[clang] Revert "[clang] Avoid memcopy for small structure with padding under … (PR #84230)

Antonio Frighetto via cfe-commits cfe-commits at lists.llvm.org
Wed Mar 6 12:33:29 PST 2024


https://github.com/antoniofrighetto created https://github.com/llvm/llvm-project/pull/84230

…-ftrivial-auto-var-init (#71677)"

This reverts commit afe8b93ffdfef5d8879e1894b9d7dda40dee2b8d.

Fixes regression: https://github.com/llvm/llvm-project/issues/84178.

>From bb22eccc90d0e8cb02be5d4c47a08a17baf4d242 Mon Sep 17 00:00:00 2001
From: Antonio Frighetto <me at antoniofrighetto.com>
Date: Wed, 6 Mar 2024 21:29:13 +0100
Subject: [PATCH] Revert "[clang] Avoid memcopy for small structure with
 padding under -ftrivial-auto-var-init (#71677)"

This reverts commit afe8b93ffdfef5d8879e1894b9d7dda40dee2b8d.

Fixes: https://github.com/llvm/llvm-project/issues/84178.
---
 clang/lib/CodeGen/CGDecl.cpp              | 35 +++++++++--------
 clang/test/CodeGen/aapcs-align.cpp        |  4 +-
 clang/test/CodeGen/aapcs64-align.cpp      |  8 ++--
 clang/test/CodeGenCXX/auto-var-init.cpp   | 47 ++++++++++++-----------
 clang/test/CodeGenOpenCL/amdgpu-printf.cl |  9 +----
 clang/test/OpenMP/bug54082.c              |  4 +-
 6 files changed, 52 insertions(+), 55 deletions(-)

diff --git a/clang/lib/CodeGen/CGDecl.cpp b/clang/lib/CodeGen/CGDecl.cpp
index bbe14ef4c17244..46cfd3f10a3fb7 100644
--- a/clang/lib/CodeGen/CGDecl.cpp
+++ b/clang/lib/CodeGen/CGDecl.cpp
@@ -1244,24 +1244,29 @@ static void emitStoresForConstant(CodeGenModule &CGM, const VarDecl &D,
   // If the initializer is small, use a handful of stores.
   if (shouldSplitConstantStore(CGM, ConstantSize)) {
     if (auto *STy = dyn_cast<llvm::StructType>(Ty)) {
-      const llvm::StructLayout *Layout =
-          CGM.getDataLayout().getStructLayout(STy);
-      for (unsigned i = 0; i != constant->getNumOperands(); i++) {
-        CharUnits CurOff = CharUnits::fromQuantity(Layout->getElementOffset(i));
-        Address EltPtr = Builder.CreateConstInBoundsByteGEP(
-            Loc.withElementType(CGM.Int8Ty), CurOff);
-        emitStoresForConstant(CGM, D, EltPtr, isVolatile, Builder,
-                              constant->getAggregateElement(i), IsAutoInit);
+      // FIXME: handle the case when STy != Loc.getElementType().
+      if (STy == Loc.getElementType()) {
+        for (unsigned i = 0; i != constant->getNumOperands(); i++) {
+          Address EltPtr = Builder.CreateStructGEP(Loc, i);
+          emitStoresForConstant(
+              CGM, D, EltPtr, isVolatile, Builder,
+              cast<llvm::Constant>(Builder.CreateExtractValue(constant, i)),
+              IsAutoInit);
+        }
+        return;
       }
-      return;
     } else if (auto *ATy = dyn_cast<llvm::ArrayType>(Ty)) {
-      for (unsigned i = 0; i != ATy->getNumElements(); i++) {
-        Address EltPtr = Builder.CreateConstGEP(
-            Loc.withElementType(ATy->getElementType()), i);
-        emitStoresForConstant(CGM, D, EltPtr, isVolatile, Builder,
-                              constant->getAggregateElement(i), IsAutoInit);
+      // FIXME: handle the case when ATy != Loc.getElementType().
+      if (ATy == Loc.getElementType()) {
+        for (unsigned i = 0; i != ATy->getNumElements(); i++) {
+          Address EltPtr = Builder.CreateConstArrayGEP(Loc, i);
+          emitStoresForConstant(
+              CGM, D, EltPtr, isVolatile, Builder,
+              cast<llvm::Constant>(Builder.CreateExtractValue(constant, i)),
+              IsAutoInit);
+        }
+        return;
       }
-      return;
     }
   }
 
diff --git a/clang/test/CodeGen/aapcs-align.cpp b/clang/test/CodeGen/aapcs-align.cpp
index 2886a32974b066..4f393d9e6b7f32 100644
--- a/clang/test/CodeGen/aapcs-align.cpp
+++ b/clang/test/CodeGen/aapcs-align.cpp
@@ -134,8 +134,8 @@ void g6() {
   f6m(1, 2, 3, 4, 5, s);
 }
 // CHECK: define{{.*}} void @g6
-// CHECK: call void @f6(i32 noundef 1, [4 x i32] [i32 6, i32 7, i32 0, i32 0])
-// CHECK: call void @f6m(i32 noundef 1, i32 noundef 2, i32 noundef 3, i32 noundef 4, i32 noundef 5, [4 x i32] [i32 6, i32 7, i32 0, i32 0])
+// CHECK: call void @f6(i32 noundef 1, [4 x i32] [i32 6, i32 7, i32 0, i32 undef])
+// CHECK: call void @f6m(i32 noundef 1, i32 noundef 2, i32 noundef 3, i32 noundef 4, i32 noundef 5, [4 x i32] [i32 6, i32 7, i32 0, i32 undef])
 // CHECK: declare void @f6(i32 noundef, [4 x i32])
 // CHECK: declare void @f6m(i32 noundef, i32 noundef, i32 noundef, i32 noundef, i32 noundef, [4 x i32])
 }
diff --git a/clang/test/CodeGen/aapcs64-align.cpp b/clang/test/CodeGen/aapcs64-align.cpp
index 759413cbc4b56f..de231f2123b975 100644
--- a/clang/test/CodeGen/aapcs64-align.cpp
+++ b/clang/test/CodeGen/aapcs64-align.cpp
@@ -75,8 +75,8 @@ void g4() {
   f4m(1, 2, 3, 4, 5, s);
 }
 // CHECK: define{{.*}} void @g4()
-// CHECK: call void @f4(i32 noundef 1, [2 x i64] %{{.*}})
-// CHECK: void @f4m(i32 noundef 1, i32 noundef 2, i32 noundef 3, i32 noundef 4, i32 noundef 5, [2 x i64] %{{.*}})
+// CHECK: call void @f4(i32 noundef 1, [2 x i64] [i64 30064771078, i64 0])
+// CHECK: void @f4m(i32 noundef 1, i32 noundef 2, i32 noundef 3, i32 noundef 4, i32 noundef 5, [2 x i64] [i64 30064771078, i64 0])
 // CHECK: declare void @f4(i32 noundef, [2 x i64])
 // CHECK: declare void @f4m(i32 noundef, i32 noundef, i32 noundef, i32 noundef, i32 noundef, [2 x i64])
 
@@ -95,8 +95,8 @@ void f5m(int, int, int, int, int, P16);
     f5m(1, 2, 3, 4, 5, s);
 }
 // CHECK: define{{.*}} void @g5()
-// CHECK: call void @f5(i32 noundef 1, [2 x i64] %{{.*}})
-// CHECK: void @f5m(i32 noundef 1, i32 noundef 2, i32 noundef 3, i32 noundef 4, i32 noundef 5, [2 x i64] %{{.*}})
+// CHECK: call void @f5(i32 noundef 1, [2 x i64] [i64 30064771078, i64 0])
+// CHECK: void @f5m(i32 noundef 1, i32 noundef 2, i32 noundef 3, i32 noundef 4, i32 noundef 5, [2 x i64] [i64 30064771078, i64 0])
 // CHECK: declare void @f5(i32 noundef, [2 x i64])
 // CHECK: declare void @f5m(i32 noundef, i32 noundef, i32 noundef, i32 noundef, i32 noundef, [2 x i64])
 
diff --git a/clang/test/CodeGenCXX/auto-var-init.cpp b/clang/test/CodeGenCXX/auto-var-init.cpp
index e5a9d015f22f27..6cb18528ebadcd 100644
--- a/clang/test/CodeGenCXX/auto-var-init.cpp
+++ b/clang/test/CodeGenCXX/auto-var-init.cpp
@@ -89,14 +89,22 @@ struct padded { char c; int i; };
 // PATTERN-O1-NOT: @__const.test_paddednullinit_custom.custom
 struct paddednullinit { char c = 0; int i = 0; };
 // PATTERN-O0: @__const.test_paddedpacked_uninit.uninit = private unnamed_addr constant %struct.paddedpacked <{ i8 [[I8]], i32 [[I32]] }>, align 1
+// PATTERN: @__const.test_paddedpacked_custom.custom = private unnamed_addr constant %struct.paddedpacked <{ i8 42, i32 13371337 }>, align 1
+// ZERO: @__const.test_paddedpacked_custom.custom = private unnamed_addr constant %struct.paddedpacked <{ i8 42, i32 13371337 }>, align 1
 struct paddedpacked { char c; int i; } __attribute__((packed));
 // PATTERN-O0: @__const.test_paddedpackedarray_uninit.uninit = private unnamed_addr constant %struct.paddedpackedarray { [2 x %struct.paddedpacked] [%struct.paddedpacked <{ i8 [[I8]], i32 [[I32]] }>, %struct.paddedpacked <{ i8 [[I8]], i32 [[I32]] }>] }, align 1
+// PATTERN: @__const.test_paddedpackedarray_custom.custom = private unnamed_addr constant %struct.paddedpackedarray { [2 x %struct.paddedpacked] [%struct.paddedpacked <{ i8 42, i32 13371337 }>, %struct.paddedpacked <{ i8 43, i32 13371338 }>] }, align 1
+// ZERO: @__const.test_paddedpackedarray_custom.custom = private unnamed_addr constant %struct.paddedpackedarray { [2 x %struct.paddedpacked] [%struct.paddedpacked <{ i8 42, i32 13371337 }>, %struct.paddedpacked <{ i8 43, i32 13371338 }>] }, align 1
 struct paddedpackedarray { struct paddedpacked p[2]; };
 // PATTERN-O0: @__const.test_unpackedinpacked_uninit.uninit = private unnamed_addr constant <{ { i8, [3 x i8], i32 }, i8 }> <{ { i8, [3 x i8], i32 } { i8 [[I8]], [3 x i8] c"\[[IC]]\[[IC]]\[[IC]]", i32 [[I32]] }, i8 [[I8]] }>, align 1
 struct unpackedinpacked { padded a; char b; } __attribute__((packed));
 // PATTERN-O0: @__const.test_paddednested_uninit.uninit = private unnamed_addr constant { { i8, [3 x i8], i32 }, { i8, [3 x i8], i32 } } { { i8, [3 x i8], i32 } { i8 [[I8]], [3 x i8] c"\[[IC]]\[[IC]]\[[IC]]", i32 [[I32]] }, { i8, [3 x i8], i32 } { i8 [[I8]], [3 x i8] c"\[[IC]]\[[IC]]\[[IC]]", i32 [[I32]] } }, align 4
+// PATTERN: @__const.test_paddednested_custom.custom = private unnamed_addr constant { { i8, [3 x i8], i32 }, { i8, [3 x i8], i32 } } { { i8, [3 x i8], i32 } { i8 42, [3 x i8] zeroinitializer, i32 13371337 }, { i8, [3 x i8], i32 } { i8 43, [3 x i8] zeroinitializer, i32 13371338 } }, align 4
+// ZERO: @__const.test_paddednested_custom.custom = private unnamed_addr constant { { i8, [3 x i8], i32 }, { i8, [3 x i8], i32 } } { { i8, [3 x i8], i32 } { i8 42, [3 x i8] zeroinitializer, i32 13371337 }, { i8, [3 x i8], i32 } { i8 43, [3 x i8] zeroinitializer, i32 13371338 } }, align 4
 struct paddednested { struct padded p1, p2; };
 // PATTERN-O0: @__const.test_paddedpackednested_uninit.uninit = private unnamed_addr constant %struct.paddedpackednested { %struct.paddedpacked <{ i8 [[I8]], i32 [[I32]] }>, %struct.paddedpacked <{ i8 [[I8]], i32 [[I32]] }> }, align 1
+// PATTERN: @__const.test_paddedpackednested_custom.custom = private unnamed_addr constant %struct.paddedpackednested { %struct.paddedpacked <{ i8 42, i32 13371337 }>, %struct.paddedpacked <{ i8 43, i32 13371338 }> }, align 1
+// ZERO: @__const.test_paddedpackednested_custom.custom = private unnamed_addr constant %struct.paddedpackednested { %struct.paddedpacked <{ i8 42, i32 13371337 }>, %struct.paddedpacked <{ i8 43, i32 13371338 }> }, align 1
 struct paddedpackednested { struct paddedpacked p1, p2; };
 // PATTERN-O0: @__const.test_bitfield_uninit.uninit = private unnamed_addr constant %struct.bitfield { i8 [[I8]], [3 x i8] c"\[[IC]]\[[IC]]\[[IC]]" }, align 4
 // PATTERN-O0: @__const.test_bitfield_custom.custom = private unnamed_addr constant %struct.bitfield { i8 20, [3 x i8] c"\[[IC]]\[[IC]]\[[IC]]" }, align 4
@@ -134,8 +142,12 @@ struct arraytail { int i; int arr[]; };
 // PATTERN-O1-NOT: @__const.test_bool4_custom.custom
 // ZERO-O1-NOT: @__const.test_bool4_custom.custom
 
+// PATTERN: @__const.test_intptr4_custom.custom = private unnamed_addr constant [4 x ptr] [ptr inttoptr ([[IPTRT]] 572662306 to ptr), ptr inttoptr ([[IPTRT]] 572662306 to ptr), ptr inttoptr ([[IPTRT]] 572662306 to ptr), ptr inttoptr ([[IPTRT]] 572662306 to ptr)], align
+// ZERO: @__const.test_intptr4_custom.custom = private unnamed_addr constant [4 x ptr] [ptr inttoptr (i64 572662306 to ptr), ptr inttoptr (i64 572662306 to ptr), ptr inttoptr (i64 572662306 to ptr), ptr inttoptr (i64 572662306 to ptr)], align 16
 // PATTERN-O0: @__const.test_tailpad4_uninit.uninit = private unnamed_addr constant [4 x { i16, i8, [1 x i8] }] [{ i16, i8, [1 x i8] } { i16 [[I16]], i8 [[I8]], [1 x i8] c"\[[IC]]" }, { i16, i8, [1 x i8] } { i16 [[I16]], i8 [[I8]], [1 x i8] c"\[[IC]]" }, { i16, i8, [1 x i8] } { i16 [[I16]], i8 [[I8]], [1 x i8] c"\[[IC]]" }, { i16, i8, [1 x i8] } { i16 [[I16]], i8 [[I8]], [1 x i8] c"\[[IC]]" }], align
 // PATTERN-O1-NOT: @__const.test_tailpad4_uninit.uninit
+// PATTERN:   @__const.test_tailpad4_custom.custom = private unnamed_addr constant [4 x { i16, i8, [1 x i8] }] [{ i16, i8, [1 x i8] } { i16 257, i8 1, [1 x i8] zeroinitializer }, { i16, i8, [1 x i8] } { i16 257, i8 1, [1 x i8] zeroinitializer }, { i16, i8, [1 x i8] } { i16 257, i8 1, [1 x i8] zeroinitializer }, { i16, i8, [1 x i8] } { i16 257, i8 1, [1 x i8] zeroinitializer }], align
+// ZERO: @__const.test_tailpad4_custom.custom = private unnamed_addr constant [4 x { i16, i8, [1 x i8] }] [{ i16, i8, [1 x i8] } { i16 257, i8 1, [1 x i8] zeroinitializer }, { i16, i8, [1 x i8] } { i16 257, i8 1, [1 x i8] zeroinitializer }, { i16, i8, [1 x i8] } { i16 257, i8 1, [1 x i8] zeroinitializer }, { i16, i8, [1 x i8] } { i16 257, i8 1, [1 x i8] zeroinitializer }], align 16
 struct tailpad { short s; char c; };
 // PATTERN-O0: @__const.test_atomicnotlockfree_uninit.uninit = private unnamed_addr constant %struct.notlockfree { [4 x i64] {{\[}}i64 [[I64]], i64 [[I64]], i64 [[I64]], i64 [[I64]]] }, align
 // PATTERN-O1-NOT: @__const.test_atomicnotlockfree_uninit.uninit
@@ -702,8 +714,7 @@ TEST_UNINIT(padded, padded);
 // CHECK-NEXT:  call void @{{.*}}used{{.*}}%uninit)
 // PATTERN-LABEL: @test_padded_uninit()
 // PATTERN-O0: call void @llvm.memcpy{{.*}} @__const.test_padded_uninit.uninit{{.+}}), !annotation [[AUTO_INIT]]
-// PATTERN-O1: store i64 [[I64]], ptr %uninit, align 8
-// PATTERN-O1-NOT:   !annotation
+// PATTERN-O1: store i64 [[I64]], ptr %uninit, align 8, !annotation [[AUTO_INIT]]
 // ZERO-LABEL: @test_padded_uninit()
 // ZERO-O0: call void @llvm.memset{{.*}}, i8 0,{{.+}}), !annotation [[AUTO_INIT]]
 // ZERO-O1: store i64 0, ptr %uninit, align 8, !annotation [[AUTO_INIT]]
@@ -729,8 +740,7 @@ TEST_UNINIT(paddednullinit, paddednullinit);
 // CHECK-NEXT:  call void @{{.*}}used{{.*}}%uninit)
 // PATTERN-LABEL: @test_paddednullinit_uninit()
 // PATTERN-O0: call void @llvm.memcpy{{.*}} @__const.test_paddednullinit_uninit.uninit{{.+}}), !annotation [[AUTO_INIT]]
-// PATTERN-O1: store i64 [[I64]], ptr %uninit, align 8
-// PATTERN-O1-NOT:   !annotation
+// PATTERN-O1: store i64 [[I64]], ptr %uninit, align 8, !annotation [[AUTO_INIT]]
 // ZERO-LABEL: @test_paddednullinit_uninit()
 // ZERO-O0: call void @llvm.memset{{.*}}, i8 0, {{.*}}, !annotation [[AUTO_INIT]]
 // ZERO-O1: store i64 0, ptr %uninit, align 8
@@ -768,8 +778,9 @@ TEST_UNINIT(paddedpacked, paddedpacked);
 // PATTERN-LABEL: @test_paddedpacked_uninit()
 // PATTERN-O0: call void @llvm.memcpy{{.*}} @__const.test_paddedpacked_uninit.uninit{{.+}}), !annotation [[AUTO_INIT]]
 // PATTERN-O1:  store i8 [[I8]], ptr %uninit, align {{.+}}, !annotation [[AUTO_INIT]]
-// PATTERN-O1:  %[[I:[^ ]*]] = getelementptr inbounds {{.*}}%uninit, i64 1
+// PATTERN-O1:  %[[I:[^ ]*]] = getelementptr inbounds {{.*}}%uninit, i64 0, i32 1
 // PATTERN-O1: store i32 [[I32]], ptr %[[I]], align {{.+}}, !annotation [[AUTO_INIT]]
+
 // ZERO-LABEL: @test_paddedpacked_uninit()
 // ZERO: call void @llvm.memset{{.*}}, i8 0,{{.+}}), !annotation [[AUTO_INIT]]
 
@@ -1181,8 +1192,7 @@ TEST_UNINIT(atomicpadded, _Atomic(padded));
 // CHECK-NEXT:  call void @{{.*}}used{{.*}}%uninit)
 // PATTERN-LABEL: @test_atomicpadded_uninit()
 // PATTERN-O0: call void @llvm.memcpy{{.*}} @__const.test_atomicpadded_uninit.uninit{{.+}}), !annotation [[AUTO_INIT]]
-// PATTERN-O1: store i64 [[IPTR]], ptr %uninit, align 8
-// PATTERN-O1-NOT: !annotation
+// PATTERN-O1: store i64 [[IPTR]], ptr %uninit, align 8, !annotation [[AUTO_INIT]]
 // ZERO-LABEL: @test_atomicpadded_uninit()
 // ZERO-O0: call void @llvm.memset{{.*}}, i8 0, {{.+}}), !annotation [[AUTO_INIT]]
 // ZERO-O1: store i64 0, ptr %uninit, align 8, !annotation [[AUTO_INIT]]
@@ -1204,7 +1214,8 @@ TEST_UNINIT(complexfloat, _Complex float);
 // PATTERN-LABEL: @test_complexfloat_uninit()
 // PATTERN-O0: call void @llvm.memcpy{{.*}} @__const.test_complexfloat_uninit.uninit{{.+}}), !annotation [[AUTO_INIT]]
 // PATTERN-O1: store float 0xFFFFFFFFE0000000, ptr %uninit, align {{.+}}, !annotation [[AUTO_INIT]]
-// PATTERN-O1:  %[[F2:[^ ]*]] = getelementptr inbounds {{.*}}%uninit, i64 4
+
+// PATTERN-O1:  %[[F2:[^ ]*]] = getelementptr inbounds {{.*}}%uninit, i64 0, i32 1
 // PATTERN-O1: store float 0xFFFFFFFFE0000000, ptr %[[F2]], align {{.+}}, !annotation [[AUTO_INIT]]
 
 // ZERO-LABEL: @test_complexfloat_uninit()
@@ -1303,9 +1314,7 @@ TEST_CUSTOM(semivolatile, semivolatile, { 0x44444444, 0x44444444 });
 // CHECK-O0:  call void @llvm.memcpy
 // CHECK-NOT:   !annotation
 // CHECK-O0:  call void @{{.*}}used{{.*}}%custom)
-// CHECK-O1:  store i32 1145324612, ptr %custom, align 4
-// CHECK-O1-NEXT:  %[[I:[^ ]*]] = getelementptr inbounds i8, ptr %custom, i64 4
-// CHECK-O1-NEXT:  store i32 1145324612, ptr %[[I]], align 4
+// CHECK-O1:  store i64 4919131752989213764, ptr %custom, align 8
 // CHECK-NOT:   !annotation
 
 TEST_UNINIT(semivolatileinit, semivolatileinit);
@@ -1418,7 +1427,7 @@ TEST_CUSTOM(matching, matching, { .f = 0xf00f });
 // CHECK-O0:  call void @llvm.memcpy
 // CHECK-NOT:   !annotation
 // CHECK-O0:  call void @{{.*}}used{{.*}}%custom)
-// CHECK-O1:  store float 6.145500e+04, ptr {{.*}}, align 4
+// CHECK-O1:  store i32 1198526208, ptr {{.*}}, align 4
 // CHECK-NOT:   !annotation
 
 TEST_UNINIT(matchingreverse, matchingreverse);
@@ -1497,16 +1506,8 @@ TEST_CUSTOM(unmatchedreverse, unmatchedreverse, { .c = 42  });
 // CHECK-O0:    call void @llvm.memcpy
 // CHECK-NOT:   !annotation
 // CHECK-O0:    call void @{{.*}}used{{.*}}%custom)
-// PATTERN-O1:  store i8 42, ptr {{.*}}, align 4
-// PATTERN-O1-NEXT:  %[[I:[^ ]*]] = getelementptr inbounds i8, ptr %custom, i64 1
-// PATTERN-O1-NEXT:  store i8 -86, ptr %[[I]], align {{.*}}
-// PATTERN-O1-NEXT:  %[[I:[^ ]*]] = getelementptr inbounds i8, ptr %custom, i64 2
-// PATTERN-O1-NEXT:  store i8 -86, ptr %[[I]], align {{.*}}
-// PATTERN-O1-NEXT:  %[[I:[^ ]*]] = getelementptr inbounds i8, ptr %custom, i64 3
-// PATTERN-O1-NEXT:  store i8 -86, ptr %[[I]], align {{.*}}
-// ZERO-O1:     store i8 42, ptr {{.*}}, align 4
-// ZERO-O1-NEXT:  %[[I:[^ ]*]] = getelementptr inbounds i8, ptr %custom, i64 1
-// ZERO-O1-NEXT:  call void @llvm.memset.{{.*}}({{.*}}, i8 0, i64 3, {{.*}})
+// PATTERN-O1:  store i32 -1431655894, ptr {{.*}}, align 4
+// ZERO-O1:     store i32 42, ptr {{.*}}, align 4
 
 TEST_UNINIT(unmatchedfp, unmatchedfp);
 // CHECK-LABEL: @test_unmatchedfp_uninit()
@@ -1531,7 +1532,7 @@ TEST_CUSTOM(unmatchedfp, unmatchedfp, { .d = 3.1415926535897932384626433 });
 // CHECK-O0:    call void @llvm.memcpy
 // CHECK-NOT:   !annotation
 // CHECK-O0:    call void @{{.*}}used{{.*}}%custom)
-// CHECK-O1:    store double 0x400921FB54442D18, ptr %custom, align 8
+// CHECK-O1:    store i64 4614256656552045848, ptr %custom, align 8
 // CHECK-NOT:   !annotation
 
 TEST_UNINIT(emptyenum, emptyenum);
diff --git a/clang/test/CodeGenOpenCL/amdgpu-printf.cl b/clang/test/CodeGenOpenCL/amdgpu-printf.cl
index 6c84485b66b4a0..edf6dbf8657cbe 100644
--- a/clang/test/CodeGenOpenCL/amdgpu-printf.cl
+++ b/clang/test/CodeGenOpenCL/amdgpu-printf.cl
@@ -30,14 +30,7 @@ __kernel void test_printf_int(int i) {
 // CHECK-NEXT:    [[S:%.*]] = alloca [4 x i8], align 1, addrspace(5)
 // CHECK-NEXT:    store i32 [[I:%.*]], ptr addrspace(5) [[I_ADDR]], align 4, !tbaa [[TBAA8]]
 // CHECK-NEXT:    call void @llvm.lifetime.start.p5(i64 4, ptr addrspace(5) [[S]]) #[[ATTR5:[0-9]+]]
-// CHECK-NEXT:    [[LOC0:%.*]] = getelementptr i8, ptr addrspace(5) [[S]], i64 0
-// CHECK-NEXT:    store i8 102, ptr addrspace(5) [[LOC0]], align 1
-// CHECK-NEXT:    [[LOC1:%.*]] = getelementptr i8, ptr addrspace(5) [[S]], i64 1
-// CHECK-NEXT:    store i8 111, ptr addrspace(5) [[LOC1]], align 1
-// CHECK-NEXT:    [[LOC2:%.*]] = getelementptr i8, ptr addrspace(5) [[S]], i64 2
-// CHECK-NEXT:    store i8 111, ptr addrspace(5) [[LOC2]], align 1
-// CHECK-NEXT:    [[LOC3:%.*]] = getelementptr i8, ptr addrspace(5) [[S]], i64 3
-// CHECK-NEXT:    store i8 0, ptr addrspace(5) [[LOC3]], align 1
+// CHECK-NEXT:    call void @llvm.memcpy.p5.p4.i64(ptr addrspace(5) align 1 [[S]], ptr addrspace(4) align 1 @__const.test_printf_str_int.s, i64 4, i1 false)
 // CHECK-NEXT:    [[ARRAYDECAY:%.*]] = getelementptr inbounds [4 x i8], ptr addrspace(5) [[S]], i64 0, i64 0
 // CHECK-NEXT:    [[TMP2:%.*]] = load i32, ptr addrspace(5) [[I_ADDR]], align 4, !tbaa [[TBAA8]]
 // CHECK-NEXT:    [[CALL:%.*]] = call i32 (ptr addrspace(4), ...) @printf(ptr addrspace(4) noundef @.str.2, ptr addrspace(5) noundef [[ARRAYDECAY]], i32 noundef [[TMP2]]) #[[ATTR4]]
diff --git a/clang/test/OpenMP/bug54082.c b/clang/test/OpenMP/bug54082.c
index b88b68fd43012a..337c120983e0a3 100644
--- a/clang/test/OpenMP/bug54082.c
+++ b/clang/test/OpenMP/bug54082.c
@@ -69,9 +69,7 @@ void foo() {
 // CHECK-NEXT:    [[X_TRAITS:%.*]] = alloca [1 x %struct.omp_alloctrait_t], align 16
 // CHECK-NEXT:    [[X_ALLOC:%.*]] = alloca i64, align 8
 // CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 16, ptr nonnull [[X_TRAITS]]) #[[ATTR5:[0-9]+]]
-// CHECK-NEXT:    store i32 2, ptr [[X_TRAITS]], align 16
-// CHECK-NEXT:    [[LOC0:%.*]] = getelementptr inbounds i8, ptr [[X_TRAITS]], i64 8
-// CHECK-NEXT:    store i64 64, ptr [[LOC0]], align 8
+// CHECK-NEXT:    call void @llvm.memcpy.p0.p0.i64(ptr noundef nonnull align 16 dereferenceable(16) [[X_TRAITS]], ptr noundef nonnull align 16 dereferenceable(16) @__const.foo.x_traits, i64 16, i1 false)
 // CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 8, ptr nonnull [[X_ALLOC]]) #[[ATTR5]]
 // CHECK-NEXT:    [[CALL:%.*]] = call i64 @omp_init_allocator(i64 noundef 0, i32 noundef 1, ptr noundef nonnull [[X_TRAITS]]) #[[ATTR5]]
 // CHECK-NEXT:    store i64 [[CALL]], ptr [[X_ALLOC]], align 8, !tbaa [[TBAA3:![0-9]+]]



More information about the cfe-commits mailing list