derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
78 lines
4.3 KiB
C
78 lines
4.3 KiB
C
// REQUIRES: systemz-registered-target
|
|
// RUN: %clang_cc1 -target-cpu z14 -triple s390x-ibm-linux -flax-vector-conversions=none \
|
|
// RUN: -ffp-exception-behavior=strict -Wall -Wno-unused -Werror -emit-llvm %s -o - | FileCheck %s
|
|
|
|
typedef __attribute__((vector_size(16))) double vec_double;
|
|
typedef __attribute__((vector_size(16))) float vec_float;
|
|
|
|
volatile vec_double vd;
|
|
volatile vec_double vd1;
|
|
volatile vec_double vd2;
|
|
volatile vec_float vf;
|
|
volatile vec_float vf1;
|
|
volatile vec_float vf2;
|
|
|
|
void test_float(void) {
|
|
vd = __builtin_s390_vfmaxdb(vd, vd1, 4);
|
|
// CHECK: call <2 x double> @llvm.experimental.constrained.maxnum.v2f64(<2 x double> %{{.*}}, <2 x double> %{{.*}})
|
|
|
|
vd = __builtin_s390_vfmindb(vd, vd1, 4);
|
|
// CHECK: call <2 x double> @llvm.experimental.constrained.minnum.v2f64(<2 x double> %{{.*}}, <2 x double> %{{.*}})
|
|
vd = __builtin_s390_vfmindb(vd, vd1, 0);
|
|
|
|
vd = __builtin_s390_vfnmadb(vd, vd1, vd2);
|
|
// CHECK: [[RES:%[^ ]+]] = call <2 x double> @llvm.experimental.constrained.fma.v2f64(<2 x double> %{{.*}}, <2 x double> %{{.*}}, <2 x double> %{{.*}})
|
|
// CHECK: fneg <2 x double> [[RES]]
|
|
|
|
vd = __builtin_s390_vfnmsdb(vd, vd1, vd2);
|
|
// CHECK: [[NEG:%[^ ]+]] = fneg <2 x double> {{.*}}
|
|
// CHECK: [[RES:%[^ ]+]] = call <2 x double> @llvm.experimental.constrained.fma.v2f64(<2 x double> %{{.*}}, <2 x double> %{{.*}}, <2 x double> [[NEG]], metadata !{{.*}})
|
|
// CHECK: fneg <2 x double> [[RES]]
|
|
|
|
vf = __builtin_s390_vfmaxsb(vf, vf1, 4);
|
|
// CHECK: call <4 x float> @llvm.experimental.constrained.maxnum.v4f32(<4 x float> %{{.*}}, <4 x float> %{{.*}}, metadata !{{.*}})
|
|
|
|
vf = __builtin_s390_vfminsb(vf, vf1, 4);
|
|
// CHECK: call <4 x float> @llvm.experimental.constrained.minnum.v4f32(<4 x float> %{{.*}}, <4 x float> %{{.*}}, metadata !{{.*}})
|
|
|
|
vf = __builtin_s390_vfsqsb(vf);
|
|
// CHECK: call <4 x float> @llvm.experimental.constrained.sqrt.v4f32(<4 x float> %{{.*}}, metadata !{{.*}})
|
|
|
|
vf = __builtin_s390_vfmasb(vf, vf1, vf2);
|
|
// CHECK: call <4 x float> @llvm.experimental.constrained.fma.v4f32(<4 x float> %{{.*}}, <4 x float> %{{.*}}, <4 x float> %{{.*}}, metadata !{{.*}})
|
|
vf = __builtin_s390_vfmssb(vf, vf1, vf2);
|
|
// CHECK: [[NEG:%[^ ]+]] = fneg <4 x float> %{{.*}}
|
|
// CHECK: call <4 x float> @llvm.experimental.constrained.fma.v4f32(<4 x float> %{{.*}}, <4 x float> %{{.*}}, <4 x float> [[NEG]], metadata !{{.*}})
|
|
vf = __builtin_s390_vfnmasb(vf, vf1, vf2);
|
|
// CHECK: [[RES:%[^ ]+]] = call <4 x float> @llvm.experimental.constrained.fma.v4f32(<4 x float> %{{.*}}, <4 x float> %{{.*}}, <4 x float> %{{.*}}, metadata !{{.*}})
|
|
// CHECK: fneg <4 x float> [[RES]]
|
|
vf = __builtin_s390_vfnmssb(vf, vf1, vf2);
|
|
// CHECK: [[NEG:%[^ ]+]] = fneg <4 x float> %{{.*}}
|
|
// CHECK: [[RES:%[^ ]+]] = call <4 x float> @llvm.experimental.constrained.fma.v4f32(<4 x float> %{{.*}}, <4 x float> %{{.*}}, <4 x float> [[NEG]], metadata !{{.*}})
|
|
// CHECK: fneg <4 x float> [[RES]]
|
|
|
|
vf = __builtin_s390_vflpsb(vf);
|
|
// CHECK: call <4 x float> @llvm.fabs.v4f32(<4 x float> %{{.*}})
|
|
vf = __builtin_s390_vflnsb(vf);
|
|
// CHECK: [[ABS:%[^ ]+]] = call <4 x float> @llvm.fabs.v4f32(<4 x float> %{{.*}})
|
|
// CHECK: fneg <4 x float> [[ABS]]
|
|
|
|
vf = __builtin_s390_vfisb(vf, 0, 0);
|
|
// CHECK: call <4 x float> @llvm.experimental.constrained.rint.v4f32(<4 x float> %{{.*}}, metadata !{{.*}})
|
|
vf = __builtin_s390_vfisb(vf, 4, 0);
|
|
// CHECK: call <4 x float> @llvm.experimental.constrained.nearbyint.v4f32(<4 x float> %{{.*}}, metadata !{{.*}})
|
|
vf = __builtin_s390_vfisb(vf, 4, 1);
|
|
// CHECK: call <4 x float> @llvm.experimental.constrained.round.v4f32(<4 x float> %{{.*}}, metadata !{{.*}})
|
|
vf = __builtin_s390_vfisb(vf, 4, 4);
|
|
// CHECK: call <4 x float> @llvm.experimental.constrained.roundeven.v4f32(<4 x float> %{{.*}}, metadata !{{.*}})
|
|
vf = __builtin_s390_vfisb(vf, 4, 5);
|
|
// CHECK: call <4 x float> @llvm.experimental.constrained.trunc.v4f32(<4 x float> %{{.*}}, metadata !{{.*}})
|
|
vf = __builtin_s390_vfisb(vf, 4, 6);
|
|
// CHECK: call <4 x float> @llvm.experimental.constrained.ceil.v4f32(<4 x float> %{{.*}}, metadata !{{.*}})
|
|
vf = __builtin_s390_vfisb(vf, 4, 7);
|
|
// CHECK: call <4 x float> @llvm.experimental.constrained.floor.v4f32(<4 x float> %{{.*}}, metadata !{{.*}})
|
|
vf = __builtin_s390_vfisb(vf, 4, 3);
|
|
// CHECK: call <4 x float> @llvm.s390.vfisb(<4 x float> %{{.*}}, i32 4, i32 3)
|
|
}
|
|
|