shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions 6 Packages Projects Releases Wiki Activity
llvm-project/clang/test/OpenMP/simd_metadata.c
Roman Lebedev 7ea46aee36
Revert "[AssumeBundles] Use operand bundles to encode alignment assumptions" 
Assume bundle can have more than one entry with the same name,
but at least AlignmentFromAssumptionsPass::extractAlignmentInfo() uses
getOperandBundle("align"), which internally assumes that it isn't the
case, and happily crashes otherwise.

Minimal reduced reproducer: run `opt -alignment-from-assumptions` on

target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"

%0 = type { i64, %1*, i8*, i64, %2, i32, %3*, i8* }
%1 = type opaque
%2 = type { i8, i8, i16 }
%3 = type { i32, i32, i32, i32 }

; Function Attrs: nounwind
define i32 @f(%0* noalias nocapture readonly %arg, %0* noalias %arg1) local_unnamed_addr #0 {
bb:
  call void @llvm.assume(i1 true) [ "align"(%0* %arg, i64 8), "align"(%0* %arg1, i64 8) ]
  ret i32 0
}

; Function Attrs: nounwind willreturn
declare void @llvm.assume(i1) #1

attributes #0 = { nounwind "reciprocal-estimates"="none" }
attributes #1 = { nounwind willreturn }


This is what we'd have with -mllvm -enable-knowledge-retention

This reverts commit c95ffadb2474a4d8c4f598d94d35a9f31d9606cb.
2020-07-04 23:49:23 +03:00

163 lines
9.4 KiB
C
Raw Blame History

// RUN: %clang_cc1 -fopenmp -triple x86_64-unknown-unknown -emit-llvm %s -o - | FileCheck %s -check-prefix=CHECK -check-prefix=X86
// RUN: %clang_cc1 -fopenmp -triple x86_64-unknown-unknown -target-feature +avx -emit-llvm %s -o - | FileCheck %s -check-prefix=CHECK -check-prefix=X86-AVX
// RUN: %clang_cc1 -fopenmp -triple x86_64-unknown-unknown -target-feature +avx512f -emit-llvm %s -o - | FileCheck %s -check-prefix=CHECK -check-prefix=X86-AVX512
// RUN: %clang_cc1 -fopenmp -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s -check-prefix=CHECK -check-prefix=X86
// RUN: %clang_cc1 -fopenmp -triple i386-unknown-unknown -target-feature +avx -emit-llvm %s -o - | FileCheck %s -check-prefix=CHECK -check-prefix=X86-AVX
// RUN: %clang_cc1 -fopenmp -triple i386-unknown-unknown -target-feature +avx512f -emit-llvm %s -o - | FileCheck %s -check-prefix=CHECK -check-prefix=X86-AVX512
// RUN: %clang_cc1 -fopenmp -triple powerpc64-unknown-unknown -emit-llvm %s -o - | FileCheck %s -check-prefix=CHECK -check-prefix=PPC
// RUN: %clang_cc1 -fopenmp -triple powerpc64-unknown-unknown -target-abi elfv1-qpx -emit-llvm %s -o - | FileCheck %s -check-prefix=CHECK -check-prefix=PPC-QPX
// RUN: %clang_cc1 -fopenmp-simd -triple x86_64-unknown-unknown -emit-llvm %s -o - | FileCheck %s -check-prefix=CHECK -check-prefix=X86
// RUN: %clang_cc1 -fopenmp-simd -triple x86_64-unknown-unknown -target-feature +avx -emit-llvm %s -o - | FileCheck %s -check-prefix=CHECK -check-prefix=X86-AVX
// RUN: %clang_cc1 -fopenmp-simd -triple x86_64-unknown-unknown -target-feature +avx512f -emit-llvm %s -o - | FileCheck %s -check-prefix=CHECK -check-prefix=X86-AVX512
// RUN: %clang_cc1 -fopenmp-simd -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s -check-prefix=CHECK -check-prefix=X86
// RUN: %clang_cc1 -fopenmp-simd -triple i386-unknown-unknown -target-feature +avx -emit-llvm %s -o - | FileCheck %s -check-prefix=CHECK -check-prefix=X86-AVX
// RUN: %clang_cc1 -fopenmp-simd -triple i386-unknown-unknown -target-feature +avx512f -emit-llvm %s -o - | FileCheck %s -check-prefix=CHECK -check-prefix=X86-AVX512
// RUN: %clang_cc1 -fopenmp-simd -triple powerpc64-unknown-unknown -emit-llvm %s -o - | FileCheck %s -check-prefix=CHECK -check-prefix=PPC
// RUN: %clang_cc1 -fopenmp-simd -triple powerpc64-unknown-unknown -target-abi elfv1-qpx -emit-llvm %s -o - | FileCheck %s -check-prefix=CHECK -check-prefix=PPC-QPX
void h1(float *c, float *a, double b[], int size)
{
// CHECK-LABEL: define void @h1
int t = 0;
#pragma omp simd safelen(16) linear(t) aligned(c:32) aligned(a,b)
// CHECK: [[C_PTRINT:%.+]] = ptrtoint
// CHECK-NEXT: [[C_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[C_PTRINT]], 31
// CHECK-NEXT: [[C_MASKCOND:%.+]] = icmp eq i{{[0-9]+}} [[C_MASKEDPTR]], 0
// CHECK-NEXT: call void @llvm.assume(i1 [[C_MASKCOND]])
// CHECK: [[A_PTRINT:%.+]] = ptrtoint
// X86-NEXT: [[A_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[A_PTRINT]], 15
// X86-AVX-NEXT: [[A_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[A_PTRINT]], 31
// X86-AVX512-NEXT: [[A_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[A_PTRINT]], 63
// PPC-NEXT: [[A_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[A_PTRINT]], 15
// PPC-QPX-NEXT: [[A_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[A_PTRINT]], 15
// CHECK-NEXT: [[A_MASKCOND:%.+]] = icmp eq i{{[0-9]+}} [[A_MASKEDPTR]], 0
// CHECK-NEXT: call void @llvm.assume(i1 [[A_MASKCOND]])
// CHECK: [[B_PTRINT:%.+]] = ptrtoint
// X86-NEXT: [[B_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[B_PTRINT]], 15
// X86-AVX-NEXT: [[B_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[B_PTRINT]], 31
// X86-AVX512-NEXT: [[B_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[B_PTRINT]], 63
// PPC-NEXT: [[B_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[B_PTRINT]], 15
// PPC-QPX-NEXT: [[B_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[B_PTRINT]], 31
// CHECK-NEXT: [[B_MASKCOND:%.+]] = icmp eq i{{[0-9]+}} [[B_MASKEDPTR]], 0
// CHECK-NEXT: call void @llvm.assume(i1 [[B_MASKCOND]])
for (int i = 0; i < size; ++i) {
c[i] = a[i] * a[i] + b[i] * b[t];
++t;
}
// do not emit llvm.access.group metadata due to usage of safelen clause.
// CHECK-NOT: store float {{.+}}, float* {{.+}}, align {{.+}}, !llvm.access.group {{![0-9]+}}
#pragma omp simd safelen(16) linear(t) aligned(c:32) aligned(a,b) simdlen(8)
// CHECK: [[C_PTRINT:%.+]] = ptrtoint
// CHECK-NEXT: [[C_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[C_PTRINT]], 31
// CHECK-NEXT: [[C_MASKCOND:%.+]] = icmp eq i{{[0-9]+}} [[C_MASKEDPTR]], 0
// CHECK-NEXT: call void @llvm.assume(i1 [[C_MASKCOND]])
// CHECK: [[A_PTRINT:%.+]] = ptrtoint
// X86-NEXT: [[A_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[A_PTRINT]], 15
// X86-AVX-NEXT: [[A_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[A_PTRINT]], 31
// X86-AVX512-NEXT: [[A_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[A_PTRINT]], 63
// PPC-NEXT: [[A_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[A_PTRINT]], 15
// PPC-QPX-NEXT: [[A_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[A_PTRINT]], 15
// CHECK-NEXT: [[A_MASKCOND:%.+]] = icmp eq i{{[0-9]+}} [[A_MASKEDPTR]], 0
// CHECK-NEXT: call void @llvm.assume(i1 [[A_MASKCOND]])
// CHECK: [[B_PTRINT:%.+]] = ptrtoint
// X86-NEXT: [[B_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[B_PTRINT]], 15
// X86-AVX-NEXT: [[B_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[B_PTRINT]], 31
// X86-AVX512-NEXT: [[B_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[B_PTRINT]], 63
// PPC-NEXT: [[B_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[B_PTRINT]], 15
// PPC-QPX-NEXT: [[B_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[B_PTRINT]], 31
// CHECK-NEXT: [[B_MASKCOND:%.+]] = icmp eq i{{[0-9]+}} [[B_MASKEDPTR]], 0
// CHECK-NEXT: call void @llvm.assume(i1 [[B_MASKCOND]])
for (int i = 0; i < size; ++i) {
c[i] = a[i] * a[i] + b[i] * b[t];
++t;
}
// do not emit llvm.access.group metadata due to usage of safelen clause.
// CHECK-NOT: store float {{.+}}, float* {{.+}}, align {{.+}}, !llvm.access.group {{![0-9]+}}
#pragma omp simd linear(t) aligned(c:32) aligned(a,b) simdlen(8)
// CHECK: [[C_PTRINT:%.+]] = ptrtoint
// CHECK-NEXT: [[C_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[C_PTRINT]], 31
// CHECK-NEXT: [[C_MASKCOND:%.+]] = icmp eq i{{[0-9]+}} [[C_MASKEDPTR]], 0
// CHECK-NEXT: call void @llvm.assume(i1 [[C_MASKCOND]])
// CHECK: [[A_PTRINT:%.+]] = ptrtoint
// X86-NEXT: [[A_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[A_PTRINT]], 15
// X86-AVX-NEXT: [[A_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[A_PTRINT]], 31
// X86-AVX512-NEXT: [[A_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[A_PTRINT]], 63
// PPC-NEXT: [[A_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[A_PTRINT]], 15
// PPC-QPX-NEXT: [[A_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[A_PTRINT]], 15
// CHECK-NEXT: [[A_MASKCOND:%.+]] = icmp eq i{{[0-9]+}} [[A_MASKEDPTR]], 0
// CHECK-NEXT: call void @llvm.assume(i1 [[A_MASKCOND]])
// CHECK: [[B_PTRINT:%.+]] = ptrtoint
// X86-NEXT: [[B_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[B_PTRINT]], 15
// X86-AVX-NEXT: [[B_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[B_PTRINT]], 31
// X86-AVX512-NEXT: [[B_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[B_PTRINT]], 63
// PPC-NEXT: [[B_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[B_PTRINT]], 15
// PPC-QPX-NEXT: [[B_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[B_PTRINT]], 31
// CHECK-NEXT: [[B_MASKCOND:%.+]] = icmp eq i{{[0-9]+}} [[B_MASKEDPTR]], 0
// CHECK-NEXT: call void @llvm.assume(i1 [[B_MASKCOND]])
for (int i = 0; i < size; ++i) {
c[i] = a[i] * a[i] + b[i] * b[t];
++t;
// CHECK: store float {{.+}}, float* {{.+}}, align {{.+}}, !llvm.access.group ![[ACCESS_GROUP_7:[0-9]+]]
}
}
void h2(float *c, float *a, float *b, int size)
{
// CHECK-LABEL: define void @h2
int t = 0;
#pragma omp simd linear(t)
for (int i = 0; i < size; ++i) {
c[i] = a[i] * a[i] + b[i] * b[t];
++t;
// CHECK: store float {{.+}}, float* {{.+}}, align {{.+}}, !llvm.access.group ![[ACCESS_GROUP_10:[0-9]+]]
}
// CHECK: br label %{{.+}}, !llvm.loop [[LOOP_H2_HEADER:![0-9]+]]
}
void h3(float *c, float *a, float *b, int size)
{
// CHECK-LABEL: define void @h3
#pragma omp simd
for (int i = 0; i < size; ++i) {
for (int j = 0; j < size; ++j) {
c[j*i] = a[i] * b[j];
}
// CHECK: store float {{.+}}, float* {{.+}}, align {{.+}}, !llvm.access.group ![[ACCESS_GROUP_13:[0-9]+]]
}
// CHECK: br label %{{.+}}, !llvm.loop [[LOOP_H3_HEADER:![0-9]+]]
}
// Metadata for h1:
// CHECK: [[LOOP_H1_HEADER:![0-9]+]] = distinct !{[[LOOP_H1_HEADER]], [[LOOP_WIDTH_16:![0-9]+]], [[LOOP_VEC_ENABLE:![0-9]+]]}
// CHECK: [[LOOP_WIDTH_16]] = !{!"llvm.loop.vectorize.width", i32 16}
// CHECK: [[LOOP_VEC_ENABLE]] = !{!"llvm.loop.vectorize.enable", i1 true}
// CHECK: [[LOOP_H1_HEADER:![0-9]+]] = distinct !{[[LOOP_H1_HEADER]], [[LOOP_WIDTH_8:![0-9]+]], [[LOOP_VEC_ENABLE]]}
// CHECK: [[LOOP_WIDTH_8]] = !{!"llvm.loop.vectorize.width", i32 8}
// CHECK: ![[ACCESS_GROUP_7]] = distinct !{}
// CHECK: [[LOOP_H1_HEADER:![0-9]+]] = distinct !{[[LOOP_H1_HEADER]], ![[PARALLEL_ACCESSES_9:[0-9]+]], [[LOOP_WIDTH_8]], [[LOOP_VEC_ENABLE]]}
// CHECK: ![[PARALLEL_ACCESSES_9]] = !{!"llvm.loop.parallel_accesses", ![[ACCESS_GROUP_7]]}
//
// Metadata for h2:
// CHECK: ![[ACCESS_GROUP_10]] = distinct !{}
// CHECK: [[LOOP_H2_HEADER]] = distinct !{[[LOOP_H2_HEADER]], ![[PARALLEL_ACCESSES_12:[0-9]+]], [[LOOP_VEC_ENABLE]]}
// CHECK: ![[PARALLEL_ACCESSES_12]] = !{!"llvm.loop.parallel_accesses", ![[ACCESS_GROUP_10]]}
//
// Metadata for h3:
// CHECK: ![[ACCESS_GROUP_13]] = distinct !{}
// CHECK: [[LOOP_H3_HEADER]] = distinct !{[[LOOP_H3_HEADER]], ![[PARALLEL_ACCESSES_15:[0-9]+]], [[LOOP_VEC_ENABLE]]}
// CHECK: ![[PARALLEL_ACCESSES_15]] = !{!"llvm.loop.parallel_accesses", ![[ACCESS_GROUP_13]]}
//
Reference in New Issue View Git Blame Copy Permalink