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
104 lines
3.3 KiB
LLVM
104 lines
3.3 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=s390x-linux-gnu -mcpu=z10 | FileCheck %s
|
|
; RUN: llc < %s -mtriple=s390x-linux-gnu -mcpu=z13 | FileCheck %s
|
|
|
|
;
|
|
; Test strict 64-bit square root.
|
|
;
|
|
|
|
declare double @llvm.experimental.constrained.sqrt.f64(double, metadata, metadata)
|
|
|
|
; Check register square root.
|
|
define double @f1(double %val) #0 {
|
|
; CHECK-LABEL: f1:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: sqdbr %f0, %f0
|
|
; CHECK-NEXT: br %r14
|
|
%res = call double @llvm.experimental.constrained.sqrt.f64(
|
|
double %val,
|
|
metadata !"round.dynamic",
|
|
metadata !"fpexcept.strict") #0
|
|
ret double %res
|
|
}
|
|
|
|
; Check the low end of the SQDB range.
|
|
define double @f2(ptr %ptr) #0 {
|
|
; CHECK-LABEL: f2:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: sqdb %f0, 0(%r2)
|
|
; CHECK-NEXT: br %r14
|
|
%val = load double, ptr %ptr
|
|
%res = call double @llvm.experimental.constrained.sqrt.f64(
|
|
double %val,
|
|
metadata !"round.dynamic",
|
|
metadata !"fpexcept.strict") #0
|
|
ret double %res
|
|
}
|
|
|
|
; Check the high end of the aligned SQDB range.
|
|
define double @f3(ptr %base) #0 {
|
|
; CHECK-LABEL: f3:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: sqdb %f0, 4088(%r2)
|
|
; CHECK-NEXT: br %r14
|
|
%ptr = getelementptr double, ptr %base, i64 511
|
|
%val = load double, ptr %ptr
|
|
%res = call double @llvm.experimental.constrained.sqrt.f64(
|
|
double %val,
|
|
metadata !"round.dynamic",
|
|
metadata !"fpexcept.strict") #0
|
|
ret double %res
|
|
}
|
|
|
|
; Check the next doubleword up, which needs separate address logic.
|
|
; Other sequences besides this one would be OK.
|
|
define double @f4(ptr %base) #0 {
|
|
; CHECK-LABEL: f4:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: aghi %r2, 4096
|
|
; CHECK-NEXT: sqdb %f0, 0(%r2)
|
|
; CHECK-NEXT: br %r14
|
|
%ptr = getelementptr double, ptr %base, i64 512
|
|
%val = load double, ptr %ptr
|
|
%res = call double @llvm.experimental.constrained.sqrt.f64(
|
|
double %val,
|
|
metadata !"round.dynamic",
|
|
metadata !"fpexcept.strict") #0
|
|
ret double %res
|
|
}
|
|
|
|
; Check negative displacements, which also need separate address logic.
|
|
define double @f5(ptr %base) #0 {
|
|
; CHECK-LABEL: f5:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: aghi %r2, -8
|
|
; CHECK-NEXT: sqdb %f0, 0(%r2)
|
|
; CHECK-NEXT: br %r14
|
|
%ptr = getelementptr double, ptr %base, i64 -1
|
|
%val = load double, ptr %ptr
|
|
%res = call double @llvm.experimental.constrained.sqrt.f64(
|
|
double %val,
|
|
metadata !"round.dynamic",
|
|
metadata !"fpexcept.strict") #0
|
|
ret double %res
|
|
}
|
|
|
|
; Check that SQDB allows indices.
|
|
define double @f6(ptr %base, i64 %index) #0 {
|
|
; CHECK-LABEL: f6:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: sllg %r1, %r3, 3
|
|
; CHECK-NEXT: sqdb %f0, 800(%r1,%r2)
|
|
; CHECK-NEXT: br %r14
|
|
%ptr1 = getelementptr double, ptr %base, i64 %index
|
|
%ptr2 = getelementptr double, ptr %ptr1, i64 100
|
|
%val = load double, ptr %ptr2
|
|
%res = call double @llvm.experimental.constrained.sqrt.f64(
|
|
double %val,
|
|
metadata !"round.dynamic",
|
|
metadata !"fpexcept.strict") #0
|
|
ret double %res
|
|
}
|
|
|
|
attributes #0 = { strictfp }
|