mips_st_b_invalid_range_tests:
; CHECK: addiu $2, $1, 512
; CHECK: addiu $2, $1, -513
; CHECK: ld.b
; CHECK: st.b [[R1:\$w[0-9]+]], 0(
; CHECK: addiu $1, $1, -513
; CHECK: addiu $1, $1, 512
; CHECK: st.b [[R1:\$w[0-9]+]], 0(
; CHECK: .size llvm_mips_st_b_invalid_range_tests
;
@ -404,8 +404,8 @@ entry:
; CHECK: llvm_mips_st_h_valid_range_tests:
; CHECK: ld.h
; CHECK-DAG: st.h [[R1:\$w[0-9]+]], -1024(
; CHECK-DAG: st.h [[R1:\$w[0-9]+]], 1022(
; CHECK: st.h [[R1:\$w[0-9]+]], -1024(
; CHECK: st.h [[R1:\$w[0-9]+]], 1022(
; CHECK: .size llvm_mips_st_h_valid_range_tests
;
@ -419,10 +419,10 @@ entry:
}
; CHECK: llvm_mips_st_h_invalid_range_tests:
; CHECK: addiu $2, $1, 1024
; CHECK: addiu $2, $1, -1026
; CHECK: ld.h
; CHECK: st.h [[R1:\$w[0-9]+]], 0(
; CHECK: addiu $1, $1, -1026
; CHECK: addiu $1, $1, 1024
; CHECK: st.h [[R1:\$w[0-9]+]], 0(
; CHECK: .size llvm_mips_st_h_invalid_range_tests
;
@ -472,8 +472,8 @@ entry:
; CHECK: llvm_mips_st_w_valid_range_tests:
; CHECK: ld.w
; CHECK-DAG: st.w [[R1:\$w[0-9]+]], -2048(
; CHECK-DAG: st.w [[R1:\$w[0-9]+]], 2044(
; CHECK: st.w [[R1:\$w[0-9]+]], -2048(
; CHECK: st.w [[R1:\$w[0-9]+]], 2044(
; CHECK: .size llvm_mips_st_w_valid_range_tests
;
@ -487,10 +487,10 @@ entry:
}
; CHECK: llvm_mips_st_w_invalid_range_tests:
; CHECK: addiu $2, $1, 2048
; CHECK: addiu $2, $1, -2052
; CHECK: ld.w
; CHECK: st.w [[R1:\$w[0-9]+]], 0(
; CHECK: addiu $1, $1, -2052
; CHECK: addiu $1, $1, 2048
; CHECK: st.w [[R1:\$w[0-9]+]], 0(
; CHECK: .size llvm_mips_st_w_invalid_range_tests
;
@ -540,8 +540,8 @@ entry:
; CHECK: llvm_mips_st_d_valid_range_tests:
; CHECK: ld.d
; CHECK-DAG: st.d [[R1:\$w[0-9]+]], -4096(
; CHECK-DAG: st.d [[R1:\$w[0-9]+]], 4088(
; CHECK: st.d [[R1:\$w[0-9]+]], -4096(
; CHECK: st.d [[R1:\$w[0-9]+]], 4088(
; CHECK: .size llvm_mips_st_d_valid_range_tests
;
@ -555,10 +555,10 @@ entry:
}
; CHECK: llvm_mips_st_d_invalid_range_tests:
; CHECK: addiu $2, $1, 4096
; CHECK: addiu $2, $1, -4104
; CHECK: ld.d
; CHECK: st.d [[R1:\$w[0-9]+]], 0(
; CHECK: addiu $1, $1, -4104
; CHECK: addiu $1, $1, 4096
; CHECK: st.d [[R1:\$w[0-9]+]], 0(
; CHECK: .size llvm_mips_st_d_invalid_range_tests
;

54
llvm/test/CodeGen/Mips/o32_cc_byval.ll
View File

@ -45,18 +45,20 @@ declare void @callee3(float, %struct.S3* byval, %struct.S1* byval)
define void @f2(float %f, %struct.S1* nocapture byval %s1) nounwind {
entry:
; CHECK: addiu $sp, $sp, -48
; CHECK-DAG: sw $7, 60($sp)
; CHECK-DAG: sw $6, 56($sp)
; CHECK-DAG: ldc1 $f[[F0:[0-9]+]], 72($sp)
; CHECK-DAG: lw $[[R3:[0-9]+]], 64($sp)
; CHECK-DAG: lw $[[R4:[0-9]+]], 68($sp)
; CHECK-DAG: lh $[[R1:[0-9]+]], 58($sp)
; CHECK-DAG: lb $[[R0:[0-9]+]], 56($sp)
; CHECK-DAG: sw $[[R0]], 32($sp)
; CHECK-DAG: sw $[[R1]], 28($sp)
; CHECK-DAG: sw $[[R4]], 20($sp)
; CHECK-DAG: sw $[[R3]], 16($sp)
; CHECK-DAG: sw $7, 24($sp)
; CHECK: sw $7, 60($sp)
; CHECK: sw $6, 56($sp)
; CHECK: lw $4, 80($sp)
; CHECK: ldc1 $f[[F0:[0-9]+]], 72($sp)
; CHECK: lw $[[R3:[0-9]+]], 64($sp)
; CHECK: lw $[[R4:[0-9]+]], 68($sp)
; CHECK: lw $[[R2:[0-9]+]], 60($sp)
; CHECK: lh $[[R1:[0-9]+]], 58($sp)
; CHECK: lb $[[R0:[0-9]+]], 56($sp)
; CHECK: sw $[[R0]], 32($sp)
; CHECK: sw $[[R1]], 28($sp)
; CHECK: sw $[[R2]], 24($sp)
; CHECK: sw $[[R4]], 20($sp)
; CHECK: sw $[[R3]], 16($sp)
; CHECK: mfc1 $6, $f[[F0]]
%i2 = getelementptr inbounds %struct.S1, %struct.S1* %s1, i32 0, i32 5
@ -80,11 +82,13 @@ declare void @callee4(i32, double, i64, i32, i16 signext, i8 signext, float)
define void @f3(%struct.S2* nocapture byval %s2) nounwind {
entry:
; CHECK: addiu $sp, $sp, -48
; CHECK-DAG: sw $7, 60($sp)
; CHECK-DAG: sw $6, 56($sp)
; CHECK-DAG: sw $5, 52($sp)
; CHECK-DAG: sw $4, 48($sp)
; CHECK-DAG: sw $7, 24($sp)
; CHECK: sw $7, 60($sp)
; CHECK: sw $6, 56($sp)
; CHECK: sw $5, 52($sp)
; CHECK: sw $4, 48($sp)
; CHECK: lw $4, 48($sp)
; CHECK: lw $[[R0:[0-9]+]], 60($sp)
; CHECK: sw $[[R0]], 24($sp)
%arrayidx = getelementptr inbounds %struct.S2, %struct.S2* %s2, i32 0, i32 0, i32 0
%tmp = load i32, i32* %arrayidx, align 4
@ -97,14 +101,14 @@ entry:
define void @f4(float %f, %struct.S3* nocapture byval %s3, %struct.S1* nocapture byval %s1) nounwind {
entry:
; CHECK: addiu $sp, $sp, -48
; CHECK-DAG: sw $7, 60($sp)
; CHECK-DAG: sw $6, 56($sp)
; CHECK-DAG: sw $5, 52($sp)
; CHECK-DAG: lw $[[R1:[0-9]+]], 80($sp)
; CHECK-DAG: lb $[[R0:[0-9]+]], 52($sp)
; CHECK-DAG: sw $[[R0]], 32($sp)
; CHECK-DAG: sw $[[R1]], 24($sp)
; CHECK: move $4, $7
; CHECK: sw $7, 60($sp)
; CHECK: sw $6, 56($sp)
; CHECK: sw $5, 52($sp)
; CHECK: lw $4, 60($sp)
; CHECK: lw $[[R1:[0-9]+]], 80($sp)
; CHECK: lb $[[R0:[0-9]+]], 52($sp)
; CHECK: sw $[[R0]], 32($sp)
; CHECK: sw $[[R1]], 24($sp)
%i = getelementptr inbounds %struct.S1, %struct.S1* %s1, i32 0, i32 2
%tmp = load i32, i32* %i, align 4

4
llvm/test/CodeGen/Mips/o32_cc_vararg.ll
View File

@ -29,9 +29,9 @@ entry:
; CHECK-LABEL: va1:
; CHECK: addiu $sp, $sp, -16
; CHECK: sw $5, 20($sp)
; CHECK: sw $7, 28($sp)
; CHECK: sw $6, 24($sp)
; CHECK: sw $5, 20($sp)
; CHECK: lw $2, 20($sp)
}
@ -83,8 +83,8 @@ entry:
; CHECK-LABEL: va3:
; CHECK: addiu $sp, $sp, -16
; CHECK: sw $6, 24($sp)
; CHECK: sw $7, 28($sp)
; CHECK: sw $6, 24($sp)
; CHECK: lw $2, 24($sp)
}

59
llvm/test/CodeGen/PowerPC/anon_aggr.ll
View File

@ -60,34 +60,33 @@ equal:
unequal:
ret i8* %array2_ptr
}
; CHECK-LABEL: func2:
; CHECK: cmpld {{([0-9]+,)?}}4, 6
; CHECK-DAG: std 6, 72(1)
; CHECK-DAG: std 5, 64(1)
; CHECK-DAG: std 6, -[[OFFSET1:[0-9]+]]
; CHECK: ld [[REG2:[0-9]+]], 72(1)
; CHECK: cmpld {{([0-9]+,)?}}4, [[REG2]]
; CHECK-DAG: std [[REG2]], -[[OFFSET1:[0-9]+]]
; CHECK-DAG: std 4, -[[OFFSET2:[0-9]+]]
; CHECK: ld 3, -[[OFFSET2]](1)
; CHECK: ld 3, -[[OFFSET1]](1)
; DARWIN32-LABEL: _func2
; DARWIN32-DAG: addi r[[REG8:[0-9]+]], r[[REGSP:[0-9]+]], 36
; DARWIN32-DAG: lwz r[[REG2:[0-9]+]], 44(r[[REGSP]])
; DARWIN32: _func2:
; DARWIN32: addi r[[REG1:[0-9]+]], r[[REGSP:[0-9]+]], 36
; DARWIN32: lwz r[[REG2:[0-9]+]], 44(r[[REGSP]])
; DARWIN32: mr
; DARWIN32: mr r[[REG7:[0-9]+]], r5
; DARWIN32-DAG: cmplw {{(cr[0-9]+,)?}}r5, r[[REG2]]
; DARWIN32-DAG: stw r[[REG7]], -[[OFFSET1:[0-9]+]]
; DARWIN32-DAG: stw r[[REG2]], -[[OFFSET2:[0-9]+]]
; DARWIN32-DAG: lwz r3, -[[OFFSET1]]
; DARWIN32-DAG: lwz r3, -[[OFFSET2]]
; DARWIN32: mr r[[REG3:[0-9]+]], r[[REGA:[0-9]+]]
; DARWIN32: cmplw {{(cr[0-9]+,)?}}r[[REGA]], r[[REG2]]
; DARWIN32: stw r[[REG3]], -[[OFFSET1:[0-9]+]]
; DARWIN32: stw r[[REG2]], -[[OFFSET2:[0-9]+]]
; DARWIN32: lwz r3, -[[OFFSET1]]
; DARWIN32: lwz r3, -[[OFFSET2]]
; DARWIN64: _func2:
; DARWIN64: ld r[[REG2:[0-9]+]], 72(r1)
; DARWIN64: mr
; DARWIN64: mr r[[REG3:[0-9]+]], r[[REGA:[0-9]+]]
; DARWIN64: cmpld {{(cr[0-9]+,)?}}r[[REGA]], r[[REG2]]
; DARWIN64: std r[[REG2]], -[[OFFSET2:[0-9]+]]
; DARWIN64: std r[[REG3]], -[[OFFSET1:[0-9]+]]
; DARWIN64: std r[[REG2]], -[[OFFSET2:[0-9]+]]
; DARWIN64: ld r3, -[[OFFSET1]]
; DARWIN64: ld r3, -[[OFFSET2]]
@ -107,24 +106,24 @@ unequal:
}
; CHECK-LABEL: func3:
; CHECK: cmpld {{([0-9]+,)?}}4, 6
; CHECK-DAG: std 4, -[[OFFSET2:[0-9]+]](1)
; CHECK-DAG: std 6, -[[OFFSET1:[0-9]+]](1)
; CHECK: ld [[REG3:[0-9]+]], 72(1)
; CHECK: ld [[REG4:[0-9]+]], 56(1)
; CHECK: cmpld {{([0-9]+,)?}}[[REG4]], [[REG3]]
; CHECK: std [[REG3]], -[[OFFSET1:[0-9]+]](1)
; CHECK: std [[REG4]], -[[OFFSET2:[0-9]+]](1)
; CHECK: ld 3, -[[OFFSET2]](1)
; CHECK: ld 3, -[[OFFSET1]](1)
; DARWIN32-LABEL: _func3:
; DARWIN32-DAG: stw r[[REG8:[0-9]+]], 44(r[[REGSP:[0-9]+]])
; DARWIN32-DAG: stw r[[REG5:[0-9]+]], 32(r[[REGSP]])
; DARWIN32-DAG: addi r[[REG5a:[0-9]+]], r[[REGSP:[0-9]+]], 36
; DARWIN32-DAG: addi r[[REG8a:[0-9]+]], r[[REGSP]], 24
; DARWIN32-DAG: lwz r[[REG5a:[0-9]+]], 44(r[[REGSP]])
; DARWIN32-DAG: lwz r[[REG8a:[0-9]+]], 32(r[[REGSP]])
; DARWIN32-DAG: cmplw {{(cr[0-9]+,)?}}r[[REG8a]], r[[REG5a]]
; DARWIN32-DAG: stw r[[REG5a]], -[[OFFSET1:[0-9]+]]
; DARWIN32-DAG: stw r[[REG8a]], -[[OFFSET2:[0-9]+]]
; DARWIN32-DAG: lwz r3, -[[OFFSET1:[0-9]+]]
; DARWIN32-DAG: lwz r3, -[[OFFSET2:[0-9]+]]
; DARWIN32: _func3:
; DARWIN32: addi r[[REG1:[0-9]+]], r[[REGSP:[0-9]+]], 36
; DARWIN32: addi r[[REG2:[0-9]+]], r[[REGSP]], 24
; DARWIN32: lwz r[[REG3:[0-9]+]], 44(r[[REGSP]])
; DARWIN32: lwz r[[REG4:[0-9]+]], 32(r[[REGSP]])
; DARWIN32: cmplw {{(cr[0-9]+,)?}}r[[REG4]], r[[REG3]]
; DARWIN32: stw r[[REG3]], -[[OFFSET1:[0-9]+]]
; DARWIN32: stw r[[REG4]], -[[OFFSET2:[0-9]+]]
; DARWIN32: lwz r3, -[[OFFSET2]]
; DARWIN32: lwz r3, -[[OFFSET1]]
; DARWIN64: _func3:
; DARWIN64: ld r[[REG3:[0-9]+]], 72(r1)

12
llvm/test/CodeGen/PowerPC/complex-return.ll
View File

@ -24,10 +24,10 @@ entry:
}
; CHECK-LABEL: foo:
; CHECK-DAG: lfd 1
; CHECK-DAG: lfd 2
; CHECK-DAG: lfd 3
; CHECK_DAG: lfd 4
; CHECK: lfd 1
; CHECK: lfd 2
; CHECK: lfd 3
; CHECK: lfd 4
define { float, float } @oof() nounwind {
entry:
@ -50,6 +50,6 @@ entry:
}
; CHECK-LABEL: oof:
; CHECK-DAG: lfs 2
; CHECK-DAG: lfs 1
; CHECK: lfs 2
; CHECK: lfs 1

52
llvm/test/CodeGen/PowerPC/jaggedstructs.ll
View File

@ -18,31 +18,31 @@ entry:
ret void
}
; CHECK-DAG: std 3, 160(1)
; CHECK-DAG: std 6, 184(1)
; CHECK-DAG: std 5, 176(1)
; CHECK-DAG: std 4, 168(1)
; CHECK-DAG: lbz {{[0-9]+}}, 167(1)
; CHECK-DAG: lhz {{[0-9]+}}, 165(1)
; CHECK-DAG: stb {{[0-9]+}}, 55(1)
; CHECK-DAG-DAG: sth {{[0-9]+}}, 53(1)
; CHECK-DAG: lbz {{[0-9]+}}, 175(1)
; CHECK-DAG: lwz {{[0-9]+}}, 171(1)
; CHECK-DAG: stb {{[0-9]+}}, 63(1)
; CHECK-DAG: stw {{[0-9]+}}, 59(1)
; CHECK-DAG: lhz {{[0-9]+}}, 182(1)
; CHECK-DAG: lwz {{[0-9]+}}, 178(1)
; CHECK-DAG: sth {{[0-9]+}}, 70(1)
; CHECK-DAG: stw {{[0-9]+}}, 66(1)
; CHECK-DAG: lbz {{[0-9]+}}, 191(1)
; CHECK-DAG: lhz {{[0-9]+}}, 189(1)
; CHECK-DAG: lwz {{[0-9]+}}, 185(1)
; CHECK-DAG: stb {{[0-9]+}}, 79(1)
; CHECK-DAG: sth {{[0-9]+}}, 77(1)
; CHECK-DAG: stw {{[0-9]+}}, 73(1)
; CHECK-DAG: ld 6, 72(1)
; CHECK-DAG: ld 5, 64(1)
; CHECK-DAG: ld 4, 56(1)
; CHECK-DAG: ld 3, 48(1)
; CHECK: std 6, 184(1)
; CHECK: std 5, 176(1)
; CHECK: std 4, 168(1)
; CHECK: std 3, 160(1)
; CHECK: lbz {{[0-9]+}}, 167(1)
; CHECK: lhz {{[0-9]+}}, 165(1)
; CHECK: stb {{[0-9]+}}, 55(1)
; CHECK: sth {{[0-9]+}}, 53(1)
; CHECK: lbz {{[0-9]+}}, 175(1)
; CHECK: lwz {{[0-9]+}}, 171(1)
; CHECK: stb {{[0-9]+}}, 63(1)
; CHECK: stw {{[0-9]+}}, 59(1)
; CHECK: lhz {{[0-9]+}}, 182(1)
; CHECK: lwz {{[0-9]+}}, 178(1)
; CHECK: sth {{[0-9]+}}, 70(1)
; CHECK: stw {{[0-9]+}}, 66(1)
; CHECK: lbz {{[0-9]+}}, 191(1)
; CHECK: lhz {{[0-9]+}}, 189(1)
; CHECK: lwz {{[0-9]+}}, 185(1)
; CHECK: stb {{[0-9]+}}, 79(1)
; CHECK: sth {{[0-9]+}}, 77(1)
; CHECK: stw {{[0-9]+}}, 73(1)
; CHECK: ld 6, 72(1)
; CHECK: ld 5, 64(1)
; CHECK: ld 4, 56(1)
; CHECK: ld 3, 48(1)
declare void @check(%struct.S3* byval, %struct.S5* byval, %struct.S6* byval, %struct.S7* byval)

41
llvm/test/CodeGen/PowerPC/ppc64-align-long-double.ll
View File

@ -1,6 +1,6 @@
; RUN: llc -verify-machineinstrs -mcpu=pwr7 -O0 -fast-isel=false -mattr=-vsx < %s | FileCheck %s
; RUN: llc -verify-machineinstrs -mcpu=pwr7 -O0 -fast-isel=false -mattr=+vsx < %s | FileCheck -check-prefix=CHECK-VSX %s
; RUN: llc -verify-machineinstrs -mcpu=pwr9 -O0 -fast-isel=false -mattr=+vsx < %s | FileCheck -check-prefix=CHECK-P9 %s
; RUN: llc -verify-machineinstrs -mcpu=pwr9 -O0 -fast-isel=false -mattr=+vsx < %s | FileCheck %s
; Verify internal alignment of long double in a struct. The double
; argument comes in in GPR3; GPR4 is skipped; GPRs 5 and 6 contain
@ -19,44 +19,19 @@ entry:
ret ppc_fp128 %0
}
; The additional stores are caused because we forward the value in the
; store->load->bitcast path to make a store and bitcast of the same
; value. Since the target does bitcast through memory and we no longer
; remember the address we need to do the store in a fresh local
; address.
; CHECK-DAG: std 6, 72(1)
; CHECK-DAG: std 5, 64(1)
; CHECK-DAG: std 4, 56(1)
; CHECK-DAG: std 3, 48(1)
; CHECK-DAG: std 5, -16(1)
; CHECK-DAG: std 6, -8(1)
; CHECK-DAG: lfd 1, -16(1)
; CHECK-DAG: lfd 2, -8(1)
; FIXMECHECK: lfd 1, 64(1)
; FIXMECHECK: lfd 2, 72(1)
; CHECK: lfd 1, 64(1)
; CHECK: lfd 2, 72(1)
; CHECK-VSX-DAG: std 6, 72(1)
; CHECK-VSX-DAG: std 5, 64(1)
; CHECK-VSX-DAG: std 4, 56(1)
; CHECK-VSX-DAG: std 3, 48(1)
; CHECK-VSX-DAG: std 5, -16(1)
; CHECK-VSX-DAG: std 6, -8(1)
; CHECK-VSX: addi 3, 1, -16
; CHECK-VSX: lxsdx 1, 0, 3
; CHECK-VSX: addi 3, 1, -8
; CHECK-VSX: lxsdx 2, 0, 3
; FIXME-VSX: addi 4, 1, 48
; FIXME-VSX: lxsdx 1, 4, 3
; FIXME-VSX: li 3, 24
; FIXME-VSX: lxsdx 2, 4, 3
; CHECK-P9: std 6, 72(1)
; CHECK-P9: std 5, 64(1)
; CHECK-P9: std 4, 56(1)
; CHECK-P9: std 3, 48(1)
; CHECK-P9: mtvsrd 1, 5
; CHECK-P9: mtvsrd 2, 6
; CHECK-VSX: li 3, 16
; CHECK-VSX: addi 4, 1, 48
; CHECK-VSX: lxsdx 1, 4, 3
; CHECK-VSX: li 3, 24
; CHECK-VSX: lxsdx 2, 4, 3

28
llvm/test/CodeGen/PowerPC/structsinmem.ll
View File

@ -113,13 +113,13 @@ entry:
%add13 = add nsw i32 %add11, %6
ret i32 %add13
; CHECK-DAG: lha {{[0-9]+}}, 126(1)
; CHECK-DAG: lha {{[0-9]+}}, 132(1)
; CHECK-DAG: lbz {{[0-9]+}}, 119(1)
; CHECK-DAG: lwz {{[0-9]+}}, 140(1)
; CHECK-DAG: lwz {{[0-9]+}}, 144(1)
; CHECK-DAG: lwz {{[0-9]+}}, 152(1)
; CHECK-DAG: lwz {{[0-9]+}}, 160(1)
; CHECK: lha {{[0-9]+}}, 126(1)
; CHECK: lha {{[0-9]+}}, 132(1)
; CHECK: lbz {{[0-9]+}}, 119(1)
; CHECK: lwz {{[0-9]+}}, 140(1)
; CHECK: lwz {{[0-9]+}}, 144(1)
; CHECK: lwz {{[0-9]+}}, 152(1)
; CHECK: lwz {{[0-9]+}}, 160(1)
}
define i32 @caller2() nounwind {
@ -205,11 +205,11 @@ entry:
%add13 = add nsw i32 %add11, %6
ret i32 %add13
; CHECK-DAG: lha {{[0-9]+}}, 126(1)
; CHECK-DAG: lha {{[0-9]+}}, 133(1)
; CHECK-DAG: lbz {{[0-9]+}}, 119(1)
; CHECK-DAG: lwz {{[0-9]+}}, 140(1)
; CHECK-DAG: lwz {{[0-9]+}}, 147(1)
; CHECK-DAG: lwz {{[0-9]+}}, 154(1)
; CHECK-DAG: lwz {{[0-9]+}}, 161(1)
; CHECK: lha {{[0-9]+}}, 126(1)
; CHECK: lha {{[0-9]+}}, 133(1)
; CHECK: lbz {{[0-9]+}}, 119(1)
; CHECK: lwz {{[0-9]+}}, 140(1)
; CHECK: lwz {{[0-9]+}}, 147(1)
; CHECK: lwz {{[0-9]+}}, 154(1)
; CHECK: lwz {{[0-9]+}}, 161(1)
}

60
llvm/test/CodeGen/PowerPC/structsinregs.ll
View File

@ -59,7 +59,6 @@ entry:
%call = call i32 @callee1(%struct.s1* byval %p1, %struct.s2* byval %p2, %struct.s3* byval %p3, %struct.s4* byval %p4, %struct.s5* byval %p5, %struct.s6* byval %p6, %struct.s7* byval %p7)
ret i32 %call
; CHECK-LABEL: caller1
; CHECK: ld 9, 112(31)
; CHECK: ld 8, 120(31)
; CHECK: ld 7, 128(31)
@ -98,21 +97,20 @@ entry:
%add13 = add nsw i32 %add11, %6
ret i32 %add13
; CHECK-LABEL: callee1
; CHECK-DAG: std 9, 96(1)
; CHECK-DAG: std 8, 88(1)
; CHECK-DAG: std 7, 80(1)
; CHECK-DAG: stw 6, 76(1)
; CHECK-DAG: stw 5, 68(1)
; CHECK-DAG: sth 4, 62(1)
; CHECK-DAG: stb 3, 55(1)
; CHECK-DAG: lha {{[0-9]+}}, 62(1)
; CHECK-DAG: lha {{[0-9]+}}, 68(1)
; CHECK-DAG: lbz {{[0-9]+}}, 55(1)
; CHECK-DAG: lwz {{[0-9]+}}, 76(1)
; CHECK-DAG: lwz {{[0-9]+}}, 80(1)
; CHECK-DAG: lwz {{[0-9]+}}, 88(1)
; CHECK-DAG: lwz {{[0-9]+}}, 96(1)
; CHECK: std 9, 96(1)
; CHECK: std 8, 88(1)
; CHECK: std 7, 80(1)
; CHECK: stw 6, 76(1)
; CHECK: stw 5, 68(1)
; CHECK: sth 4, 62(1)
; CHECK: stb 3, 55(1)
; CHECK: lha {{[0-9]+}}, 62(1)
; CHECK: lha {{[0-9]+}}, 68(1)
; CHECK: lbz {{[0-9]+}}, 55(1)
; CHECK: lwz {{[0-9]+}}, 76(1)
; CHECK: lwz {{[0-9]+}}, 80(1)
; CHECK: lwz {{[0-9]+}}, 88(1)
; CHECK: lwz {{[0-9]+}}, 96(1)
}
define i32 @caller2() nounwind {
@ -141,7 +139,6 @@ entry:
%call = call i32 @callee2(%struct.t1* byval %p1, %struct.t2* byval %p2, %struct.t3* byval %p3, %struct.t4* byval %p4, %struct.t5* byval %p5, %struct.t6* byval %p6, %struct.t7* byval %p7)
ret i32 %call
; CHECK-LABEL: caller2
; CHECK: stb {{[0-9]+}}, 71(1)
; CHECK: sth {{[0-9]+}}, 69(1)
; CHECK: stb {{[0-9]+}}, 87(1)
@ -187,19 +184,18 @@ entry:
%add13 = add nsw i32 %add11, %6
ret i32 %add13
; CHECK-LABEL: callee2
; CHECK-DAG: std 9, 96(1)
; CHECK-DAG: std 8, 88(1)
; CHECK-DAG: std 7, 80(1)
; CHECK-DAG: stw 6, 76(1)
; CHECK-DAG: std 5, 64(1)
; CHECK-DAG: sth 4, 62(1)
; CHECK-DAG: stb 3, 55(1)
; CHECK-DAG: lha {{[0-9]+}}, 62(1)
; CHECK-DAG: lha {{[0-9]+}}, 69(1)
; CHECK-DAG: lbz {{[0-9]+}}, 55(1)
; CHECK-DAG: lwz {{[0-9]+}}, 76(1)
; CHECK-DAG: lwz {{[0-9]+}}, 83(1)
; CHECK-DAG: lwz {{[0-9]+}}, 90(1)
; CHECK-DAG: lwz {{[0-9]+}}, 97(1)
; CHECK: std 9, 96(1)
; CHECK: std 8, 88(1)
; CHECK: std 7, 80(1)
; CHECK: stw 6, 76(1)
; CHECK: std 5, 64(1)
; CHECK: sth 4, 62(1)
; CHECK: stb 3, 55(1)
; CHECK: lha {{[0-9]+}}, 62(1)
; CHECK: lha {{[0-9]+}}, 69(1)
; CHECK: lbz {{[0-9]+}}, 55(1)
; CHECK: lwz {{[0-9]+}}, 76(1)
; CHECK: lwz {{[0-9]+}}, 83(1)
; CHECK: lwz {{[0-9]+}}, 90(1)
; CHECK: lwz {{[0-9]+}}, 97(1)
}

5
llvm/test/CodeGen/SystemZ/unaligned-01.ll
View File

@ -1,7 +1,10 @@
; Check that unaligned accesses are allowed in general. We check the
; few exceptions (like CRL) in their respective test files.
;
; RUN: llc < %s -mtriple=s390x-linux-gnu | FileCheck %s
; FIXME: -combiner-alias-analysis (the default for SystemZ) stops
; f1 from being optimized.
; RUN: llc < %s -mtriple=s390x-linux-gnu -combiner-alias-analysis=false \
; RUN: | FileCheck %s
; Check that these four byte stores become a single word store.
define void @f1(i8 *%ptr) {

2
llvm/test/CodeGen/Thumb/2010-07-15-debugOrdering.ll
View File

@ -9,8 +9,8 @@
define void @_Z19getClosestDiagonal3ii(%0* noalias sret, i32, i32) nounwind {
; CHECK: bl ___muldf3
; CHECK: beq LBB0
; CHECK: bl ___muldf3
; CHECK: beq LBB0
; CHECK: bl ___muldf3
; <label>:3
switch i32 %1, label %4 [

26
llvm/test/CodeGen/Thumb/stack-access.ll
View File

@ -74,17 +74,15 @@ define zeroext i16 @test6() {
}
; Accessing the bottom of a large array shouldn't require materializing a base
;
; CHECK: movs [[REG:r[0-9]+]], #1
; CHECK: str [[REG]], [sp, #16]
; CHECK: str [[REG]], [sp, #4]
define void @test7() {
%arr = alloca [200 x i32], align 4
; CHECK: movs [[REG:r[0-9]+]], #1
; CHECK: str [[REG]], [sp, #4]
%arrayidx = getelementptr inbounds [200 x i32], [200 x i32]* %arr, i32 0, i32 1
store i32 1, i32* %arrayidx, align 4
; CHECK: str [[REG]], [sp, #16]
%arrayidx1 = getelementptr inbounds [200 x i32], [200 x i32]* %arr, i32 0, i32 4
store i32 1, i32* %arrayidx1, align 4
@ -98,36 +96,30 @@ define void @test8() {
%arr1 = alloca [224 x i32], align 4
; CHECK: movs [[REG:r[0-9]+]], #1
; CHECK-DAG: str [[REG]], [sp]
; CHECK: str [[REG]], [sp]
%arr1idx1 = getelementptr inbounds [224 x i32], [224 x i32]* %arr1, i32 0, i32 0
store i32 1, i32* %arr1idx1, align 4
; Offset in range for sp-based store, but not for non-sp-based store
; CHECK-DAG: str [[REG]], [sp, #128]
; CHECK: str [[REG]], [sp, #128]
%arr1idx2 = getelementptr inbounds [224 x i32], [224 x i32]* %arr1, i32 0, i32 32
store i32 1, i32* %arr1idx2, align 4
; CHECK-DAG: str [[REG]], [sp, #896]
; CHECK: str [[REG]], [sp, #896]
%arr2idx1 = getelementptr inbounds [224 x i32], [224 x i32]* %arr2, i32 0, i32 0
store i32 1, i32* %arr2idx1, align 4
; %arr2 is in range, but this element of it is not
; CHECK-DAG: ldr [[RA:r[0-9]+]], .LCPI7_2
; CHECK-DAG: add [[RA]], sp
; CHECK-DAG: str [[REG]], [{{r[0-9]+}}]
; CHECK: str [[REG]], [{{r[0-9]+}}]
%arr2idx2 = getelementptr inbounds [224 x i32], [224 x i32]* %arr2, i32 0, i32 32
store i32 1, i32* %arr2idx2, align 4
; %arr3 is not in range
; CHECK-DAG: ldr [[RB:r[0-9]+]], .LCPI7_3
; CHECK-DAG: add [[RB]], sp
; CHECK-DAG: str [[REG]], [{{r[0-9]+}}]
; CHECK: str [[REG]], [{{r[0-9]+}}]
%arr3idx1 = getelementptr inbounds [224 x i32], [224 x i32]* %arr3, i32 0, i32 0
store i32 1, i32* %arr3idx1, align 4
; CHECK-DAG: ldr [[RC:r[0-9]+]], .LCPI7_4
; CHECK-DAG: add [[RC]], sp
; CHECK-DAG: str [[REG]], [{{r[0-9]+}}]
; CHECK: str [[REG]], [{{r[0-9]+}}]
%arr3idx2 = getelementptr inbounds [224 x i32], [224 x i32]* %arr3, i32 0, i32 32
store i32 1, i32* %arr3idx2, align 4

2
llvm/test/CodeGen/X86/2010-09-17-SideEffectsInChain.ll
View File

@ -1,4 +1,4 @@
; RUN: llc < %s -march=x86-64 -mcpu=core2 | FileCheck %s
; RUN: llc < %s -combiner-alias-analysis -march=x86-64 -mcpu=core2 | FileCheck %s
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
target triple = "x86_64-apple-darwin10.4"

2
llvm/test/CodeGen/X86/2012-11-28-merge-store-alias.ll
View File

@ -3,8 +3,8 @@
; CHECK: merge_stores_can
; CHECK: callq foo
; CHECK: xorps %xmm0, %xmm0
; CHECK-NEXT: movups %xmm0
; CHECK-NEXT: movl 36(%rsp), %ebp
; CHECK-NEXT: movups %xmm0
; CHECK: callq foo
; CHECK: ret
declare i32 @foo([10 x i32]* )

17
llvm/test/CodeGen/X86/MergeConsecutiveStores.ll
View File

@ -111,7 +111,8 @@ define void @merge_const_store_vec(i32 %count, %struct.B* nocapture %p) nounwind
; CHECK-LABEL: merge_nonconst_store:
; CHECK: movl $67305985
; CHECK: movb
; CHECK: movw
; CHECK: movb
; CHECK: movb
; CHECK: movb
; CHECK: ret
define void @merge_nonconst_store(i32 %count, i8 %zz, %struct.A* nocapture %p) nounwind uwtable noinline ssp {
@ -291,12 +292,16 @@ block4: ; preds = %4, %.lr.ph
ret void
}
;; On x86, even unaligned copies can be merged to vector ops.
;; On x86, even unaligned copies should be merged to vector ops.
;; TODO: however, this cannot happen at the moment, due to brokenness
;; in MergeConsecutiveStores. See UseAA FIXME in DAGCombiner.cpp
;; visitSTORE.
; CHECK-LABEL: merge_loads_no_align:
; load:
; CHECK: vmovups
; CHECK-NOT: vmovups ;; TODO
; store:
; CHECK: vmovups
; CHECK-NOT: vmovups ;; TODO
; CHECK: ret
define void @merge_loads_no_align(i32 %count, %struct.B* noalias nocapture %q, %struct.B* noalias nocapture %p) nounwind uwtable noinline ssp {
%a1 = icmp sgt i32 %count, 0
@ -578,8 +583,8 @@ define void @merge_vec_element_and_scalar_load([6 x i64]* %array) {
; CHECK-LABEL: merge_vec_element_and_scalar_load
; CHECK: movq (%rdi), %rax
; CHECK-NEXT: movq 8(%rdi), %rcx
; CHECK-NEXT: movq %rax, 32(%rdi)
; CHECK-NEXT: movq %rcx, 40(%rdi)
; CHECK-NEXT: movq 8(%rdi), %rax
; CHECK-NEXT: movq %rax, 40(%rdi)
; CHECK-NEXT: retq
}

4
llvm/test/CodeGen/X86/avx512-mask-op.ll
View File

@ -1159,6 +1159,10 @@ define void @ktest_2(<32 x float> %in, float * %base) {
; KNL-NEXT: kmovw %k0, %eax
; KNL-NEXT: vpinsrb $15, %eax, %xmm2, %xmm2
; KNL-NEXT: vinserti128 $1, %xmm3, %ymm2, %ymm2
; KNL-NEXT: vpsllw $7, %ymm2, %ymm2
; KNL-NEXT: vpand {{.*}}(%rip), %ymm2, %ymm2
; KNL-NEXT: vpxor %ymm3, %ymm3, %ymm3
; KNL-NEXT: vpcmpgtb %ymm2, %ymm3, %ymm2
; KNL-NEXT: vmovups 4(%rdi), %zmm3 {%k2} {z}
; KNL-NEXT: vmovups 68(%rdi), %zmm4 {%k1} {z}
; KNL-NEXT: vcmpltps %zmm4, %zmm1, %k0

4
llvm/test/CodeGen/X86/chain_order.ll
View File

@ -11,9 +11,9 @@ define void @cftx020(double* nocapture %a) {
; CHECK-NEXT: vmovhpd {{.*#+}} xmm1 = xmm1[0],mem[0]
; CHECK-NEXT: vaddpd %xmm1, %xmm0, %xmm0
; CHECK-NEXT: vmovupd (%rdi), %xmm1
; CHECK-NEXT: vsubpd 16(%rdi), %xmm1, %xmm1
; CHECK-NEXT: vmovupd %xmm0, (%rdi)
; CHECK-NEXT: vsubpd 16(%rdi), %xmm1, %xmm0
; CHECK-NEXT: vmovupd %xmm0, 16(%rdi)
; CHECK-NEXT: vmovupd %xmm1, 16(%rdi)
; CHECK-NEXT: retq
entry:
%0 = load double, double* %a, align 8

400
llvm/test/CodeGen/X86/clear_upper_vector_element_bits.ll
View File

@ -360,47 +360,47 @@ define <16 x i8> @_clearupper16xi8a(<16 x i8>) nounwind {
; SSE-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm0
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %r9d
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %edx
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %esi
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %r8d
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %edi
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm1
; SSE-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]
; SSE-NEXT: movd %esi, %xmm0
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm0
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm2
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %esi
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE-NEXT: movd %ecx, %xmm2
; SSE-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3],xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3],xmm2[4],xmm1[4],xmm2[5],xmm1[5],xmm2[6],xmm1[6],xmm2[7],xmm1[7]
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm0
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm3
; SSE-NEXT: movd %edx, %xmm0
; SSE-NEXT: movd %esi, %xmm1
; SSE-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]
; SSE-NEXT: movd %edi, %xmm0
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %edx
; SSE-NEXT: movd %edx, %xmm3
; SSE-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1],xmm3[2],xmm0[2],xmm3[3],xmm0[3],xmm3[4],xmm0[4],xmm3[5],xmm0[5],xmm3[6],xmm0[6],xmm3[7],xmm0[7]
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm0
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1],xmm3[2],xmm1[2],xmm3[3],xmm1[3],xmm3[4],xmm1[4],xmm3[5],xmm1[5],xmm3[6],xmm1[6],xmm3[7],xmm1[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm2[0],xmm3[1],xmm2[1],xmm3[2],xmm2[2],xmm3[3],xmm2[3],xmm3[4],xmm2[4],xmm3[5],xmm2[5],xmm3[6],xmm2[6],xmm3[7],xmm2[7]
; SSE-NEXT: movd %r9d, %xmm0
; SSE-NEXT: movd %eax, %xmm1
; SSE-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]
; SSE-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm3[0],xmm1[1],xmm3[1],xmm1[2],xmm3[2],xmm1[3],xmm3[3],xmm1[4],xmm3[4],xmm1[5],xmm3[5],xmm1[6],xmm3[6],xmm1[7],xmm3[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3],xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; SSE-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSE-NEXT: movd {{.*#+}} xmm2 = mem[0],zero,zero,zero
; SSE-NEXT: movd %r8d, %xmm0
; SSE-NEXT: movd %ecx, %xmm2
; SSE-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3],xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7]
; SSE-NEXT: movd {{.*#+}} xmm3 = mem[0],zero,zero,zero
; SSE-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3],xmm2[4],xmm1[4],xmm2[5],xmm1[5],xmm2[6],xmm1[6],xmm2[7],xmm1[7]
; SSE-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSE-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSE-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]
; SSE-NEXT: movd {{.*#+}} xmm4 = mem[0],zero,zero,zero
; SSE-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSE-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1],xmm0[2],xmm3[2],xmm0[3],xmm3[3],xmm0[4],xmm3[4],xmm0[5],xmm3[5],xmm0[6],xmm3[6],xmm0[7],xmm3[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm2
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm3
; SSE-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm2[0],xmm3[1],xmm2[1],xmm3[2],xmm2[2],xmm3[3],xmm2[3],xmm3[4],xmm2[4],xmm3[5],xmm2[5],xmm3[6],xmm2[6],xmm3[7],xmm2[7]
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm2
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm4
; SSE-NEXT: punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm2[0],xmm4[1],xmm2[1],xmm4[2],xmm2[2],xmm4[3],xmm2[3],xmm4[4],xmm2[4],xmm4[5],xmm2[5],xmm4[6],xmm2[6],xmm4[7],xmm2[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1],xmm4[2],xmm3[2],xmm4[3],xmm3[3],xmm4[4],xmm3[4],xmm4[5],xmm3[5],xmm4[6],xmm3[6],xmm4[7],xmm3[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1],xmm0[2],xmm4[2],xmm0[3],xmm4[3],xmm0[4],xmm4[4],xmm0[5],xmm4[5],xmm0[6],xmm4[6],xmm0[7],xmm4[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1],xmm0[2],xmm3[2],xmm0[3],xmm3[3],xmm0[4],xmm3[4],xmm0[5],xmm3[5],xmm0[6],xmm3[6],xmm0[7],xmm3[7]
; SSE-NEXT: pand {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
@ -487,92 +487,92 @@ define <32 x i8> @_clearupper32xi8a(<32 x i8>) nounwind {
; SSE-NEXT: movaps %xmm1, -{{[0-9]+}}(%rsp)
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm0
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %r9d
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %edx
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %esi
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %r8d
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %edi
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm1
; SSE-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]
; SSE-NEXT: movd %esi, %xmm0
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm0
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm2
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %esi
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE-NEXT: movd %ecx, %xmm2
; SSE-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3],xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3],xmm2[4],xmm1[4],xmm2[5],xmm1[5],xmm2[6],xmm1[6],xmm2[7],xmm1[7]
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm0
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm3
; SSE-NEXT: movd %edx, %xmm0
; SSE-NEXT: movd %esi, %xmm1
; SSE-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]
; SSE-NEXT: movd %edi, %xmm0
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %edx
; SSE-NEXT: movd %edx, %xmm3
; SSE-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1],xmm3[2],xmm0[2],xmm3[3],xmm0[3],xmm3[4],xmm0[4],xmm3[5],xmm0[5],xmm3[6],xmm0[6],xmm3[7],xmm0[7]
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm0
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1],xmm3[2],xmm1[2],xmm3[3],xmm1[3],xmm3[4],xmm1[4],xmm3[5],xmm1[5],xmm3[6],xmm1[6],xmm3[7],xmm1[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm2[0],xmm3[1],xmm2[1],xmm3[2],xmm2[2],xmm3[3],xmm2[3],xmm3[4],xmm2[4],xmm3[5],xmm2[5],xmm3[6],xmm2[6],xmm3[7],xmm2[7]
; SSE-NEXT: movd %r9d, %xmm0
; SSE-NEXT: movd %eax, %xmm1
; SSE-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]
; SSE-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm3[0],xmm1[1],xmm3[1],xmm1[2],xmm3[2],xmm1[3],xmm3[3],xmm1[4],xmm3[4],xmm1[5],xmm3[5],xmm1[6],xmm3[6],xmm1[7],xmm3[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3],xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; SSE-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSE-NEXT: movd {{.*#+}} xmm2 = mem[0],zero,zero,zero
; SSE-NEXT: movd %r8d, %xmm0
; SSE-NEXT: movd %ecx, %xmm2
; SSE-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3],xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7]
; SSE-NEXT: movd {{.*#+}} xmm3 = mem[0],zero,zero,zero
; SSE-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3],xmm2[4],xmm1[4],xmm2[5],xmm1[5],xmm2[6],xmm1[6],xmm2[7],xmm1[7]
; SSE-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSE-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSE-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]
; SSE-NEXT: movd {{.*#+}} xmm4 = mem[0],zero,zero,zero
; SSE-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSE-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1],xmm0[2],xmm3[2],xmm0[3],xmm3[3],xmm0[4],xmm3[4],xmm0[5],xmm3[5],xmm0[6],xmm3[6],xmm0[7],xmm3[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm2
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm3
; SSE-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm2[0],xmm3[1],xmm2[1],xmm3[2],xmm2[2],xmm3[3],xmm2[3],xmm3[4],xmm2[4],xmm3[5],xmm2[5],xmm3[6],xmm2[6],xmm3[7],xmm2[7]
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm2
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm4
; SSE-NEXT: punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm2[0],xmm4[1],xmm2[1],xmm4[2],xmm2[2],xmm4[3],xmm2[3],xmm4[4],xmm2[4],xmm4[5],xmm2[5],xmm4[6],xmm2[6],xmm4[7],xmm2[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1],xmm4[2],xmm3[2],xmm4[3],xmm3[3],xmm4[4],xmm3[4],xmm4[5],xmm3[5],xmm4[6],xmm3[6],xmm4[7],xmm3[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1],xmm0[2],xmm4[2],xmm0[3],xmm4[3],xmm0[4],xmm4[4],xmm0[5],xmm4[5],xmm0[6],xmm4[6],xmm0[7],xmm4[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1],xmm0[2],xmm3[2],xmm0[3],xmm3[3],xmm0[4],xmm3[4],xmm0[5],xmm3[5],xmm0[6],xmm3[6],xmm0[7],xmm3[7]
; SSE-NEXT: movdqa {{.*#+}} xmm2 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
; SSE-NEXT: pand %xmm2, %xmm0
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm1
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %r9d
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %edx
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %esi
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %r8d
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %edi
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm3
; SSE-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1],xmm3[2],xmm1[2],xmm3[3],xmm1[3],xmm3[4],xmm1[4],xmm3[5],xmm1[5],xmm3[6],xmm1[6],xmm3[7],xmm1[7]
; SSE-NEXT: movd %esi, %xmm1
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm1
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm4
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %esi
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE-NEXT: movd %ecx, %xmm4
; SSE-NEXT: punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1],xmm4[2],xmm1[2],xmm4[3],xmm1[3],xmm4[4],xmm1[4],xmm4[5],xmm1[5],xmm4[6],xmm1[6],xmm4[7],xmm1[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1],xmm4[2],xmm3[2],xmm4[3],xmm3[3],xmm4[4],xmm3[4],xmm4[5],xmm3[5],xmm4[6],xmm3[6],xmm4[7],xmm3[7]
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm1
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm5
; SSE-NEXT: movd %edx, %xmm1
; SSE-NEXT: movd %esi, %xmm3
; SSE-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1],xmm3[2],xmm1[2],xmm3[3],xmm1[3],xmm3[4],xmm1[4],xmm3[5],xmm1[5],xmm3[6],xmm1[6],xmm3[7],xmm1[7]
; SSE-NEXT: movd %edi, %xmm1
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %edx
; SSE-NEXT: movd %edx, %xmm5
; SSE-NEXT: punpcklbw {{.*#+}} xmm5 = xmm5[0],xmm1[0],xmm5[1],xmm1[1],xmm5[2],xmm1[2],xmm5[3],xmm1[3],xmm5[4],xmm1[4],xmm5[5],xmm1[5],xmm5[6],xmm1[6],xmm5[7],xmm1[7]
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm1
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: punpcklbw {{.*#+}} xmm5 = xmm5[0],xmm3[0],xmm5[1],xmm3[1],xmm5[2],xmm3[2],xmm5[3],xmm3[3],xmm5[4],xmm3[4],xmm5[5],xmm3[5],xmm5[6],xmm3[6],xmm5[7],xmm3[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm5 = xmm5[0],xmm4[0],xmm5[1],xmm4[1],xmm5[2],xmm4[2],xmm5[3],xmm4[3],xmm5[4],xmm4[4],xmm5[5],xmm4[5],xmm5[6],xmm4[6],xmm5[7],xmm4[7]
; SSE-NEXT: movd %r9d, %xmm1
; SSE-NEXT: movd %eax, %xmm3
; SSE-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1],xmm3[2],xmm1[2],xmm3[3],xmm1[3],xmm3[4],xmm1[4],xmm3[5],xmm1[5],xmm3[6],xmm1[6],xmm3[7],xmm1[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm5[0],xmm3[1],xmm5[1],xmm3[2],xmm5[2],xmm3[3],xmm5[3],xmm3[4],xmm5[4],xmm3[5],xmm5[5],xmm3[6],xmm5[6],xmm3[7],xmm5[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1],xmm3[2],xmm4[2],xmm3[3],xmm4[3],xmm3[4],xmm4[4],xmm3[5],xmm4[5],xmm3[6],xmm4[6],xmm3[7],xmm4[7]
; SSE-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSE-NEXT: movd {{.*#+}} xmm4 = mem[0],zero,zero,zero
; SSE-NEXT: movd %r8d, %xmm1
; SSE-NEXT: movd %ecx, %xmm4
; SSE-NEXT: punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1],xmm4[2],xmm1[2],xmm4[3],xmm1[3],xmm4[4],xmm1[4],xmm4[5],xmm1[5],xmm4[6],xmm1[6],xmm4[7],xmm1[7]
; SSE-NEXT: movd {{.*#+}} xmm5 = mem[0],zero,zero,zero
; SSE-NEXT: punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1],xmm4[2],xmm3[2],xmm4[3],xmm3[3],xmm4[4],xmm3[4],xmm4[5],xmm3[5],xmm4[6],xmm3[6],xmm4[7],xmm3[7]
; SSE-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSE-NEXT: movd {{.*#+}} xmm3 = mem[0],zero,zero,zero
; SSE-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1],xmm3[2],xmm1[2],xmm3[3],xmm1[3],xmm3[4],xmm1[4],xmm3[5],xmm1[5],xmm3[6],xmm1[6],xmm3[7],xmm1[7]
; SSE-NEXT: movd {{.*#+}} xmm6 = mem[0],zero,zero,zero
; SSE-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSE-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm5[0],xmm1[1],xmm5[1],xmm1[2],xmm5[2],xmm1[3],xmm5[3],xmm1[4],xmm5[4],xmm1[5],xmm5[5],xmm1[6],xmm5[6],xmm1[7],xmm5[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3],xmm1[4],xmm4[4],xmm1[5],xmm4[5],xmm1[6],xmm4[6],xmm1[7],xmm4[7]
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm4
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm5
; SSE-NEXT: punpcklbw {{.*#+}} xmm5 = xmm5[0],xmm4[0],xmm5[1],xmm4[1],xmm5[2],xmm4[2],xmm5[3],xmm4[3],xmm5[4],xmm4[4],xmm5[5],xmm4[5],xmm5[6],xmm4[6],xmm5[7],xmm4[7]
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm4
; SSE-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE-NEXT: movd %eax, %xmm6
; SSE-NEXT: punpcklbw {{.*#+}} xmm6 = xmm6[0],xmm4[0],xmm6[1],xmm4[1],xmm6[2],xmm4[2],xmm6[3],xmm4[3],xmm6[4],xmm4[4],xmm6[5],xmm4[5],xmm6[6],xmm4[6],xmm6[7],xmm4[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm6 = xmm6[0],xmm5[0],xmm6[1],xmm5[1],xmm6[2],xmm5[2],xmm6[3],xmm5[3],xmm6[4],xmm5[4],xmm6[5],xmm5[5],xmm6[6],xmm5[6],xmm6[7],xmm5[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm6[0],xmm1[1],xmm6[1],xmm1[2],xmm6[2],xmm1[3],xmm6[3],xmm1[4],xmm6[4],xmm1[5],xmm6[5],xmm1[6],xmm6[6],xmm1[7],xmm6[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm3[0],xmm1[1],xmm3[1],xmm1[2],xmm3[2],xmm1[3],xmm3[3],xmm1[4],xmm3[4],xmm1[5],xmm3[5],xmm1[6],xmm3[6],xmm1[7],xmm3[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3],xmm1[4],xmm4[4],xmm1[5],xmm4[5],xmm1[6],xmm4[6],xmm1[7],xmm4[7]
; SSE-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm5[0],xmm1[1],xmm5[1],xmm1[2],xmm5[2],xmm1[3],xmm5[3],xmm1[4],xmm5[4],xmm1[5],xmm5[5],xmm1[6],xmm5[6],xmm1[7],xmm5[7]
; SSE-NEXT: pand %xmm2, %xmm1
; SSE-NEXT: retq
;
@ -1180,87 +1180,91 @@ define <32 x i8> @_clearupper32xi8b(<32 x i8>) nounwind {
;
; AVX1-LABEL: _clearupper32xi8b:
; AVX1: # BB#0:
; AVX1-NEXT: pushq %rbp
; AVX1-NEXT: pushq %r15
; AVX1-NEXT: pushq %r14
; AVX1-NEXT: pushq %r13
; AVX1-NEXT: pushq %r12
; AVX1-NEXT: pushq %rbx
; AVX1-NEXT: vpextrq $1, %xmm0, -{{[0-9]+}}(%rsp)
; AVX1-NEXT: vmovq %xmm0, -{{[0-9]+}}(%rsp)
; AVX1-NEXT: movq -{{[0-9]+}}(%rsp), %r14
; AVX1-NEXT: vpextrq $1, %xmm0, %rdx
; AVX1-NEXT: movq %rdx, %r8
; AVX1-NEXT: movq %rdx, %r9
; AVX1-NEXT: movq %rdx, %r11
; AVX1-NEXT: movq %rdx, %rsi
; AVX1-NEXT: movq -{{[0-9]+}}(%rsp), %rcx
; AVX1-NEXT: movq -{{[0-9]+}}(%rsp), %rdx
; AVX1-NEXT: movq %rcx, %r8
; AVX1-NEXT: movq %rcx, %r9
; AVX1-NEXT: movq %rcx, %r10
; AVX1-NEXT: movq %rcx, %r11
; AVX1-NEXT: movq %rcx, %r14
; AVX1-NEXT: movq %rcx, %r15
; AVX1-NEXT: movq %rdx, %r12
; AVX1-NEXT: movq %rdx, %r13
; AVX1-NEXT: movq %rdx, %rdi
; AVX1-NEXT: movq %rdx, %rcx
; AVX1-NEXT: movq %rdx, %rax
; AVX1-NEXT: movq %rdx, %rsi
; AVX1-NEXT: movq %rdx, %rbx
; AVX1-NEXT: movq %rdx, %rbp
; AVX1-NEXT: andb $15, %dl
; AVX1-NEXT: movb %dl, -{{[0-9]+}}(%rsp)
; AVX1-NEXT: shrq $56, %rax
; AVX1-NEXT: andb $15, %al
; AVX1-NEXT: movb %al, -{{[0-9]+}}(%rsp)
; AVX1-NEXT: movq %r14, %r10
; AVX1-NEXT: shrq $48, %rcx
; AVX1-NEXT: movq %rcx, %rdx
; AVX1-NEXT: andb $15, %cl
; AVX1-NEXT: movb %cl, -{{[0-9]+}}(%rsp)
; AVX1-NEXT: movq %r14, %rdx
; AVX1-NEXT: shrq $40, %rdi
; AVX1-NEXT: andb $15, %dil
; AVX1-NEXT: movb %dil, -{{[0-9]+}}(%rsp)
; AVX1-NEXT: movq %r14, %rax
; AVX1-NEXT: shrq $32, %rsi
; AVX1-NEXT: andb $15, %sil
; AVX1-NEXT: movb %sil, -{{[0-9]+}}(%rsp)
; AVX1-NEXT: movq %r14, %rcx
; AVX1-NEXT: shrq $24, %r11
; AVX1-NEXT: andb $15, %r11b
; AVX1-NEXT: movb %r11b, -{{[0-9]+}}(%rsp)
; AVX1-NEXT: movq %r14, %rsi
; AVX1-NEXT: shrq $16, %r9
; AVX1-NEXT: andb $15, %r9b
; AVX1-NEXT: movb %r9b, -{{[0-9]+}}(%rsp)
; AVX1-NEXT: movq %r14, %rdi
; AVX1-NEXT: shrq $8, %r8
; AVX1-NEXT: andb $15, %r8b
; AVX1-NEXT: movb %r8b, -{{[0-9]+}}(%rsp)
; AVX1-NEXT: movq %r14, %rbx
; AVX1-NEXT: andb $15, %r14b
; AVX1-NEXT: movb %r14b, -{{[0-9]+}}(%rsp)
; AVX1-NEXT: shrq $8, %r10
; AVX1-NEXT: shrq $16, %rdx
; AVX1-NEXT: shrq $24, %rax
; AVX1-NEXT: shrq $32, %rcx
; AVX1-NEXT: shrq $40, %rsi
; AVX1-NEXT: shrq $48, %rdi
; AVX1-NEXT: shrq $56, %rbx
; AVX1-NEXT: shrq $56, %rbp
; AVX1-NEXT: andb $15, %bpl
; AVX1-NEXT: movb %bpl, -{{[0-9]+}}(%rsp)
; AVX1-NEXT: shrq $48, %rbx
; AVX1-NEXT: andb $15, %bl
; AVX1-NEXT: movb %bl, -{{[0-9]+}}(%rsp)
; AVX1-NEXT: andb $15, %dil
; AVX1-NEXT: movb %dil, -{{[0-9]+}}(%rsp)
; AVX1-NEXT: shrq $40, %rsi
; AVX1-NEXT: andb $15, %sil
; AVX1-NEXT: movb %sil, -{{[0-9]+}}(%rsp)
; AVX1-NEXT: andb $15, %cl
; AVX1-NEXT: movb %cl, -{{[0-9]+}}(%rsp)
; AVX1-NEXT: shrq $32, %rax
; AVX1-NEXT: andb $15, %al
; AVX1-NEXT: movb %al, -{{[0-9]+}}(%rsp)
; AVX1-NEXT: shrq $24, %rdi
; AVX1-NEXT: andb $15, %dil
; AVX1-NEXT: movb %dil, -{{[0-9]+}}(%rsp)
; AVX1-NEXT: shrq $16, %r13
; AVX1-NEXT: andb $15, %r13b
; AVX1-NEXT: movb %r13b, -{{[0-9]+}}(%rsp)
; AVX1-NEXT: shrq $8, %r12
; AVX1-NEXT: andb $15, %r12b
; AVX1-NEXT: movb %r12b, -{{[0-9]+}}(%rsp)
; AVX1-NEXT: shrq $8, %r8
; AVX1-NEXT: shrq $16, %r9
; AVX1-NEXT: shrq $24, %r10
; AVX1-NEXT: shrq $32, %r11
; AVX1-NEXT: shrq $40, %r14
; AVX1-NEXT: shrq $48, %r15
; AVX1-NEXT: shrq $56, %rdx
; AVX1-NEXT: andb $15, %dl
; AVX1-NEXT: movb %dl, -{{[0-9]+}}(%rsp)
; AVX1-NEXT: andb $15, %r15b
; AVX1-NEXT: movb %r15b, -{{[0-9]+}}(%rsp)
; AVX1-NEXT: andb $15, %r14b
; AVX1-NEXT: movb %r14b, -{{[0-9]+}}(%rsp)
; AVX1-NEXT: andb $15, %r11b
; AVX1-NEXT: movb %r11b, -{{[0-9]+}}(%rsp)
; AVX1-NEXT: andb $15, %r10b
; AVX1-NEXT: movb %r10b, -{{[0-9]+}}(%rsp)
; AVX1-NEXT: andb $15, %r9b
; AVX1-NEXT: movb %r9b, -{{[0-9]+}}(%rsp)
; AVX1-NEXT: andb $15, %r8b
; AVX1-NEXT: movb %r8b, -{{[0-9]+}}(%rsp)
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vmovq %xmm0, %rax
; AVX1-NEXT: movq %rax, %r8
; AVX1-NEXT: movq %rax, %rcx
; AVX1-NEXT: movq %rax, %rdx
; AVX1-NEXT: movq %rax, %rsi
; AVX1-NEXT: movq %rax, %rdi
; AVX1-NEXT: movl %eax, %ebp
; AVX1-NEXT: movl %eax, %ebx
; AVX1-NEXT: movl %eax, %ecx
; AVX1-NEXT: vmovd %eax, %xmm1
; AVX1-NEXT: shrl $8, %eax
; AVX1-NEXT: vpinsrb $1, %eax, %xmm1, %xmm1
; AVX1-NEXT: shrl $16, %ecx
; AVX1-NEXT: vpinsrb $2, %ecx, %xmm1, %xmm1
; AVX1-NEXT: shrl $24, %ebx
; AVX1-NEXT: vpinsrb $3, %ebx, %xmm1, %xmm1
; AVX1-NEXT: shrl $16, %ebx
; AVX1-NEXT: vpinsrb $2, %ebx, %xmm1, %xmm1
; AVX1-NEXT: shrl $24, %ebp
; AVX1-NEXT: vpinsrb $3, %ebp, %xmm1, %xmm1
; AVX1-NEXT: shrq $32, %rdi
; AVX1-NEXT: vpinsrb $4, %edi, %xmm1, %xmm1
; AVX1-NEXT: shrq $40, %rsi
@ -1270,8 +1274,8 @@ define <32 x i8> @_clearupper32xi8b(<32 x i8>) nounwind {
; AVX1-NEXT: shrq $48, %rdx
; AVX1-NEXT: vpinsrb $6, %edx, %xmm1, %xmm1
; AVX1-NEXT: vpextrq $1, %xmm0, %rax
; AVX1-NEXT: shrq $56, %r8
; AVX1-NEXT: vpinsrb $7, %r8d, %xmm1, %xmm0
; AVX1-NEXT: shrq $56, %rcx
; AVX1-NEXT: vpinsrb $7, %ecx, %xmm1, %xmm0
; AVX1-NEXT: movl %eax, %ecx
; AVX1-NEXT: shrl $8, %ecx
; AVX1-NEXT: vpinsrb $8, %eax, %xmm0, %xmm0
@ -1339,92 +1343,100 @@ define <32 x i8> @_clearupper32xi8b(<32 x i8>) nounwind {
; AVX1-NEXT: vpinsrb $15, %eax, %xmm1, %xmm1
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: popq %rbx
; AVX1-NEXT: popq %r12
; AVX1-NEXT: popq %r13
; AVX1-NEXT: popq %r14
; AVX1-NEXT: popq %r15
; AVX1-NEXT: popq %rbp
; AVX1-NEXT: retq
;
; AVX2-LABEL: _clearupper32xi8b:
; AVX2: # BB#0:
; AVX2-NEXT: pushq %rbp
; AVX2-NEXT: pushq %r15
; AVX2-NEXT: pushq %r14
; AVX2-NEXT: pushq %r13
; AVX2-NEXT: pushq %r12
; AVX2-NEXT: pushq %rbx
; AVX2-NEXT: vpextrq $1, %xmm0, -{{[0-9]+}}(%rsp)
; AVX2-NEXT: vmovq %xmm0, -{{[0-9]+}}(%rsp)
; AVX2-NEXT: movq -{{[0-9]+}}(%rsp), %r14
; AVX2-NEXT: vpextrq $1, %xmm0, %rdx
; AVX2-NEXT: movq %rdx, %r8
; AVX2-NEXT: movq %rdx, %r9
; AVX2-NEXT: movq %rdx, %r11
; AVX2-NEXT: movq %rdx, %rsi
; AVX2-NEXT: movq -{{[0-9]+}}(%rsp), %rcx
; AVX2-NEXT: movq -{{[0-9]+}}(%rsp), %rdx
; AVX2-NEXT: movq %rcx, %r8
; AVX2-NEXT: movq %rcx, %r9
; AVX2-NEXT: movq %rcx, %r10
; AVX2-NEXT: movq %rcx, %r11
; AVX2-NEXT: movq %rcx, %r14
; AVX2-NEXT: movq %rcx, %r15
; AVX2-NEXT: movq %rdx, %r12
; AVX2-NEXT: movq %rdx, %r13
; AVX2-NEXT: movq %rdx, %rdi
; AVX2-NEXT: movq %rdx, %rcx
; AVX2-NEXT: movq %rdx, %rax
; AVX2-NEXT: movq %rdx, %rsi
; AVX2-NEXT: movq %rdx, %rbx
; AVX2-NEXT: movq %rdx, %rbp
; AVX2-NEXT: andb $15, %dl
; AVX2-NEXT: movb %dl, -{{[0-9]+}}(%rsp)
; AVX2-NEXT: shrq $56, %rax
; AVX2-NEXT: andb $15, %al
; AVX2-NEXT: movb %al, -{{[0-9]+}}(%rsp)
; AVX2-NEXT: movq %r14, %r10
; AVX2-NEXT: shrq $48, %rcx
; AVX2-NEXT: movq %rcx, %rdx
; AVX2-NEXT: andb $15, %cl
; AVX2-NEXT: movb %cl, -{{[0-9]+}}(%rsp)
; AVX2-NEXT: movq %r14, %rdx
; AVX2-NEXT: shrq $40, %rdi
; AVX2-NEXT: andb $15, %dil
; AVX2-NEXT: movb %dil, -{{[0-9]+}}(%rsp)
; AVX2-NEXT: movq %r14, %rax
; AVX2-NEXT: shrq $32, %rsi
; AVX2-NEXT: andb $15, %sil
; AVX2-NEXT: movb %sil, -{{[0-9]+}}(%rsp)
; AVX2-NEXT: movq %r14, %rcx
; AVX2-NEXT: shrq $24, %r11
; AVX2-NEXT: andb $15, %r11b
; AVX2-NEXT: movb %r11b, -{{[0-9]+}}(%rsp)
; AVX2-NEXT: movq %r14, %rsi
; AVX2-NEXT: shrq $16, %r9
; AVX2-NEXT: andb $15, %r9b
; AVX2-NEXT: movb %r9b, -{{[0-9]+}}(%rsp)
; AVX2-NEXT: movq %r14, %rdi
; AVX2-NEXT: shrq $8, %r8
; AVX2-NEXT: andb $15, %r8b
; AVX2-NEXT: movb %r8b, -{{[0-9]+}}(%rsp)
; AVX2-NEXT: movq %r14, %rbx
; AVX2-NEXT: andb $15, %r14b
; AVX2-NEXT: movb %r14b, -{{[0-9]+}}(%rsp)
; AVX2-NEXT: shrq $8, %r10
; AVX2-NEXT: shrq $16, %rdx
; AVX2-NEXT: shrq $24, %rax
; AVX2-NEXT: shrq $32, %rcx
; AVX2-NEXT: shrq $40, %rsi
; AVX2-NEXT: shrq $48, %rdi
; AVX2-NEXT: shrq $56, %rbx
; AVX2-NEXT: shrq $56, %rbp
; AVX2-NEXT: andb $15, %bpl
; AVX2-NEXT: movb %bpl, -{{[0-9]+}}(%rsp)
; AVX2-NEXT: shrq $48, %rbx
; AVX2-NEXT: andb $15, %bl
; AVX2-NEXT: movb %bl, -{{[0-9]+}}(%rsp)
; AVX2-NEXT: andb $15, %dil
; AVX2-NEXT: movb %dil, -{{[0-9]+}}(%rsp)
; AVX2-NEXT: shrq $40, %rsi
; AVX2-NEXT: andb $15, %sil
; AVX2-NEXT: movb %sil, -{{[0-9]+}}(%rsp)
; AVX2-NEXT: andb $15, %cl
; AVX2-NEXT: movb %cl, -{{[0-9]+}}(%rsp)
; AVX2-NEXT: shrq $32, %rax
; AVX2-NEXT: andb $15, %al
; AVX2-NEXT: movb %al, -{{[0-9]+}}(%rsp)
; AVX2-NEXT: shrq $24, %rdi
; AVX2-NEXT: andb $15, %dil
; AVX2-NEXT: movb %dil, -{{[0-9]+}}(%rsp)
; AVX2-NEXT: shrq $16, %r13
; AVX2-NEXT: andb $15, %r13b
; AVX2-NEXT: movb %r13b, -{{[0-9]+}}(%rsp)
; AVX2-NEXT: shrq $8, %r12
; AVX2-NEXT: andb $15, %r12b
; AVX2-NEXT: movb %r12b, -{{[0-9]+}}(%rsp)
; AVX2-NEXT: shrq $8, %r8
; AVX2-NEXT: shrq $16, %r9
; AVX2-NEXT: shrq $24, %r10
; AVX2-NEXT: shrq $32, %r11
; AVX2-NEXT: shrq $40, %r14
; AVX2-NEXT: shrq $48, %r15
; AVX2-NEXT: shrq $56, %rdx
; AVX2-NEXT: andb $15, %dl
; AVX2-NEXT: movb %dl, -{{[0-9]+}}(%rsp)
; AVX2-NEXT: andb $15, %r15b
; AVX2-NEXT: movb %r15b, -{{[0-9]+}}(%rsp)
; AVX2-NEXT: andb $15, %r14b
; AVX2-NEXT: movb %r14b, -{{[0-9]+}}(%rsp)
; AVX2-NEXT: andb $15, %r11b
; AVX2-NEXT: movb %r11b, -{{[0-9]+}}(%rsp)
; AVX2-NEXT: andb $15, %r10b
; AVX2-NEXT: movb %r10b, -{{[0-9]+}}(%rsp)
; AVX2-NEXT: andb $15, %r9b
; AVX2-NEXT: movb %r9b, -{{[0-9]+}}(%rsp)
; AVX2-NEXT: andb $15, %r8b
; AVX2-NEXT: movb %r8b, -{{[0-9]+}}(%rsp)
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm0
; AVX2-NEXT: vmovq %xmm0, %rax
; AVX2-NEXT: movq %rax, %r8
; AVX2-NEXT: movq %rax, %rcx
; AVX2-NEXT: movq %rax, %rdx
; AVX2-NEXT: movq %rax, %rsi
; AVX2-NEXT: movq %rax, %rdi
; AVX2-NEXT: movl %eax, %ebp
; AVX2-NEXT: movl %eax, %ebx
; AVX2-NEXT: movl %eax, %ecx
; AVX2-NEXT: vmovd %eax, %xmm1
; AVX2-NEXT: shrl $8, %eax
; AVX2-NEXT: vpinsrb $1, %eax, %xmm1, %xmm1
; AVX2-NEXT: shrl $16, %ecx
; AVX2-NEXT: vpinsrb $2, %ecx, %xmm1, %xmm1
; AVX2-NEXT: shrl $24, %ebx
; AVX2-NEXT: vpinsrb $3, %ebx, %xmm1, %xmm1
; AVX2-NEXT: shrl $16, %ebx
; AVX2-NEXT: vpinsrb $2, %ebx, %xmm1, %xmm1
; AVX2-NEXT: shrl $24, %ebp
; AVX2-NEXT: vpinsrb $3, %ebp, %xmm1, %xmm1
; AVX2-NEXT: shrq $32, %rdi
; AVX2-NEXT: vpinsrb $4, %edi, %xmm1, %xmm1
; AVX2-NEXT: shrq $40, %rsi
@ -1434,8 +1446,8 @@ define <32 x i8> @_clearupper32xi8b(<32 x i8>) nounwind {
; AVX2-NEXT: shrq $48, %rdx
; AVX2-NEXT: vpinsrb $6, %edx, %xmm1, %xmm1
; AVX2-NEXT: vpextrq $1, %xmm0, %rax
; AVX2-NEXT: shrq $56, %r8
; AVX2-NEXT: vpinsrb $7, %r8d, %xmm1, %xmm0
; AVX2-NEXT: shrq $56, %rcx
; AVX2-NEXT: vpinsrb $7, %ecx, %xmm1, %xmm0
; AVX2-NEXT: movl %eax, %ecx
; AVX2-NEXT: shrl $8, %ecx
; AVX2-NEXT: vpinsrb $8, %eax, %xmm0, %xmm0
@ -1503,7 +1515,11 @@ define <32 x i8> @_clearupper32xi8b(<32 x i8>) nounwind {
; AVX2-NEXT: vpinsrb $15, %eax, %xmm1, %xmm1
; AVX2-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX2-NEXT: popq %rbx
; AVX2-NEXT: popq %r12
; AVX2-NEXT: popq %r13
; AVX2-NEXT: popq %r14
; AVX2-NEXT: popq %r15
; AVX2-NEXT: popq %rbp
; AVX2-NEXT: retq
%x4 = bitcast <32 x i8> %0 to <64 x i4>
%r0 = insertelement <64 x i4> %x4, i4 zeroinitializer, i32 1

20
llvm/test/CodeGen/X86/combiner-aa-0.ll Normal file
View File

@ -0,0 +1,20 @@
; RUN: llc < %s -march=x86-64 -combiner-global-alias-analysis -combiner-alias-analysis
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128"
%struct.Hash_Key = type { [4 x i32], i32 }
@g_flipV_hashkey = external global %struct.Hash_Key, align 16 ; <%struct.Hash_Key*> [#uses=1]
define void @foo() nounwind {
%t0 = load i32, i32* undef, align 16 ; <i32> [#uses=1]
%t1 = load i32, i32* null, align 4 ; <i32> [#uses=1]
%t2 = srem i32 %t0, 32 ; <i32> [#uses=1]
%t3 = shl i32 1, %t2 ; <i32> [#uses=1]
%t4 = xor i32 %t3, %t1 ; <i32> [#uses=1]
store i32 %t4, i32* null, align 4
%t5 = getelementptr %struct.Hash_Key, %struct.Hash_Key* @g_flipV_hashkey, i64 0, i32 0, i64 0 ; <i32*> [#uses=2]
%t6 = load i32, i32* %t5, align 4 ; <i32> [#uses=1]
%t7 = shl i32 1, undef ; <i32> [#uses=1]
%t8 = xor i32 %t7, %t6 ; <i32> [#uses=1]
store i32 %t8, i32* %t5, align 4
unreachable
}

23
llvm/test/CodeGen/X86/combiner-aa-1.ll Normal file
View File

@ -0,0 +1,23 @@
; RUN: llc < %s --combiner-alias-analysis --combiner-global-alias-analysis
; PR4880
target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:32:32"
target triple = "i386-pc-linux-gnu"
%struct.alst_node = type { %struct.node }
%struct.arg_node = type { %struct.node, i8*, %struct.alst_node* }
%struct.arglst_node = type { %struct.alst_node, %struct.arg_node*, %struct.arglst_node* }
%struct.lam_node = type { %struct.alst_node, %struct.arg_node*, %struct.alst_node* }
%struct.node = type { i32 (...)**, %struct.node* }
define i32 @._ZN8lam_node18resolve_name_clashEP8arg_nodeP9alst_node._ZNK8lam_nodeeqERK8exp_node._ZN11arglst_nodeD0Ev(%struct.lam_node* %this.this, %struct.arg_node* %outer_arg, %struct.alst_node* %env.cmp, %struct.arglst_node* %this, i32 %functionID) {
comb_entry:
%.SV59 = alloca %struct.node* ; <%struct.node**> [#uses=1]
%0 = load i32 (...)**, i32 (...)*** null, align 4 ; <i32 (...)**> [#uses=1]
%1 = getelementptr inbounds i32 (...)*, i32 (...)** %0, i32 3 ; <i32 (...)**> [#uses=1]
%2 = load i32 (...)*, i32 (...)** %1, align 4 ; <i32 (...)*> [#uses=1]
store %struct.node* undef, %struct.node** %.SV59
%3 = bitcast i32 (...)* %2 to i32 (%struct.node*)* ; <i32 (%struct.node*)*> [#uses=1]
%4 = tail call i32 %3(%struct.node* undef) ; <i32> [#uses=0]
unreachable
}

17
llvm/test/CodeGen/X86/copy-eflags.ll
View File

@ -9,22 +9,19 @@ target triple = "i686-unknown-linux-gnu"
@.str = private unnamed_addr constant [4 x i8] c"%d\0A\00", align 1
; CHECK-LABEL: func:
; This tests whether eax is properly saved/restored around the
; lahf/sahf instruction sequences. We make mem op volatile to prevent
; their reordering to avoid spills.
; This tests whether eax is properly saved/restored around the lahf/sahf
; instruction sequences.
define i32 @func() {
entry:
%bval = load i8, i8* @b
%inc = add i8 %bval, 1
store volatile i8 %inc, i8* @b
%cval = load volatile i32, i32* @c
store i8 %inc, i8* @b
%cval = load i32, i32* @c
%inc1 = add nsw i32 %cval, 1
store volatile i32 %inc1, i32* @c
%aval = load volatile i8, i8* @a
store i32 %inc1, i32* @c
%aval = load i8, i8* @a
%inc2 = add i8 %aval, 1
store volatile i8 %inc2, i8* @a
store i8 %inc2, i8* @a
; Copy flags produced by the incb of %inc1 to a register, need to save+restore
; eax around it. The flags will be reused by %tobool.
; CHECK: pushl %eax

12
llvm/test/CodeGen/X86/dag-merge-fast-accesses.ll
View File

@ -51,11 +51,19 @@ define void @merge_vec_element_store(<4 x double> %v, double* %ptr) {
}
;; TODO: FAST *should* be:
;; movups (%rdi), %xmm0
;; movups %xmm0, 40(%rdi)
;; ..but is not currently. See the UseAA FIXME in DAGCombiner.cpp
;; visitSTORE.
define void @merge_vec_load_and_stores(i64 *%ptr) {
; FAST-LABEL: merge_vec_load_and_stores:
; FAST: # BB#0:
; FAST-NEXT: movups (%rdi), %xmm0
; FAST-NEXT: movups %xmm0, 40(%rdi)
; FAST-NEXT: movq (%rdi), %rax
; FAST-NEXT: movq 8(%rdi), %rcx
; FAST-NEXT: movq %rax, 40(%rdi)
; FAST-NEXT: movq %rcx, 48(%rdi)
; FAST-NEXT: retq
;
; SLOW-LABEL: merge_vec_load_and_stores:

6
llvm/test/CodeGen/X86/dont-trunc-store-double-to-float.ll
View File

@ -1,9 +1,9 @@
; RUN: llc -march=x86 < %s | FileCheck %s
; CHECK-LABEL: @bar
; CHECK-DAG: movl $1074339512,
; CHECK-DAG: movl $1374389535,
; CHECK-DAG: movl $1078523331,
; CHECK: movl $1074339512,
; CHECK: movl $1374389535,
; CHECK: movl $1078523331,
define void @bar() unnamed_addr {
entry-block:
%a = alloca double

15
llvm/test/CodeGen/X86/extractelement-legalization-store-ordering.ll
View File

@ -16,20 +16,19 @@ target datalayout = "e-m:o-p:32:32-f64:32:64-f80:128-n8:16:32-S128"
; CHECK-NEXT: movl 20(%esp), %edx
; CHECK-NEXT: paddd (%edx), %xmm0
; CHECK-NEXT: movdqa %xmm0, (%edx)
; CHECK-NEXT: movl (%edx), %esi
; CHECK-NEXT: movl 4(%edx), %edi
; CHECK-NEXT: shll $4, %ecx
; CHECK-NEXT: movl 8(%edx), %ebx
; CHECK-NEXT: movl 12(%edx), %edx
; CHECK-NEXT: movl (%edx), %esi
; CHECK-NEXT: movl 12(%edx), %edi
; CHECK-NEXT: movl 8(%edx), %ebx
; CHECK-NEXT: movl 4(%edx), %edx
; CHECK-NEXT: shll $4, %ecx
; CHECK-NEXT: movl %esi, 12(%eax,%ecx)
; CHECK-NEXT: movl %edi, (%eax,%ecx)
; CHECK-NEXT: movl %edx, (%eax,%ecx)
; CHECK-NEXT: movl %ebx, 8(%eax,%ecx)
; CHECK-NEXT: movl %edx, 4(%eax,%ecx)
; CHECK-NEXT: movl %edi, 4(%eax,%ecx)
; CHECK-NEXT: popl %esi
; CHECK-NEXT: popl %edi
; CHECK-NEXT: popl %ebx
; CHECK-NEXT: retl
define void @test_extractelement_legalization_storereuse(<4 x i32> %a, i32* nocapture %x, i32* nocapture readonly %y, i32 %i) #0 {
entry:
%0 = bitcast i32* %y to <4 x i32>*

350
llvm/test/CodeGen/X86/i256-add.ll
View File

@ -6,122 +6,45 @@ define void @add(i256* %p, i256* %q) nounwind {
; X32-LABEL: add:
; X32: # BB#0:
; X32-NEXT: pushl %ebp
; X32-NEXT: movl %esp, %ebp
; X32-NEXT: pushl %ebx
; X32-NEXT: pushl %edi
; X32-NEXT: pushl %esi
; X32-NEXT: subl $28, %esp
; X32-NEXT: movl 12(%ebp), %edi
; X32-NEXT: movl 8(%ebp), %eax
; X32-NEXT: movl (%eax), %ecx
; X32-NEXT: movl (%edi), %edx
; X32-NEXT: movl %ecx, %esi
; X32-NEXT: addl %edx, %esi
; X32-NEXT: movl 4(%edi), %ebx
; X32-NEXT: movl 4(%eax), %esi
; X32-NEXT: adcl %ebx, %esi
; X32-NEXT: pushl %eax
; X32-NEXT: seto %al
; X32-NEXT: lahf
; X32-NEXT: movl %eax, %esi
; X32-NEXT: popl %eax
; X32-NEXT: movl %esi, -32(%ebp) # 4-byte Spill
; X32-NEXT: movl %esi, -16(%ebp) # 4-byte Spill
; X32-NEXT: addl %edx, %ecx
; X32-NEXT: movl %ecx, -40(%ebp) # 4-byte Spill
; X32-NEXT: movl 8(%edi), %edx
; X32-NEXT: movl %edx, -28(%ebp) # 4-byte Spill
; X32-NEXT: movl 28(%edi), %ecx
; X32-NEXT: movl %ecx, -36(%ebp) # 4-byte Spill
; X32-NEXT: movl 24(%edi), %ecx
; X32-NEXT: movl %ecx, -20(%ebp) # 4-byte Spill
; X32-NEXT: movl 20(%edi), %ecx
; X32-NEXT: movl 16(%edi), %esi
; X32-NEXT: movl %esi, -24(%ebp) # 4-byte Spill
; X32-NEXT: movl 12(%edi), %edi
; X32-NEXT: adcl %ebx, 4(%eax)
; X32-NEXT: movl 8(%eax), %ebx
; X32-NEXT: movl -16(%ebp), %esi # 4-byte Reload
; X32-NEXT: pushl %eax
; X32-NEXT: movl %esi, %eax
; X32-NEXT: addb $127, %al
; X32-NEXT: sahf
; X32-NEXT: popl %eax
; X32-NEXT: adcl %edx, %ebx
; X32-NEXT: pushl %eax
; X32-NEXT: seto %al
; X32-NEXT: lahf
; X32-NEXT: movl %eax, %ebx
; X32-NEXT: popl %eax
; X32-NEXT: adcl %edi, 12(%eax)
; X32-NEXT: pushl %eax
; X32-NEXT: movl %ebx, %eax
; X32-NEXT: addb $127, %al
; X32-NEXT: sahf
; X32-NEXT: popl %eax
; X32-NEXT: adcl 12(%eax), %edi
; X32-NEXT: pushl %eax
; X32-NEXT: seto %al
; X32-NEXT: lahf
; X32-NEXT: movl %eax, %esi
; X32-NEXT: popl %eax
; X32-NEXT: movl 16(%eax), %ebx
; X32-NEXT: movl -24(%ebp), %edx # 4-byte Reload
; X32-NEXT: adcl %edx, %ebx
; X32-NEXT: pushl %eax
; X32-NEXT: seto %al
; X32-NEXT: lahf
; X32-NEXT: movl %eax, %ebx
; X32-NEXT: popl %eax
; X32-NEXT: pushl %eax
; X32-NEXT: seto %al
; X32-NEXT: lahf
; X32-NEXT: movl %eax, %edi
; X32-NEXT: popl %eax
; X32-NEXT: pushl %eax
; X32-NEXT: movl %esi, %eax
; X32-NEXT: addb $127, %al
; X32-NEXT: sahf
; X32-NEXT: popl %eax
; X32-NEXT: adcl %edx, 16(%eax)
; X32-NEXT: movl -32(%ebp), %edx # 4-byte Reload
; X32-NEXT: pushl %eax
; X32-NEXT: movl %edx, %eax
; X32-NEXT: addb $127, %al
; X32-NEXT: sahf
; X32-NEXT: popl %eax
; X32-NEXT: movl -28(%ebp), %edx # 4-byte Reload
; X32-NEXT: adcl %edx, 8(%eax)
; X32-NEXT: pushl %eax
; X32-NEXT: movl %edi, %eax
; X32-NEXT: addb $127, %al
; X32-NEXT: sahf
; X32-NEXT: popl %eax
; X32-NEXT: adcl %ecx, 20(%eax)
; X32-NEXT: pushl %eax
; X32-NEXT: movl %ebx, %eax
; X32-NEXT: addb $127, %al
; X32-NEXT: sahf
; X32-NEXT: popl %eax
; X32-NEXT: adcl 20(%eax), %ecx
; X32-NEXT: pushl %eax
; X32-NEXT: seto %al
; X32-NEXT: lahf
; X32-NEXT: movl %eax, %ecx
; X32-NEXT: popl %eax
; X32-NEXT: movl -20(%ebp), %edx # 4-byte Reload
; X32-NEXT: adcl %edx, 24(%eax)
; X32-NEXT: pushl %eax
; X32-NEXT: movl %ecx, %eax
; X32-NEXT: addb $127, %al
; X32-NEXT: sahf
; X32-NEXT: popl %eax
; X32-NEXT: adcl 24(%eax), %edx
; X32-NEXT: movl -36(%ebp), %ecx # 4-byte Reload
; X32-NEXT: adcl %ecx, 28(%eax)
; X32-NEXT: movl -40(%ebp), %ecx # 4-byte Reload
; X32-NEXT: movl %ecx, (%eax)
; X32-NEXT: addl $28, %esp
; X32-NEXT: subl $16, %esp
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X32-NEXT: movl 8(%ecx), %edi
; X32-NEXT: movl (%ecx), %esi
; X32-NEXT: movl 4(%ecx), %ebx
; X32-NEXT: movl 28(%eax), %edx
; X32-NEXT: movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
; X32-NEXT: movl 24(%eax), %edx
; X32-NEXT: addl (%eax), %esi
; X32-NEXT: movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
; X32-NEXT: adcl 4(%eax), %ebx
; X32-NEXT: movl %ebx, (%esp) # 4-byte Spill
; X32-NEXT: adcl 8(%eax), %edi
; X32-NEXT: movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
; X32-NEXT: movl 20(%eax), %ebx
; X32-NEXT: movl 12(%eax), %esi
; X32-NEXT: movl 16(%eax), %edi
; X32-NEXT: adcl 12(%ecx), %esi
; X32-NEXT: adcl 16(%ecx), %edi
; X32-NEXT: adcl 20(%ecx), %ebx
; X32-NEXT: adcl 24(%ecx), %edx
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
; X32-NEXT: adcl 28(%ecx), %eax
; X32-NEXT: movl {{[0-9]+}}(%esp), %ebp # 4-byte Reload
; X32-NEXT: movl %ebp, 8(%ecx)
; X32-NEXT: movl (%esp), %ebp # 4-byte Reload
; X32-NEXT: movl %ebp, 4(%ecx)
; X32-NEXT: movl {{[0-9]+}}(%esp), %ebp # 4-byte Reload
; X32-NEXT: movl %ebp, (%ecx)
; X32-NEXT: movl %esi, 12(%ecx)
; X32-NEXT: movl %edi, 16(%ecx)
; X32-NEXT: movl %ebx, 20(%ecx)
; X32-NEXT: movl %edx, 24(%ecx)
; X32-NEXT: movl %eax, 28(%ecx)
; X32-NEXT: addl $16, %esp
; X32-NEXT: popl %esi
; X32-NEXT: popl %edi
; X32-NEXT: popl %ebx
@ -130,28 +53,18 @@ define void @add(i256* %p, i256* %q) nounwind {
;
; X64-LABEL: add:
; X64: # BB#0:
; X64-NEXT: pushq %rbp
; X64-NEXT: movq %rsp, %rbp
; X64-NEXT: movq (%rdi), %rdx
; X64-NEXT: movq 8(%rdi), %r9
; X64-NEXT: movq 24(%rsi), %r8
; X64-NEXT: movq 8(%rsi), %r10
; X64-NEXT: movq 16(%rsi), %rcx
; X64-NEXT: movq (%rsi), %rsi
; X64-NEXT: movq %rdx, %rax
; X64-NEXT: addq %rsi, %rax
; X64-NEXT: adcq %r10, 8(%rdi)
; X64-NEXT: addq %rsi, %rdx
; X64-NEXT: adcq %r10, %r9
; X64-NEXT: pushfq
; X64-NEXT: popq %rax
; X64-NEXT: adcq %rcx, 16(%rdi)
; X64-NEXT: pushq %rax
; X64-NEXT: popfq
; X64-NEXT: adcq 16(%rdi), %rcx
; X64-NEXT: adcq %r8, 24(%rdi)
; X64-NEXT: movq %rdx, (%rdi)
; X64-NEXT: popq %rbp
; X64-NEXT: movq 16(%rdi), %rax
; X64-NEXT: movq (%rdi), %r8
; X64-NEXT: movq 8(%rdi), %rdx
; X64-NEXT: movq 24(%rsi), %rcx
; X64-NEXT: addq (%rsi), %r8
; X64-NEXT: adcq 8(%rsi), %rdx
; X64-NEXT: adcq 16(%rsi), %rax
; X64-NEXT: adcq 24(%rdi), %rcx
; X64-NEXT: movq %rax, 16(%rdi)
; X64-NEXT: movq %rdx, 8(%rdi)
; X64-NEXT: movq %r8, (%rdi)
; X64-NEXT: movq %rcx, 24(%rdi)
; X64-NEXT: retq
%a = load i256, i256* %p
%b = load i256, i256* %q
@ -163,110 +76,43 @@ define void @sub(i256* %p, i256* %q) nounwind {
; X32-LABEL: sub:
; X32: # BB#0:
; X32-NEXT: pushl %ebp
; X32-NEXT: movl %esp, %ebp
; X32-NEXT: pushl %ebx
; X32-NEXT: pushl %edi
; X32-NEXT: pushl %esi
; X32-NEXT: subl $24, %esp
; X32-NEXT: movl 12(%ebp), %edi
; X32-NEXT: movl 8(%ebp), %ecx
; X32-NEXT: movl (%ecx), %eax
; X32-NEXT: movl 4(%ecx), %edx
; X32-NEXT: movl (%edi), %esi
; X32-NEXT: cmpl %esi, %eax
; X32-NEXT: movl 4(%edi), %ebx
; X32-NEXT: sbbl %ebx, %edx
; X32-NEXT: pushl %eax
; X32-NEXT: seto %al
; X32-NEXT: lahf
; X32-NEXT: movl %eax, %edx
; X32-NEXT: popl %eax
; X32-NEXT: movl %edx, -24(%ebp) # 4-byte Spill
; X32-NEXT: movl %edx, -16(%ebp) # 4-byte Spill
; X32-NEXT: subl %esi, %eax
; X32-NEXT: movl %eax, -36(%ebp) # 4-byte Spill
; X32-NEXT: movl 8(%edi), %esi
; X32-NEXT: movl 28(%edi), %eax
; X32-NEXT: movl %eax, -32(%ebp) # 4-byte Spill
; X32-NEXT: movl 24(%edi), %eax
; X32-NEXT: movl %eax, -28(%ebp) # 4-byte Spill
; X32-NEXT: movl 20(%edi), %eax
; X32-NEXT: movl %eax, -20(%ebp) # 4-byte Spill
; X32-NEXT: movl 16(%edi), %edx
; X32-NEXT: movl 12(%edi), %edi
; X32-NEXT: sbbl %ebx, 4(%ecx)
; X32-NEXT: movl 8(%ecx), %ebx
; X32-NEXT: movl -16(%ebp), %eax # 4-byte Reload
; X32-NEXT: movl %eax, %eax
; X32-NEXT: addb $127, %al
; X32-NEXT: sahf
; X32-NEXT: sbbl %esi, %ebx
; X32-NEXT: pushl %eax
; X32-NEXT: seto %al
; X32-NEXT: lahf
; X32-NEXT: movl %eax, %ebx
; X32-NEXT: popl %eax
; X32-NEXT: sbbl %edi, 12(%ecx)
; X32-NEXT: movl 12(%ecx), %eax
; X32-NEXT: pushl %eax
; X32-NEXT: movl %ebx, %eax
; X32-NEXT: addb $127, %al
; X32-NEXT: sahf
; X32-NEXT: popl %eax
; X32-NEXT: sbbl %edi, %eax
; X32-NEXT: seto %al
; X32-NEXT: lahf
; X32-NEXT: movl %eax, %eax
; X32-NEXT: movl 16(%ecx), %edi
; X32-NEXT: sbbl %edx, %edi
; X32-NEXT: pushl %eax
; X32-NEXT: seto %al
; X32-NEXT: lahf
; X32-NEXT: movl %eax, %edi
; X32-NEXT: popl %eax
; X32-NEXT: pushl %eax
; X32-NEXT: seto %al
; X32-NEXT: lahf
; X32-NEXT: movl %eax, %ebx
; X32-NEXT: popl %eax
; X32-NEXT: movl %eax, %eax
; X32-NEXT: addb $127, %al
; X32-NEXT: sahf
; X32-NEXT: sbbl %edx, 16(%ecx)
; X32-NEXT: movl -24(%ebp), %eax # 4-byte Reload
; X32-NEXT: movl %eax, %eax
; X32-NEXT: addb $127, %al
; X32-NEXT: sahf
; X32-NEXT: sbbl %esi, 8(%ecx)
; X32-NEXT: pushl %eax
; X32-NEXT: movl %ebx, %eax
; X32-NEXT: addb $127, %al
; X32-NEXT: sahf
; X32-NEXT: popl %eax
; X32-NEXT: movl -20(%ebp), %edx # 4-byte Reload
; X32-NEXT: sbbl %edx, 20(%ecx)
; X32-NEXT: movl 20(%ecx), %eax
; X32-NEXT: pushl %eax
; X32-NEXT: movl %edi, %eax
; X32-NEXT: addb $127, %al
; X32-NEXT: sahf
; X32-NEXT: popl %eax
; X32-NEXT: sbbl %edx, %eax
; X32-NEXT: seto %al
; X32-NEXT: lahf
; X32-NEXT: movl %eax, %eax
; X32-NEXT: movl -28(%ebp), %esi # 4-byte Reload
; X32-NEXT: sbbl %esi, 24(%ecx)
; X32-NEXT: subl $12, %esp
; X32-NEXT: movl {{[0-9]+}}(%esp), %ebx
; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X32-NEXT: movl 16(%ecx), %eax
; X32-NEXT: movl 12(%ecx), %edx
; X32-NEXT: movl 8(%ecx), %edi
; X32-NEXT: movl (%ecx), %esi
; X32-NEXT: movl 4(%ecx), %ebp
; X32-NEXT: subl (%ebx), %esi
; X32-NEXT: movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
; X32-NEXT: sbbl 4(%ebx), %ebp
; X32-NEXT: sbbl 8(%ebx), %edi
; X32-NEXT: sbbl 12(%ebx), %edx
; X32-NEXT: movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
; X32-NEXT: sbbl 16(%ebx), %eax
; X32-NEXT: movl %eax, (%esp) # 4-byte Spill
; X32-NEXT: movl 20(%ecx), %esi
; X32-NEXT: sbbl 20(%ebx), %esi
; X32-NEXT: movl 24(%ecx), %edx
; X32-NEXT: movl %eax, %eax
; X32-NEXT: addb $127, %al
; X32-NEXT: sahf
; X32-NEXT: sbbl %esi, %edx
; X32-NEXT: movl -32(%ebp), %eax # 4-byte Reload
; X32-NEXT: sbbl %eax, 28(%ecx)
; X32-NEXT: movl -36(%ebp), %eax # 4-byte Reload
; X32-NEXT: movl %eax, (%ecx)
; X32-NEXT: addl $24, %esp
; X32-NEXT: sbbl 24(%ebx), %edx
; X32-NEXT: movl 28(%ecx), %eax
; X32-NEXT: sbbl 28(%ebx), %eax
; X32-NEXT: movl %edi, 8(%ecx)
; X32-NEXT: movl %ebp, 4(%ecx)
; X32-NEXT: movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
; X32-NEXT: movl %edi, (%ecx)
; X32-NEXT: movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
; X32-NEXT: movl %edi, 12(%ecx)
; X32-NEXT: movl (%esp), %edi # 4-byte Reload
; X32-NEXT: movl %edi, 16(%ecx)
; X32-NEXT: movl %esi, 20(%ecx)
; X32-NEXT: movl %edx, 24(%ecx)
; X32-NEXT: movl %eax, 28(%ecx)
; X32-NEXT: addl $12, %esp
; X32-NEXT: popl %esi
; X32-NEXT: popl %edi
; X32-NEXT: popl %ebx
@ -275,28 +121,18 @@ define void @sub(i256* %p, i256* %q) nounwind {
;
; X64-LABEL: sub:
; X64: # BB#0:
; X64-NEXT: pushq %rbp
; X64-NEXT: movq %rsp, %rbp
; X64-NEXT: movq (%rdi), %rax
; X64-NEXT: movq 8(%rdi), %rcx
; X64-NEXT: movq 24(%rsi), %r8
; X64-NEXT: movq 8(%rsi), %rdx
; X64-NEXT: movq 16(%rsi), %r9
; X64-NEXT: movq (%rsi), %rsi
; X64-NEXT: cmpq %rsi, %rax
; X64-NEXT: sbbq %rdx, 8(%rdi)
; X64-NEXT: subq %rsi, %rax
; X64-NEXT: sbbq %rdx, %rcx
; X64-NEXT: pushfq
; X64-NEXT: popq %rcx
; X64-NEXT: sbbq %r9, 16(%rdi)
; X64-NEXT: movq 16(%rdi), %rdx
; X64-NEXT: pushq %rcx
; X64-NEXT: popfq
; X64-NEXT: sbbq %r9, %rdx
; X64-NEXT: sbbq %r8, 24(%rdi)
; X64-NEXT: movq %rax, (%rdi)
; X64-NEXT: popq %rbp
; X64-NEXT: movq 24(%rdi), %r8
; X64-NEXT: movq 16(%rdi), %rcx
; X64-NEXT: movq (%rdi), %rdx
; X64-NEXT: movq 8(%rdi), %rax
; X64-NEXT: subq (%rsi), %rdx
; X64-NEXT: sbbq 8(%rsi), %rax
; X64-NEXT: sbbq 16(%rsi), %rcx
; X64-NEXT: sbbq 24(%rsi), %r8
; X64-NEXT: movq %rcx, 16(%rdi)
; X64-NEXT: movq %rax, 8(%rdi)
; X64-NEXT: movq %rdx, (%rdi)
; X64-NEXT: movq %r8, 24(%rdi)
; X64-NEXT: retq
%a = load i256, i256* %p
%b = load i256, i256* %q

5
llvm/test/CodeGen/X86/i386-shrink-wrapping.ll
View File

@ -55,7 +55,8 @@ target triple = "i386-apple-macosx10.5"
;
; CHECK-NEXT: L_e$non_lazy_ptr, [[E:%[a-z]+]]
; CHECK-NEXT: movb [[D]], ([[E]])
; CHECK-NEXT: movsbl ([[E]]), [[CONV:%[a-z]+]]
; CHECK-NEXT: L_f$non_lazy_ptr, [[F:%[a-z]+]]
; CHECK-NEXT: movsbl ([[F]]), [[CONV:%[a-z]+]]
; CHECK-NEXT: movl $6, [[CONV:%[a-z]+]]
; The eflags is used in the next instruction.
; If that instruction disappear, we are not exercising the bug
@ -95,7 +96,7 @@ for.end: ; preds = %for.cond.preheader
%.b3 = load i1, i1* @d, align 1
%tmp2 = select i1 %.b3, i8 0, i8 6
store i8 %tmp2, i8* @e, align 1
%tmp3 = load i8, i8* @e, align 1
%tmp3 = load i8, i8* @f, align 1
%conv = sext i8 %tmp3 to i32
%add = add nsw i32 %conv, 1
%rem = srem i32 %tmp1, %add

38
llvm/test/CodeGen/X86/illegal-bitfield-loadstore.ll
View File

@ -65,20 +65,20 @@ define void @i24_insert_bit(i24* %a, i1 zeroext %bit) {
define void @i56_or(i56* %a) {
; CHECK-LABEL: i56_or:
; CHECK: # BB#0:
; CHECK-NEXT: movzwl 4(%rdi), %eax
; CHECK-NEXT: movzbl 6(%rdi), %ecx
; CHECK-NEXT: movl (%rdi), %edx
; CHECK-NEXT: movb %cl, 6(%rdi)
; CHECK-NEXT: # kill: %ECX<def> %ECX<kill> %RCX<kill> %RCX<def>
; CHECK-NEXT: shll $16, %ecx
; CHECK-NEXT: orl %eax, %ecx
; CHECK-NEXT: shlq $32, %rcx
; CHECK-NEXT: orq %rcx, %rdx
; CHECK-NEXT: orq $384, %rdx # imm = 0x180
; CHECK-NEXT: movl %edx, (%rdi)
; CHECK-NEXT: shrq $32, %rdx
; CHECK-NEXT: movw %dx, 4(%rdi)
; CHECK-NEXT: retq
; ACHECK-NEXT: movzwl 4(%rdi), %eax
; ACHECK-NEXT: movzbl 6(%rdi), %ecx
; ACHECK-NEXT: movl (%rdi), %edx
; ACHECK-NEXT: movb %cl, 6(%rdi)
; ACHECK-NEXT: # kill: %ECX<def> %ECX<kill> %RCX<kill> %RCX<def>
; ACHECK-NEXT: shll $16, %ecx
; ACHECK-NEXT: orl %eax, %ecx
; ACHECK-NEXT: shlq $32, %rcx
; ACHECK-NEXT: orq %rcx, %rdx
; ACHECK-NEXT: orq $384, %rdx # imm = 0x180
; ACHECK-NEXT: movl %edx, (%rdi)
; ACHECK-NEXT: shrq $32, %rdx
; ACHECK-NEXT: movw %dx, 4(%rdi)
; ACHECK-NEXT: retq
%aa = load i56, i56* %a, align 1
%b = or i56 %aa, 384
store i56 %b, i56* %a, align 1
@ -100,10 +100,10 @@ define void @i56_and_or(i56* %a) {
; CHECK-NEXT: andq %rax, %rcx
; CHECK-NEXT: movl %ecx, (%rdi)
; CHECK-NEXT: movq %rcx, %rax
; CHECK-NEXT: shrq $32, %rax
; CHECK-NEXT: movw %ax, 4(%rdi)
; CHECK-NEXT: shrq $48, %rcx
; CHECK-NEXT: movb %cl, 6(%rdi)
; CHECK-NEXT: shrq $48, %rax
; CHECK-NEXT: movb %al, 6(%rdi)
; CHECK-NEXT: shrq $32, %rcx
; CHECK-NEXT: movw %cx, 4(%rdi)
; CHECK-NEXT: retq
%b = load i56, i56* %a, align 1
%c = and i56 %b, -128
@ -127,9 +127,9 @@ define void @i56_insert_bit(i56* %a, i1 zeroext %bit) {
; CHECK-NEXT: movabsq $72057594037919743, %rdx # imm = 0xFFFFFFFFFFDFFF
; CHECK-NEXT: andq %rcx, %rdx
; CHECK-NEXT: orq %rdx, %rax
; CHECK-NEXT: movl %eax, (%rdi)
; CHECK-NEXT: shrq $48, %rdx
; CHECK-NEXT: movb %dl, 6(%rdi)
; CHECK-NEXT: movl %eax, (%rdi)
; CHECK-NEXT: shrq $32, %rax
; CHECK-NEXT: movw %ax, 4(%rdi)
; CHECK-NEXT: retq

5
llvm/test/CodeGen/X86/live-range-nosubreg.ll
View File

@ -1,6 +1,7 @@
; RUN: llc -march=x86-64 < %s
; RUN: llc -march=x86-64 < %s | FileCheck %s
; This testcase used to crash. See PR29132.
; Check for a sane output. This testcase used to crash. See PR29132.
; CHECK: leal -1
target triple = "x86_64-unknown-linux-gnu"

2
llvm/test/CodeGen/X86/longlong-deadload.ll
View File

@ -7,8 +7,10 @@ define void @test(i64* %P) nounwind {
; CHECK: # BB#0:
; CHECK-NEXT: movl {{[0-9]+}}(%esp), %eax
; CHECK-NEXT: movl (%eax), %ecx
; CHECK-NEXT: movl 4(%eax), %edx
; CHECK-NEXT: xorl $1, %ecx
; CHECK-NEXT: orl $2, %ecx
; CHECK-NEXT: movl %edx, 4(%eax)
; CHECK-NEXT: movl %ecx, (%eax)
; CHECK-NEXT: retl
%tmp1 = load i64, i64* %P, align 8

22
llvm/test/CodeGen/X86/merge-consecutive-loads-128.ll
View File

@ -1037,12 +1037,12 @@ define <2 x i64> @merge_2i64_i64_12_volatile(i64* %ptr) nounwind uwtable noinlin
define <4 x float> @merge_4f32_f32_2345_volatile(float* %ptr) nounwind uwtable noinline ssp {
; SSE2-LABEL: merge_4f32_f32_2345_volatile:
; SSE2: # BB#0:
; SSE2-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSE2-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSE2-NEXT: movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; SSE2-NEXT: unpcklps {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
; SSE2-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSE2-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE2-NEXT: movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; SSE2-NEXT: movss {{.*#+}} xmm3 = mem[0],zero,zero,zero
; SSE2-NEXT: unpcklps {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
; SSE2-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1]
; SSE2-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; SSE2-NEXT: retq
;
@ -1065,13 +1065,13 @@ define <4 x float> @merge_4f32_f32_2345_volatile(float* %ptr) nounwind uwtable n
; X32-SSE1-LABEL: merge_4f32_f32_2345_volatile:
; X32-SSE1: # BB#0:
; X32-SSE1-NEXT: movl {{[0-9]+}}(%esp), %eax
; X32-SSE1-DAG: movss 8(%eax), %[[R0:xmm[0-3]]] # [[R0]] = mem[0],zero,zero,zero
; X32-SSE1-DAG: movss 12(%eax), %[[R1:xmm[0-3]]] # [[R1]] = mem[0],zero,zero,zero
; X32-SSE1-DAG: movss 16(%eax), %[[R2:xmm[0-3]]] # [[R2]] = mem[0],zero,zero,zero
; X32-SSE1-DAG: movss 20(%eax), %[[R3:xmm[0-3]]] # [[R3]] = mem[0],zero,zero,zero
; X32-SSE1-DAG: unpcklps %[[R2]], %[[R0]] # [[R0]] = [[R0]][0],[[R2]][0],[[R0]][1],[[R2]][1]
; X32-SSE1-DAG: unpcklps %[[R3]], %[[R1]] # [[R1]] = [[R1]][0],[[R3]][0],[[R1]][1],[[R3]][1]
; X32-SSE1-DAG: unpcklps %[[R1]], %[[R0]] # [[R0]] = [[R0]][0],[[R1]][0],[[R0]][1],[[R1]][1]
; X32-SSE1-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X32-SSE1-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; X32-SSE1-NEXT: movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; X32-SSE1-NEXT: movss {{.*#+}} xmm3 = mem[0],zero,zero,zero
; X32-SSE1-NEXT: unpcklps {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
; X32-SSE1-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1]
; X32-SSE1-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; X32-SSE1-NEXT: retl
;
; X32-SSE41-LABEL: merge_4f32_f32_2345_volatile:

8
llvm/test/CodeGen/X86/merge-consecutive-loads-256.ll
View File

@ -668,10 +668,10 @@ define <16 x i16> @merge_16i16_i16_0uu3zzuuuuuzCuEF_volatile(i16* %ptr) nounwind
; AVX1: # BB#0:
; AVX1-NEXT: vpxor %xmm0, %xmm0, %xmm0
; AVX1-NEXT: vpinsrw $0, (%rdi), %xmm0, %xmm1
; AVX1-NEXT: vpinsrw $3, 6(%rdi), %xmm1, %xmm1
; AVX1-NEXT: vpinsrw $4, 24(%rdi), %xmm0, %xmm0
; AVX1-NEXT: vpinsrw $6, 28(%rdi), %xmm0, %xmm0
; AVX1-NEXT: vpinsrw $7, 30(%rdi), %xmm0, %xmm0
; AVX1-NEXT: vpinsrw $3, 6(%rdi), %xmm1, %xmm1
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: retq
;
@ -679,10 +679,10 @@ define <16 x i16> @merge_16i16_i16_0uu3zzuuuuuzCuEF_volatile(i16* %ptr) nounwind
; AVX2: # BB#0:
; AVX2-NEXT: vpxor %xmm0, %xmm0, %xmm0
; AVX2-NEXT: vpinsrw $0, (%rdi), %xmm0, %xmm1
; AVX2-NEXT: vpinsrw $3, 6(%rdi), %xmm1, %xmm1
; AVX2-NEXT: vpinsrw $4, 24(%rdi), %xmm0, %xmm0
; AVX2-NEXT: vpinsrw $6, 28(%rdi), %xmm0, %xmm0
; AVX2-NEXT: vpinsrw $7, 30(%rdi), %xmm0, %xmm0
; AVX2-NEXT: vpinsrw $3, 6(%rdi), %xmm1, %xmm1
; AVX2-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX2-NEXT: retq
;
@ -690,10 +690,10 @@ define <16 x i16> @merge_16i16_i16_0uu3zzuuuuuzCuEF_volatile(i16* %ptr) nounwind
; AVX512F: # BB#0:
; AVX512F-NEXT: vpxor %xmm0, %xmm0, %xmm0
; AVX512F-NEXT: vpinsrw $0, (%rdi), %xmm0, %xmm1
; AVX512F-NEXT: vpinsrw $3, 6(%rdi), %xmm1, %xmm1
; AVX512F-NEXT: vpinsrw $4, 24(%rdi), %xmm0, %xmm0
; AVX512F-NEXT: vpinsrw $6, 28(%rdi), %xmm0, %xmm0
; AVX512F-NEXT: vpinsrw $7, 30(%rdi), %xmm0, %xmm0
; AVX512F-NEXT: vpinsrw $3, 6(%rdi), %xmm1, %xmm1
; AVX512F-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX512F-NEXT: retq
;
@ -702,10 +702,10 @@ define <16 x i16> @merge_16i16_i16_0uu3zzuuuuuzCuEF_volatile(i16* %ptr) nounwind
; X32-AVX-NEXT: movl {{[0-9]+}}(%esp), %eax
; X32-AVX-NEXT: vpxor %xmm0, %xmm0, %xmm0
; X32-AVX-NEXT: vpinsrw $0, (%eax), %xmm0, %xmm1
; X32-AVX-NEXT: vpinsrw $3, 6(%eax), %xmm1, %xmm1
; X32-AVX-NEXT: vpinsrw $4, 24(%eax), %xmm0, %xmm0
; X32-AVX-NEXT: vpinsrw $6, 28(%eax), %xmm0, %xmm0
; X32-AVX-NEXT: vpinsrw $7, 30(%eax), %xmm0, %xmm0
; X32-AVX-NEXT: vpinsrw $3, 6(%eax), %xmm1, %xmm1
; X32-AVX-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; X32-AVX-NEXT: retl
%ptr0 = getelementptr inbounds i16, i16* %ptr, i64 0

8
llvm/test/CodeGen/X86/merge-store-partially-alias-loads.ll
View File

@ -21,11 +21,11 @@
; DBGDAG-DAG: [[LD2:t[0-9]+]]: i16,ch = load<LD2[%tmp81](align=1)> [[ENTRYTOKEN]], [[BASEPTR]], undef:i64
; DBGDAG-DAG: [[LD1:t[0-9]+]]: i8,ch = load<LD1[%tmp12]> [[ENTRYTOKEN]], [[ADDPTR]], undef:i64
; DBGDAG-DAG: [[ST1:t[0-9]+]]: ch = store<ST1[%tmp14]> [[ENTRYTOKEN]], [[LD1]], t{{[0-9]+}}, undef:i64
; DBGDAG-DAG: [[LOADTOKEN:t[0-9]+]]: ch = TokenFactor [[LD2]]:1, [[LD1]]:1
; DBGDAG-DAG: [[ST2:t[0-9]+]]: ch = store<ST2[%tmp10](align=1)> [[LOADTOKEN]], [[LD2]], t{{[0-9]+}}, undef:i64
; DBGDAG: [[LOADTOKEN:t[0-9]+]]: ch = TokenFactor [[LD2]]:1, [[LD1]]:1
; DBGDAG: X86ISD::RET_FLAG t{{[0-9]+}},
; DBGDAG-DAG: [[ST2:t[0-9]+]]: ch = store<ST2[%tmp10](align=1)> [[LOADTOKEN]], [[LD2]], t{{[0-9]+}}, undef:i64
; DBGDAG-DAG: [[ST1:t[0-9]+]]: ch = store<ST1[%tmp14]> [[ST2]], [[LD1]], t{{[0-9]+}}, undef:i64
; DBGDAG: X86ISD::RET_FLAG [[ST1]],
; DBGDAG: Type-legalized selection DAG: BB#0 'merge_store_partial_overlap_load:'
define void @merge_store_partial_overlap_load([4 x i8]* %tmp) {

31
llvm/test/CodeGen/X86/pr18023.ll Normal file
View File

@ -0,0 +1,31 @@
; RUN: llc < %s -mtriple x86_64-apple-macosx10.9.0 | FileCheck %s
; PR18023
; CHECK: movabsq $4294967296, %rcx
; CHECK: movq %rcx, (%rax)
; CHECK: movl $1, 4(%rax)
; CHECK: movl $0, 4(%rax)
; CHECK: movq $1, 4(%rax)
@c = common global i32 0, align 4
@a = common global [3 x i32] zeroinitializer, align 4
@b = common global i32 0, align 4
@.str = private unnamed_addr constant [4 x i8] c"%d\0A\00", align 1
define void @func() {
store i32 1, i32* getelementptr inbounds ([3 x i32], [3 x i32]* @a, i64 0, i64 1), align 4
store i32 0, i32* getelementptr inbounds ([3 x i32], [3 x i32]* @a, i64 0, i64 0), align 4
%1 = load volatile i32, i32* @b, align 4
store i32 1, i32* getelementptr inbounds ([3 x i32], [3 x i32]* @a, i64 0, i64 1), align 4
store i32 0, i32* getelementptr inbounds ([3 x i32], [3 x i32]* @a, i64 0, i64 1), align 4
%2 = load volatile i32, i32* @b, align 4
store i32 1, i32* getelementptr inbounds ([3 x i32], [3 x i32]* @a, i64 0, i64 1), align 4
store i32 0, i32* getelementptr inbounds ([3 x i32], [3 x i32]* @a, i64 0, i64 2), align 4
%3 = load volatile i32, i32* @b, align 4
store i32 3, i32* @c, align 4
%4 = load i32, i32* getelementptr inbounds ([3 x i32], [3 x i32]* @a, i64 0, i64 1), align 4
%call = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([4 x i8], [4 x i8]* @.str, i64 0, i64 0), i32 %4)
ret void
}
declare i32 @printf(i8*, ...)

27
llvm/test/CodeGen/X86/split-store.ll
View File

@ -1,8 +1,8 @@
; RUN: llc -mtriple=x86_64-unknown-unknown -force-split-store < %s | FileCheck %s
; CHECK-LABEL: int32_float_pair
; CHECK-DAG: movl %edi, (%rsi)
; CHECK-DAG: movss %xmm0, 4(%rsi)
; CHECK: movl %edi, (%rsi)
; CHECK: movss %xmm0, 4(%rsi)
define void @int32_float_pair(i32 %tmp1, float %tmp2, i64* %ref.tmp) {
entry:
%t0 = bitcast float %tmp2 to i32
@ -15,8 +15,8 @@ entry:
}
; CHECK-LABEL: float_int32_pair
; CHECK-DAG: movss %xmm0, (%rsi)
; CHECK-DAG: movl %edi, 4(%rsi)
; CHECK: movss %xmm0, (%rsi)
; CHECK: movl %edi, 4(%rsi)
define void @float_int32_pair(float %tmp1, i32 %tmp2, i64* %ref.tmp) {
entry:
%t0 = bitcast float %tmp1 to i32
@ -29,9 +29,9 @@ entry:
}
; CHECK-LABEL: int16_float_pair
; CHECK-DAG: movzwl %di, %eax
; CHECK-DAG: movl %eax, (%rsi)
; CHECK-DAG: movss %xmm0, 4(%rsi)
; CHECK: movzwl %di, %eax
; CHECK: movl %eax, (%rsi)
; CHECK: movss %xmm0, 4(%rsi)
define void @int16_float_pair(i16 signext %tmp1, float %tmp2, i64* %ref.tmp) {
entry:
%t0 = bitcast float %tmp2 to i32
@ -44,9 +44,9 @@ entry:
}
; CHECK-LABEL: int8_float_pair
; CHECK-DAG: movzbl %dil, %eax
; CHECK-DAG: movl %eax, (%rsi)
; CHECK-DAG: movss %xmm0, 4(%rsi)
; CHECK: movzbl %dil, %eax
; CHECK: movl %eax, (%rsi)
; CHECK: movss %xmm0, 4(%rsi)
define void @int8_float_pair(i8 signext %tmp1, float %tmp2, i64* %ref.tmp) {
entry:
%t0 = bitcast float %tmp2 to i32
@ -146,9 +146,10 @@ entry:
; CHECK: movw %di, (%rdx)
; CHECK: shrl $16, %edi
; CHECK: movb %dil, 2(%rdx)
; CHECK: movw %si, 4(%rdx)
; CHECK: shrl $16, %esi
; CHECK: movb %sil, 6(%rdx)
; CHECK: movl %esi, %eax
; CHECK: shrl $16, %eax
; CHECK: movb %al, 6(%rdx)
; CHECK: movw %si, 4(%rdx)
define void @int24_int24_pair(i24 signext %tmp1, i24 signext %tmp2, i48* %ref.tmp) {
entry:
%t1 = zext i24 %tmp2 to i48

11
llvm/test/CodeGen/X86/stores-merging.ll
View File

@ -13,9 +13,9 @@ target triple = "x86_64-unknown-linux-gnu"
;; the same result in memory in the end.
; CHECK-LABEL: redundant_stores_merging:
; CHECK: movabsq $528280977409, %rax
; CHECK: movl $123, e+8(%rip)
; CHECK: movabsq $1958505086977, %rax
; CHECK: movq %rax, e+4(%rip)
; CHECK: movl $456, e+8(%rip)
define void @redundant_stores_merging() {
entry:
store i32 1, i32* getelementptr inbounds (%structTy, %structTy* @e, i64 0, i32 1), align 4
@ -26,9 +26,9 @@ entry:
;; This variant tests PR25154.
; CHECK-LABEL: redundant_stores_merging_reverse:
; CHECK: movabsq $528280977409, %rax
; CHECK: movl $123, e+8(%rip)
; CHECK: movabsq $1958505086977, %rax
; CHECK: movq %rax, e+4(%rip)
; CHECK: movl $456, e+8(%rip)
define void @redundant_stores_merging_reverse() {
entry:
store i32 123, i32* getelementptr inbounds (%structTy, %structTy* @e, i64 0, i32 2), align 4
@ -45,8 +45,9 @@ entry:
;; a movl, after the store to 3).
;; CHECK-LABEL: overlapping_stores_merging:
;; CHECK: movl $1, b(%rip)
;; CHECK: movw $0, b+2(%rip)
;; CHECK: movw $2, b+3(%rip)
;; CHECK: movw $1, b(%rip)
define void @overlapping_stores_merging() {
entry:
store i16 0, i16* bitcast (i8* getelementptr inbounds ([8 x i8], [8 x i8]* @b, i64 0, i64 2) to i16*), align 2

1872
llvm/test/CodeGen/X86/vector-compare-results.ll
View File

File diff suppressed because it is too large Load Diff

1088
llvm/test/CodeGen/X86/vector-shuffle-variable-128.ll
View File

File diff suppressed because it is too large Load Diff

233
llvm/test/CodeGen/X86/vector-shuffle-variable-256.ll
View File

@ -1,5 +1,4 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; NOTE: Assertions have been autogenerated by update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+avx | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX1
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+avx2 | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX2
@ -14,16 +13,16 @@ define <4 x double> @var_shuffle_v4f64_v4f64_xxxx_i64(<4 x double> %x, i64 %i0,
; ALL-NEXT: movq %rsp, %rbp
; ALL-NEXT: andq $-32, %rsp
; ALL-NEXT: subq $64, %rsp
; ALL-NEXT: andl $3, %esi
; ALL-NEXT: andl $3, %edi
; ALL-NEXT: andl $3, %ecx
; ALL-NEXT: andl $3, %edx
; ALL-NEXT: andl $3, %esi
; ALL-NEXT: andl $3, %edi
; ALL-NEXT: vmovaps %ymm0, (%rsp)
; ALL-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
; ALL-NEXT: vmovhpd {{.*#+}} xmm0 = xmm0[0],mem[0]
; ALL-NEXT: vmovsd {{.*#+}} xmm1 = mem[0],zero
; ALL-NEXT: vmovhpd {{.*#+}} xmm1 = xmm1[0],mem[0]
; ALL-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; ALL-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; ALL-NEXT: movq %rbp, %rsp
; ALL-NEXT: popq %rbp
; ALL-NEXT: retq
@ -69,16 +68,16 @@ define <4 x double> @var_shuffle_v4f64_v4f64_uxx0_i64(<4 x double> %x, i64 %i0,
define <4 x double> @var_shuffle_v4f64_v2f64_xxxx_i64(<2 x double> %x, i64 %i0, i64 %i1, i64 %i2, i64 %i3) nounwind {
; ALL-LABEL: var_shuffle_v4f64_v2f64_xxxx_i64:
; ALL: # BB#0:
; ALL-NEXT: andl $1, %esi
; ALL-NEXT: andl $1, %edi
; ALL-NEXT: andl $1, %ecx
; ALL-NEXT: andl $1, %edx
; ALL-NEXT: andl $1, %esi
; ALL-NEXT: andl $1, %edi
; ALL-NEXT: vmovaps %xmm0, -{{[0-9]+}}(%rsp)
; ALL-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
; ALL-NEXT: vmovhpd {{.*#+}} xmm0 = xmm0[0],mem[0]
; ALL-NEXT: vmovsd {{.*#+}} xmm1 = mem[0],zero
; ALL-NEXT: vmovhpd {{.*#+}} xmm1 = xmm1[0],mem[0]
; ALL-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; ALL-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; ALL-NEXT: retq
%x0 = extractelement <2 x double> %x, i64 %i0
%x1 = extractelement <2 x double> %x, i64 %i1
@ -98,18 +97,18 @@ define <4 x i64> @var_shuffle_v4i64_v4i64_xxxx_i64(<4 x i64> %x, i64 %i0, i64 %i
; AVX1-NEXT: movq %rsp, %rbp
; AVX1-NEXT: andq $-32, %rsp
; AVX1-NEXT: subq $64, %rsp
; AVX1-NEXT: andl $3, %edi
; AVX1-NEXT: andl $3, %esi
; AVX1-NEXT: andl $3, %edx
; AVX1-NEXT: andl $3, %ecx
; AVX1-NEXT: andl $3, %edx
; AVX1-NEXT: andl $3, %esi
; AVX1-NEXT: andl $3, %edi
; AVX1-NEXT: vmovaps %ymm0, (%rsp)
; AVX1-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
; AVX1-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX1-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX1-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm2[0],xmm1[0]
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: movq %rbp, %rsp
; AVX1-NEXT: popq %rbp
; AVX1-NEXT: retq
@ -120,18 +119,18 @@ define <4 x i64> @var_shuffle_v4i64_v4i64_xxxx_i64(<4 x i64> %x, i64 %i0, i64 %i
; AVX2-NEXT: movq %rsp, %rbp
; AVX2-NEXT: andq $-32, %rsp
; AVX2-NEXT: subq $64, %rsp
; AVX2-NEXT: andl $3, %edi
; AVX2-NEXT: andl $3, %esi
; AVX2-NEXT: andl $3, %edx
; AVX2-NEXT: andl $3, %ecx
; AVX2-NEXT: andl $3, %edx
; AVX2-NEXT: andl $3, %esi
; AVX2-NEXT: andl $3, %edi
; AVX2-NEXT: vmovaps %ymm0, (%rsp)
; AVX2-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
; AVX2-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX2-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX2-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm2[0],xmm1[0]
; AVX2-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
; AVX2-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-NEXT: movq %rbp, %rsp
; AVX2-NEXT: popq %rbp
; AVX2-NEXT: retq
@ -153,12 +152,12 @@ define <4 x i64> @var_shuffle_v4i64_v4i64_xx00_i64(<4 x i64> %x, i64 %i0, i64 %i
; AVX1-NEXT: movq %rsp, %rbp
; AVX1-NEXT: andq $-32, %rsp
; AVX1-NEXT: subq $64, %rsp
; AVX1-NEXT: andl $3, %edi
; AVX1-NEXT: andl $3, %esi
; AVX1-NEXT: andl $3, %edi
; AVX1-NEXT: vmovaps %ymm0, (%rsp)
; AVX1-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
; AVX1-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX1-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: movq %rbp, %rsp
@ -171,12 +170,12 @@ define <4 x i64> @var_shuffle_v4i64_v4i64_xx00_i64(<4 x i64> %x, i64 %i0, i64 %i
; AVX2-NEXT: movq %rsp, %rbp
; AVX2-NEXT: andq $-32, %rsp
; AVX2-NEXT: subq $64, %rsp
; AVX2-NEXT: andl $3, %edi
; AVX2-NEXT: andl $3, %esi
; AVX2-NEXT: andl $3, %edi
; AVX2-NEXT: vmovaps %ymm0, (%rsp)
; AVX2-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
; AVX2-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX2-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX2-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-NEXT: movq %rbp, %rsp
@ -196,34 +195,34 @@ define <4 x i64> @var_shuffle_v4i64_v4i64_xx00_i64(<4 x i64> %x, i64 %i0, i64 %i
define <4 x i64> @var_shuffle_v4i64_v2i64_xxxx_i64(<2 x i64> %x, i64 %i0, i64 %i1, i64 %i2, i64 %i3) nounwind {
; AVX1-LABEL: var_shuffle_v4i64_v2i64_xxxx_i64:
; AVX1: # BB#0:
; AVX1-NEXT: andl $1, %edi
; AVX1-NEXT: andl $1, %esi
; AVX1-NEXT: andl $1, %edx
; AVX1-NEXT: andl $1, %ecx
; AVX1-NEXT: andl $1, %edx
; AVX1-NEXT: andl $1, %esi
; AVX1-NEXT: andl $1, %edi
; AVX1-NEXT: vmovaps %xmm0, -{{[0-9]+}}(%rsp)
; AVX1-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
; AVX1-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX1-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX1-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm2[0],xmm1[0]
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: var_shuffle_v4i64_v2i64_xxxx_i64:
; AVX2: # BB#0:
; AVX2-NEXT: andl $1, %edi
; AVX2-NEXT: andl $1, %esi
; AVX2-NEXT: andl $1, %edx
; AVX2-NEXT: andl $1, %ecx
; AVX2-NEXT: andl $1, %edx
; AVX2-NEXT: andl $1, %esi
; AVX2-NEXT: andl $1, %edi
; AVX2-NEXT: vmovaps %xmm0, -{{[0-9]+}}(%rsp)
; AVX2-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
; AVX2-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX2-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX2-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm2[0],xmm1[0]
; AVX2-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
; AVX2-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-NEXT: retq
%x0 = extractelement <2 x i64> %x, i64 %i0
%x1 = extractelement <2 x i64> %x, i64 %i1
@ -261,14 +260,16 @@ define <8 x float> @var_shuffle_v8f32_v8f32_xxxxxxxx_i32(<8 x float> %x, i32 %i0
; ALL-NEXT: movl 24(%rbp), %eax
; ALL-NEXT: andl $7, %eax
; ALL-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; ALL-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0],mem[0],xmm0[2,3]
; ALL-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0,1],mem[0],xmm0[3]
; ALL-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0,1,2],mem[0]
; ALL-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; ALL-NEXT: vinsertps {{.*#+}} xmm1 = xmm1[0],mem[0],xmm1[2,3]
; ALL-NEXT: vinsertps {{.*#+}} xmm1 = xmm1[0,1],mem[0],xmm1[3]
; ALL-NEXT: vinsertps {{.*#+}} xmm1 = xmm1[0,1,2],mem[0]
; ALL-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; ALL-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; ALL-NEXT: vinsertps {{.*#+}} xmm2 = xmm2[0],mem[0],xmm2[2,3]
; ALL-NEXT: vinsertps {{.*#+}} xmm2 = xmm2[0,1],mem[0],xmm2[3]
; ALL-NEXT: vinsertps {{.*#+}} xmm2 = xmm2[0,1,2],mem[0]
; ALL-NEXT: vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero
; ALL-NEXT: vinsertps {{.*#+}} xmm3 = xmm3[0],mem[0],xmm3[2,3]
; ALL-NEXT: vinsertps {{.*#+}} xmm0 = xmm3[0,1],xmm0[0],xmm3[3]
; ALL-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0,1,2],xmm1[0]
; ALL-NEXT: vinsertf128 $1, %xmm0, %ymm2, %ymm0
; ALL-NEXT: movq %rbp, %rsp
; ALL-NEXT: popq %rbp
; ALL-NEXT: retq
@ -312,14 +313,16 @@ define <8 x float> @var_shuffle_v8f32_v4f32_xxxxxxxx_i32(<4 x float> %x, i32 %i0
; ALL-NEXT: movl {{[0-9]+}}(%rsp), %eax
; ALL-NEXT: andl $3, %eax
; ALL-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; ALL-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0],mem[0],xmm0[2,3]
; ALL-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0,1],mem[0],xmm0[3]
; ALL-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0,1,2],mem[0]
; ALL-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; ALL-NEXT: vinsertps {{.*#+}} xmm1 = xmm1[0],mem[0],xmm1[2,3]
; ALL-NEXT: vinsertps {{.*#+}} xmm1 = xmm1[0,1],mem[0],xmm1[3]
; ALL-NEXT: vinsertps {{.*#+}} xmm1 = xmm1[0,1,2],mem[0]
; ALL-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; ALL-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; ALL-NEXT: vinsertps {{.*#+}} xmm2 = xmm2[0],mem[0],xmm2[2,3]
; ALL-NEXT: vinsertps {{.*#+}} xmm2 = xmm2[0,1],mem[0],xmm2[3]
; ALL-NEXT: vinsertps {{.*#+}} xmm2 = xmm2[0,1,2],mem[0]
; ALL-NEXT: vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero
; ALL-NEXT: vinsertps {{.*#+}} xmm3 = xmm3[0],mem[0],xmm3[2,3]
; ALL-NEXT: vinsertps {{.*#+}} xmm0 = xmm3[0,1],xmm0[0],xmm3[3]
; ALL-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0,1,2],xmm1[0]
; ALL-NEXT: vinsertf128 $1, %xmm0, %ymm2, %ymm0
; ALL-NEXT: retq
%x0 = extractelement <4 x float> %x, i32 %i0
%x1 = extractelement <4 x float> %x, i32 %i1
@ -360,25 +363,32 @@ define <16 x i16> @var_shuffle_v16i16_v16i16_xxxxxxxxxxxxxxxx_i16(<16 x i16> %x,
; AVX1-NEXT: vmovd %eax, %xmm0
; AVX1-NEXT: movl 40(%rbp), %eax
; AVX1-NEXT: andl $15, %eax
; AVX1-NEXT: vpinsrw $1, (%rsp,%rax,2), %xmm0, %xmm0
; AVX1-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $1, %eax, %xmm0, %xmm0
; AVX1-NEXT: movl 48(%rbp), %eax
; AVX1-NEXT: andl $15, %eax
; AVX1-NEXT: vpinsrw $2, (%rsp,%rax,2), %xmm0, %xmm0
; AVX1-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $2, %eax, %xmm0, %xmm0
; AVX1-NEXT: movl 56(%rbp), %eax
; AVX1-NEXT: andl $15, %eax
; AVX1-NEXT: vpinsrw $3, (%rsp,%rax,2), %xmm0, %xmm0
; AVX1-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $3, %eax, %xmm0, %xmm0
; AVX1-NEXT: movl 64(%rbp), %eax
; AVX1-NEXT: andl $15, %eax
; AVX1-NEXT: vpinsrw $4, (%rsp,%rax,2), %xmm0, %xmm0
; AVX1-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $4, %eax, %xmm0, %xmm0
; AVX1-NEXT: movl 72(%rbp), %eax
; AVX1-NEXT: andl $15, %eax
; AVX1-NEXT: vpinsrw $5, (%rsp,%rax,2), %xmm0, %xmm0
; AVX1-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $5, %eax, %xmm0, %xmm0
; AVX1-NEXT: movl 80(%rbp), %eax
; AVX1-NEXT: andl $15, %eax
; AVX1-NEXT: vpinsrw $6, (%rsp,%rax,2), %xmm0, %xmm0
; AVX1-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $6, %eax, %xmm0, %xmm0
; AVX1-NEXT: movl 88(%rbp), %eax
; AVX1-NEXT: andl $15, %eax
; AVX1-NEXT: vpinsrw $7, (%rsp,%rax,2), %xmm0, %xmm0
; AVX1-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $7, %eax, %xmm0, %xmm0
; AVX1-NEXT: andl $15, %edi
; AVX1-NEXT: movzwl (%rsp,%rdi,2), %eax
; AVX1-NEXT: vmovd %eax, %xmm1
@ -394,10 +404,12 @@ define <16 x i16> @var_shuffle_v16i16_v16i16_xxxxxxxxxxxxxxxx_i16(<16 x i16> %x,
; AVX1-NEXT: vpinsrw $5, (%rsp,%r9,2), %xmm1, %xmm1
; AVX1-NEXT: movl 16(%rbp), %eax
; AVX1-NEXT: andl $15, %eax
; AVX1-NEXT: vpinsrw $6, (%rsp,%rax,2), %xmm1, %xmm1
; AVX1-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $6, %eax, %xmm1, %xmm1
; AVX1-NEXT: movl 24(%rbp), %eax
; AVX1-NEXT: andl $15, %eax
; AVX1-NEXT: vpinsrw $7, (%rsp,%rax,2), %xmm1, %xmm1
; AVX1-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $7, %eax, %xmm1, %xmm1
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: movq %rbp, %rsp
; AVX1-NEXT: popq %rbp
@ -422,25 +434,32 @@ define <16 x i16> @var_shuffle_v16i16_v16i16_xxxxxxxxxxxxxxxx_i16(<16 x i16> %x,
; AVX2-NEXT: vmovd %eax, %xmm0
; AVX2-NEXT: movl 40(%rbp), %eax
; AVX2-NEXT: andl $15, %eax
; AVX2-NEXT: vpinsrw $1, (%rsp,%rax,2), %xmm0, %xmm0
; AVX2-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $1, %eax, %xmm0, %xmm0
; AVX2-NEXT: movl 48(%rbp), %eax
; AVX2-NEXT: andl $15, %eax
; AVX2-NEXT: vpinsrw $2, (%rsp,%rax,2), %xmm0, %xmm0
; AVX2-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $2, %eax, %xmm0, %xmm0
; AVX2-NEXT: movl 56(%rbp), %eax
; AVX2-NEXT: andl $15, %eax
; AVX2-NEXT: vpinsrw $3, (%rsp,%rax,2), %xmm0, %xmm0
; AVX2-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $3, %eax, %xmm0, %xmm0
; AVX2-NEXT: movl 64(%rbp), %eax
; AVX2-NEXT: andl $15, %eax
; AVX2-NEXT: vpinsrw $4, (%rsp,%rax,2), %xmm0, %xmm0
; AVX2-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $4, %eax, %xmm0, %xmm0
; AVX2-NEXT: movl 72(%rbp), %eax
; AVX2-NEXT: andl $15, %eax
; AVX2-NEXT: vpinsrw $5, (%rsp,%rax,2), %xmm0, %xmm0
; AVX2-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $5, %eax, %xmm0, %xmm0
; AVX2-NEXT: movl 80(%rbp), %eax
; AVX2-NEXT: andl $15, %eax
; AVX2-NEXT: vpinsrw $6, (%rsp,%rax,2), %xmm0, %xmm0
; AVX2-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $6, %eax, %xmm0, %xmm0
; AVX2-NEXT: movl 88(%rbp), %eax
; AVX2-NEXT: andl $15, %eax
; AVX2-NEXT: vpinsrw $7, (%rsp,%rax,2), %xmm0, %xmm0
; AVX2-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $7, %eax, %xmm0, %xmm0
; AVX2-NEXT: andl $15, %edi
; AVX2-NEXT: movzwl (%rsp,%rdi,2), %eax
; AVX2-NEXT: vmovd %eax, %xmm1
@ -456,10 +475,12 @@ define <16 x i16> @var_shuffle_v16i16_v16i16_xxxxxxxxxxxxxxxx_i16(<16 x i16> %x,
; AVX2-NEXT: vpinsrw $5, (%rsp,%r9,2), %xmm1, %xmm1
; AVX2-NEXT: movl 16(%rbp), %eax
; AVX2-NEXT: andl $15, %eax
; AVX2-NEXT: vpinsrw $6, (%rsp,%rax,2), %xmm1, %xmm1
; AVX2-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $6, %eax, %xmm1, %xmm1
; AVX2-NEXT: movl 24(%rbp), %eax
; AVX2-NEXT: andl $15, %eax
; AVX2-NEXT: vpinsrw $7, (%rsp,%rax,2), %xmm1, %xmm1
; AVX2-NEXT: movzwl (%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $7, %eax, %xmm1, %xmm1
; AVX2-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX2-NEXT: movq %rbp, %rsp
; AVX2-NEXT: popq %rbp
@ -515,25 +536,32 @@ define <16 x i16> @var_shuffle_v16i16_v8i16_xxxxxxxxxxxxxxxx_i16(<8 x i16> %x, i
; AVX1-NEXT: vmovd %eax, %xmm0
; AVX1-NEXT: movl {{[0-9]+}}(%rsp), %eax
; AVX1-NEXT: andl $7, %eax
; AVX1-NEXT: vpinsrw $1, -24(%rsp,%rax,2), %xmm0, %xmm0
; AVX1-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $1, %eax, %xmm0, %xmm0
; AVX1-NEXT: movl {{[0-9]+}}(%rsp), %eax
; AVX1-NEXT: andl $7, %eax
; AVX1-NEXT: vpinsrw $2, -24(%rsp,%rax,2), %xmm0, %xmm0
; AVX1-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $2, %eax, %xmm0, %xmm0
; AVX1-NEXT: movl {{[0-9]+}}(%rsp), %eax
; AVX1-NEXT: andl $7, %eax
; AVX1-NEXT: vpinsrw $3, -24(%rsp,%rax,2), %xmm0, %xmm0
; AVX1-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $3, %eax, %xmm0, %xmm0
; AVX1-NEXT: movl {{[0-9]+}}(%rsp), %eax
; AVX1-NEXT: andl $7, %eax
; AVX1-NEXT: vpinsrw $4, -24(%rsp,%rax,2), %xmm0, %xmm0
; AVX1-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $4, %eax, %xmm0, %xmm0
; AVX1-NEXT: movl {{[0-9]+}}(%rsp), %eax
; AVX1-NEXT: andl $7, %eax
; AVX1-NEXT: vpinsrw $5, -24(%rsp,%rax,2), %xmm0, %xmm0
; AVX1-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $5, %eax, %xmm0, %xmm0
; AVX1-NEXT: movl {{[0-9]+}}(%rsp), %eax
; AVX1-NEXT: andl $7, %eax
; AVX1-NEXT: vpinsrw $6, -24(%rsp,%rax,2), %xmm0, %xmm0
; AVX1-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $6, %eax, %xmm0, %xmm0
; AVX1-NEXT: movl {{[0-9]+}}(%rsp), %eax
; AVX1-NEXT: andl $7, %eax
; AVX1-NEXT: vpinsrw $7, -24(%rsp,%rax,2), %xmm0, %xmm0
; AVX1-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $7, %eax, %xmm0, %xmm0
; AVX1-NEXT: andl $7, %edi
; AVX1-NEXT: movzwl -24(%rsp,%rdi,2), %eax
; AVX1-NEXT: vmovd %eax, %xmm1
@ -549,10 +577,12 @@ define <16 x i16> @var_shuffle_v16i16_v8i16_xxxxxxxxxxxxxxxx_i16(<8 x i16> %x, i
; AVX1-NEXT: vpinsrw $5, -24(%rsp,%r9,2), %xmm1, %xmm1
; AVX1-NEXT: movl {{[0-9]+}}(%rsp), %eax
; AVX1-NEXT: andl $7, %eax
; AVX1-NEXT: vpinsrw $6, -24(%rsp,%rax,2), %xmm1, %xmm1
; AVX1-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $6, %eax, %xmm1, %xmm1
; AVX1-NEXT: movl {{[0-9]+}}(%rsp), %eax
; AVX1-NEXT: andl $7, %eax
; AVX1-NEXT: vpinsrw $7, -24(%rsp,%rax,2), %xmm1, %xmm1
; AVX1-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX1-NEXT: vpinsrw $7, %eax, %xmm1, %xmm1
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: retq
;
@ -571,25 +601,32 @@ define <16 x i16> @var_shuffle_v16i16_v8i16_xxxxxxxxxxxxxxxx_i16(<8 x i16> %x, i
; AVX2-NEXT: vmovd %eax, %xmm0
; AVX2-NEXT: movl {{[0-9]+}}(%rsp), %eax
; AVX2-NEXT: andl $7, %eax
; AVX2-NEXT: vpinsrw $1, -24(%rsp,%rax,2), %xmm0, %xmm0
; AVX2-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $1, %eax, %xmm0, %xmm0
; AVX2-NEXT: movl {{[0-9]+}}(%rsp), %eax
; AVX2-NEXT: andl $7, %eax
; AVX2-NEXT: vpinsrw $2, -24(%rsp,%rax,2), %xmm0, %xmm0
; AVX2-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $2, %eax, %xmm0, %xmm0
; AVX2-NEXT: movl {{[0-9]+}}(%rsp), %eax
; AVX2-NEXT: andl $7, %eax
; AVX2-NEXT: vpinsrw $3, -24(%rsp,%rax,2), %xmm0, %xmm0
; AVX2-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $3, %eax, %xmm0, %xmm0
; AVX2-NEXT: movl {{[0-9]+}}(%rsp), %eax
; AVX2-NEXT: andl $7, %eax
; AVX2-NEXT: vpinsrw $4, -24(%rsp,%rax,2), %xmm0, %xmm0
; AVX2-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $4, %eax, %xmm0, %xmm0
; AVX2-NEXT: movl {{[0-9]+}}(%rsp), %eax
; AVX2-NEXT: andl $7, %eax
; AVX2-NEXT: vpinsrw $5, -24(%rsp,%rax,2), %xmm0, %xmm0
; AVX2-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $5, %eax, %xmm0, %xmm0
; AVX2-NEXT: movl {{[0-9]+}}(%rsp), %eax
; AVX2-NEXT: andl $7, %eax
; AVX2-NEXT: vpinsrw $6, -24(%rsp,%rax,2), %xmm0, %xmm0
; AVX2-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $6, %eax, %xmm0, %xmm0
; AVX2-NEXT: movl {{[0-9]+}}(%rsp), %eax
; AVX2-NEXT: andl $7, %eax
; AVX2-NEXT: vpinsrw $7, -24(%rsp,%rax,2), %xmm0, %xmm0
; AVX2-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $7, %eax, %xmm0, %xmm0
; AVX2-NEXT: andl $7, %edi
; AVX2-NEXT: movzwl -24(%rsp,%rdi,2), %eax
; AVX2-NEXT: vmovd %eax, %xmm1
@ -605,10 +642,12 @@ define <16 x i16> @var_shuffle_v16i16_v8i16_xxxxxxxxxxxxxxxx_i16(<8 x i16> %x, i
; AVX2-NEXT: vpinsrw $5, -24(%rsp,%r9,2), %xmm1, %xmm1
; AVX2-NEXT: movl {{[0-9]+}}(%rsp), %eax
; AVX2-NEXT: andl $7, %eax
; AVX2-NEXT: vpinsrw $6, -24(%rsp,%rax,2), %xmm1, %xmm1
; AVX2-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $6, %eax, %xmm1, %xmm1
; AVX2-NEXT: movl {{[0-9]+}}(%rsp), %eax
; AVX2-NEXT: andl $7, %eax
; AVX2-NEXT: vpinsrw $7, -24(%rsp,%rax,2), %xmm1, %xmm1
; AVX2-NEXT: movzwl -24(%rsp,%rax,2), %eax
; AVX2-NEXT: vpinsrw $7, %eax, %xmm1, %xmm1
; AVX2-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX2-NEXT: retq
%x0 = extractelement <8 x i16> %x, i32 %i0
@ -668,11 +707,11 @@ define <4 x i64> @mem_shuffle_v4i64_v4i64_xxxx_i64(<4 x i64> %x, i64* %i) nounwi
; AVX1-NEXT: vmovaps %ymm0, (%rsp)
; AVX1-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
; AVX1-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
; AVX1-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX1-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm2[0],xmm1[0]
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: movq %rbp, %rsp
; AVX1-NEXT: popq %rbp
; AVX1-NEXT: retq
@ -694,11 +733,11 @@ define <4 x i64> @mem_shuffle_v4i64_v4i64_xxxx_i64(<4 x i64> %x, i64* %i) nounwi
; AVX2-NEXT: vmovaps %ymm0, (%rsp)
; AVX2-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
; AVX2-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
; AVX2-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX2-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm2[0],xmm1[0]
; AVX2-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX2-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
; AVX2-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-NEXT: movq %rbp, %rsp
; AVX2-NEXT: popq %rbp
; AVX2-NEXT: retq
@ -735,11 +774,11 @@ define <4 x i64> @mem_shuffle_v4i64_v2i64_xxxx_i64(<2 x i64> %x, i64* %i) nounwi
; AVX1-NEXT: vmovaps %xmm0, -{{[0-9]+}}(%rsp)
; AVX1-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
; AVX1-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
; AVX1-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX1-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm2[0],xmm1[0]
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: mem_shuffle_v4i64_v2i64_xxxx_i64:
@ -755,11 +794,11 @@ define <4 x i64> @mem_shuffle_v4i64_v2i64_xxxx_i64(<2 x i64> %x, i64* %i) nounwi
; AVX2-NEXT: vmovaps %xmm0, -{{[0-9]+}}(%rsp)
; AVX2-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
; AVX2-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
; AVX2-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX2-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm2[0],xmm1[0]
; AVX2-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX2-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
; AVX2-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-NEXT: retq
%p0 = getelementptr inbounds i64, i64* %i, i32 0
%p1 = getelementptr inbounds i64, i64* %i, i32 1

4
llvm/test/CodeGen/X86/vectorcall.ll
View File

@ -103,7 +103,7 @@ entry:
}
; CHECK-LABEL: test_mixed_1
; CHECK: movaps %xmm1, 16(%{{(e|r)}}sp)
; CHECK: movaps %xmm1, %xmm0
; CHECK: movaps 16(%{{(e|r)}}sp), %xmm0
; CHECK: ret{{q|l}}
define x86_vectorcallcc <4 x float> @test_mixed_2(%struct.HVA4 inreg %a, %struct.HVA4* %b, <4 x float> %c) {
@ -149,7 +149,7 @@ entry:
}
; CHECK-LABEL: test_mixed_5
; CHECK: movaps %xmm5, 16(%{{(e|r)}}sp)
; CHECK: movaps %xmm5, %xmm0
; CHECK: movaps 16(%{{(e|r)}}sp), %xmm0
; CHECK: ret{{[ql]}}
define x86_vectorcallcc %struct.HVA4 @test_mixed_6(%struct.HVA4 inreg %a, %struct.HVA4* %b) {

157
llvm/test/CodeGen/X86/win32-eh.ll
View File

@ -27,26 +27,23 @@ catch:
; CHECK-LABEL: _use_except_handler3:
; CHECK: pushl %ebp
; CHECK-NEXT: movl %esp, %ebp
; CHECK-NEXT: pushl %ebx
; CHECK-NEXT: pushl %edi
; CHECK-NEXT: pushl %esi
; CHECK-NEXT: subl ${{[0-9]+}}, %esp
; CHECK-NEXT: movl %esp, -36(%ebp)
; CHECK-NEXT: movl $-1, -16(%ebp)
; CHECK-NEXT: movl $L__ehtable$use_except_handler3, -20(%ebp)
; CHECK-NEXT: leal -28(%ebp), %[[node:[^ ,]*]]
; CHECK-NEXT: movl $__except_handler3, -24(%ebp)
; CHECK-NEXT: movl %fs:0, %[[next:[^ ,]*]]
; CHECK-NEXT: movl %[[next]], -28(%ebp)
; CHECK-NEXT: movl %[[node]], %fs:0
; CHECK-NEXT: movl $0, -16(%ebp)
; CHECK-NEXT: calll _may_throw_or_crash
; CHECK: movl %esp, %ebp
; CHECK: pushl %ebx
; CHECK: pushl %edi
; CHECK: pushl %esi
; CHECK: subl ${{[0-9]+}}, %esp
; CHECK: movl $-1, -16(%ebp)
; CHECK: movl $L__ehtable$use_except_handler3, -20(%ebp)
; CHECK: leal -28(%ebp), %[[node:[^ ,]*]]
; CHECK: movl $__except_handler3, -24(%ebp)
; CHECK: movl %fs:0, %[[next:[^ ,]*]]
; CHECK: movl %[[next]], -28(%ebp)
; CHECK: movl %[[node]], %fs:0
; CHECK: calll _may_throw_or_crash
; CHECK: movl -28(%ebp), %[[next:[^ ,]*]]
; CHECK-NEXT: movl %[[next]], %fs:0
; CHECK: movl %[[next]], %fs:0
; CHECK: retl
; CHECK-NEXT: LBB1_2: # %catch{{$}}
; CHECK: LBB1_2: # %catch{{$}}
; CHECK: .section .xdata,"dr"
; CHECK-LABEL: L__ehtable$use_except_handler3:
@ -69,37 +66,23 @@ catch:
; CHECK-LABEL: _use_except_handler4:
; CHECK: pushl %ebp
; CHECK-NEXT: movl %esp, %ebp
; CHECK-NEXT: pushl %ebx
; CHECK-NEXT: pushl %edi
; CHECK-NEXT: pushl %esi
; CHECK-NEXT: subl ${{[0-9]+}}, %esp
; CHECK-NEXT: movl %ebp, %eax
; CHECK-NEXT: movl %esp, -36(%ebp)
; CHECK-NEXT: movl $-2, -16(%ebp)
; CHECK-NEXT: movl $L__ehtable$use_except_handler4, %[[lsda:[^ ,]*]]
; CHECK-NEXT: movl ___security_cookie, %[[seccookie:[^ ,]*]]
; CHECK-NEXT: xorl %[[seccookie]], %[[lsda]]
; CHECK-NEXT: movl %[[lsda]], -20(%ebp)
; CHECK-NEXT: xorl %[[seccookie]], %[[tmp1:[^ ,]*]]
; CHECK-NEXT: movl %[[tmp1]], -40(%ebp)
; CHECK-NEXT: leal -28(%ebp), %[[node:[^ ,]*]]
; CHECK-NEXT: movl $__except_handler4, -24(%ebp)
; CHECK-NEXT: movl %fs:0, %[[next:[^ ,]*]]
; CHECK-NEXT: movl %[[next]], -28(%ebp)
; CHECK-NEXT: movl %[[node]], %fs:0
; CHECK-NEXT: movl $0, -16(%ebp)
; CHECK-NEXT: calll _may_throw_or_crash
; CHECK: movl %esp, %ebp
; CHECK: subl ${{[0-9]+}}, %esp
; CHECK: movl %esp, -36(%ebp)
; CHECK: movl $-2, -16(%ebp)
; CHECK: movl $L__ehtable$use_except_handler4, %[[lsda:[^ ,]*]]
; CHECK: xorl ___security_cookie, %[[lsda]]
; CHECK: movl %[[lsda]], -20(%ebp)
; CHECK: leal -28(%ebp), %[[node:[^ ,]*]]
; CHECK: movl $__except_handler4, -24(%ebp)
; CHECK: movl %fs:0, %[[next:[^ ,]*]]
; CHECK: movl %[[next]], -28(%ebp)
; CHECK: movl %[[node]], %fs:0
; CHECK: calll _may_throw_or_crash
; CHECK: movl -28(%ebp), %[[next:[^ ,]*]]
; CHECK-NEXT: movl %[[next]], %fs:0
; CHECK-NEXT: addl $28, %esp
; CHECK-NEXT: popl %esi
; CHECK-NEXT: popl %edi
; CHECK-NEXT: popl %ebx
; CHECK-NEXT: popl %ebp
; CHECK-NEXT: retl
; CHECK-NEXT: LBB2_2: # %catch{{$}}
; CHECK: movl %[[next]], %fs:0
; CHECK: retl
; CHECK: LBB2_2: # %catch{{$}}
; CHECK: .section .xdata,"dr"
; CHECK-LABEL: L__ehtable$use_except_handler4:
@ -126,33 +109,26 @@ catch:
; CHECK-LABEL: _use_except_handler4_ssp:
; CHECK: pushl %ebp
; CHECK-NEXT: movl %esp, %ebp
; CHECK-NEXT: pushl %ebx
; CHECK-NEXT: pushl %edi
; CHECK-NEXT: pushl %esi
; CHECK-NEXT: subl ${{[0-9]+}}, %esp
; CHECK-NEXT: movl %ebp, %[[ehguard:[^ ,]*]]
; CHECK-NEXT: movl %esp, -36(%ebp)
; CHECK-NEXT: movl $-2, -16(%ebp)
; CHECK-NEXT: movl $L__ehtable$use_except_handler4_ssp, %[[lsda:[^ ,]*]]
; CHECK-NEXT: movl ___security_cookie, %[[seccookie:[^ ,]*]]
; CHECK-NEXT: xorl %[[seccookie]], %[[lsda]]
; CHECK-NEXT: movl %[[lsda]], -20(%ebp)
; CHECK-NEXT: xorl %[[seccookie]], %[[ehguard]]
; CHECK-NEXT: movl %[[ehguard]], -40(%ebp)
; CHECK-NEXT: leal -28(%ebp), %[[node:[^ ,]*]]
; CHECK-NEXT: movl $__except_handler4, -24(%ebp)
; CHECK-NEXT: movl %fs:0, %[[next:[^ ,]*]]
; CHECK-NEXT: movl %[[next]], -28(%ebp)
; CHECK-NEXT: movl %[[node]], %fs:0
; CHECK-NEXT: movl $0, -16(%ebp)
; CHECK-NEXT: calll _may_throw_or_crash
; CHECK: movl %esp, %ebp
; CHECK: subl ${{[0-9]+}}, %esp
; CHECK: movl %ebp, %[[ehguard:[^ ,]*]]
; CHECK: movl %esp, -36(%ebp)
; CHECK: movl $-2, -16(%ebp)
; CHECK: movl $L__ehtable$use_except_handler4_ssp, %[[lsda:[^ ,]*]]
; CHECK: xorl ___security_cookie, %[[lsda]]
; CHECK: movl %[[lsda]], -20(%ebp)
; CHECK: xorl ___security_cookie, %[[ehguard]]
; CHECK: movl %[[ehguard]], -40(%ebp)
; CHECK: leal -28(%ebp), %[[node:[^ ,]*]]
; CHECK: movl $__except_handler4, -24(%ebp)
; CHECK: movl %fs:0, %[[next:[^ ,]*]]
; CHECK: movl %[[next]], -28(%ebp)
; CHECK: movl %[[node]], %fs:0
; CHECK: calll _may_throw_or_crash
; CHECK: movl -28(%ebp), %[[next:[^ ,]*]]
; CHECK-NEXT: movl %[[next]], %fs:0
; CHECK: movl %[[next]], %fs:0
; CHECK: retl
; CHECK-NEXT: [[catch:[^ ,]*]]: # %catch{{$}}
; CHECK: [[catch:[^ ,]*]]: # %catch{{$}}
; CHECK: .section .xdata,"dr"
; CHECK-LABEL: L__ehtable$use_except_handler4_ssp:
@ -179,26 +155,23 @@ catch:
; CHECK-LABEL: _use_CxxFrameHandler3:
; CHECK: pushl %ebp
; CHECK-NEXT: movl %esp, %ebp
; CHECK-NEXT: pushl %ebx
; CHECK-NEXT: pushl %edi
; CHECK-NEXT: pushl %esi
; CHECK-NEXT: subl ${{[0-9]+}}, %esp
; CHECK-NEXT: movl %esp, -28(%ebp)
; CHECK-NEXT: movl $-1, -16(%ebp)
; CHECK-NEXT: leal -24(%ebp), %[[node:[^ ,]*]]
; CHECK-NEXT: movl $___ehhandler$use_CxxFrameHandler3, -20(%ebp)
; CHECK-NEXT: movl %fs:0, %[[next:[^ ,]*]]
; CHECK-NEXT: movl %[[next]], -24(%ebp)
; CHECK-NEXT: movl %[[node]], %fs:0
; CHECK-NEXT: movl $0, -16(%ebp)
; CHECK-NEXT: calll _may_throw_or_crash
; CHECK: movl %esp, %ebp
; CHECK: subl ${{[0-9]+}}, %esp
; CHECK: movl %esp, -28(%ebp)
; CHECK: movl $-1, -16(%ebp)
; CHECK: leal -24(%ebp), %[[node:[^ ,]*]]
; CHECK: movl $___ehhandler$use_CxxFrameHandler3, -20(%ebp)
; CHECK: movl %fs:0, %[[next:[^ ,]*]]
; CHECK: movl %[[next]], -24(%ebp)
; CHECK: movl %[[node]], %fs:0
; CHECK: movl $0, -16(%ebp)
; CHECK: calll _may_throw_or_crash
; CHECK: movl -24(%ebp), %[[next:[^ ,]*]]
; CHECK-NEXT: movl %[[next]], %fs:0
; CHECK: movl %[[next]], %fs:0
; CHECK: retl
; CHECK: .section .xdata,"dr"
; CHECK-NEXT: .p2align 2
; CHECK: .p2align 2
; CHECK-LABEL: L__ehtable$use_CxxFrameHandler3:
; CHECK-NEXT: .long 429065506
; CHECK-NEXT: .long 2
@ -212,8 +185,8 @@ catch:
; CHECK-LABEL: ___ehhandler$use_CxxFrameHandler3:
; CHECK: movl $L__ehtable$use_CxxFrameHandler3, %eax
; CHECK-NEXT: jmp ___CxxFrameHandler3 # TAILCALL
; CHECK: jmp ___CxxFrameHandler3 # TAILCALL
; CHECK: .safeseh __except_handler3
; CHECK-NEXT: .safeseh __except_handler4
; CHECK-NEXT: .safeseh ___ehhandler$use_CxxFrameHandler3
; CHECK: .safeseh __except_handler4
; CHECK: .safeseh ___ehhandler$use_CxxFrameHandler3

2
llvm/test/CodeGen/XCore/varargs.ll
View File

@ -26,10 +26,10 @@ entry:
; CHECK-LABEL: test_vararg
; CHECK: extsp 6
; CHECK: stw lr, sp[1]
; CHECK: stw r3, sp[6]
; CHECK: stw r0, sp[3]
; CHECK: stw r1, sp[4]
; CHECK: stw r2, sp[5]
; CHECK: stw r3, sp[6]
; CHECK: ldaw r0, sp[3]
; CHECK: stw r0, sp[2]
%list = alloca i8*, align 4