================
@@ -0,0 +1,101 @@
+// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
UTC_ARGS: --version 5
+// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve
-target-feature +sve2 -target-feature +fp8 -disable-O0-optnone -Werror -Wall
-emit-llvm -o - %s | opt -S -p mem2reg,instcombine,tailcallelim | FileCheck %s
+// RUN: %clang_cc1 -x c++ -triple aarch64-none-linux-gnu -target-feature +sme
-target-feature +sme2 -target-feature +fp8 -disable-O0-optnone -Werror -Wall
-emit-llvm -o - %s | opt -S -p mem2reg,instcombine,tailcallelim | FileCheck %s
-check-prefix=CHECK-CXX
+
+// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -triple
aarch64-none-linux-gnu -target-feature +sme -target-feature +sme2
-target-feature +fp8 -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt
-S -p mem2reg,instcombine,tailcallelim | FileCheck %s
+// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -x c++ -triple
aarch64-none-linux-gnu -target-feature +sve -target-feature +sve2
-target-feature +fp8 -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt
-S -p mem2reg,instcombine,tailcallelim | FileCheck %s -check-prefix=CHECK-CXX
+
+// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve
-target-feature +sve2 -target-feature +fp8 -S -disable-O0-optnone -Werror -Wall
-o /dev/null %s
+// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sme
-target-feature +sme2 -target-feature +fp8 -S -disable-O0-optnone -Werror -Wall
-o /dev/null %s
+
+// REQUIRES: aarch64-registered-target
+
+#ifdef __ARM_FEATURE_SME
+#include <arm_sme.h>
+#else
+#include <arm_sve.h>
+#endif
+
+#ifdef SVE_OVERLOADED_FORMS
+#define SVE_ACLE_FUNC(A1,A2_UNUSED,A3) A1##A3
+#else
+#define SVE_ACLE_FUNC(A1,A2,A3) A1##A2##A3
+#endif
+
+#ifdef __ARM_FEATURE_SME
+#define STREAMING __arm_streaming
+#else
+#define STREAMING
+#endif
+
+// CHECK-LABEL: define dso_local <vscale x 16 x i8> @test_svcvtn_f8_bf16(
+// CHECK-SAME: <vscale x 8 x bfloat> [[ZN_ZM_COERCE0:%.*]], <vscale x 8 x
bfloat> [[ZN_ZM_COERCE1:%.*]], i64 noundef [[FPM:%.*]]) #[[ATTR0:[0-9]+]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: tail call void @llvm.aarch64.set.fpmr(i64 [[FPM]])
+// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8>
@llvm.aarch64.sve.fp8.cvtn.nxv8bf16(<vscale x 8 x bfloat> [[ZN_ZM_COERCE0]],
<vscale x 8 x bfloat> [[ZN_ZM_COERCE1]])
+// CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
+//
+// CHECK-CXX-LABEL: define dso_local <vscale x 16 x i8>
@_Z19test_svcvtn_f8_bf1614svbfloat16x2_tm(
+// CHECK-CXX-SAME: <vscale x 8 x bfloat> [[ZN_ZM_COERCE0:%.*]], <vscale x 8 x
bfloat> [[ZN_ZM_COERCE1:%.*]], i64 noundef [[FPM:%.*]]) #[[ATTR0:[0-9]+]] {
+// CHECK-CXX-NEXT: [[ENTRY:.*:]]
+// CHECK-CXX-NEXT: tail call void @llvm.aarch64.set.fpmr(i64 [[FPM]])
+// CHECK-CXX-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8>
@llvm.aarch64.sve.fp8.cvtn.nxv8bf16(<vscale x 8 x bfloat> [[ZN_ZM_COERCE0]],
<vscale x 8 x bfloat> [[ZN_ZM_COERCE1]])
+// CHECK-CXX-NEXT: ret <vscale x 16 x i8> [[TMP0]]
+//
+svmfloat8_t test_svcvtn_f8_bf16(svbfloat16x2_t zn_zm, fpm_t fpm) STREAMING {
+ return SVE_ACLE_FUNC(svcvtn_mf8,_bf16_x2,_fpm)(zn_zm, fpm);
----------------
CarolineConcatto wrote:
Out of curiosity: what zn_zm.
In the assembly I see:
BFCVTN <Zd>.B, { <Zn1>.H-<Zn2>.H }
I would imagine zn1_zn2 would be more fit, but I dont think you need change.
https://github.com/llvm/llvm-project/pull/118124
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
