Revert "[LSV] Refactoring + supporting bitcasts to a type of different size"

This reverts commit r337489.
It causes asserts to fire in some TensorFlow tests, e.g.
tensorflow/compiler/tests/gather_test.py on GPU.

Example stack trace:
Start test case: GatherTest.testHigherRank
assertion failed at third_party/llvm/llvm/lib/Support/APInt.cpp:819 in llvm::APInt llvm::APInt::trunc(unsigned int) const: width && "Can't truncate to 0 bits"
    @     0x5559446ebe10  __assert_fail
    @     0x55593ef32f5e  llvm::APInt::trunc()
    @     0x55593d78f86e  (anonymous namespace)::Vectorizer::lookThroughComplexAddresses()
    @     0x55593d78f2bc  (anonymous namespace)::Vectorizer::areConsecutivePointers()
    @     0x55593d78d128  (anonymous namespace)::Vectorizer::isConsecutiveAccess()
    @     0x55593d78c926  (anonymous namespace)::Vectorizer::vectorizeInstructions()
    @     0x55593d78c221  (anonymous namespace)::Vectorizer::vectorizeChains()
    @     0x55593d78b948  (anonymous namespace)::Vectorizer::run()
    @     0x55593d78b725  (anonymous namespace)::LoadStoreVectorizer::runOnFunction()
    @     0x55593edf4b17  llvm::FPPassManager::runOnFunction()
    @     0x55593edf4e55  llvm::FPPassManager::runOnModule()
    @     0x55593edf563c  (anonymous namespace)::MPPassManager::runOnModule()
    @     0x55593edf5137  llvm::legacy::PassManagerImpl::run()
    @     0x55593edf5b71  llvm::legacy::PassManager::run()
    @     0x55593ced250d  xla::gpu::IrDumpingPassManager::run()
    @     0x55593ced5033  xla::gpu::(anonymous namespace)::EmitModuleToPTX()
    @     0x55593ced40ba  xla::gpu::(anonymous namespace)::CompileModuleToPtx()
    @     0x55593ced33d0  xla::gpu::CompileToPtx()
    @     0x55593b26b2a2  xla::gpu::NVPTXCompiler::RunBackend()
    @     0x55593b21f973  xla::Service::BuildExecutable()
    @     0x555938f44e64  xla::LocalService::CompileExecutable()
    @     0x555938f30a85  xla::LocalClient::Compile()
    @     0x555938de3c29  tensorflow::XlaCompilationCache::BuildExecutable()
    @     0x555938de4e9e  tensorflow::XlaCompilationCache::CompileImpl()
    @     0x555938de3da5  tensorflow::XlaCompilationCache::Compile()
    @     0x555938c5d962  tensorflow::XlaLocalLaunchBase::Compute()
    @     0x555938c68151  tensorflow::XlaDevice::Compute()
    @     0x55593f389e1f  tensorflow::(anonymous namespace)::ExecutorState::Process()
    @     0x55593f38a625  tensorflow::(anonymous namespace)::ExecutorState::ScheduleReady()::$_1::operator()()
*** SIGABRT received by PID 7798 (TID 7837) from PID 7798; ***

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337541 91177308-0d34-0410-b5e6-96231b3b80d8

2 files changed, 4 insertions, 35 deletions

diff --git a/test/CodeGen/X86/loadStore_vectorizer.ll b/test/CodeGen/X86/loadStore_vectorizer.ll
index 48f31563c24..03f6ccce6c4 100644
--- a/test/CodeGen/X86/loadStore_vectorizer.ll
+++ b/test/CodeGen/X86/loadStore_vectorizer.ll
@@ -1,9 +1,8 @@
-; RUN: opt -mtriple x86_64-- -load-store-vectorizer < %s -S | FileCheck %s
+; RUN: opt -load-store-vectorizer < %s -S | FileCheck %s
 
 %struct_render_pipeline_state = type opaque
 
-define fastcc void @test1(%struct_render_pipeline_state addrspace(1)* %pso) unnamed_addr {
-; CHECK-LABEL: @test1
+define fastcc void @main(%struct_render_pipeline_state addrspace(1)* %pso) unnamed_addr {
 ; CHECK: load i16
 ; CHECK: load i16
 entry:
@@ -15,16 +14,3 @@ entry:
   %tmp4 = load i16, i16 addrspace(1)* %tmp3, align 2
   ret void
 }
-
-define fastcc void @test2(%struct_render_pipeline_state addrspace(1)* %pso) unnamed_addr {
-; CHECK-LABEL: @test2
-; CHECK: load <2 x i16>
-entry:
-  %tmp = bitcast %struct_render_pipeline_state addrspace(1)* %pso to i16 addrspace(1)*
-  %tmp1 = load i16, i16 addrspace(1)* %tmp, align 2
-  %tmp2 = bitcast %struct_render_pipeline_state addrspace(1)* %pso to i8 addrspace(1)*
-  %sunkaddr51 = getelementptr i8, i8 addrspace(1)* %tmp2, i64 2
-  %tmp3 = bitcast i8 addrspace(1)* %sunkaddr51 to i16 addrspace(1)*
-  %tmp4 = load i16, i16 addrspace(1)* %tmp3, align 2
-  ret void
-}
diff --git a/test/Transforms/LoadStoreVectorizer/AMDGPU/gep-bitcast.ll b/test/Transforms/LoadStoreVectorizer/AMDGPU/gep-bitcast.ll
index a9c3fbf7b64..b67dc058453 100644
--- a/test/Transforms/LoadStoreVectorizer/AMDGPU/gep-bitcast.ll
+++ b/test/Transforms/LoadStoreVectorizer/AMDGPU/gep-bitcast.ll
@@ -56,8 +56,8 @@ define void @vect_zext_bitcast_i8_st1_to_i32_idx(i8 addrspace(1)* %arg1, i32 %ba
   ret void
 }
 
+; TODO: This can be vectorized, but currently vectorizer unable to do it.
 ; CHECK-LABEL: @vect_zext_bitcast_i8_st4_to_i32_idx
-; CHECK: load <4 x i32>
 define void @vect_zext_bitcast_i8_st4_to_i32_idx(i8 addrspace(1)* %arg1, i32 %base) {
   %add1 = add nuw i32 %base, 0
   %zext1 = zext i32 %add1 to i64
@@ -74,27 +74,10 @@ define void @vect_zext_bitcast_i8_st4_to_i32_idx(i8 addrspace(1)* %arg1, i32 %ba
   %gep3 = getelementptr inbounds i8, i8 addrspace(1)* %arg1, i64 %zext3
   %f2i3 = bitcast i8 addrspace(1)* %gep3 to i32 addrspace(1)*
   %load3 = load i32, i32 addrspace(1)* %f2i3, align 4
-  %add4 = add nuw i32 %base, 12
+  %add4 = add nuw i32 %base, 16
   %zext4 = zext i32 %add4 to i64
   %gep4 = getelementptr inbounds i8, i8 addrspace(1)* %arg1, i64 %zext4
   %f2i4 = bitcast i8 addrspace(1)* %gep4 to i32 addrspace(1)*
   %load4 = load i32, i32 addrspace(1)* %f2i4, align 4
   ret void
 }
-
-; CHECK-LABEL: @vect_zext_bitcast_negative_ptr_delta
-; CHECK: load <2 x i32>
-define void @vect_zext_bitcast_negative_ptr_delta(i32 addrspace(1)* %p, i32 %base) {
-  %p.bitcasted = bitcast i32 addrspace(1)* %p to i16 addrspace(1)*
-  %a.offset = add nuw i32 %base, 4
-  %t.offset.zexted = zext i32 %base to i64
-  %a.offset.zexted = zext i32 %a.offset to i64
-  %t.ptr = getelementptr inbounds i16, i16 addrspace(1)* %p.bitcasted, i64 %t.offset.zexted
-  %a.ptr = getelementptr inbounds i16, i16 addrspace(1)* %p.bitcasted, i64 %a.offset.zexted
-  %b.ptr = getelementptr inbounds i16, i16 addrspace(1)* %t.ptr, i64 6
-  %a.ptr.bitcasted = bitcast i16 addrspace(1)* %a.ptr to i32 addrspace(1)*
-  %b.ptr.bitcasted = bitcast i16 addrspace(1)* %b.ptr to i32 addrspace(1)*
-  %a.val = load i32, i32 addrspace(1)* %a.ptr.bitcasted
-  %b.val = load i32, i32 addrspace(1)* %b.ptr.bitcasted
-  ret void
-}