[clang] [RISCV] Add -march string as Module metadata in IR. (PR #80760)
via cfe-commits
cfe-commits at lists.llvm.org
Mon Feb 5 15:19:46 PST 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-clang
@llvm/pr-subscribers-clang-codegen
Author: Craig Topper (topperc)
<details>
<summary>Changes</summary>
In an LTO build, we don't set the ELF attributes to indicate what extensions were compiled with. The target CPU/Attrs in RISCVTargetMachine do not get set for an LTO build. Each function gets a target-cpu/feature attribute, but this isn't usable to set ELF attributs since we wouldn't know what function to use. We can't just once since it might have been compiler with an attribute likes target_verson.
This patch adds the ISA as Module metadata so we can retrieve it in the backend. Individual translation units can still be compiled with different strings so we need to collect the unique set when Modules are merged.
The backend will need to combine the unique ISA strings to produce a single value for the ELF attributes. This will be done in a separate patch.
---
Patch is 49.81 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/80760.diff
3 Files Affected:
- (modified) clang/lib/CodeGen/CodeGenModule.cpp (+11)
- (modified) clang/test/CodeGen/RISCV/ntlh-intrinsics/riscv32-zihintntl.c (+175-175)
- (added) clang/test/CodeGen/RISCV/riscv-metadata-arch.c (+20)
``````````diff
diff --git a/clang/lib/CodeGen/CodeGenModule.cpp b/clang/lib/CodeGen/CodeGenModule.cpp
index 36b63d78b06f83..25b8d5cae36d3a 100644
--- a/clang/lib/CodeGen/CodeGenModule.cpp
+++ b/clang/lib/CodeGen/CodeGenModule.cpp
@@ -67,6 +67,7 @@
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/ConvertUTF.h"
#include "llvm/Support/ErrorHandling.h"
+#include "llvm/Support/RISCVISAInfo.h"
#include "llvm/Support/TimeProfiler.h"
#include "llvm/Support/xxhash.h"
#include "llvm/TargetParser/Triple.h"
@@ -1056,6 +1057,16 @@ void CodeGenModule::Release() {
llvm::LLVMContext &Ctx = TheModule.getContext();
getModule().addModuleFlag(llvm::Module::Error, "target-abi",
llvm::MDString::get(Ctx, ABIStr));
+
+ const std::vector<std::string> &Features =
+ getTarget().getTargetOpts().Features;
+ auto ParseResult =
+ llvm::RISCVISAInfo::parseFeatures(T.isRISCV64() ? 64 : 32, Features);
+ if (!errorToBool(ParseResult.takeError()))
+ getModule().addModuleFlag(
+ llvm::Module::AppendUnique, "riscv-arch",
+ llvm::MDNode::get(
+ Ctx, llvm::MDString::get(Ctx, (*ParseResult)->toString())));
}
if (CodeGenOpts.SanitizeCfiCrossDso) {
diff --git a/clang/test/CodeGen/RISCV/ntlh-intrinsics/riscv32-zihintntl.c b/clang/test/CodeGen/RISCV/ntlh-intrinsics/riscv32-zihintntl.c
index 897edbc6450af6..b11c2ca010e7ce 100644
--- a/clang/test/CodeGen/RISCV/ntlh-intrinsics/riscv32-zihintntl.c
+++ b/clang/test/CodeGen/RISCV/ntlh-intrinsics/riscv32-zihintntl.c
@@ -28,190 +28,190 @@ vint8m1_t *scvc1, *scvc2;
// clang-format off
void ntl_all_sizes() { // CHECK-LABEL: ntl_all_sizes
- uc = __riscv_ntl_load(&sc, __RISCV_NTLH_INNERMOST_PRIVATE); // CHECK: load i8{{.*}}align 1, !nontemporal !4, !riscv-nontemporal-domain !5
- sc = __riscv_ntl_load(&uc, __RISCV_NTLH_INNERMOST_PRIVATE); // CHECK: load i8{{.*}}align 1, !nontemporal !4, !riscv-nontemporal-domain !5
- us = __riscv_ntl_load(&ss, __RISCV_NTLH_INNERMOST_PRIVATE); // CHECK: load i16{{.*}}align 2, !nontemporal !4, !riscv-nontemporal-domain !5
- ss = __riscv_ntl_load(&us, __RISCV_NTLH_INNERMOST_PRIVATE); // CHECK: load i16{{.*}}align 2, !nontemporal !4, !riscv-nontemporal-domain !5
- ui = __riscv_ntl_load(&si, __RISCV_NTLH_INNERMOST_PRIVATE); // CHECK: load i32{{.*}}align 4, !nontemporal !4, !riscv-nontemporal-domain !5
- si = __riscv_ntl_load(&ui, __RISCV_NTLH_INNERMOST_PRIVATE); // CHECK: load i32{{.*}}align 4, !nontemporal !4, !riscv-nontemporal-domain !5
- ull = __riscv_ntl_load(&sll, __RISCV_NTLH_INNERMOST_PRIVATE); // CHECK: load i64{{.*}}align 8, !nontemporal !4, !riscv-nontemporal-domain !5
- sll = __riscv_ntl_load(&ull, __RISCV_NTLH_INNERMOST_PRIVATE); // CHECK: load i64{{.*}}align 8, !nontemporal !4, !riscv-nontemporal-domain !5
- h1 = __riscv_ntl_load(&h2, __RISCV_NTLH_INNERMOST_PRIVATE); // CHECK: load half{{.*}}align 2, !nontemporal !4, !riscv-nontemporal-domain !5
- f1 = __riscv_ntl_load(&f2, __RISCV_NTLH_INNERMOST_PRIVATE); // CHECK: load float{{.*}}align 4, !nontemporal !4, !riscv-nontemporal-domain !5
- d1 = __riscv_ntl_load(&d2, __RISCV_NTLH_INNERMOST_PRIVATE); // CHECK: load double{{.*}}align 8, !nontemporal !4, !riscv-nontemporal-domain !5
- v4si1 = __riscv_ntl_load(&v4si2, __RISCV_NTLH_INNERMOST_PRIVATE); // CHECK: load <4 x i32>{{.*}}align 16, !nontemporal !4, !riscv-nontemporal-domain !5
- v8ss1 = __riscv_ntl_load(&v8ss2, __RISCV_NTLH_INNERMOST_PRIVATE); // CHECK: load <8 x i16>{{.*}}align 16, !nontemporal !4, !riscv-nontemporal-domain !5
- v16sc1 = __riscv_ntl_load(&v16sc2, __RISCV_NTLH_INNERMOST_PRIVATE); // CHECK: load <16 x i8>{{.*}}align 16, !nontemporal !4, !riscv-nontemporal-domain !5
- *scvi1 = __riscv_ntl_load(scvi2, __RISCV_NTLH_INNERMOST_PRIVATE); // CHECK: load <vscale x 2 x i32>{{.*}}align 8, !nontemporal !4, !riscv-nontemporal-domain !5
- *scvs1 = __riscv_ntl_load(scvs2, __RISCV_NTLH_INNERMOST_PRIVATE); // CHECK: load <vscale x 4 x i16>{{.*}}align 8, !nontemporal !4, !riscv-nontemporal-domain !5
- *scvc1 = __riscv_ntl_load(scvc2, __RISCV_NTLH_INNERMOST_PRIVATE); // CHECK: load <vscale x 8 x i8>{{.*}}align 8, !nontemporal !4, !riscv-nontemporal-domain !5
+ uc = __riscv_ntl_load(&sc, __RISCV_NTLH_INNERMOST_PRIVATE); // CHECK: load i8{{.*}}align 1, !nontemporal !6, !riscv-nontemporal-domain !7
+ sc = __riscv_ntl_load(&uc, __RISCV_NTLH_INNERMOST_PRIVATE); // CHECK: load i8{{.*}}align 1, !nontemporal !6, !riscv-nontemporal-domain !7
+ us = __riscv_ntl_load(&ss, __RISCV_NTLH_INNERMOST_PRIVATE); // CHECK: load i16{{.*}}align 2, !nontemporal !6, !riscv-nontemporal-domain !7
+ ss = __riscv_ntl_load(&us, __RISCV_NTLH_INNERMOST_PRIVATE); // CHECK: load i16{{.*}}align 2, !nontemporal !6, !riscv-nontemporal-domain !7
+ ui = __riscv_ntl_load(&si, __RISCV_NTLH_INNERMOST_PRIVATE); // CHECK: load i32{{.*}}align 4, !nontemporal !6, !riscv-nontemporal-domain !7
+ si = __riscv_ntl_load(&ui, __RISCV_NTLH_INNERMOST_PRIVATE); // CHECK: load i32{{.*}}align 4, !nontemporal !6, !riscv-nontemporal-domain !7
+ ull = __riscv_ntl_load(&sll, __RISCV_NTLH_INNERMOST_PRIVATE); // CHECK: load i64{{.*}}align 8, !nontemporal !6, !riscv-nontemporal-domain !7
+ sll = __riscv_ntl_load(&ull, __RISCV_NTLH_INNERMOST_PRIVATE); // CHECK: load i64{{.*}}align 8, !nontemporal !6, !riscv-nontemporal-domain !7
+ h1 = __riscv_ntl_load(&h2, __RISCV_NTLH_INNERMOST_PRIVATE); // CHECK: load half{{.*}}align 2, !nontemporal !6, !riscv-nontemporal-domain !7
+ f1 = __riscv_ntl_load(&f2, __RISCV_NTLH_INNERMOST_PRIVATE); // CHECK: load float{{.*}}align 4, !nontemporal !6, !riscv-nontemporal-domain !7
+ d1 = __riscv_ntl_load(&d2, __RISCV_NTLH_INNERMOST_PRIVATE); // CHECK: load double{{.*}}align 8, !nontemporal !6, !riscv-nontemporal-domain !7
+ v4si1 = __riscv_ntl_load(&v4si2, __RISCV_NTLH_INNERMOST_PRIVATE); // CHECK: load <4 x i32>{{.*}}align 16, !nontemporal !6, !riscv-nontemporal-domain !7
+ v8ss1 = __riscv_ntl_load(&v8ss2, __RISCV_NTLH_INNERMOST_PRIVATE); // CHECK: load <8 x i16>{{.*}}align 16, !nontemporal !6, !riscv-nontemporal-domain !7
+ v16sc1 = __riscv_ntl_load(&v16sc2, __RISCV_NTLH_INNERMOST_PRIVATE); // CHECK: load <16 x i8>{{.*}}align 16, !nontemporal !6, !riscv-nontemporal-domain !7
+ *scvi1 = __riscv_ntl_load(scvi2, __RISCV_NTLH_INNERMOST_PRIVATE); // CHECK: load <vscale x 2 x i32>{{.*}}align 8, !nontemporal !6, !riscv-nontemporal-domain !7
+ *scvs1 = __riscv_ntl_load(scvs2, __RISCV_NTLH_INNERMOST_PRIVATE); // CHECK: load <vscale x 4 x i16>{{.*}}align 8, !nontemporal !6, !riscv-nontemporal-domain !7
+ *scvc1 = __riscv_ntl_load(scvc2, __RISCV_NTLH_INNERMOST_PRIVATE); // CHECK: load <vscale x 8 x i8>{{.*}}align 8, !nontemporal !6, !riscv-nontemporal-domain !7
- uc = __riscv_ntl_load(&sc, __RISCV_NTLH_ALL_PRIVATE); // CHECK: load i8{{.*}}align 1, !nontemporal !4, !riscv-nontemporal-domain !6
- sc = __riscv_ntl_load(&uc, __RISCV_NTLH_ALL_PRIVATE); // CHECK: load i8{{.*}}align 1, !nontemporal !4, !riscv-nontemporal-domain !6
- us = __riscv_ntl_load(&ss, __RISCV_NTLH_ALL_PRIVATE); // CHECK: load i16{{.*}}align 2, !nontemporal !4, !riscv-nontemporal-domain !6
- ss = __riscv_ntl_load(&us, __RISCV_NTLH_ALL_PRIVATE); // CHECK: load i16{{.*}}align 2, !nontemporal !4, !riscv-nontemporal-domain !6
- ui = __riscv_ntl_load(&si, __RISCV_NTLH_ALL_PRIVATE); // CHECK: load i32{{.*}}align 4, !nontemporal !4, !riscv-nontemporal-domain !6
- si = __riscv_ntl_load(&ui, __RISCV_NTLH_ALL_PRIVATE); // CHECK: load i32{{.*}}align 4, !nontemporal !4, !riscv-nontemporal-domain !6
- ull = __riscv_ntl_load(&sll, __RISCV_NTLH_ALL_PRIVATE); // CHECK: load i64{{.*}}align 8, !nontemporal !4, !riscv-nontemporal-domain !6
- sll = __riscv_ntl_load(&ull, __RISCV_NTLH_ALL_PRIVATE); // CHECK: load i64{{.*}}align 8, !nontemporal !4, !riscv-nontemporal-domain !6
- h1 = __riscv_ntl_load(&h2, __RISCV_NTLH_ALL_PRIVATE); // CHECK: load half{{.*}}align 2, !nontemporal !4, !riscv-nontemporal-domain !6
- f1 = __riscv_ntl_load(&f2, __RISCV_NTLH_ALL_PRIVATE); // CHECK: load float{{.*}}align 4, !nontemporal !4, !riscv-nontemporal-domain !6
- d1 = __riscv_ntl_load(&d2, __RISCV_NTLH_ALL_PRIVATE); // CHECK: load double{{.*}}align 8, !nontemporal !4, !riscv-nontemporal-domain !6
- v4si1 = __riscv_ntl_load(&v4si2, __RISCV_NTLH_ALL_PRIVATE); // CHECK: load <4 x i32>{{.*}}align 16, !nontemporal !4, !riscv-nontemporal-domain !6
- v8ss1 = __riscv_ntl_load(&v8ss2, __RISCV_NTLH_ALL_PRIVATE); // CHECK: load <8 x i16>{{.*}}align 16, !nontemporal !4, !riscv-nontemporal-domain !6
- v16sc1 = __riscv_ntl_load(&v16sc2, __RISCV_NTLH_ALL_PRIVATE); // CHECK: load <16 x i8>{{.*}}align 16, !nontemporal !4, !riscv-nontemporal-domain !6
- *scvi1 = __riscv_ntl_load(scvi2, __RISCV_NTLH_ALL_PRIVATE); // CHECK: load <vscale x 2 x i32>{{.*}}align 8, !nontemporal !4, !riscv-nontemporal-domain !6
- *scvs1 = __riscv_ntl_load(scvs2, __RISCV_NTLH_ALL_PRIVATE); // CHECK: load <vscale x 4 x i16>{{.*}}align 8, !nontemporal !4, !riscv-nontemporal-domain !6
- *scvc1 = __riscv_ntl_load(scvc2, __RISCV_NTLH_ALL_PRIVATE); // CHECK: load <vscale x 8 x i8>{{.*}}align 8, !nontemporal !4, !riscv-nontemporal-domain !6
+ uc = __riscv_ntl_load(&sc, __RISCV_NTLH_ALL_PRIVATE); // CHECK: load i8{{.*}}align 1, !nontemporal !6, !riscv-nontemporal-domain !8
+ sc = __riscv_ntl_load(&uc, __RISCV_NTLH_ALL_PRIVATE); // CHECK: load i8{{.*}}align 1, !nontemporal !6, !riscv-nontemporal-domain !8
+ us = __riscv_ntl_load(&ss, __RISCV_NTLH_ALL_PRIVATE); // CHECK: load i16{{.*}}align 2, !nontemporal !6, !riscv-nontemporal-domain !8
+ ss = __riscv_ntl_load(&us, __RISCV_NTLH_ALL_PRIVATE); // CHECK: load i16{{.*}}align 2, !nontemporal !6, !riscv-nontemporal-domain !8
+ ui = __riscv_ntl_load(&si, __RISCV_NTLH_ALL_PRIVATE); // CHECK: load i32{{.*}}align 4, !nontemporal !6, !riscv-nontemporal-domain !8
+ si = __riscv_ntl_load(&ui, __RISCV_NTLH_ALL_PRIVATE); // CHECK: load i32{{.*}}align 4, !nontemporal !6, !riscv-nontemporal-domain !8
+ ull = __riscv_ntl_load(&sll, __RISCV_NTLH_ALL_PRIVATE); // CHECK: load i64{{.*}}align 8, !nontemporal !6, !riscv-nontemporal-domain !8
+ sll = __riscv_ntl_load(&ull, __RISCV_NTLH_ALL_PRIVATE); // CHECK: load i64{{.*}}align 8, !nontemporal !6, !riscv-nontemporal-domain !8
+ h1 = __riscv_ntl_load(&h2, __RISCV_NTLH_ALL_PRIVATE); // CHECK: load half{{.*}}align 2, !nontemporal !6, !riscv-nontemporal-domain !8
+ f1 = __riscv_ntl_load(&f2, __RISCV_NTLH_ALL_PRIVATE); // CHECK: load float{{.*}}align 4, !nontemporal !6, !riscv-nontemporal-domain !8
+ d1 = __riscv_ntl_load(&d2, __RISCV_NTLH_ALL_PRIVATE); // CHECK: load double{{.*}}align 8, !nontemporal !6, !riscv-nontemporal-domain !8
+ v4si1 = __riscv_ntl_load(&v4si2, __RISCV_NTLH_ALL_PRIVATE); // CHECK: load <4 x i32>{{.*}}align 16, !nontemporal !6, !riscv-nontemporal-domain !8
+ v8ss1 = __riscv_ntl_load(&v8ss2, __RISCV_NTLH_ALL_PRIVATE); // CHECK: load <8 x i16>{{.*}}align 16, !nontemporal !6, !riscv-nontemporal-domain !8
+ v16sc1 = __riscv_ntl_load(&v16sc2, __RISCV_NTLH_ALL_PRIVATE); // CHECK: load <16 x i8>{{.*}}align 16, !nontemporal !6, !riscv-nontemporal-domain !8
+ *scvi1 = __riscv_ntl_load(scvi2, __RISCV_NTLH_ALL_PRIVATE); // CHECK: load <vscale x 2 x i32>{{.*}}align 8, !nontemporal !6, !riscv-nontemporal-domain !8
+ *scvs1 = __riscv_ntl_load(scvs2, __RISCV_NTLH_ALL_PRIVATE); // CHECK: load <vscale x 4 x i16>{{.*}}align 8, !nontemporal !6, !riscv-nontemporal-domain !8
+ *scvc1 = __riscv_ntl_load(scvc2, __RISCV_NTLH_ALL_PRIVATE); // CHECK: load <vscale x 8 x i8>{{.*}}align 8, !nontemporal !6, !riscv-nontemporal-domain !8
- uc = __riscv_ntl_load(&sc, __RISCV_NTLH_INNERMOST_SHARED); // CHECK: load i8{{.*}}align 1, !nontemporal !4, !riscv-nontemporal-domain !7
- sc = __riscv_ntl_load(&uc, __RISCV_NTLH_INNERMOST_SHARED); // CHECK: load i8{{.*}}align 1, !nontemporal !4, !riscv-nontemporal-domain !7
- us = __riscv_ntl_load(&ss, __RISCV_NTLH_INNERMOST_SHARED); // CHECK: load i16{{.*}}align 2, !nontemporal !4, !riscv-nontemporal-domain !7
- ss = __riscv_ntl_load(&us, __RISCV_NTLH_INNERMOST_SHARED); // CHECK: load i16{{.*}}align 2, !nontemporal !4, !riscv-nontemporal-domain !7
- ui = __riscv_ntl_load(&si, __RISCV_NTLH_INNERMOST_SHARED); // CHECK: load i32{{.*}}align 4, !nontemporal !4, !riscv-nontemporal-domain !7
- si = __riscv_ntl_load(&ui, __RISCV_NTLH_INNERMOST_SHARED); // CHECK: load i32{{.*}}align 4, !nontemporal !4, !riscv-nontemporal-domain !7
- ull = __riscv_ntl_load(&sll, __RISCV_NTLH_INNERMOST_SHARED); // CHECK: load i64{{.*}}align 8, !nontemporal !4, !riscv-nontemporal-domain !7
- sll = __riscv_ntl_load(&ull, __RISCV_NTLH_INNERMOST_SHARED); // CHECK: load i64{{.*}}align 8, !nontemporal !4, !riscv-nontemporal-domain !7
- h1 = __riscv_ntl_load(&h2, __RISCV_NTLH_INNERMOST_SHARED); // CHECK: load half{{.*}}align 2, !nontemporal !4, !riscv-nontemporal-domain !7
- f1 = __riscv_ntl_load(&f2, __RISCV_NTLH_INNERMOST_SHARED); // CHECK: load float{{.*}}align 4, !nontemporal !4, !riscv-nontemporal-domain !7
- d1 = __riscv_ntl_load(&d2, __RISCV_NTLH_INNERMOST_SHARED); // CHECK: load double{{.*}}align 8, !nontemporal !4, !riscv-nontemporal-domain !7
- v4si1 = __riscv_ntl_load(&v4si2, __RISCV_NTLH_INNERMOST_SHARED); // CHECK: load <4 x i32>{{.*}}align 16, !nontemporal !4, !riscv-nontemporal-domain !7
- v8ss1 = __riscv_ntl_load(&v8ss2, __RISCV_NTLH_INNERMOST_SHARED); // CHECK: load <8 x i16>{{.*}}align 16, !nontemporal !4, !riscv-nontemporal-domain !7
- v16sc1 = __riscv_ntl_load(&v16sc2, __RISCV_NTLH_INNERMOST_SHARED); // CHECK: load <16 x i8>{{.*}}align 16, !nontemporal !4, !riscv-nontemporal-domain !7
- *scvi1 = __riscv_ntl_load(scvi2, __RISCV_NTLH_INNERMOST_SHARED); // CHECK: load <vscale x 2 x i32>{{.*}}align 8, !nontemporal !4, !riscv-nontemporal-domain !7
- *scvs1 = __riscv_ntl_load(scvs2, __RISCV_NTLH_INNERMOST_SHARED); // CHECK: load <vscale x 4 x i16>{{.*}}align 8, !nontemporal !4, !riscv-nontemporal-domain !7
- *scvc1 = __riscv_ntl_load(scvc2, __RISCV_NTLH_INNERMOST_SHARED); // CHECK: load <vscale x 8 x i8>{{.*}}align 8, !nontemporal !4, !riscv-nontemporal-domain !7
+ uc = __riscv_ntl_load(&sc, __RISCV_NTLH_INNERMOST_SHARED); // CHECK: load i8{{.*}}align 1, !nontemporal !6, !riscv-nontemporal-domain !9
+ sc = __riscv_ntl_load(&uc, __RISCV_NTLH_INNERMOST_SHARED); // CHECK: load i8{{.*}}align 1, !nontemporal !6, !riscv-nontemporal-domain !9
+ us = __riscv_ntl_load(&ss, __RISCV_NTLH_INNERMOST_SHARED); // CHECK: load i16{{.*}}align 2, !nontemporal !6, !riscv-nontemporal-domain !9
+ ss = __riscv_ntl_load(&us, __RISCV_NTLH_INNERMOST_SHARED); // CHECK: load i16{{.*}}align 2, !nontemporal !6, !riscv-nontemporal-domain !9
+ ui = __riscv_ntl_load(&si, __RISCV_NTLH_INNERMOST_SHARED); // CHECK: load i32{{.*}}align 4, !nontemporal !6, !riscv-nontemporal-domain !9
+ si = __riscv_ntl_load(&ui, __RISCV_NTLH_INNERMOST_SHARED); // CHECK: load i32{{.*}}align 4, !nontemporal !6, !riscv-nontemporal-domain !9
+ ull = __riscv_ntl_load(&sll, __RISCV_NTLH_INNERMOST_SHARED); // CHECK: load i64{{.*}}align 8, !nontemporal !6, !riscv-nontemporal-domain !9
+ sll = __riscv_ntl_load(&ull, __RISCV_NTLH_INNERMOST_SHARED); // CHECK: load i64{{.*}}align 8, !nontemporal !6, !riscv-nontemporal-domain !9
+ h1 = __riscv_ntl_load(&h2, __RISCV_NTLH_INNERMOST_SHARED); // CHECK: load half{{.*}}align 2, !nontemporal !6, !riscv-nontemporal-domain !9
+ f1 = __riscv_ntl_load(&f2, __RISCV_NTLH_INNERMOST_SHARED); // CHECK: load float{{.*}}align 4, !nontemporal !6, !riscv-nontemporal-domain !9
+ d1 = __riscv_ntl_load(&d2, __RISCV_NTLH_INNERMOST_SHARED); // CHECK: load double{{.*}}align 8, !nontemporal !6, !riscv-nontemporal-domain !9
+ v4si1 = __riscv_ntl_load(&v4si2, __RISCV_NTLH_INNERMOST_SHARED); // CHECK: load <4 x i32>{{.*}}align 16, !nontemporal !6, !riscv-nontemporal-domain !9
+ v8ss1 = __riscv_ntl_load(&v8ss2, __RISCV_NTLH_INNERMOST_SHARED); // CHECK: load <8 x i16>{{.*}}align 16, !nontemporal !6, !riscv-nontemporal-domain !9
+ v16sc1 = __riscv_ntl_load(&v16sc2, __RISCV_NTLH_INNERMOST_SHARED); // CHECK: load <16 x i8>{{.*}}align 16, !nontemporal !6, !riscv-nontemporal-domain !9
+ *scvi1 = __riscv_ntl_load(scvi2, __RISCV_NTLH_INNERMOST_SHARED); // CHECK: load <vscale x 2 x i32>{{.*}}align 8, !nontemporal !6, !riscv-nontemporal-domain !9
+ *scvs1 = __riscv_ntl_load(scvs2, __RISCV_NTLH_INNERMOST_SHARED); // CHECK: load <vscale x 4 x i16>{{.*}}align 8, !nontemporal !6, !riscv-nontemporal-domain !9
+ *scvc1 = __riscv_ntl_load(scvc2, __RISCV_NTLH_INNERMOST_SHARED); // CHECK: load <vscale x 8 x i8>{{.*}}align 8, !nontemporal !6, !riscv-nontemporal-domain !9
- uc = __riscv_ntl_load(&sc, __RISCV_NTLH_ALL); // CHECK: load i8{{.*}}align 1, !nontemporal !4, !riscv-nontemporal-domain !8
- sc = __riscv_ntl_load(&uc, __RISCV_NTLH_ALL); // CHECK: load i8{{.*}}align 1, !nontemporal !4, !riscv-nontemporal-domain !8
- us = __riscv_ntl_load(&ss, __RISCV_NTLH_ALL); // CHECK: load i16{{.*}}align 2, !nontemporal !4, !riscv-nontemporal-domain !8
- ss = __riscv_ntl_load(&us, __RISCV_NTLH_ALL); // CHECK: load i16{{.*}}align 2, !nontemporal !4, !riscv-nontemporal-domain !8
- ui = __riscv_ntl_load(&si, __RISCV_NTLH_ALL); // CHECK: load i32{{.*}}align 4, !nontemporal !4, !riscv-nontemporal-domain !8
- si = __riscv_ntl_load(&ui, __RISCV_NTLH_ALL); // CHECK: load i32{{.*}}align 4, !nontemporal !4, !riscv-nontemporal-domain !8
- ull = __riscv_ntl_load(&sll, __RISCV_NTLH_ALL); // CHECK: load i64{{.*}}align 8, !nontemporal !4, !riscv-nontemporal-domain !8
- sll = __riscv_ntl_load(&ull, __RISCV_NTLH_ALL); // CHECK: load i64{{.*}}align 8, !nontemporal !4, !riscv-nontemporal-domain !8
- h1 = __riscv_ntl_load(&h2, __RISCV_NTLH_ALL); // CHECK: load half{{.*}}align 2, !nontemporal !4, !riscv-nontemporal-domain !8
- f1 = __riscv_ntl_load(&f2, __RISCV_NTLH_ALL); // CHECK: load float{{.*}}align 4, !nontemporal !4, !riscv-nontemporal-domain !8
- d1 = __riscv_ntl_load(&d2, __RISCV_NTLH_ALL); // CHECK: load double{{.*}}align 8, !nontemporal !4, !riscv-nontemporal-domain !8
- v4si1 = __riscv_ntl_load(&v4si2, __RISCV_NTLH_ALL); // CHECK: load <4 x i32>{{.*}}align 16, !nontemporal !4, !riscv-nontemporal-domain !8
- v8ss1 = __riscv_ntl_load(&v8ss2, __RISCV_NTLH_ALL); // CHECK: load <8 x i16>{{.*}}align 16, !nontemporal !4, !riscv-nontemporal-domain !8
- v16sc1 = __riscv_ntl_load(&v16sc2, __RISCV_NTLH_ALL); // CHECK: load <16 x i8>{{.*}}align 16, !nontemporal !4, !riscv-nontemporal-domain !8
- *scvi1 = __riscv_ntl_load(scvi2, __RISCV_NTLH_ALL); // CHECK: load <vscale x 2 x i32>{{.*}}align 8, !nontemporal !4, !riscv-nontemporal-domain !8
- *scvs1 = __riscv_ntl_load(scvs2, __RISCV_NTLH_ALL); // CHECK: load <vscale x 4 x i16>{{.*}}align 8, !nontemporal !4, !riscv-nontemporal-domain !8
- *scvc1 = __riscv_ntl_load(scvc2, __RISCV_NTLH_ALL); // CHECK: load <vscale x 8 x i8>{{.*}}align 8, !nontemporal !4, !riscv-nontemporal-domain !8
+ uc = __riscv_ntl_load(&sc, __RISCV_NTLH_ALL); // CHECK: load i8{{.*}}align 1, !nontemporal !6, !riscv-nontemporal-domain !10
+ sc = __riscv_ntl_load(&uc, __RISCV_NTLH_ALL); // CHECK: load i8{{.*}}align 1, !nontemporal !6, !riscv-nontemporal-domain !10
+ us = __riscv_ntl_load(&ss, __RISCV_NTLH_ALL); // CHECK: load i16{{.*}}align 2, !nontemporal !6, !riscv-nontemporal-domain !10
+ ss = __riscv_ntl_load(&us, __RISCV_NTLH_ALL); // CHECK: load i16{{.*}}align 2, !nontemporal !6, !riscv-nontemporal-domain !10
+ ui = __riscv_ntl_load(&si, __RISCV_NTLH_ALL); // CHECK: load i32{{.*}}align 4, !nontemporal !6, !riscv-nontemporal-domain !10
+ si = __riscv_ntl_load(&ui, __RISCV_NTLH_ALL); // CHECK: load i32{{.*}}align 4, !nontemporal !6, !riscv-nontemporal-domain !10
+ ull = __riscv_ntl_load(&sll, __RISCV_NTLH_ALL); // CHECK: load i64{{.*}}align 8, !nontemporal !6, !riscv-nontemporal-domain !10
+ sll = __riscv_ntl_load(&ull, __RISCV_NTLH_ALL); // CHECK: load i64{{.*}}align 8, !nontemporal !6, !riscv-nontemporal-domain !10
+ h1 = __riscv_ntl_load(&h2, __RISCV_NTLH_ALL); // CHECK: load half{{.*}}align 2, !nontemporal !6, !riscv-nontemporal-domain !10
+ f1 = __riscv_ntl_load(&f2, __RISCV_NTLH_ALL); // CHECK: load float{{.*}}align 4, !nontemporal !6, !riscv-nontemporal-domain !10
+ d1 = __riscv_ntl_load(&d2, __RISCV_NTL...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/80760
More information about the cfe-commits
mailing list