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
118 lines
5.0 KiB
LLVM
118 lines
5.0 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=fiji < %s | FileCheck -check-prefix=GCN %s
|
|
; RUN: llc -global-isel -new-reg-bank-select -mtriple=amdgcn-amd-amdhsa -mcpu=fiji < %s | FileCheck -check-prefix=GCN %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1100 -mattr=+real-true16 < %s | FileCheck -check-prefixes=GFX11-SDAG-TRUE16 %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1100 -mattr=-real-true16 < %s | FileCheck -check-prefixes=GFX11-SDAG-FAKE16 %s
|
|
; RUN: llc -global-isel -new-reg-bank-select -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1100 -mattr=+real-true16 < %s | FileCheck -check-prefixes=GFX11-GISEL-TRUE16 %s
|
|
; RUN: llc -global-isel -new-reg-bank-select -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1100 -mattr=-real-true16 < %s | FileCheck -check-prefixes=GFX11-GISEL-FAKE16 %s
|
|
|
|
define half @v_sqrt_f16(half %src) {
|
|
; GCN-LABEL: v_sqrt_f16:
|
|
; GCN: ; %bb.0:
|
|
; GCN-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GCN-NEXT: v_sqrt_f16_e32 v0, v0
|
|
; GCN-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-SDAG-TRUE16-LABEL: v_sqrt_f16:
|
|
; GFX11-SDAG-TRUE16: ; %bb.0:
|
|
; GFX11-SDAG-TRUE16-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-SDAG-TRUE16-NEXT: v_sqrt_f16_e32 v0.l, v0.l
|
|
; GFX11-SDAG-TRUE16-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-SDAG-FAKE16-LABEL: v_sqrt_f16:
|
|
; GFX11-SDAG-FAKE16: ; %bb.0:
|
|
; GFX11-SDAG-FAKE16-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-SDAG-FAKE16-NEXT: v_sqrt_f16_e32 v0, v0
|
|
; GFX11-SDAG-FAKE16-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-GISEL-TRUE16-LABEL: v_sqrt_f16:
|
|
; GFX11-GISEL-TRUE16: ; %bb.0:
|
|
; GFX11-GISEL-TRUE16-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-GISEL-TRUE16-NEXT: v_sqrt_f16_e32 v0.l, v0.l
|
|
; GFX11-GISEL-TRUE16-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-GISEL-FAKE16-LABEL: v_sqrt_f16:
|
|
; GFX11-GISEL-FAKE16: ; %bb.0:
|
|
; GFX11-GISEL-FAKE16-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-GISEL-FAKE16-NEXT: v_sqrt_f16_e32 v0, v0
|
|
; GFX11-GISEL-FAKE16-NEXT: s_setpc_b64 s[30:31]
|
|
%sqrt = call half @llvm.amdgcn.sqrt.f16(half %src)
|
|
ret half %sqrt
|
|
}
|
|
|
|
define half @v_fabs_sqrt_f16(half %src) {
|
|
; GCN-LABEL: v_fabs_sqrt_f16:
|
|
; GCN: ; %bb.0:
|
|
; GCN-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GCN-NEXT: v_sqrt_f16_e64 v0, |v0|
|
|
; GCN-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-SDAG-TRUE16-LABEL: v_fabs_sqrt_f16:
|
|
; GFX11-SDAG-TRUE16: ; %bb.0:
|
|
; GFX11-SDAG-TRUE16-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-SDAG-TRUE16-NEXT: v_sqrt_f16_e64 v0.l, |v0.l|
|
|
; GFX11-SDAG-TRUE16-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-SDAG-FAKE16-LABEL: v_fabs_sqrt_f16:
|
|
; GFX11-SDAG-FAKE16: ; %bb.0:
|
|
; GFX11-SDAG-FAKE16-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-SDAG-FAKE16-NEXT: v_sqrt_f16_e64 v0, |v0|
|
|
; GFX11-SDAG-FAKE16-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-GISEL-TRUE16-LABEL: v_fabs_sqrt_f16:
|
|
; GFX11-GISEL-TRUE16: ; %bb.0:
|
|
; GFX11-GISEL-TRUE16-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-GISEL-TRUE16-NEXT: v_sqrt_f16_e64 v0.l, |v0.l|
|
|
; GFX11-GISEL-TRUE16-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-GISEL-FAKE16-LABEL: v_fabs_sqrt_f16:
|
|
; GFX11-GISEL-FAKE16: ; %bb.0:
|
|
; GFX11-GISEL-FAKE16-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-GISEL-FAKE16-NEXT: v_sqrt_f16_e64 v0, |v0|
|
|
; GFX11-GISEL-FAKE16-NEXT: s_setpc_b64 s[30:31]
|
|
%fabs.src = call half @llvm.fabs.f16(half %src)
|
|
%sqrt = call half @llvm.amdgcn.sqrt.f16(half %fabs.src)
|
|
ret half %sqrt
|
|
}
|
|
|
|
define half @v_fneg_fabs_sqrt_f16(half %src) {
|
|
; GCN-LABEL: v_fneg_fabs_sqrt_f16:
|
|
; GCN: ; %bb.0:
|
|
; GCN-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GCN-NEXT: v_sqrt_f16_e64 v0, -|v0|
|
|
; GCN-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-SDAG-TRUE16-LABEL: v_fneg_fabs_sqrt_f16:
|
|
; GFX11-SDAG-TRUE16: ; %bb.0:
|
|
; GFX11-SDAG-TRUE16-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-SDAG-TRUE16-NEXT: v_sqrt_f16_e64 v0.l, -|v0.l|
|
|
; GFX11-SDAG-TRUE16-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-SDAG-FAKE16-LABEL: v_fneg_fabs_sqrt_f16:
|
|
; GFX11-SDAG-FAKE16: ; %bb.0:
|
|
; GFX11-SDAG-FAKE16-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-SDAG-FAKE16-NEXT: v_sqrt_f16_e64 v0, -|v0|
|
|
; GFX11-SDAG-FAKE16-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-GISEL-TRUE16-LABEL: v_fneg_fabs_sqrt_f16:
|
|
; GFX11-GISEL-TRUE16: ; %bb.0:
|
|
; GFX11-GISEL-TRUE16-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-GISEL-TRUE16-NEXT: v_sqrt_f16_e64 v0.l, -|v0.l|
|
|
; GFX11-GISEL-TRUE16-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-GISEL-FAKE16-LABEL: v_fneg_fabs_sqrt_f16:
|
|
; GFX11-GISEL-FAKE16: ; %bb.0:
|
|
; GFX11-GISEL-FAKE16-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-GISEL-FAKE16-NEXT: v_sqrt_f16_e64 v0, -|v0|
|
|
; GFX11-GISEL-FAKE16-NEXT: s_setpc_b64 s[30:31]
|
|
%fabs.src = call half @llvm.fabs.f16(half %src)
|
|
%neg.fabs.src = fneg half %fabs.src
|
|
%sqrt = call half @llvm.amdgcn.sqrt.f16(half %neg.fabs.src)
|
|
ret half %sqrt
|
|
}
|
|
|
|
declare half @llvm.amdgcn.sqrt.f16(half) #0
|
|
declare half @llvm.fabs.f16(half) #0
|
|
|
|
attributes #0 = { nounwind readnone speculatable willreturn }
|