Imported Upstream version 5.18.0.167

Former-commit-id: 289509151e0fee68a1b591a20c9f109c3c789d3a

external/llvm/test/Transforms/LoadStoreVectorizer/NVPTX/lit.local.cfg

@@ -1,3 +0,0 @@
-if not 'NVPTX' in config.root.targets:
-    config.unsupported = True
-

external/llvm/test/Transforms/LoadStoreVectorizer/NVPTX/merge-across-side-effects.ll

@@ -1,209 +0,0 @@
-; RUN: opt -mtriple=nvptx64-nvidia-cuda -load-store-vectorizer -S -o - %s | FileCheck %s
-
-; Check that the load/store vectorizer is willing to move loads/stores across
-; intervening instructions only if it's safe.
-;
-;  - Loads can be moved across instructions that don't write or throw.
-;  - Stores can only be moved across instructions which don't read, write, or
-;    throw.
-
-declare void @fn()
-declare void @fn_nounwind() #0
-declare void @fn_nounwind_writeonly() #1
-declare void @fn_nounwind_readonly() #2
-declare void @fn_writeonly() #3
-declare void @fn_readonly() #4
-declare void @fn_readnone() #5
-
-; CHECK-LABEL: @load_fn
-; CHECK: load
-; CHECK: call void @fn()
-; CHECK: load
-define void @load_fn(i32* %p) #0 {
-  %p.1 = getelementptr i32, i32* %p, i32 1
-
-  %v0 = load i32, i32* %p, align 8
-  call void @fn()
-  %v1 = load i32, i32* %p.1, align 4
-  ret void
-}
-
-; CHECK-LABEL: @load_fn_nounwind
-; CHECK: load
-; CHECK: call void @fn_nounwind()
-; CHECK: load
-define void @load_fn_nounwind(i32* %p) #0 {
-  %p.1 = getelementptr i32, i32* %p, i32 1
-
-  %v0 = load i32, i32* %p, align 8
-  call void @fn_nounwind() #0
-  %v1 = load i32, i32* %p.1, align 4
-  ret void
-}
-
-; CHECK-LABEL: @load_fn_nounwind_writeonly
-; CHECK: load
-; CHECK: call void @fn_nounwind_writeonly()
-; CHECK: load
-define void @load_fn_nounwind_writeonly(i32* %p) #0 {
-  %p.1 = getelementptr i32, i32* %p, i32 1
-
-  %v0 = load i32, i32* %p, align 8
-  call void @fn_nounwind_writeonly() #1
-  %v1 = load i32, i32* %p.1, align 4
-  ret void
-}
-
-; CHECK-LABEL: @load_fn_nounwind_readonly
-; CHECK-DAG: load <2 x i32>
-; CHECK-DAG: call void @fn_nounwind_readonly()
-define void @load_fn_nounwind_readonly(i32* %p) #0 {
-  %p.1 = getelementptr i32, i32* %p, i32 1
-
-  %v0 = load i32, i32* %p, align 8
-  call void @fn_nounwind_readonly() #2
-  %v1 = load i32, i32* %p.1, align 4
-  ret void
-}
-
-; CHECK-LABEL: @load_fn_readonly
-; CHECK: load
-; CHECK: call void @fn_readonly
-; CHECK: load
-define void @load_fn_readonly(i32* %p) #0 {
-  %p.1 = getelementptr i32, i32* %p, i32 1
-
-  %v0 = load i32, i32* %p, align 8
-  call void @fn_readonly() #4
-  %v1 = load i32, i32* %p.1, align 4
-  ret void
-}
-
-; CHECK-LABEL: @load_fn_writeonly
-; CHECK: load
-; CHECK: call void @fn_writeonly()
-; CHECK: load
-define void @load_fn_writeonly(i32* %p) #0 {
-  %p.1 = getelementptr i32, i32* %p, i32 1
-
-  %v0 = load i32, i32* %p, align 8
-  call void @fn_writeonly() #3
-  %v1 = load i32, i32* %p.1, align 4
-  ret void
-}
-
-; CHECK-LABEL: @load_fn_readnone
-; CHECK-DAG: load <2 x i32>
-; CHECK-DAG: call void @fn_readnone()
-define void @load_fn_readnone(i32* %p) #0 {
-  %p.1 = getelementptr i32, i32* %p, i32 1
-
-  %v0 = load i32, i32* %p, align 8
-  call void @fn_readnone() #5
-  %v1 = load i32, i32* %p.1, align 4
-  ret void
-}
-
-; ------------------------------------------------
-; Same tests, but now for stores instead of loads.
-; ------------------------------------------------
-
-; CHECK-LABEL: @store_fn
-; CHECK: store
-; CHECK: call void @fn()
-; CHECK: store
-define void @store_fn(i32* %p) #0 {
-  %p.1 = getelementptr i32, i32* %p, i32 1
-
-  store i32 0, i32* %p
-  call void @fn()
-  store i32 0, i32* %p.1
-  ret void
-}
-
-; CHECK-LABEL: @store_fn_nounwind
-; CHECK: store
-; CHECK: call void @fn_nounwind()
-; CHECK: store
-define void @store_fn_nounwind(i32* %p) #0 {
-  %p.1 = getelementptr i32, i32* %p, i32 1
-
-  store i32 0, i32* %p
-  call void @fn_nounwind() #0
-  store i32 0, i32* %p.1
-  ret void
-}
-
-; CHECK-LABEL: @store_fn_nounwind_writeonly
-; CHECK: store
-; CHECK: call void @fn_nounwind_writeonly()
-; CHECK: store
-define void @store_fn_nounwind_writeonly(i32* %p) #0 {
-  %p.1 = getelementptr i32, i32* %p, i32 1
-
-  store i32 0, i32* %p
-  call void @fn_nounwind_writeonly() #1
-  store i32 0, i32* %p.1
-  ret void
-}
-
-; CHECK-LABEL: @store_fn_nounwind_readonly
-; CHECK: store
-; CHECK: call void @fn_nounwind_readonly()
-; CHECK: store
-define void @store_fn_nounwind_readonly(i32* %p) #0 {
-  %p.1 = getelementptr i32, i32* %p, i32 1
-
-  store i32 0, i32* %p
-  call void @fn_nounwind_readonly() #2
-  store i32 0, i32* %p.1
-  ret void
-}
-
-; CHECK-LABEL: @store_fn_readonly
-; CHECK: store
-; CHECK: call void @fn_readonly
-; CHECK: store
-define void @store_fn_readonly(i32* %p) #0 {
-  %p.1 = getelementptr i32, i32* %p, i32 1
-
-  store i32 0, i32* %p
-  call void @fn_readonly() #4
-  store i32 0, i32* %p.1
-  ret void
-}
-
-; CHECK-LABEL: @store_fn_writeonly
-; CHECK: store
-; CHECK: call void @fn_writeonly()
-; CHECK: store
-define void @store_fn_writeonly(i32* %p) #0 {
-  %p.1 = getelementptr i32, i32* %p, i32 1
-
-  store i32 0, i32* %p
-  call void @fn_writeonly() #3
-  store i32 0, i32* %p.1
-  ret void
-}
-
-; This is the only store idiom we can vectorize.
-; CHECK-LABEL: @store_fn_readnone
-; CHECK-DAG: store <2 x i32>
-; CHECK-DAG: call void @fn_readnone()
-define void @store_fn_readnone(i32* %p) #0 {
-  %p.1 = getelementptr i32, i32* %p, i32 1
-
-  store i32 0, i32* %p, align 8
-  call void @fn_readnone() #5
-  store i32 0, i32* %p.1, align 8
-  ret void
-}
-
-
-attributes #0 = { nounwind }
-attributes #1 = { nounwind writeonly }
-attributes #2 = { nounwind readonly }
-attributes #3 = { writeonly }
-attributes #4 = { readonly }
-; readnone implies nounwind, so no need to test separately
-attributes #5 = { nounwind readnone }

external/llvm/test/Transforms/LoadStoreVectorizer/NVPTX/non-instr-bitcast.ll

@@ -1,14 +0,0 @@
-; RUN: opt -mtriple=nvptx64-nvidia-cuda -load-store-vectorizer -S -o - %s | FileCheck %s
-
-; Load from a constant.  This can be vectorized, but shouldn't crash us.
-
-@global = internal addrspace(1) constant [4 x float] [float 0xBF71111120000000, float 0x3F70410420000000, float 0xBF81111120000000, float 0x3FB5555560000000], align 4
-
-define void @foo() {
-  ; CHECK: load <4 x float>
-  %a = load float, float addrspace(1)* getelementptr inbounds ([4 x float], [4 x float] addrspace(1)* @global, i64 0, i64 0), align 16
-  %b = load float, float addrspace(1)* getelementptr inbounds ([4 x float], [4 x float] addrspace(1)* @global, i64 0, i64 1), align 4
-  %c = load float, float addrspace(1)* getelementptr inbounds ([4 x float], [4 x float] addrspace(1)* @global, i64 0, i64 2), align 4
-  %d = load float, float addrspace(1)* getelementptr inbounds ([4 x float], [4 x float] addrspace(1)* @global, i64 0, i64 3), align 4
-  ret void
-}

external/llvm/test/Transforms/LoadStoreVectorizer/NVPTX/propagate-invariance-metadata.ll

@@ -1,17 +0,0 @@
-; RUN: opt -load-store-vectorizer -march=nvptx64 -mcpu=sm_35 -S < %s | 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-v16:16:16-v32:32:32-v64:64:64-v128:128:128-n16:32:64"
-target triple = "nvptx64-nvidia-cuda"
-
-; CHECK-LABEL: @foo
-define i32 @foo(i32* %ptr) {
-  %ptr1 = getelementptr i32, i32* %ptr, i32 1
-  %p1 = addrspacecast i32* %ptr1 to i32 addrspace(1)*
-  ; CHECK: load <2 x i32>, <2 x i32>* %{{[0-9]+}}, align 8, !invariant.load !0
-  %v0 = load i32, i32* %ptr, align 8, !invariant.load !0
-  %v1 = load i32, i32* %ptr1, align 4, !invariant.load !0
-  %sum = add i32 %v0, %v1
-  ret i32 %sum
-}
-
-!0 = !{}