[llvm] [clang] [Offloading][NFC] Refactor handling of offloading entries (PR #72544)

2023-11-17 Thread Joseph Huber via cfe-commits 

https://github.com/jhuber6 closed 
https://github.com/llvm/llvm-project/pull/72544
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[llvm] [clang] [Offloading][NFC] Refactor handling of offloading entries (PR #72544)

2023-11-17 Thread Jon Chesterfield via cfe-commits 

https://github.com/JonChesterfield approved this pull request.

Test change is suspect for a patch claiming NFC but it looks like the change is 
harmless. Thanks for separating refactor from functional change

https://github.com/llvm/llvm-project/pull/72544
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[llvm] [clang] [Offloading][NFC] Refactor handling of offloading entries (PR #72544)

2023-11-16 Thread via cfe-commits 

llvmbot wrote:




@llvm/pr-subscribers-clang

Author: Joseph Huber (jhuber6)


Changes

Summary:
This patch is a simple refactoring of code out of the linker wrapper
into a common location. The main motivation behind this change is to
make it easier to change the handling in the future to accept a triple
to be used to emit entries that function on that target.


---

Patch is 21.18 KiB, truncated to 20.00 KiB below, full version: 
https://github.com/llvm/llvm-project/pull/72544.diff


5 Files Affected:

- (modified) clang/test/Driver/linker-wrapper-image.c (+19-19) 
- (modified) clang/tools/clang-linker-wrapper/CMakeLists.txt (+1) 
- (modified) clang/tools/clang-linker-wrapper/OffloadWrapper.cpp (+22-94) 
- (modified) llvm/include/llvm/Frontend/Offloading/Utility.h (+10-1) 
- (modified) llvm/lib/Frontend/Offloading/Utility.cpp (+30-1) 


``diff
diff --git a/clang/test/Driver/linker-wrapper-image.c 
b/clang/test/Driver/linker-wrapper-image.c
index 83e7db6a49a6bb3..bb641a08bc023d5 100644
--- a/clang/test/Driver/linker-wrapper-image.c
+++ b/clang/test/Driver/linker-wrapper-image.c
@@ -10,9 +10,9 @@
 // RUN: clang-linker-wrapper --print-wrapped-module --dry-run 
--host-triple=x86_64-unknown-linux-gnu \
 // RUN:   --linker-path=/usr/bin/ld -- %t.o -o a.out 2>&1 | FileCheck %s 
--check-prefix=OPENMP
 
-//  OPENMP: @__start_omp_offloading_entries = external hidden constant 
%__tgt_offload_entry
-// OPENMP-NEXT: @__stop_omp_offloading_entries = external hidden constant 
%__tgt_offload_entry
-// OPENMP-NEXT: @__dummy.omp_offloading.entry = hidden constant [0 x 
%__tgt_offload_entry] zeroinitializer, section "omp_offloading_entries"
+//  OPENMP: @__start_omp_offloading_entries = external hidden constant [0 
x %struct.__tgt_offload_entry]
+// OPENMP-NEXT: @__stop_omp_offloading_entries = external hidden constant [0 x 
%struct.__tgt_offload_entry]
+// OPENMP-NEXT: @__dummy.omp_offloading_entries = hidden constant [0 x 
%struct.__tgt_offload_entry] zeroinitializer, section "omp_offloading_entries"
 // OPENMP-NEXT: @.omp_offloading.device_image = internal unnamed_addr constant 
[[[SIZE:[0-9]+]] x i8] c"\10\FF\10\AD{{.*}}"
 // OPENMP-NEXT: @.omp_offloading.device_images = internal unnamed_addr 
constant [1 x %__tgt_device_image] [%__tgt_device_image { ptr 
@.omp_offloading.device_image, ptr getelementptr inbounds ([[[SIZE]] x i8], ptr 
@.omp_offloading.device_image, i64 1, i64 0), ptr 
@__start_omp_offloading_entries, ptr @__stop_omp_offloading_entries }]
 // OPENMP-NEXT: @.omp_offloading.descriptor = internal constant 
%__tgt_bin_desc { i32 1, ptr @.omp_offloading.device_images, ptr 
@__start_omp_offloading_entries, ptr @__stop_omp_offloading_entries }
@@ -39,10 +39,10 @@
 
 //  CUDA: @.fatbin_image = internal constant [0 x i8] zeroinitializer, 
section ".nv_fatbin"
 // CUDA-NEXT: @.fatbin_wrapper = internal constant %fatbin_wrapper { i32 
1180844977, i32 1, ptr @.fatbin_image, ptr null }, section ".nvFatBinSegment", 
align 8
-// CUDA-NEXT: @__dummy.cuda_offloading.entry = hidden constant [0 x 
%__tgt_offload_entry] zeroinitializer, section "cuda_offloading_entries"
 // CUDA-NEXT: @.cuda.binary_handle = internal global ptr null
-// CUDA-NEXT: @__start_cuda_offloading_entries = external hidden constant [0 x 
%__tgt_offload_entry]
-// CUDA-NEXT: @__stop_cuda_offloading_entries = external hidden constant [0 x 
%__tgt_offload_entry]
+// CUDA-NEXT: @__start_cuda_offloading_entries = external hidden constant [0 x 
%struct.__tgt_offload_entry]
+// CUDA-NEXT: @__stop_cuda_offloading_entries = external hidden constant [0 x 
%struct.__tgt_offload_entry]
+// CUDA-NEXT: @__dummy.cuda_offloading_entries = hidden constant [0 x 
%struct.__tgt_offload_entry] zeroinitializer, section "cuda_offloading_entries"
 // CUDA-NEXT: @llvm.global_ctors = appending global [1 x { i32, ptr, ptr }] [{ 
i32, ptr, ptr } { i32 1, ptr @.cuda.fatbin_reg, ptr null }]
 
 //  CUDA: define internal void @.cuda.fatbin_reg() section ".text.startup" 
{
@@ -68,13 +68,13 @@
 
 //  CUDA: while.entry:
 // CUDA-NEXT:  %entry1 = phi ptr [ @__start_cuda_offloading_entries, %entry ], 
[ %7, %if.end ]
-// CUDA-NEXT:  %1 = getelementptr inbounds %__tgt_offload_entry, ptr %entry1, 
i64 0, i32 0
+// CUDA-NEXT:  %1 = getelementptr inbounds %struct.__tgt_offload_entry, ptr 
%entry1, i64 0, i32 0
 // CUDA-NEXT:  %addr = load ptr, ptr %1, align 8
-// CUDA-NEXT:  %2 = getelementptr inbounds %__tgt_offload_entry, ptr %entry1, 
i64 0, i32 1
+// CUDA-NEXT:  %2 = getelementptr inbounds %struct.__tgt_offload_entry, ptr 
%entry1, i64 0, i32 1
 // CUDA-NEXT:  %name = load ptr, ptr %2, align 8
-// CUDA-NEXT:  %3 = getelementptr inbounds %__tgt_offload_entry, ptr %entry1, 
i64 0, i32 2
+// CUDA-NEXT:  %3 = getelementptr inbounds %struct.__tgt_offload_entry, ptr 
%entry1, i64 0, i32 2
 // CUDA-NEXT:  %size = load i64, ptr %3, align 4
-// CUDA-NEXT:  %4 = getelementptr inbounds %__tgt_offload_entry, ptr %entry1, 
i64 0, i32 3
+// CUDA-NEXT:  %4 =

[llvm] [clang] [Offloading][NFC] Refactor handling of offloading entries (PR #72544)

2023-11-16 Thread Joseph Huber via cfe-commits 

https://github.com/jhuber6 created 
https://github.com/llvm/llvm-project/pull/72544

Summary:
This patch is a simple refactoring of code out of the linker wrapper
into a common location. The main motivation behind this change is to
make it easier to change the handling in the future to accept a triple
to be used to emit entries that function on that target.


>From 0047be2207b775e6de6dda24751daa933bd66ce5 Mon Sep 17 00:00:00 2001
From: Joseph Huber 
Date: Thu, 16 Nov 2023 12:05:09 -0600
Subject: [PATCH] [Offloading][NFC] Refactor handling of offloading entries

Summary:
This patch is a simple refactoring of code out of the linker wrapper
into a common location. The main motivation behind this change is to
make it easier to change the handling in the future to accept a triple
to be used to emit entries that function on that target.
---
 clang/test/Driver/linker-wrapper-image.c  |  38 +++---
 .../tools/clang-linker-wrapper/CMakeLists.txt |   1 +
 .../clang-linker-wrapper/OffloadWrapper.cpp   | 116 --
 .../llvm/Frontend/Offloading/Utility.h|  11 +-
 llvm/lib/Frontend/Offloading/Utility.cpp  |  31 -
 5 files changed, 82 insertions(+), 115 deletions(-)

diff --git a/clang/test/Driver/linker-wrapper-image.c 
b/clang/test/Driver/linker-wrapper-image.c
index 83e7db6a49a6bb3..bb641a08bc023d5 100644
--- a/clang/test/Driver/linker-wrapper-image.c
+++ b/clang/test/Driver/linker-wrapper-image.c
@@ -10,9 +10,9 @@
 // RUN: clang-linker-wrapper --print-wrapped-module --dry-run 
--host-triple=x86_64-unknown-linux-gnu \
 // RUN:   --linker-path=/usr/bin/ld -- %t.o -o a.out 2>&1 | FileCheck %s 
--check-prefix=OPENMP
 
-//  OPENMP: @__start_omp_offloading_entries = external hidden constant 
%__tgt_offload_entry
-// OPENMP-NEXT: @__stop_omp_offloading_entries = external hidden constant 
%__tgt_offload_entry
-// OPENMP-NEXT: @__dummy.omp_offloading.entry = hidden constant [0 x 
%__tgt_offload_entry] zeroinitializer, section "omp_offloading_entries"
+//  OPENMP: @__start_omp_offloading_entries = external hidden constant [0 
x %struct.__tgt_offload_entry]
+// OPENMP-NEXT: @__stop_omp_offloading_entries = external hidden constant [0 x 
%struct.__tgt_offload_entry]
+// OPENMP-NEXT: @__dummy.omp_offloading_entries = hidden constant [0 x 
%struct.__tgt_offload_entry] zeroinitializer, section "omp_offloading_entries"
 // OPENMP-NEXT: @.omp_offloading.device_image = internal unnamed_addr constant 
[[[SIZE:[0-9]+]] x i8] c"\10\FF\10\AD{{.*}}"
 // OPENMP-NEXT: @.omp_offloading.device_images = internal unnamed_addr 
constant [1 x %__tgt_device_image] [%__tgt_device_image { ptr 
@.omp_offloading.device_image, ptr getelementptr inbounds ([[[SIZE]] x i8], ptr 
@.omp_offloading.device_image, i64 1, i64 0), ptr 
@__start_omp_offloading_entries, ptr @__stop_omp_offloading_entries }]
 // OPENMP-NEXT: @.omp_offloading.descriptor = internal constant 
%__tgt_bin_desc { i32 1, ptr @.omp_offloading.device_images, ptr 
@__start_omp_offloading_entries, ptr @__stop_omp_offloading_entries }
@@ -39,10 +39,10 @@
 
 //  CUDA: @.fatbin_image = internal constant [0 x i8] zeroinitializer, 
section ".nv_fatbin"
 // CUDA-NEXT: @.fatbin_wrapper = internal constant %fatbin_wrapper { i32 
1180844977, i32 1, ptr @.fatbin_image, ptr null }, section ".nvFatBinSegment", 
align 8
-// CUDA-NEXT: @__dummy.cuda_offloading.entry = hidden constant [0 x 
%__tgt_offload_entry] zeroinitializer, section "cuda_offloading_entries"
 // CUDA-NEXT: @.cuda.binary_handle = internal global ptr null
-// CUDA-NEXT: @__start_cuda_offloading_entries = external hidden constant [0 x 
%__tgt_offload_entry]
-// CUDA-NEXT: @__stop_cuda_offloading_entries = external hidden constant [0 x 
%__tgt_offload_entry]
+// CUDA-NEXT: @__start_cuda_offloading_entries = external hidden constant [0 x 
%struct.__tgt_offload_entry]
+// CUDA-NEXT: @__stop_cuda_offloading_entries = external hidden constant [0 x 
%struct.__tgt_offload_entry]
+// CUDA-NEXT: @__dummy.cuda_offloading_entries = hidden constant [0 x 
%struct.__tgt_offload_entry] zeroinitializer, section "cuda_offloading_entries"
 // CUDA-NEXT: @llvm.global_ctors = appending global [1 x { i32, ptr, ptr }] [{ 
i32, ptr, ptr } { i32 1, ptr @.cuda.fatbin_reg, ptr null }]
 
 //  CUDA: define internal void @.cuda.fatbin_reg() section ".text.startup" 
{
@@ -68,13 +68,13 @@
 
 //  CUDA: while.entry:
 // CUDA-NEXT:  %entry1 = phi ptr [ @__start_cuda_offloading_entries, %entry ], 
[ %7, %if.end ]
-// CUDA-NEXT:  %1 = getelementptr inbounds %__tgt_offload_entry, ptr %entry1, 
i64 0, i32 0
+// CUDA-NEXT:  %1 = getelementptr inbounds %struct.__tgt_offload_entry, ptr 
%entry1, i64 0, i32 0
 // CUDA-NEXT:  %addr = load ptr, ptr %1, align 8
-// CUDA-NEXT:  %2 = getelementptr inbounds %__tgt_offload_entry, ptr %entry1, 
i64 0, i32 1
+// CUDA-NEXT:  %2 = getelementptr inbounds %struct.__tgt_offload_entry, ptr 
%entry1, i64 0, i32 1
 // CUDA-NEXT:  %name = load ptr, ptr %2, align 8
-// CUDA-NEXT:  %3 =