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
107 lines
4.4 KiB
LLVM
107 lines
4.4 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: llc -global-isel -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx908 %s -o - | FileCheck %s
|
|
|
|
define float @test_fmamix_constant_bus_violation_sss(i32 inreg %val.0, i32 inreg %val.1, i32 inreg %val.2) #0 {
|
|
; CHECK-LABEL: test_fmamix_constant_bus_violation_sss:
|
|
; CHECK: ; %bb.0:
|
|
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; CHECK-NEXT: s_lshr_b32 s5, s17, 16
|
|
; CHECK-NEXT: s_lshr_b32 s6, s18, 16
|
|
; CHECK-NEXT: s_lshr_b32 s4, s16, 16
|
|
; CHECK-NEXT: v_mov_b32_e32 v0, s5
|
|
; CHECK-NEXT: v_mov_b32_e32 v1, s6
|
|
; CHECK-NEXT: v_fma_mix_f32 v0, s4, v0, v1 op_sel_hi:[1,1,1]
|
|
; CHECK-NEXT: s_setpc_b64 s[30:31]
|
|
%lshr.0 = lshr i32 %val.0, 16
|
|
%lshr.1 = lshr i32 %val.1, 16
|
|
%lshr.2 = lshr i32 %val.2, 16
|
|
%trunc.0 = trunc i32 %lshr.0 to i16
|
|
%trunc.1 = trunc i32 %lshr.1 to i16
|
|
%trunc.2 = trunc i32 %lshr.2 to i16
|
|
%cast.0 = bitcast i16 %trunc.0 to half
|
|
%cast.1 = bitcast i16 %trunc.1 to half
|
|
%cast.2 = bitcast i16 %trunc.2 to half
|
|
%fpext.0 = fpext half %cast.0 to float
|
|
%fpext.1 = fpext half %cast.1 to float
|
|
%fpext.2 = fpext half %cast.2 to float
|
|
%fma = call float @llvm.fma.f32(float %fpext.0, float %fpext.1, float %fpext.2)
|
|
ret float %fma
|
|
}
|
|
|
|
define float @test_fmamix_constant_bus_violation_ssv(i32 inreg %val.0, i32 inreg %val.1, i32 %val.2) #0 {
|
|
; CHECK-LABEL: test_fmamix_constant_bus_violation_ssv:
|
|
; CHECK: ; %bb.0:
|
|
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; CHECK-NEXT: s_lshr_b32 s5, s17, 16
|
|
; CHECK-NEXT: s_lshr_b32 s4, s16, 16
|
|
; CHECK-NEXT: v_mov_b32_e32 v1, s5
|
|
; CHECK-NEXT: v_fma_mix_f32 v0, s4, v1, v0 op_sel:[0,0,1] op_sel_hi:[1,1,1]
|
|
; CHECK-NEXT: s_setpc_b64 s[30:31]
|
|
%lshr.0 = lshr i32 %val.0, 16
|
|
%lshr.1 = lshr i32 %val.1, 16
|
|
%lshr.2 = lshr i32 %val.2, 16
|
|
%trunc.0 = trunc i32 %lshr.0 to i16
|
|
%trunc.1 = trunc i32 %lshr.1 to i16
|
|
%trunc.2 = trunc i32 %lshr.2 to i16
|
|
%cast.0 = bitcast i16 %trunc.0 to half
|
|
%cast.1 = bitcast i16 %trunc.1 to half
|
|
%cast.2 = bitcast i16 %trunc.2 to half
|
|
%fpext.0 = fpext half %cast.0 to float
|
|
%fpext.1 = fpext half %cast.1 to float
|
|
%fpext.2 = fpext half %cast.2 to float
|
|
%fma = call float @llvm.fma.f32(float %fpext.0, float %fpext.1, float %fpext.2)
|
|
ret float %fma
|
|
}
|
|
|
|
define float @test_fmamix_constant_bus_violation_svs(i32 inreg %val.0, i32 %val.1, i32 inreg %val.2) #0 {
|
|
; CHECK-LABEL: test_fmamix_constant_bus_violation_svs:
|
|
; CHECK: ; %bb.0:
|
|
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; CHECK-NEXT: s_lshr_b32 s5, s17, 16
|
|
; CHECK-NEXT: s_lshr_b32 s4, s16, 16
|
|
; CHECK-NEXT: v_mov_b32_e32 v1, s5
|
|
; CHECK-NEXT: v_fma_mix_f32 v0, s4, v0, v1 op_sel:[0,1,0] op_sel_hi:[1,1,1]
|
|
; CHECK-NEXT: s_setpc_b64 s[30:31]
|
|
%lshr.0 = lshr i32 %val.0, 16
|
|
%lshr.1 = lshr i32 %val.1, 16
|
|
%lshr.2 = lshr i32 %val.2, 16
|
|
%trunc.0 = trunc i32 %lshr.0 to i16
|
|
%trunc.1 = trunc i32 %lshr.1 to i16
|
|
%trunc.2 = trunc i32 %lshr.2 to i16
|
|
%cast.0 = bitcast i16 %trunc.0 to half
|
|
%cast.1 = bitcast i16 %trunc.1 to half
|
|
%cast.2 = bitcast i16 %trunc.2 to half
|
|
%fpext.0 = fpext half %cast.0 to float
|
|
%fpext.1 = fpext half %cast.1 to float
|
|
%fpext.2 = fpext half %cast.2 to float
|
|
%fma = call float @llvm.fma.f32(float %fpext.0, float %fpext.1, float %fpext.2)
|
|
ret float %fma
|
|
}
|
|
|
|
define float @test_fmamix_constant_bus_violation_vss(i32 %val.0, i32 inreg %val.1, i32 inreg %val.2) #0 {
|
|
; CHECK-LABEL: test_fmamix_constant_bus_violation_vss:
|
|
; CHECK: ; %bb.0:
|
|
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; CHECK-NEXT: s_lshr_b32 s5, s17, 16
|
|
; CHECK-NEXT: s_lshr_b32 s4, s16, 16
|
|
; CHECK-NEXT: v_mov_b32_e32 v1, s5
|
|
; CHECK-NEXT: v_fma_mix_f32 v0, v0, s4, v1 op_sel:[1,0,0] op_sel_hi:[1,1,1]
|
|
; CHECK-NEXT: s_setpc_b64 s[30:31]
|
|
%lshr.0 = lshr i32 %val.0, 16
|
|
%lshr.1 = lshr i32 %val.1, 16
|
|
%lshr.2 = lshr i32 %val.2, 16
|
|
%trunc.0 = trunc i32 %lshr.0 to i16
|
|
%trunc.1 = trunc i32 %lshr.1 to i16
|
|
%trunc.2 = trunc i32 %lshr.2 to i16
|
|
%cast.0 = bitcast i16 %trunc.0 to half
|
|
%cast.1 = bitcast i16 %trunc.1 to half
|
|
%cast.2 = bitcast i16 %trunc.2 to half
|
|
%fpext.0 = fpext half %cast.0 to float
|
|
%fpext.1 = fpext half %cast.1 to float
|
|
%fpext.2 = fpext half %cast.2 to float
|
|
%fma = call float @llvm.fma.f32(float %fpext.0, float %fpext.1, float %fpext.2)
|
|
ret float %fma
|
|
}
|
|
|
|
attributes #0 = { denormal_fpenv(float: preservesign) }
|