Merged master:4589dd924dfc into amd-gfx:9a4c659a6ab9

Local branch amd-gfx 9a4c659 Merged master:891759db73f into amd-gfx:64f77d560c5
Remote branch master 4589dd9 [mlir][DialectConversion] Enable deeper integration of type conversions

lld/test/CMakeLists.txt

@@ -34,7 +34,7 @@ configure_lit_site_cfg(
 set(LLD_TEST_DEPS lld)
 if (NOT LLD_BUILT_STANDALONE)
   list(APPEND LLD_TEST_DEPS
-    FileCheck count llc llvm-ar llvm-as llvm-bcanalyzer llvm-config llvm-cvtres
+    FileCheck count extract llc llvm-ar llvm-as llvm-bcanalyzer llvm-config llvm-cvtres
     llvm-dis llvm-dwarfdump llvm-lib llvm-lipo llvm-mc llvm-nm llvm-objcopy
     llvm-objdump llvm-pdbutil llvm-readelf llvm-readobj llvm-strip not obj2yaml
     opt yaml2obj

lld/test/ELF/linkerscript/noload.s

@@ -1,11 +1,7 @@
 # REQUIRES: x86
-# RUN: llvm-mc -filetype=obj -triple=x86_64-unknown-linux %s -o %t.o
-# RUN: echo "SECTIONS { \
-# RUN:        .data_noload_a (NOLOAD) : { *(.data_noload_a) } \
-# RUN:        .data_noload_b (0x10000) (NOLOAD) : { *(.data_noload_b) } \
-# RUN:        .no_input_sec_noload (NOLOAD) : { . += 1; } \
-# RUN:        .text (0x20000) : { *(.text) } };" > %t.script
-# RUN: ld.lld -o %t --script %t.script %t.o
+# RUN: extract asm %s -o %t.s && extract lds %s -o %t.lds
+# RUN: llvm-mc -filetype=obj -triple=x86_64 %t.s -o %t.o
+# RUN: ld.lld -o %t --script %t.lds %t.o
 # RUN: llvm-readelf -S -l %t | FileCheck %s
 
 # CHECK:      Name                 Type   Address          Off               Size
@@ -16,6 +12,7 @@
 # CHECK:      Type Offset   VirtAddr           PhysAddr
 # CHECK-NEXT: LOAD 0x001000 0x0000000000020000 0x0000000000020000
 
+#--- asm
 .section .text,"ax",@progbits
   nop
 
@@ -24,3 +21,11 @@
 
 .section .data_noload_b,"aw",@progbits
 .zero 4096
+
+#--- lds
+SECTIONS {
+  .data_noload_a (NOLOAD) : { *(.data_noload_a) }
+  .data_noload_b (0x10000) (NOLOAD) : { *(.data_noload_b) }
+  .no_input_sec_noload (NOLOAD) : { . += 1; }
+  .text (0x20000) : { *(.text) }
+}

lld/test/lit.cfg.py

@@ -39,9 +39,9 @@
 llvm_config.use_lld()
 
 tool_patterns = [
-    'llc', 'llvm-as', 'llvm-mc', 'llvm-nm', 'llvm-objdump', 'llvm-pdbutil',
-    'llvm-dwarfdump', 'llvm-readelf', 'llvm-readobj', 'obj2yaml', 'yaml2obj',
-    'opt', 'llvm-dis']
+    'extract', 'llc', 'llvm-as', 'llvm-mc', 'llvm-nm', 'llvm-objdump',
+    'llvm-pdbutil', 'llvm-dwarfdump', 'llvm-readelf', 'llvm-readobj',
+    'obj2yaml', 'yaml2obj', 'opt', 'llvm-dis']
 
 llvm_config.add_tool_substitutions(tool_patterns)
 
@@ -87,7 +87,7 @@
 # Indirectly check if the mt.exe Microsoft utility exists by searching for
 # cvtres, which always accompanies it.  Alternatively, check if we can use
 # libxml2 to merge manifests.
-if (lit.util.which('cvtres', config.environment['PATH']) or 
+if (lit.util.which('cvtres', config.environment['PATH']) or
         config.llvm_libxml2_enabled):
     config.available_features.add('manifest_tool')
 

llvm/docs/TestingGuide.rst

@@ -271,8 +271,27 @@ adding your code there instead of creating a new file.
 Extra files
 -----------
 
-If your test requires extra files besides the file containing the ``RUN:``
-lines, the idiomatic place to put them is in a subdirectory ``Inputs``.
+If your test requires extra files besides the file containing the ``RUN:`` lines
+and the extra files are small, consider specifying them in the same file and
+using ``extract`` to extract them. For example,
+
+.. code-block:: llvm
+
+  ; RUN: extract b %s -o %tb.ll
+  ; RUN: extract a %s | llvm-link - %tb.ll -S | FileCheck %s
+
+  ; CHECK: ...
+
+  ;--- a
+  ...
+  ;--- b
+  ...
+
+The parts are separated by the regex ``^(.|//)--- <part>``. By default the
+extracted content has leading empty lines to preserve line numbers. Specify
+``--no-leading-lines`` to drop leading lines.
+
+If the extra files are large, the idiomatic place to put them is in a subdirectory ``Inputs``.
 You can then refer to the extra files as ``%S/Inputs/foo.bar``.
 
 For example, consider ``test/Linker/ident.ll``. The directory structure is

llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp

@@ -4912,7 +4912,8 @@ SDValue DAGTypeLegalizer::GenWidenVectorLoads(SmallVectorImpl<SDValue> &LdChain,
 
   int LdWidth = LdVT.getSizeInBits();
   int WidthDiff = WidenWidth - LdWidth;
-  // Allow wider loads.
+  // Allow wider loads if they are sufficiently aligned to avoid memory faults
+  // and if the original load is simple.
   unsigned LdAlign = (!LD->isSimple()) ? 0 : LD->getAlignment();
 
   // Find the vector type that can load from.
@@ -4964,19 +4965,6 @@ SDValue DAGTypeLegalizer::GenWidenVectorLoads(SmallVectorImpl<SDValue> &LdChain,
                       LD->getPointerInfo().getWithOffset(Offset),
                       LD->getOriginalAlign(), MMOFlags, AAInfo);
       LdChain.push_back(L.getValue(1));
-      if (L->getValueType(0).isVector() && NewVTWidth >= LdWidth) {
-        // Later code assumes the vector loads produced will be mergeable, so we
-        // must pad the final entry up to the previous width. Scalars are
-        // combined separately.
-        SmallVector<SDValue, 16> Loads;
-        Loads.push_back(L);
-        unsigned size = L->getValueSizeInBits(0);
-        while (size < LdOp->getValueSizeInBits(0)) {
-          Loads.push_back(DAG.getUNDEF(L->getValueType(0)));
-          size += L->getValueSizeInBits(0);
-        }
-        L = DAG.getNode(ISD::CONCAT_VECTORS, dl, LdOp->getValueType(0), Loads);
-      }
     } else {
       L = DAG.getLoad(NewVT, dl, Chain, BasePtr,
                       LD->getPointerInfo().getWithOffset(Offset),
@@ -5017,8 +5005,17 @@ SDValue DAGTypeLegalizer::GenWidenVectorLoads(SmallVectorImpl<SDValue> &LdChain,
     EVT NewLdTy = LdOps[i].getValueType();
     if (NewLdTy != LdTy) {
       // Create a larger vector.
+      unsigned NumOps = NewLdTy.getSizeInBits() / LdTy.getSizeInBits();
+      assert(NewLdTy.getSizeInBits() % LdTy.getSizeInBits() == 0);
+      SmallVector<SDValue, 16> WidenOps(NumOps);
+      unsigned j = 0;
+      for (; j != End-Idx; ++j)
+        WidenOps[j] = ConcatOps[Idx+j];
+      for (; j != NumOps; ++j)
+        WidenOps[j] = DAG.getUNDEF(LdTy);
+
       ConcatOps[End-1] = DAG.getNode(ISD::CONCAT_VECTORS, dl, NewLdTy,
-                                     makeArrayRef(&ConcatOps[Idx], End - Idx));
+                                     WidenOps);
       Idx = End - 1;
       LdTy = NewLdTy;
     }

llvm/test/CMakeLists.txt

@@ -52,6 +52,7 @@ set(LLVM_TEST_DEPENDS
           UnitTests
           bugpoint
           count
+          extract
           llc
           lli
           lli-child-target

llvm/test/CodeGen/X86/pr46820.ll

@@ -0,0 +1,47 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=x86_64-unknown-linux-gnu -mattr=avx512f | FileCheck %s
+
+; The alignment of 16 causes type legalization to split this as 3 loads,
+; v16f32, v4f32, and v4f32. This loads 24 elements, but the load is aligned
+; to 16 bytes so this i safe. There was an issue with type legalization building
+; the proper concat_vectors for this because the two v4f32s don't add up to
+; v16f32 and require padding.
+
+define <23 x float> @load23(<23 x float>* %p) {
+; CHECK-LABEL: load23:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    movq %rdi, %rax
+; CHECK-NEXT:    vmovups 64(%rsi), %ymm0
+; CHECK-NEXT:    vmovups (%rsi), %zmm1
+; CHECK-NEXT:    vmovaps 64(%rsi), %xmm2
+; CHECK-NEXT:    vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero
+; CHECK-NEXT:    vmovss %xmm3, 88(%rdi)
+; CHECK-NEXT:    vmovaps %xmm2, 64(%rdi)
+; CHECK-NEXT:    vmovaps %zmm1, (%rdi)
+; CHECK-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; CHECK-NEXT:    vmovlps %xmm0, 80(%rdi)
+; CHECK-NEXT:    vzeroupper
+; CHECK-NEXT:    retq
+  %t0 = load <23 x float>, <23 x float>* %p, align 16
+  ret <23 x float> %t0
+}
+
+; Same test as above with minimal alignment just to demonstrate the different
+; codegen.
+define <23 x float> @load23_align_1(<23 x float>* %p) {
+; CHECK-LABEL: load23_align_1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    movq %rdi, %rax
+; CHECK-NEXT:    vmovups (%rsi), %zmm0
+; CHECK-NEXT:    vmovups 64(%rsi), %xmm1
+; CHECK-NEXT:    movq 80(%rsi), %rcx
+; CHECK-NEXT:    vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
+; CHECK-NEXT:    vmovss %xmm2, 88(%rdi)
+; CHECK-NEXT:    movq %rcx, 80(%rdi)
+; CHECK-NEXT:    vmovaps %xmm1, 64(%rdi)
+; CHECK-NEXT:    vmovaps %zmm0, (%rdi)
+; CHECK-NEXT:    vzeroupper
+; CHECK-NEXT:    retq
+  %t0 = load <23 x float>, <23 x float>* %p, align 1
+  ret <23 x float> %t0
+}

llvm/test/lit.cfg.py

@@ -130,6 +130,7 @@ def get_asan_rtlib():
 config.llvm_locstats_used = os.path.exists(llvm_locstats_tool)
 
 tools = [
+    ToolSubst('%extract', FindTool('extract')),
     ToolSubst('%lli', FindTool('lli'), post='.', extra_args=lli_args),
     ToolSubst('%llc_dwarf', FindTool('llc'), extra_args=llc_args),
     ToolSubst('%go', config.go_executable, unresolved='ignore'),

llvm/test/tools/extract/Inputs/basic-aa.txt

@@ -0,0 +1,6 @@
+
+
+
+aa
+; BB-NOT: {{.}}
+; BB: {{^}}bb{{$}}

llvm/test/tools/extract/Inputs/basic-bb.txt

@@ -0,0 +1,10 @@
+
+
+
+
+
+
+
+bb
+
+// CC: // Comments are preserved.

llvm/test/tools/extract/basic.test

@@ -0,0 +1,32 @@
+# AA-NOT: {{.}}
+# AA: {{^}}aa{{$}}
+#--- aa
+aa
+; BB-NOT: {{.}}
+; BB: {{^}}bb{{$}}
+;--- bb
+bb
+
+// CC: // Comments are preserved.
+//--- cc
+cc
+// Comments are preserved.
+;--- dup
+;--- dup
+
+# RUN: extract aa %s | diff %S/Inputs/basic-aa.txt -
+# RUN: extract bb - < %s | diff %S/Inputs/basic-bb.txt -
+# RUN: extract cc %s -o %t
+# RUN: FileCheck %s --check-prefix=CC < %t
+
+# RUN: not %extract aa 2>&1 | FileCheck %s --check-prefix=NO_INPUT
+
+# NO_INPUT: extract: error: input filename is not specified
+
+# RUN: not %extract dup %s 2>&1 | FileCheck %s --check-prefix=DUP
+
+# DUP: extract: error: {{.*}}.test: ';--- dup' occurs more than once
+
+# RUN: not %extract not_exist %s 2>&1 | FileCheck %s --check-prefix=NOT_EXIST
+
+# NOT_EXIST: extract: error: {{.*}}.test: ';--- not_exist' was not found

llvm/test/tools/extract/help.test

@@ -0,0 +1,5 @@
+RUN: extract --help 2>&1 | FileCheck --implicit-check-not='General Options:' %s
+CHECK: OVERVIEW: Split input {{.*}}
+CHECK: Generic Options:
+CHECK: extract Options:
+CHECK:   -o

llvm/test/tools/extract/no-leading-lines.test

@@ -0,0 +1,10 @@
+## With --no-leading-lines, don't add leading lines (which is used to preserve line numbers).
+
+# RUN: extract --no-leading-lines input %s -o %t
+# RUN: count 1 < %t
+# RUN: FileCheck %s < %t
+
+# CHECK: input
+
+#--- input
+input

llvm/test/tools/gold/X86/multiple-sections.ll

@@ -1,10 +1,8 @@
-; RUN: echo ".text.tin" > %t_order_lto.txt
-; RUN: echo ".text._start" >> %t_order_lto.txt
-; RUN: echo ".text.pat" >> %t_order_lto.txt
-; RUN: llvm-as %s -o %t.o
+; RUN: extract order %s -o %t.order
+; RUN: extract ir %s | llvm-as -o %t.o
 ; RUN: %gold -plugin %llvmshlibdir/LLVMgold%shlibext \
 ; RUN:     -m elf_x86_64 -o %t.exe %t.o \
-; RUN:     --section-ordering-file=%t_order_lto.txt
+; RUN:     --section-ordering-file=%t.order
 ; RUN: llvm-readelf -s %t.exe | FileCheck %s
 
 ; Check that the order of the sections is tin -> _start -> pat.
@@ -13,6 +11,12 @@
 ; CHECK:      00000000004000b0     1 FUNC    LOCAL  DEFAULT    1 tin
 ; CHECK:      00000000004000c0    15 FUNC    GLOBAL DEFAULT    1 _start
 
+;--- order
+.text.tin
+.text._start
+.text.pat
+
+;--- ir
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 

llvm/test/tools/llvm-objcopy/ELF/strip-symbol.test

@@ -1,19 +1,24 @@
-# RUN: yaml2obj %s -o %t
+# RUN: extract yaml %s | yaml2obj - -o %t
 # RUN: llvm-objcopy --strip-symbol baz -N bar %t %t2
 # RUN: llvm-readobj --symbols --sections %t2 | FileCheck %s
 # RUN: llvm-strip --strip-symbol baz -N bar %t -o %t3
 # RUN: cmp %t2 %t3
 # RUN: llvm-strip --regex --strip-symbol '^b.*' -N bar %t -o %t4
 # RUN: cmp %t3 %t4
-# RUN: echo " bar # bar" > %t-list.txt
-# RUN: echo " baz # baz" >> %t-list.txt
-# RUN: echo " # no symbol" >> %t-list.txt
-# RUN: llvm-objcopy --strip-symbols %t-list.txt %t %t5
+# RUN: extract list1 %s -o %t-list.txt && llvm-objcopy --strip-symbols %t-list.txt %t %t5
 # RUN: cmp %t3 %t5
-# RUN: echo "b.* # bar & baz" > %t-list2.txt
-# RUN: llvm-objcopy --regex --strip-symbols %t-list2.txt %t %t6
+# RUN: extract list2 %s -o %t-list2.txt && llvm-objcopy --regex --strip-symbols %t-list2.txt %t %t6
 # RUN: cmp %t3 %t6
 
+#--- list1
+bar # bar
+baz # baz
+# no symbol
+
+#--- list2
+b.* # bar & baz
+
+#--- yaml
 !ELF
 FileHeader:
   Class:           ELFCLASS64

llvm/test/tools/llvm-strings/radix.test

@@ -1,15 +1,18 @@
 ## Show that llvm-strings can handle the -t/--radix switch properly.
 
-RUN: echo one > %t
-RUN: echo two >> %t
-RUN: echo three >> %t
-RUN: echo four >> %t
-RUN: echo five >> %t
-RUN: echo six >> %t
-RUN: echo seven >> %t
-RUN: echo eight >> %t
-RUN: echo nine >> %t
-RUN: echo ten >> %t
+RUN: extract --no-leading-lines input %s -o %t
+#--- input
+one
+two
+three
+four
+five
+six
+seven
+eight
+nine
+ten
+#--- end
 
 RUN: llvm-strings %t | FileCheck %s -check-prefix CHECK-NONE --implicit-check-not={{.}}
 RUN: llvm-strings -t d %t | FileCheck %s -check-prefix CHECK-DEC --strict-whitespace --implicit-check-not={{.}}

llvm/tools/extract/.clang-tidy

@@ -0,0 +1,19 @@
+# Almost identical to the top-level .clang-tidy, except that {Member,Parameter,Variable}Case use camelBack.
+Checks: '-*,clang-diagnostic-*,llvm-*,misc-*,-misc-unused-parameters,-misc-non-private-member-variables-in-classes,readability-identifier-naming'
+CheckOptions:
+  - key:             readability-identifier-naming.ClassCase
+    value:           CamelCase
+  - key:             readability-identifier-naming.EnumCase
+    value:           CamelCase
+  - key:             readability-identifier-naming.FunctionCase
+    value:           camelBack
+  - key:             readability-identifier-naming.MemberCase
+    value:           camelBack
+  - key:             readability-identifier-naming.ParameterCase
+    value:           camelBack
+  - key:             readability-identifier-naming.UnionCase
+    value:           CamelCase
+  - key:             readability-identifier-naming.VariableCase
+    value:           camelBack
+  - key:             readability-identifier-naming.IgnoreMainLikeFunctions
+    value:           1

llvm/tools/extract/CMakeLists.txt

@@ -0,0 +1,7 @@
+set(LLVM_LINK_COMPONENTS
+  Support
+  )
+
+add_llvm_tool(extract
+  extract.cpp
+  )