tmatheson created this revision.
Herald added subscribers: danielkiss, dmgreen, kristof.beyls.
tmatheson requested review of this revision.
Herald added a project: clang.
Herald added a subscriber: cfe-commits.
Use of bitcast resulted in lanes being swapped for vcreateq with big
endian. Fix this by using vreinterpret. No code change for little
endian. Adds IR lit test.
Repository:
rG LLVM Github Monorepo
https://reviews.llvm.org/D101606
Files:
clang/include/clang/Basic/arm_mve.td
clang/test/CodeGen/arm-mve-intrinsics/admin.c
Index: clang/test/CodeGen/arm-mve-intrinsics/admin.c
===================================================================
--- clang/test/CodeGen/arm-mve-intrinsics/admin.c
+++ clang/test/CodeGen/arm-mve-intrinsics/admin.c
@@ -1,6 +1,9 @@
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
-// RUN: %clang_cc1 -triple thumbv8.1m.main-none-none-eabi -target-feature +mve.fp -mfloat-abi hard -fallow-half-arguments-and-returns -O0 -disable-O0-optnone -S -emit-llvm -o - %s | opt -S -mem2reg -sroa -early-cse | FileCheck %s
-// RUN: %clang_cc1 -triple thumbv8.1m.main-none-none-eabi -target-feature +mve.fp -mfloat-abi hard -fallow-half-arguments-and-returns -O0 -disable-O0-optnone -DPOLYMORPHIC -S -emit-llvm -o - %s | opt -S -mem2reg -sroa -early-cse | FileCheck %s
+// RUN: %clang_cc1 -triple thumbv8.1m.main-none-none-eabi -target-feature +mve.fp -mfloat-abi hard -fallow-half-arguments-and-returns -O0 -disable-O0-optnone -S -emit-llvm -o - %s | opt -S -mem2reg -sroa -early-cse | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-LE
+// RUN: %clang_cc1 -triple thumbv8.1m.main-none-none-eabi -target-feature +mve.fp -mfloat-abi hard -fallow-half-arguments-and-returns -O0 -disable-O0-optnone -DPOLYMORPHIC -S -emit-llvm -o - %s | opt -S -mem2reg -sroa -early-cse | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-LE
+// RUN: %clang_cc1 -triple thumbebv8.1m.main-none-none-eabi -target-feature +mve.fp -mfloat-abi hard -fallow-half-arguments-and-returns -O0 -disable-O0-optnone -S -emit-llvm -o - %s | opt -S -mem2reg -sroa -early-cse | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-BE
+// RUN: %clang_cc1 -triple thumbebv8.1m.main-none-none-eabi -target-feature +mve.fp -mfloat-abi hard -fallow-half-arguments-and-returns -O0 -disable-O0-optnone -DPOLYMORPHIC -S -emit-llvm -o - %s | opt -S -mem2reg -sroa -early-cse | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-BE
+
#include <arm_mve.h>
@@ -8,7 +11,8 @@
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = insertelement <2 x i64> undef, i64 [[A:%.*]], i64 0
// CHECK-NEXT: [[TMP1:%.*]] = insertelement <2 x i64> [[TMP0]], i64 [[B:%.*]], i64 1
-// CHECK-NEXT: [[TMP2:%.*]] = bitcast <2 x i64> [[TMP1]] to <8 x half>
+// CHECK-LE-NEXT: [[TMP2:%.*]] = bitcast <2 x i64> [[TMP1]] to <8 x half>
+// CHECK-BE-NEXT: [[TMP2:%.*]] = call <8 x half> @llvm.arm.mve.vreinterpretq.v8f16.v2i64(<2 x i64> [[TMP1]])
// CHECK-NEXT: ret <8 x half> [[TMP2]]
//
float16x8_t test_vcreateq_f16(uint64_t a, uint64_t b)
@@ -20,7 +24,8 @@
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = insertelement <2 x i64> undef, i64 [[A:%.*]], i64 0
// CHECK-NEXT: [[TMP1:%.*]] = insertelement <2 x i64> [[TMP0]], i64 [[B:%.*]], i64 1
-// CHECK-NEXT: [[TMP2:%.*]] = bitcast <2 x i64> [[TMP1]] to <4 x float>
+// CHECK-LE-NEXT: [[TMP2:%.*]] = bitcast <2 x i64> [[TMP1]] to <4 x float>
+// CHECK-BE-NEXT: [[TMP2:%.*]] = call <4 x float> @llvm.arm.mve.vreinterpretq.v4f32.v2i64(<2 x i64> [[TMP1]])
// CHECK-NEXT: ret <4 x float> [[TMP2]]
//
float32x4_t test_vcreateq_f32(uint64_t a, uint64_t b)
@@ -32,7 +37,8 @@
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = insertelement <2 x i64> undef, i64 [[A:%.*]], i64 0
// CHECK-NEXT: [[TMP1:%.*]] = insertelement <2 x i64> [[TMP0]], i64 [[B:%.*]], i64 1
-// CHECK-NEXT: [[TMP2:%.*]] = bitcast <2 x i64> [[TMP1]] to <8 x i16>
+// CHECK-LE-NEXT: [[TMP2:%.*]] = bitcast <2 x i64> [[TMP1]] to <8 x i16>
+// CHECK-BE-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.vreinterpretq.v8i16.v2i64(<2 x i64> [[TMP1]])
// CHECK-NEXT: ret <8 x i16> [[TMP2]]
//
int16x8_t test_vcreateq_s16(uint64_t a, uint64_t b)
@@ -44,7 +50,8 @@
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = insertelement <2 x i64> undef, i64 [[A:%.*]], i64 0
// CHECK-NEXT: [[TMP1:%.*]] = insertelement <2 x i64> [[TMP0]], i64 [[B:%.*]], i64 1
-// CHECK-NEXT: [[TMP2:%.*]] = bitcast <2 x i64> [[TMP1]] to <4 x i32>
+// CHECK-LE-NEXT: [[TMP2:%.*]] = bitcast <2 x i64> [[TMP1]] to <4 x i32>
+// CHECK-BE-NEXT: [[TMP2:%.*]] = call <4 x i32> @llvm.arm.mve.vreinterpretq.v4i32.v2i64(<2 x i64> [[TMP1]])
// CHECK-NEXT: ret <4 x i32> [[TMP2]]
//
int32x4_t test_vcreateq_s32(uint64_t a, uint64_t b)
@@ -67,7 +74,8 @@
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = insertelement <2 x i64> undef, i64 [[A:%.*]], i64 0
// CHECK-NEXT: [[TMP1:%.*]] = insertelement <2 x i64> [[TMP0]], i64 [[B:%.*]], i64 1
-// CHECK-NEXT: [[TMP2:%.*]] = bitcast <2 x i64> [[TMP1]] to <16 x i8>
+// CHECK-LE-NEXT: [[TMP2:%.*]] = bitcast <2 x i64> [[TMP1]] to <16 x i8>
+// CHECK-BE-NEXT: [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.vreinterpretq.v16i8.v2i64(<2 x i64> [[TMP1]])
// CHECK-NEXT: ret <16 x i8> [[TMP2]]
//
int8x16_t test_vcreateq_s8(uint64_t a, uint64_t b)
@@ -79,7 +87,8 @@
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = insertelement <2 x i64> undef, i64 [[A:%.*]], i64 0
// CHECK-NEXT: [[TMP1:%.*]] = insertelement <2 x i64> [[TMP0]], i64 [[B:%.*]], i64 1
-// CHECK-NEXT: [[TMP2:%.*]] = bitcast <2 x i64> [[TMP1]] to <8 x i16>
+// CHECK-LE-NEXT: [[TMP2:%.*]] = bitcast <2 x i64> [[TMP1]] to <8 x i16>
+// CHECK-BE-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.vreinterpretq.v8i16.v2i64(<2 x i64> [[TMP1]])
// CHECK-NEXT: ret <8 x i16> [[TMP2]]
//
uint16x8_t test_vcreateq_u16(uint64_t a, uint64_t b)
@@ -91,7 +100,8 @@
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = insertelement <2 x i64> undef, i64 [[A:%.*]], i64 0
// CHECK-NEXT: [[TMP1:%.*]] = insertelement <2 x i64> [[TMP0]], i64 [[B:%.*]], i64 1
-// CHECK-NEXT: [[TMP2:%.*]] = bitcast <2 x i64> [[TMP1]] to <4 x i32>
+// CHECK-LE-NEXT: [[TMP2:%.*]] = bitcast <2 x i64> [[TMP1]] to <4 x i32>
+// CHECK-BE-NEXT: [[TMP2:%.*]] = call <4 x i32> @llvm.arm.mve.vreinterpretq.v4i32.v2i64(<2 x i64> [[TMP1]])
// CHECK-NEXT: ret <4 x i32> [[TMP2]]
//
uint32x4_t test_vcreateq_u32(uint64_t a, uint64_t b)
@@ -114,7 +124,8 @@
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = insertelement <2 x i64> undef, i64 [[A:%.*]], i64 0
// CHECK-NEXT: [[TMP1:%.*]] = insertelement <2 x i64> [[TMP0]], i64 [[B:%.*]], i64 1
-// CHECK-NEXT: [[TMP2:%.*]] = bitcast <2 x i64> [[TMP1]] to <16 x i8>
+// CHECK-LE-NEXT: [[TMP2:%.*]] = bitcast <2 x i64> [[TMP1]] to <16 x i8>
+// CHECK-BE-NEXT: [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.vreinterpretq.v16i8.v2i64(<2 x i64> [[TMP1]])
// CHECK-NEXT: ret <16 x i8> [[TMP2]]
//
uint8x16_t test_vcreateq_u8(uint64_t a, uint64_t b)
Index: clang/include/clang/Basic/arm_mve.td
===================================================================
--- clang/include/clang/Basic/arm_mve.td
+++ clang/include/clang/Basic/arm_mve.td
@@ -1543,7 +1543,7 @@
let params = T.All in {
let pnt = PNT_None in {
def vcreateq: Intrinsic<Vector, (args u64:$a, u64:$b),
- (bitcast (ielt_const (ielt_const (undef VecOf<u64>), $a, 0),
+ (vreinterpret (ielt_const (ielt_const (undef VecOf<u64>), $a, 0),
$b, 1), Vector)>;
def vuninitializedq: Intrinsic<Vector, (args), (undef Vector)>;
}
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
