This is an archive of the discontinued LLVM Phabricator instance.

Differential D94151

[NFC] Removed unused prefixes from CodeGen/AMDGPU
ClosedPublic

Authored by mtrofin on Jan 5 2021, 8:24 PM.

Details

Reviewers
arsenm
Commits
rGb47063091304: [NFC] Removed unused prefixes from CodeGen/AMDGPU
Summary

All the 'l'-starting tests.

Diff Detail

Event Timeline

mtrofin created this revision.Jan 5 2021, 8:24 PM
Herald added subscribers: kerbowa, jfb, t-tye and 6 others. · View Herald TranscriptJan 5 2021, 8:24 PM
mtrofin requested review of this revision.Jan 5 2021, 8:24 PM
Herald added a project: Restricted Project. · View Herald TranscriptJan 5 2021, 8:24 PM
Herald added subscribers: llvm-commits, wdng. · View Herald Transcript
Harbormaster completed remote builds in B84155: Diff 314788.Jan 5 2021, 8:59 PM
arsenm accepted this revision.Jan 6 2021, 9:02 AM
This revision is now accepted and ready to land.Jan 6 2021, 9:02 AM
mtrofin updated this revision to Diff 314919.Jan 6 2021, 9:30 AM

rebased and fixed the following 2 files by accepting upstream, then re-running update_test_prefix.py

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.buffer.store.format.d16.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.buffer.store.format.d16.ll

This revision was landed with ongoing or failed builds.Jan 6 2021, 9:34 AM
Closed by commit rGb47063091304: [NFC] Removed unused prefixes from CodeGen/AMDGPU (authored by mtrofin). · Explain Why
This revision was automatically updated to reflect the committed changes.
mtrofin added a commit: rGb47063091304: [NFC] Removed unused prefixes from CodeGen/AMDGPU.
Harbormaster completed remote builds in B84224: Diff 314919.Jan 6 2021, 10:04 AM

Revision Contents

PathSize
llvm/
test/
CodeGen/
AMDGPU/
12 lines
2 lines
4 lines
4 lines
4 lines
4 lines
4 lines
4 lines
4 lines
2 lines
4 lines
4 lines
4 lines
4 lines
2 lines
6 lines
2 lines
2 lines
4 lines
4 lines
6 lines
4 lines
2 lines
8 lines
2 lines
4 lines
4 lines
6 lines
4 lines
4 lines
4 lines
4 lines
4 lines
4 lines
2 lines
4 lines
6 lines
4 lines
12 lines
12 lines
4 lines
6 lines
12 lines
6 lines
8 lines
6 lines
8 lines
6 lines
4 lines
6 lines
6 lines
8 lines
6 lines
8 lines
8 lines
10 lines
6 lines
10 lines
10 lines
8 lines
6 lines
6 lines
6 lines
6 lines
10 lines
2 lines
6 lines
4 lines
10 lines

Diff 314920

llvm/test/CodeGen/AMDGPU/large-alloca-compute.ll

; RUN: llc -march=amdgcn -mcpu=bonaire -show-mc-encoding < %s | FileCheck -check-prefix=GCN -check-prefix=CI -check-prefix=ALL %s ; RUN: llc -march=amdgcn -mcpu=bonaire -show-mc-encoding < %s | FileCheck --check-prefixes=GCN,CI,ALL %s
; RUN: llc -march=amdgcn -mcpu=carrizo --show-mc-encoding < %s | FileCheck -check-prefix=GCN -check-prefix=VI -check-prefix=ALL %s ; RUN: llc -march=amdgcn -mcpu=carrizo --show-mc-encoding < %s | FileCheck --check-prefixes=GCN,VI,ALL %s
; RUN: llc -march=amdgcn -mcpu=gfx900 --show-mc-encoding < %s | FileCheck -check-prefix=GCN -check-prefix=GFX9 -check-prefix=ALL %s ; RUN: llc -march=amdgcn -mcpu=gfx900 --show-mc-encoding < %s | FileCheck --check-prefixes=GCN,GFX9,ALL %s
; RUN: llc -march=amdgcn -mcpu=bonaire -mtriple=amdgcn-unknown-amdhsa --amdhsa-code-object-version=2 < %s -mattr=-flat-for-global | FileCheck -check-prefix=GCNHSA -check-prefix=CIHSA -check-prefix=ALL %s ; RUN: llc -march=amdgcn -mcpu=bonaire -mtriple=amdgcn-unknown-amdhsa --amdhsa-code-object-version=2 < %s -mattr=-flat-for-global | FileCheck --check-prefixes=GCNHSA,ALL %s
; RUN: llc -march=amdgcn -mcpu=carrizo -mtriple=amdgcn-unknown-amdhsa --amdhsa-code-object-version=2 -mattr=-flat-for-global < %s | FileCheck -check-prefix=GCNHSA -check-prefix=VIHSA -check-prefix=ALL %s ; RUN: llc -march=amdgcn -mcpu=carrizo -mtriple=amdgcn-unknown-amdhsa --amdhsa-code-object-version=2 -mattr=-flat-for-global < %s | FileCheck --check-prefixes=GCNHSA,ALL %s
; RUN: llc -march=amdgcn -mcpu=gfx1010 -mtriple=amdgcn-unknown-amdhsa --amdhsa-code-object-version=2 -mattr=-flat-for-global < %s | FileCheck -check-prefix=GCNHSA -check-prefix=GFX10HSA -check-prefix=ALL %s ; RUN: llc -march=amdgcn -mcpu=gfx1010 -mtriple=amdgcn-unknown-amdhsa --amdhsa-code-object-version=2 -mattr=-flat-for-global < %s | FileCheck --check-prefixes=GCNHSA,GFX10HSA,ALL %s
; FIXME: align on alloca seems to be ignored for private_segment_alignment ; FIXME: align on alloca seems to be ignored for private_segment_alignment
; ALL-LABEL: {{^}}large_alloca_compute_shader: ; ALL-LABEL: {{^}}large_alloca_compute_shader:
; GCN-DAG: s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD0 ; GCN-DAG: s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD0
; GCN-DAG: ; fixup A - offset: 4, value: SCRATCH_RSRC_DWORD0 ; GCN-DAG: ; fixup A - offset: 4, value: SCRATCH_RSRC_DWORD0
; GCN-DAG: s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD1 ; GCN-DAG: s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD1
▲ Show 20 Lines • Show All 52 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/lds-alignment.ll

; RUN: llc -march=amdgcn -mtriple=amdgcn-unknown-amdhsa --amdhsa-code-object-version=2 < %s | FileCheck -check-prefix=HSA -check-prefix=FUNC %s ; RUN: llc -march=amdgcn -mtriple=amdgcn-unknown-amdhsa --amdhsa-code-object-version=2 < %s | FileCheck -check-prefix=HSA %s
@lds.align16.0 = internal unnamed_addr addrspace(3) global [38 x i8] undef, align 16 @lds.align16.0 = internal unnamed_addr addrspace(3) global [38 x i8] undef, align 16
@lds.align16.1 = internal unnamed_addr addrspace(3) global [38 x i8] undef, align 16 @lds.align16.1 = internal unnamed_addr addrspace(3) global [38 x i8] undef, align 16
@lds.align8.0 = internal unnamed_addr addrspace(3) global [38 x i8] undef, align 8 @lds.align8.0 = internal unnamed_addr addrspace(3) global [38 x i8] undef, align 8
@lds.align32.0 = internal unnamed_addr addrspace(3) global [38 x i8] undef, align 32 @lds.align32.0 = internal unnamed_addr addrspace(3) global [38 x i8] undef, align 32
@lds.missing.align.0 = internal unnamed_addr addrspace(3) global [39 x i32] undef @lds.missing.align.0 = internal unnamed_addr addrspace(3) global [39 x i32] undef
▲ Show 20 Lines • Show All 259 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.buffer.store.format.d16.ll

; RUN: llc -global-isel=0 -mtriple=amdgcn-amd-amdhsa -mcpu=tonga -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,UNPACKED %s ; RUN: llc -global-isel=0 -mtriple=amdgcn-amd-amdhsa -mcpu=tonga -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,UNPACKED %s
; RUN: llc -global-isel=0 -mtriple=amdgcn-amd-amdhsa -mcpu=gfx810 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,PACKED,GFX81 %s ; RUN: llc -global-isel=0 -mtriple=amdgcn-amd-amdhsa -mcpu=gfx810 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,PACKED %s
; RUN: llc -global-isel=0 -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,PACKED,GFX9 %s ; RUN: llc -global-isel=0 -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,PACKED %s
; GCN-LABEL: {{^}}buffer_store_format_d16_x: ; GCN-LABEL: {{^}}buffer_store_format_d16_x:
; GCN: s_load_dword s[[LO:[0-9]+]] ; GCN: s_load_dword s[[LO:[0-9]+]]
; GCN: v_mov_b32_e32 v[[V_LO:[0-9]+]], s[[LO]] ; GCN: v_mov_b32_e32 v[[V_LO:[0-9]+]], s[[LO]]
; GCN: buffer_store_format_d16_x v[[V_LO]], v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 idxen ; GCN: buffer_store_format_d16_x v[[V_LO]], v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 idxen
define amdgpu_kernel void @buffer_store_format_d16_x(<4 x i32> %rsrc, [8 x i32], half %data, [8 x i32], i32 %index) { define amdgpu_kernel void @buffer_store_format_d16_x(<4 x i32> %rsrc, [8 x i32], half %data, [8 x i32], i32 %index) {
main_body: main_body:
call void @llvm.amdgcn.buffer.store.format.f16(half %data, <4 x i32> %rsrc, i32 %index, i32 0, i1 0, i1 0) call void @llvm.amdgcn.buffer.store.format.f16(half %data, <4 x i32> %rsrc, i32 %index, i32 0, i1 0, i1 0)
▲ Show 20 Lines • Show All 53 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.cos.ll

; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=GCN %s ; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=GCN %s ; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
declare float @llvm.amdgcn.cos.f32(float) #0 declare float @llvm.amdgcn.cos.f32(float) #0
; GCN-LABEL: {{^}}v_cos_f32: ; GCN-LABEL: {{^}}v_cos_f32:
; GCN: v_cos_f32_e32 {{v[0-9]+}}, {{s[0-9]+}} ; GCN: v_cos_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}
define amdgpu_kernel void @v_cos_f32(float addrspace(1)* %out, float %src) #1 { define amdgpu_kernel void @v_cos_f32(float addrspace(1)* %out, float %src) #1 {
%cos = call float @llvm.amdgcn.cos.f32(float %src) #0 %cos = call float @llvm.amdgcn.cos.f32(float %src) #0
store float %cos, float addrspace(1)* %out store float %cos, float addrspace(1)* %out
ret void ret void
} }
attributes #0 = { nounwind readnone } attributes #0 = { nounwind readnone }
attributes #1 = { nounwind } attributes #1 = { nounwind }

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.cubeid.ll

; RUN: llc -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=SI %s ; RUN: llc -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
; RUN: llc -march=amdgcn -mcpu=fiji -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VI %s ; RUN: llc -march=amdgcn -mcpu=fiji -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
declare float @llvm.amdgcn.cubeid(float, float, float) #0 declare float @llvm.amdgcn.cubeid(float, float, float) #0
; GCN-LABEL: {{^}}test_cubeid: ; GCN-LABEL: {{^}}test_cubeid:
; GCN: v_cubeid_f32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} ; GCN: v_cubeid_f32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
define amdgpu_kernel void @test_cubeid(float addrspace(1)* %out, float %a, float %b, float %c) #1 { define amdgpu_kernel void @test_cubeid(float addrspace(1)* %out, float %a, float %b, float %c) #1 {
%result = call float @llvm.amdgcn.cubeid(float %a, float %b, float %c) %result = call float @llvm.amdgcn.cubeid(float %a, float %b, float %c)
store float %result, float addrspace(1)* %out store float %result, float addrspace(1)* %out
ret void ret void
} }
attributes #0 = { nounwind readnone } attributes #0 = { nounwind readnone }
attributes #1 = { nounwind } attributes #1 = { nounwind }

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.cubema.ll

; RUN: llc -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=SI %s ; RUN: llc -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
; RUN: llc -march=amdgcn -mcpu=fiji -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VI %s ; RUN: llc -march=amdgcn -mcpu=fiji -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
declare float @llvm.amdgcn.cubema(float, float, float) #0 declare float @llvm.amdgcn.cubema(float, float, float) #0
; GCN-LABEL: {{^}}test_cubema: ; GCN-LABEL: {{^}}test_cubema:
; GCN: v_cubema_f32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} ; GCN: v_cubema_f32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
define amdgpu_kernel void @test_cubema(float addrspace(1)* %out, float %a, float %b, float %c) #1 { define amdgpu_kernel void @test_cubema(float addrspace(1)* %out, float %a, float %b, float %c) #1 {
%result = call float @llvm.amdgcn.cubema(float %a, float %b, float %c) %result = call float @llvm.amdgcn.cubema(float %a, float %b, float %c)
store float %result, float addrspace(1)* %out store float %result, float addrspace(1)* %out
ret void ret void
} }
attributes #0 = { nounwind readnone } attributes #0 = { nounwind readnone }
attributes #1 = { nounwind } attributes #1 = { nounwind }

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.cubesc.ll

; RUN: llc -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=SI %s ; RUN: llc -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
; RUN: llc -march=amdgcn -mcpu=fiji -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VI %s ; RUN: llc -march=amdgcn -mcpu=fiji -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
declare float @llvm.amdgcn.cubesc(float, float, float) #0 declare float @llvm.amdgcn.cubesc(float, float, float) #0
; GCN-LABEL: {{^}}test_cubesc: ; GCN-LABEL: {{^}}test_cubesc:
; GCN: v_cubesc_f32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} ; GCN: v_cubesc_f32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
define amdgpu_kernel void @test_cubesc(float addrspace(1)* %out, float %a, float %b, float %c) #1 { define amdgpu_kernel void @test_cubesc(float addrspace(1)* %out, float %a, float %b, float %c) #1 {
%result = call float @llvm.amdgcn.cubesc(float %a, float %b, float %c) %result = call float @llvm.amdgcn.cubesc(float %a, float %b, float %c)
store float %result, float addrspace(1)* %out store float %result, float addrspace(1)* %out
ret void ret void
} }
attributes #0 = { nounwind readnone } attributes #0 = { nounwind readnone }
attributes #1 = { nounwind } attributes #1 = { nounwind }

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.cubetc.ll

; RUN: llc -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=SI %s ; RUN: llc -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
; RUN: llc -march=amdgcn -mcpu=fiji -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VI %s ; RUN: llc -march=amdgcn -mcpu=fiji -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
declare float @llvm.amdgcn.cubetc(float, float, float) #0 declare float @llvm.amdgcn.cubetc(float, float, float) #0
; GCN-LABEL: {{^}}test_cubetc: ; GCN-LABEL: {{^}}test_cubetc:
; GCN: v_cubetc_f32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} ; GCN: v_cubetc_f32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
define amdgpu_kernel void @test_cubetc(float addrspace(1)* %out, float %a, float %b, float %c) #1 { define amdgpu_kernel void @test_cubetc(float addrspace(1)* %out, float %a, float %b, float %c) #1 {
%result = call float @llvm.amdgcn.cubetc(float %a, float %b, float %c) %result = call float @llvm.amdgcn.cubetc(float %a, float %b, float %c)
store float %result, float addrspace(1)* %out store float %result, float addrspace(1)* %out
ret void ret void
} }
attributes #0 = { nounwind readnone } attributes #0 = { nounwind readnone }
attributes #1 = { nounwind } attributes #1 = { nounwind }

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.cvt.pkrtz.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck %s -enable-var-scope -check-prefixes=GCN,SI ; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck %s -enable-var-scope -check-prefixes=GCN,SI
; RUN: llc -march=amdgcn -mcpu=fiji -verify-machineinstrs < %s | FileCheck %s -enable-var-scope -check-prefixes=GCN,GFX89,VI ; RUN: llc -march=amdgcn -mcpu=fiji -verify-machineinstrs < %s | FileCheck %s -enable-var-scope -check-prefixes=GCN,VI
; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck %s -enable-var-scope -check-prefixes=GCN,GFX89,GFX9 ; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck %s -enable-var-scope -check-prefixes=GCN,GFX9
define amdgpu_kernel void @s_cvt_pkrtz_v2f16_f32(<2 x half> addrspace(1)* %out, float %x, float %y) #0 { define amdgpu_kernel void @s_cvt_pkrtz_v2f16_f32(<2 x half> addrspace(1)* %out, float %x, float %y) #0 {
; SI-LABEL: s_cvt_pkrtz_v2f16_f32: ; SI-LABEL: s_cvt_pkrtz_v2f16_f32:
; SI: ; %bb.0: ; SI: ; %bb.0:
; SI-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0xb ; SI-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0xb
; SI-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x9 ; SI-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x9
; SI-NEXT: s_mov_b32 s7, 0xf000 ; SI-NEXT: s_mov_b32 s7, 0xf000
; SI-NEXT: s_mov_b32 s6, -1 ; SI-NEXT: s_mov_b32 s6, -1
▲ Show 20 Lines • Show All 531 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.ds.gws.sema.br.ll

; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=tahiti -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,LOOP %s ; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=tahiti -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,LOOP %s
; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=hawaii -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,LOOP %s ; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=hawaii -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,LOOP %s
; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=fiji -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,LOOP %s ; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=fiji -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,LOOP %s
; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx900 -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,NOLOOP %s ; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx900 -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,NOLOOP %s
; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1010 -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,NOLOOP,GFX10 %s ; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1010 -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,NOLOOP %s
; GCN-LABEL: {{^}}gws_sema_br_offset0: ; GCN-LABEL: {{^}}gws_sema_br_offset0:
; NOLOOP-DAG: s_load_dword [[BAR_NUM:s[0-9]+]] ; NOLOOP-DAG: s_load_dword [[BAR_NUM:s[0-9]+]]
; NOLOOP-DAG: s_mov_b32 m0, 0{{$}} ; NOLOOP-DAG: s_mov_b32 m0, 0{{$}}
; NOLOOP: v_mov_b32_e32 v0, [[BAR_NUM]] ; NOLOOP: v_mov_b32_e32 v0, [[BAR_NUM]]
; NOLOOP: ds_gws_sema_br v0 gds{{$}} ; NOLOOP: ds_gws_sema_br v0 gds{{$}}
; LOOP: s_mov_b32 m0, 0{{$}} ; LOOP: s_mov_b32 m0, 0{{$}}
Show All 15 Lines

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.ds.gws.sema.p.ll

; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=tahiti -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,LOOP %s ; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=tahiti -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,LOOP %s
; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=hawaii -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,LOOP %s ; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=hawaii -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,LOOP %s
; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=fiji -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,LOOP,GFX8 %s ; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=fiji -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,LOOP %s
; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx900 -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,NOLOOP %s ; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx900 -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,NOLOOP %s
; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1010 -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,NOLOOP,GFX10 %s ; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1010 -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,NOLOOP %s
; GCN-LABEL: {{^}}gws_sema_p_offset0: ; GCN-LABEL: {{^}}gws_sema_p_offset0:
; NOLOOP-DAG: s_mov_b32 m0, 0{{$}} ; NOLOOP-DAG: s_mov_b32 m0, 0{{$}}
; NOLOOP: ds_gws_sema_p gds{{$}} ; NOLOOP: ds_gws_sema_p gds{{$}}
; LOOP: s_mov_b32 m0, 0{{$}} ; LOOP: s_mov_b32 m0, 0{{$}}
; LOOP: [[LOOP:BB[0-9]+_[0-9]+]]: ; LOOP: [[LOOP:BB[0-9]+_[0-9]+]]:
; LOOP-NEXT: s_setreg_imm32_b32 hwreg(HW_REG_TRAPSTS, 8, 1), 0 ; LOOP-NEXT: s_setreg_imm32_b32 hwreg(HW_REG_TRAPSTS, 8, 1), 0
Show All 13 Lines

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.ds.gws.sema.release.all.ll

; RUN: not --crash llc -global-isel=0 -mtriple=amdgcn-mesa-mesa3d -mcpu=tahiti -o - < %s 2>&1 | FileCheck -enable-var-scope -check-prefix=GFX6ERR-SDAG %s ; RUN: not --crash llc -global-isel=0 -mtriple=amdgcn-mesa-mesa3d -mcpu=tahiti -o - < %s 2>&1 | FileCheck -enable-var-scope -check-prefix=GFX6ERR-SDAG %s
; RUN: not --crash llc -global-isel=1 -mtriple=amdgcn-mesa-mesa3d -mcpu=tahiti -o - < %s 2>&1 | FileCheck -enable-var-scope -check-prefix=GFX6ERR-GISEL %s ; RUN: not --crash llc -global-isel=1 -mtriple=amdgcn-mesa-mesa3d -mcpu=tahiti -o - < %s 2>&1 | FileCheck -enable-var-scope -check-prefix=GFX6ERR-GISEL %s
; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=hawaii -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,LOOP %s ; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=hawaii -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,LOOP %s
; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=fiji -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,LOOP,GFX8 %s ; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=fiji -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,LOOP %s
; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx900 -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,NOLOOP %s ; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx900 -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,NOLOOP %s
; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1010 -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,NOLOOP,GFX10 %s ; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1010 -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,NOLOOP %s
; GFX6ERR-SDAG: LLVM ERROR: Cannot select: intrinsic %llvm.amdgcn.ds.gws.sema.release.all ; GFX6ERR-SDAG: LLVM ERROR: Cannot select: intrinsic %llvm.amdgcn.ds.gws.sema.release.all
; GFX6ERR-GISEL: LLVM ERROR: cannot select: G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.ds.gws.sema.release.all), %{{[0-9]+}}:sgpr(s32) :: (store 4 into custom "GWSResource") (in function: gws_sema_release_all_offset0) ; GFX6ERR-GISEL: LLVM ERROR: cannot select: G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.ds.gws.sema.release.all), %{{[0-9]+}}:sgpr(s32) :: (store 4 into custom "GWSResource") (in function: gws_sema_release_all_offset0)
; GCN-LABEL: {{^}}gws_sema_release_all_offset0: ; GCN-LABEL: {{^}}gws_sema_release_all_offset0:
; NOLOOP-DAG: s_mov_b32 m0, 0{{$}} ; NOLOOP-DAG: s_mov_b32 m0, 0{{$}}
; NOLOOP: ds_gws_sema_release_all gds{{$}} ; NOLOOP: ds_gws_sema_release_all gds{{$}}
Show All 16 Lines

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.ds.gws.sema.v.ll

; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=tahiti -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,LOOP %s ; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=tahiti -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,LOOP %s
; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=hawaii -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,LOOP %s ; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=hawaii -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,LOOP %s
; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=fiji -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,LOOP,GFX8 %s ; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=fiji -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,LOOP %s
; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx900 -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,NOLOOP %s ; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx900 -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,NOLOOP %s
; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1010 -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,NOLOOP,GFX10 %s ; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1010 -o - -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,NOLOOP %s
; GCN-LABEL: {{^}}gws_sema_v_offset0: ; GCN-LABEL: {{^}}gws_sema_v_offset0:
; NOLOOP-DAG: s_mov_b32 m0, 0{{$}} ; NOLOOP-DAG: s_mov_b32 m0, 0{{$}}
; NOLOOP: ds_gws_sema_v gds{{$}} ; NOLOOP: ds_gws_sema_v gds{{$}}
; LOOP: s_mov_b32 m0, 0{{$}} ; LOOP: s_mov_b32 m0, 0{{$}}
; LOOP: [[LOOP:BB[0-9]+_[0-9]+]]: ; LOOP: [[LOOP:BB[0-9]+_[0-9]+]]:
; LOOP-NEXT: s_setreg_imm32_b32 hwreg(HW_REG_TRAPSTS, 8, 1), 0 ; LOOP-NEXT: s_setreg_imm32_b32 hwreg(HW_REG_TRAPSTS, 8, 1), 0
Show All 13 Lines

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.fract.ll

; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=GCN %s ; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=GCN %s ; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
declare float @llvm.amdgcn.fract.f32(float) #0 declare float @llvm.amdgcn.fract.f32(float) #0
declare double @llvm.amdgcn.fract.f64(double) #0 declare double @llvm.amdgcn.fract.f64(double) #0
; GCN-LABEL: {{^}}v_fract_f32: ; GCN-LABEL: {{^}}v_fract_f32:
; GCN: v_fract_f32_e32 {{v[0-9]+}}, {{s[0-9]+}} ; GCN: v_fract_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}
define amdgpu_kernel void @v_fract_f32(float addrspace(1)* %out, float %src) #1 { define amdgpu_kernel void @v_fract_f32(float addrspace(1)* %out, float %src) #1 {
%fract = call float @llvm.amdgcn.fract.f32(float %src) %fract = call float @llvm.amdgcn.fract.f32(float %src)
Show All 23 Lines

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.d16.dim.ll

; RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck -check-prefixes=GCN,UNPACKED,GFX89 %s ; RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck -check-prefixes=GCN,UNPACKED,GFX89 %s
; RUN: llc < %s -march=amdgcn -mcpu=gfx810 -verify-machineinstrs | FileCheck -check-prefixes=GCN,GFX81,GFX89 %s ; RUN: llc < %s -march=amdgcn -mcpu=gfx810 -verify-machineinstrs | FileCheck -check-prefixes=GCN,GFX81,GFX89 %s
; RUN: llc < %s -march=amdgcn -mcpu=gfx900 -verify-machineinstrs | FileCheck -check-prefixes=GCN,PACKED,GFX9,GFX89 %s ; RUN: llc < %s -march=amdgcn -mcpu=gfx900 -verify-machineinstrs | FileCheck -check-prefixes=GCN,PACKED,GFX89 %s
; RUN: llc < %s -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs | FileCheck -check-prefixes=GCN,GFX10 %s ; RUN: llc < %s -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs | FileCheck -check-prefixes=GCN,GFX10 %s
; GCN-LABEL: {{^}}image_load_f16: ; GCN-LABEL: {{^}}image_load_f16:
; GFX89: image_load v0, v[0:1], s[0:7] dmask:0x1 unorm d16{{$}} ; GFX89: image_load v0, v[0:1], s[0:7] dmask:0x1 unorm d16{{$}}
; GFX10: image_load v0, v[0:1], s[0:7] dmask:0x1 dim:SQ_RSRC_IMG_2D unorm d16{{$}} ; GFX10: image_load v0, v[0:1], s[0:7] dmask:0x1 dim:SQ_RSRC_IMG_2D unorm d16{{$}}
define amdgpu_ps half @image_load_f16(<8 x i32> inreg %rsrc, i32 %s, i32 %t) { define amdgpu_ps half @image_load_f16(<8 x i32> inreg %rsrc, i32 %s, i32 %t) {
main_body: main_body:
%tex = call half @llvm.amdgcn.image.load.2d.f16.i32(i32 1, i32 %s, i32 %t, <8 x i32> %rsrc, i32 0, i32 0) %tex = call half @llvm.amdgcn.image.load.2d.f16.i32(i32 1, i32 %s, i32 %t, <8 x i32> %rsrc, i32 0, i32 0)
▲ Show 20 Lines • Show All 164 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.gather4.d16.dim.ll

; RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck -check-prefixes=GCN,UNPACKED,GFX89 %s ; RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck -check-prefixes=GCN,UNPACKED %s
; RUN: llc < %s -march=amdgcn -mcpu=gfx810 -verify-machineinstrs | FileCheck -check-prefixes=GCN,GFX81,GFX89 %s ; RUN: llc < %s -march=amdgcn -mcpu=gfx810 -verify-machineinstrs | FileCheck --check-prefix=GCN %s
; RUN: llc < %s -march=amdgcn -mcpu=gfx900 -verify-machineinstrs | FileCheck -check-prefixes=GCN,GFX9,GFX89 %s ; RUN: llc < %s -march=amdgcn -mcpu=gfx900 -verify-machineinstrs | FileCheck -check-prefixes=GCN,GFX9 %s
; RUN: llc < %s -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs | FileCheck -check-prefixes=GCN,GFX10 %s ; RUN: llc < %s -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs | FileCheck -check-prefixes=GCN,GFX10 %s
; GCN-LABEL: {{^}}image_gather4_b_2d_v4f16: ; GCN-LABEL: {{^}}image_gather4_b_2d_v4f16:
; UNPACKED: image_gather4_b v[0:3], v[0:2], s[0:7], s[8:11] dmask:0x4 d16{{$}} ; UNPACKED: image_gather4_b v[0:3], v[0:2], s[0:7], s[8:11] dmask:0x4 d16{{$}}
; PACKED: image_gather4_b v[0:1], v[0:2], s[0:7], s[8:11] dmask:0x4 d16{{$}} ; PACKED: image_gather4_b v[0:1], v[0:2], s[0:7], s[8:11] dmask:0x4 d16{{$}}
; GFX810: image_gather4_b v[0:3], v[0:2], s[0:7], s[8:11] dmask:0x4 d16{{$}} ; GFX810: image_gather4_b v[0:3], v[0:2], s[0:7], s[8:11] dmask:0x4 d16{{$}}
; GFX9: image_gather4_b v[0:3], v[0:2], s[0:7], s[8:11] dmask:0x4 d16{{$}} ; GFX9: image_gather4_b v[0:3], v[0:2], s[0:7], s[8:11] dmask:0x4 d16{{$}}
; GFX10: image_gather4_b v[0:1], v[0:2], s[0:7], s[8:11] dmask:0x4 dim:SQ_RSRC_IMG_2D d16{{$}} ; GFX10: image_gather4_b v[0:1], v[0:2], s[0:7], s[8:11] dmask:0x4 dim:SQ_RSRC_IMG_2D d16{{$}}
Show All 12 Lines

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.interp.ll

; RUN: llc -march=amdgcn -mcpu=verde -verify-machineinstrs < %s | FileCheck -allow-deprecated-dag-overlap -check-prefix=GCN %s ; RUN: llc -march=amdgcn -mcpu=verde -verify-machineinstrs < %s | FileCheck -allow-deprecated-dag-overlap -check-prefix=GCN %s
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -allow-deprecated-dag-overlap -check-prefixes=GCN,VI %s ; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -allow-deprecated-dag-overlap --check-prefix=GCN %s
; RUN: llc -march=amdgcn -mcpu=kabini -verify-machineinstrs < %s | FileCheck -allow-deprecated-dag-overlap -check-prefixes=GCN,16BANK %s ; RUN: llc -march=amdgcn -mcpu=kabini -verify-machineinstrs < %s | FileCheck -allow-deprecated-dag-overlap -check-prefixes=GCN,16BANK %s
; RUN: llc -march=amdgcn -mcpu=stoney -verify-machineinstrs < %s | FileCheck -allow-deprecated-dag-overlap -check-prefixes=GCN,16BANK %s ; RUN: llc -march=amdgcn -mcpu=stoney -verify-machineinstrs < %s | FileCheck -allow-deprecated-dag-overlap -check-prefixes=GCN,16BANK %s
; GCN-LABEL: {{^}}v_interp: ; GCN-LABEL: {{^}}v_interp:
; GCN-NOT: s_wqm ; GCN-NOT: s_wqm
; GCN: s_mov_b32 m0, s{{[0-9]+}} ; GCN: s_mov_b32 m0, s{{[0-9]+}}
; GCN-DAG: v_interp_p1_f32{{(_e32)*}} v{{[0-9]+}}, v{{[0-9]+}}, attr0.x{{$}} ; GCN-DAG: v_interp_p1_f32{{(_e32)*}} v{{[0-9]+}}, v{{[0-9]+}}, attr0.x{{$}}
; GCN-DAG: v_interp_p1_f32{{(_e32)*}} v{{[0-9]+}}, v{{[0-9]+}}, attr0.y{{$}} ; GCN-DAG: v_interp_p1_f32{{(_e32)*}} v{{[0-9]+}}, v{{[0-9]+}}, attr0.y{{$}}
▲ Show 20 Lines • Show All 216 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.log.clamp.ll

; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=GCN %s ; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
; RUN: not llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s 2>&1 | FileCheck -check-prefix=ERR %s ; RUN: not llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s 2>&1 | FileCheck -check-prefix=ERR %s
; ERR: intrinsic not supported on subtarget ; ERR: intrinsic not supported on subtarget
declare float @llvm.amdgcn.log.clamp.f32(float) #0 declare float @llvm.amdgcn.log.clamp.f32(float) #0
; GCN-LABEL: {{^}}v_log_clamp_f32: ; GCN-LABEL: {{^}}v_log_clamp_f32:
; GCN: v_log_clamp_f32_e32 {{v[0-9]+}}, {{s[0-9]+}} ; GCN: v_log_clamp_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}
define amdgpu_kernel void @v_log_clamp_f32(float addrspace(1)* %out, float %src) #1 { define amdgpu_kernel void @v_log_clamp_f32(float addrspace(1)* %out, float %src) #1 {
%log.clamp = call float @llvm.amdgcn.log.clamp.f32(float %src) #0 %log.clamp = call float @llvm.amdgcn.log.clamp.f32(float %src) #0
store float %log.clamp, float addrspace(1)* %out store float %log.clamp, float addrspace(1)* %out
ret void ret void
} }
attributes #0 = { nounwind readnone } attributes #0 = { nounwind readnone }
attributes #1 = { nounwind } attributes #1 = { nounwind }

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.buffer.atomic.ll

;RUN: llc < %s -march=amdgcn -mcpu=verde -amdgpu-atomic-optimizations=false -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=SICI ;RUN: llc < %s -march=amdgcn -mcpu=verde -amdgpu-atomic-optimizations=false -verify-machineinstrs | FileCheck %s
;RUN: llc < %s -march=amdgcn -mcpu=tonga -amdgpu-atomic-optimizations=false -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=VI ;RUN: llc < %s -march=amdgcn -mcpu=tonga -amdgpu-atomic-optimizations=false -verify-machineinstrs | FileCheck %s
;CHECK-LABEL: {{^}}test1: ;CHECK-LABEL: {{^}}test1:
;CHECK-NOT: s_waitcnt ;CHECK-NOT: s_waitcnt
;CHECK: buffer_atomic_swap v0, off, s[0:3], 0 glc ;CHECK: buffer_atomic_swap v0, off, s[0:3], 0 glc
;CHECK: s_movk_i32 [[SOFS:s[0-9]+]], 0x1ffc ;CHECK: s_movk_i32 [[SOFS:s[0-9]+]], 0x1ffc
;CHECK: s_waitcnt vmcnt(0) ;CHECK: s_waitcnt vmcnt(0)
;CHECK: buffer_atomic_swap v0, v1, s[0:3], 0 offen glc ;CHECK: buffer_atomic_swap v0, v1, s[0:3], 0 offen glc
;CHECK: s_waitcnt vmcnt(0) ;CHECK: s_waitcnt vmcnt(0)
▲ Show 20 Lines • Show All 116 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.buffer.load.format.ll

;RUN: llc < %s -march=amdgcn -mcpu=verde -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=SICI ;RUN: llc < %s -march=amdgcn -mcpu=verde -verify-machineinstrs | FileCheck %s
;RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=VI ;RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck %s
;CHECK-LABEL: {{^}}buffer_load: ;CHECK-LABEL: {{^}}buffer_load:
;CHECK: buffer_load_format_xyzw v[0:3], off, s[0:3], 0 ;CHECK: buffer_load_format_xyzw v[0:3], off, s[0:3], 0
;CHECK: buffer_load_format_xyzw v[4:7], off, s[0:3], 0 glc ;CHECK: buffer_load_format_xyzw v[4:7], off, s[0:3], 0 glc
;CHECK: buffer_load_format_xyzw v[8:11], off, s[0:3], 0 slc ;CHECK: buffer_load_format_xyzw v[8:11], off, s[0:3], 0 slc
;CHECK: s_waitcnt ;CHECK: s_waitcnt
define amdgpu_ps {<4 x float>, <4 x float>, <4 x float>} @buffer_load(<4 x i32> inreg) { define amdgpu_ps {<4 x float>, <4 x float>, <4 x float>} @buffer_load(<4 x i32> inreg) {
main_body: main_body:
▲ Show 20 Lines • Show All 77 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.buffer.load.ll

;RUN: llc < %s -march=amdgcn -mcpu=verde -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefixes=SICI,PREGFX10 ;RUN: llc < %s -march=amdgcn -mcpu=verde -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK,PREGFX10
;RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefixes=VI,PREGFX10 ;RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK,VI,PREGFX10
;RUN: llc < %s -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=GFX10 ;RUN: llc < %s -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK,GFX10
;CHECK-LABEL: {{^}}buffer_load: ;CHECK-LABEL: {{^}}buffer_load:
;CHECK: buffer_load_dwordx4 v[0:3], off, s[0:3], 0{{$}} ;CHECK: buffer_load_dwordx4 v[0:3], off, s[0:3], 0{{$}}
;CHECK: buffer_load_dwordx4 v[4:7], off, s[0:3], 0 glc{{$}} ;CHECK: buffer_load_dwordx4 v[4:7], off, s[0:3], 0 glc{{$}}
;CHECK: buffer_load_dwordx4 v[8:11], off, s[0:3], 0 slc{{$}} ;CHECK: buffer_load_dwordx4 v[8:11], off, s[0:3], 0 slc{{$}}
;CHECK: s_waitcnt ;CHECK: s_waitcnt
define amdgpu_ps {<4 x float>, <4 x float>, <4 x float>} @buffer_load(<4 x i32> inreg) { define amdgpu_ps {<4 x float>, <4 x float>, <4 x float>} @buffer_load(<4 x i32> inreg) {
main_body: main_body:
▲ Show 20 Lines • Show All 453 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.buffer.store.format.d16.ll

; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=tonga -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,UNPACKED %s ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=tonga -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,UNPACKED %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx810 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,PACKED,GFX81 %s ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx810 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,PACKED %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,PACKED,GFX9 %s ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,PACKED %s
; GCN-LABEL: {{^}}buffer_store_format_d16_x: ; GCN-LABEL: {{^}}buffer_store_format_d16_x:
; GCN: s_load_dword s[[LO:[0-9]+]] ; GCN: s_load_dword s[[LO:[0-9]+]]
; GCN: v_mov_b32_e32 v[[V_LO:[0-9]+]], s[[LO]] ; GCN: v_mov_b32_e32 v[[V_LO:[0-9]+]], s[[LO]]
; GCN: buffer_store_format_d16_x v[[V_LO]], v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 offen ; GCN: buffer_store_format_d16_x v[[V_LO]], v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 offen
define amdgpu_kernel void @buffer_store_format_d16_x(<4 x i32> %rsrc, [8 x i32], half %data, [8 x i32], i32 %voffset) { define amdgpu_kernel void @buffer_store_format_d16_x(<4 x i32> %rsrc, [8 x i32], half %data, [8 x i32], i32 %voffset) {
main_body: main_body:
call void @llvm.amdgcn.raw.buffer.store.format.f16(half %data, <4 x i32> %rsrc, i32 %voffset, i32 0, i32 0) call void @llvm.amdgcn.raw.buffer.store.format.f16(half %data, <4 x i32> %rsrc, i32 %voffset, i32 0, i32 0)
▲ Show 20 Lines • Show All 72 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.tbuffer.store.ll

;RUN: llc < %s -march=amdgcn -mcpu=verde -verify-machineinstrs | FileCheck -check-prefixes=GCN,VERDE,PREGFX10 %s ;RUN: llc < %s -march=amdgcn -mcpu=verde -verify-machineinstrs | FileCheck -check-prefixes=GCN,PREGFX10 %s
;RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck -check-prefixes=GCN,PREGFX10 %s ;RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck -check-prefixes=GCN,PREGFX10 %s
;RUN: llc < %s -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs | FileCheck -check-prefixes=GCN,GFX10 %s ;RUN: llc < %s -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs | FileCheck -check-prefixes=GCN,GFX10 %s
; GCN-LABEL: {{^}}tbuffer_store: ; GCN-LABEL: {{^}}tbuffer_store:
; PREGFX10: tbuffer_store_format_xyzw v[0:3], off, s[0:3], 0 format:[BUF_DATA_FORMAT_16_16_16_16,BUF_NUM_FORMAT_USCALED] ; PREGFX10: tbuffer_store_format_xyzw v[0:3], off, s[0:3], 0 format:[BUF_DATA_FORMAT_16_16_16_16,BUF_NUM_FORMAT_USCALED]
; PREGFX10: tbuffer_store_format_xyzw v[4:7], off, s[0:3], 0 format:[BUF_DATA_FORMAT_32_32_32,BUF_NUM_FORMAT_SSCALED] glc ; PREGFX10: tbuffer_store_format_xyzw v[4:7], off, s[0:3], 0 format:[BUF_DATA_FORMAT_32_32_32,BUF_NUM_FORMAT_SSCALED] glc
; PREGFX10: tbuffer_store_format_xyzw v[8:11], off, s[0:3], 0 format:[BUF_DATA_FORMAT_32_32_32_32,BUF_NUM_FORMAT_UINT] slc ; PREGFX10: tbuffer_store_format_xyzw v[8:11], off, s[0:3], 0 format:[BUF_DATA_FORMAT_32_32_32_32,BUF_NUM_FORMAT_UINT] slc
; PREGFX10: tbuffer_store_format_xyzw v[8:11], off, s[0:3], 0 format:[BUF_DATA_FORMAT_32_32_32_32,BUF_NUM_FORMAT_UINT] glc ; PREGFX10: tbuffer_store_format_xyzw v[8:11], off, s[0:3], 0 format:[BUF_DATA_FORMAT_32_32_32_32,BUF_NUM_FORMAT_UINT] glc
▲ Show 20 Lines • Show All 73 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.s.barrier.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX8,VARIANT0 %s ; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck --check-prefix=VARIANT0 %s
; RUN: llc -march=amdgcn -mattr=+auto-waitcnt-before-barrier -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX8,VARIANT1 %s ; RUN: llc -march=amdgcn -mattr=+auto-waitcnt-before-barrier -verify-machineinstrs < %s | FileCheck --check-prefix=VARIANT1 %s
; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX9,VARIANT2 %s ; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck --check-prefix=VARIANT2 %s
; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=+auto-waitcnt-before-barrier -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX9,VARIANT3 %s ; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=+auto-waitcnt-before-barrier -verify-machineinstrs < %s | FileCheck --check-prefix=VARIANT3 %s
define amdgpu_kernel void @test_barrier(i32 addrspace(1)* %out, i32 %size) #0 { define amdgpu_kernel void @test_barrier(i32 addrspace(1)* %out, i32 %size) #0 {
; VARIANT0-LABEL: test_barrier: ; VARIANT0-LABEL: test_barrier:
; VARIANT0: ; %bb.0: ; %entry ; VARIANT0: ; %bb.0: ; %entry
; VARIANT0-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x9 ; VARIANT0-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x9
; VARIANT0-NEXT: s_load_dword s2, s[0:1], 0xb ; VARIANT0-NEXT: s_load_dword s2, s[0:1], 0xb
; VARIANT0-NEXT: s_mov_b32 s7, 0xf000 ; VARIANT0-NEXT: s_mov_b32 s7, 0xf000
; VARIANT0-NEXT: s_mov_b32 s6, 0 ; VARIANT0-NEXT: s_mov_b32 s6, 0
▲ Show 20 Lines • Show All 93 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.s.memrealtime.ll

; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=VI -check-prefix=GCN %s ; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
declare i64 @llvm.amdgcn.s.memrealtime() #0 declare i64 @llvm.amdgcn.s.memrealtime() #0
; GCN-LABEL: {{^}}test_s_memrealtime: ; GCN-LABEL: {{^}}test_s_memrealtime:
; GCN-DAG: s_memrealtime s{{\[[0-9]+:[0-9]+\]}} ; GCN-DAG: s_memrealtime s{{\[[0-9]+:[0-9]+\]}}
; GCN-DAG: s_load_dwordx2 ; GCN-DAG: s_load_dwordx2
; GCN: lgkmcnt ; GCN: lgkmcnt
; GCN: _store_dwordx2 ; GCN: _store_dwordx2
Show All 13 Lines

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.s.memtime.ll

; RUN: llc -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=SIVI -check-prefix=GCN %s ; RUN: llc -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck --check-prefixes=SIVI,GCN %s
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=VI -check-prefix=SIVI -check-prefix=GCN %s ; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck --check-prefixes=SIVI,GCN %s
; RUN: llc -march=amdgcn -mcpu=gfx1010 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s ; RUN: llc -march=amdgcn -mcpu=gfx1010 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
; RUN: not --crash llc -march=amdgcn -mcpu=gfx1030 -mattr=-flat-for-global -verify-machineinstrs < %s 2>&1 | FileCheck -check-prefix=GFX1030-ERR %s ; RUN: not --crash llc -march=amdgcn -mcpu=gfx1030 -mattr=-flat-for-global -verify-machineinstrs < %s 2>&1 | FileCheck -check-prefix=GFX1030-ERR %s
declare i64 @llvm.amdgcn.s.memtime() #0 declare i64 @llvm.amdgcn.s.memtime() #0
; GCN-LABEL: {{^}}test_s_memtime: ; GCN-LABEL: {{^}}test_s_memtime:
; GCN-DAG: s_memtime s{{\[[0-9]+:[0-9]+\]}} ; GCN-DAG: s_memtime s{{\[[0-9]+:[0-9]+\]}}
; GCN-DAG: s_load_dwordx2 ; GCN-DAG: s_load_dwordx2
Show All 16 Lines

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.sbfe.ll

; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=SI %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VI %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
; GCN-LABEL: {{^}}bfe_i32_arg_arg_arg: ; GCN-LABEL: {{^}}bfe_i32_arg_arg_arg:
; GCN: v_bfe_i32 ; GCN: v_bfe_i32
define amdgpu_kernel void @bfe_i32_arg_arg_arg(i32 addrspace(1)* %out, i32 %src0, i32 %src1, i32 %src2) #0 { define amdgpu_kernel void @bfe_i32_arg_arg_arg(i32 addrspace(1)* %out, i32 %src0, i32 %src1, i32 %src2) #0 {
%bfe_i32 = call i32 @llvm.amdgcn.sbfe.i32(i32 %src0, i32 %src1, i32 %src1) %bfe_i32 = call i32 @llvm.amdgcn.sbfe.i32(i32 %src0, i32 %src1, i32 %src1)
store i32 %bfe_i32, i32 addrspace(1)* %out, align 4 store i32 %bfe_i32, i32 addrspace(1)* %out, align 4
ret void ret void
} }
▲ Show 20 Lines • Show All 546 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.sendmsg.ll

;RUN: llc -march=amdgcn -mcpu=verde -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=SI -check-prefix=SIVI %s ;RUN: llc -march=amdgcn -mcpu=verde -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,SIVI %s
;RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VIPLUS -check-prefix=SIVI %s ;RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,VIPLUS,SIVI %s
;RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VIPLUS -check-prefix=GFX9 %s ;RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,VIPLUS,GFX9 %s
; GCN-LABEL: {{^}}test_interrupt: ; GCN-LABEL: {{^}}test_interrupt:
; GCN: s_mov_b32 m0, 0 ; GCN: s_mov_b32 m0, 0
; GCN-NOT: s_mov_b32 m0 ; GCN-NOT: s_mov_b32 m0
; GCN: s_sendmsg sendmsg(MSG_INTERRUPT) ; GCN: s_sendmsg sendmsg(MSG_INTERRUPT)
define amdgpu_kernel void @test_interrupt() { define amdgpu_kernel void @test_interrupt() {
body: body:
call void @llvm.amdgcn.s.sendmsg(i32 1, i32 0); call void @llvm.amdgcn.s.sendmsg(i32 1, i32 0);
▲ Show 20 Lines • Show All 159 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.set.inactive.ll

; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=GCN %s ; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=GCN %s ; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
; GCN-LABEL: {{^}}set_inactive: ; GCN-LABEL: {{^}}set_inactive:
; GCN: s_not_b64 exec, exec ; GCN: s_not_b64 exec, exec
; GCN: v_mov_b32_e32 {{v[0-9]+}}, 42 ; GCN: v_mov_b32_e32 {{v[0-9]+}}, 42
; GCN: s_not_b64 exec, exec ; GCN: s_not_b64 exec, exec
define amdgpu_kernel void @set_inactive(i32 addrspace(1)* %out, i32 %in) { define amdgpu_kernel void @set_inactive(i32 addrspace(1)* %out, i32 %in) {
%tmp = call i32 @llvm.amdgcn.set.inactive.i32(i32 %in, i32 42) #0 %tmp = call i32 @llvm.amdgcn.set.inactive.i32(i32 %in, i32 42) #0
Show All 19 Lines

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.sin.ll

; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=GCN %s ; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=GCN %s ; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
declare float @llvm.amdgcn.sin.f32(float) #0 declare float @llvm.amdgcn.sin.f32(float) #0
; GCN-LABEL: {{^}}v_sin_f32: ; GCN-LABEL: {{^}}v_sin_f32:
; GCN: v_sin_f32_e32 {{v[0-9]+}}, {{s[0-9]+}} ; GCN: v_sin_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}
define amdgpu_kernel void @v_sin_f32(float addrspace(1)* %out, float %src) #1 { define amdgpu_kernel void @v_sin_f32(float addrspace(1)* %out, float %src) #1 {
%sin = call float @llvm.amdgcn.sin.f32(float %src) #0 %sin = call float @llvm.amdgcn.sin.f32(float %src) #0
store float %sin, float addrspace(1)* %out store float %sin, float addrspace(1)* %out
ret void ret void
} }
attributes #0 = { nounwind readnone } attributes #0 = { nounwind readnone }
attributes #1 = { nounwind } attributes #1 = { nounwind }

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.buffer.atomic.ll

;RUN: llc < %s -march=amdgcn -mcpu=verde -amdgpu-atomic-optimizations=false -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=SICI ;RUN: llc < %s -march=amdgcn -mcpu=verde -amdgpu-atomic-optimizations=false -verify-machineinstrs | FileCheck %s
;RUN: llc < %s -march=amdgcn -mcpu=tonga -amdgpu-atomic-optimizations=false -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=VI ;RUN: llc < %s -march=amdgcn -mcpu=tonga -amdgpu-atomic-optimizations=false -verify-machineinstrs | FileCheck %s
;CHECK-LABEL: {{^}}test1: ;CHECK-LABEL: {{^}}test1:
;CHECK-NOT: s_waitcnt ;CHECK-NOT: s_waitcnt
;CHECK: buffer_atomic_swap v0, {{v[0-9]+}}, s[0:3], 0 idxen glc ;CHECK: buffer_atomic_swap v0, {{v[0-9]+}}, s[0:3], 0 idxen glc
;CHECK: s_waitcnt vmcnt(0) ;CHECK: s_waitcnt vmcnt(0)
;CHECK: buffer_atomic_swap v0, {{v[0-9]+}}, s[0:3], 0 idxen glc ;CHECK: buffer_atomic_swap v0, {{v[0-9]+}}, s[0:3], 0 idxen glc
;CHECK: s_movk_i32 [[SOFS:s[0-9]+]], 0x1ffc ;CHECK: s_movk_i32 [[SOFS:s[0-9]+]], 0x1ffc
;CHECK: s_waitcnt vmcnt(0) ;CHECK: s_waitcnt vmcnt(0)
▲ Show 20 Lines • Show All 128 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.buffer.load.format.ll

;RUN: llc < %s -march=amdgcn -mcpu=verde -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=SICI ;RUN: llc < %s -march=amdgcn -mcpu=verde -verify-machineinstrs | FileCheck %s
;RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=VI ;RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck %s
;CHECK-LABEL: {{^}}buffer_load: ;CHECK-LABEL: {{^}}buffer_load:
;CHECK: buffer_load_format_xyzw v[0:3], {{v[0-9]+}}, s[0:3], 0 idxen ;CHECK: buffer_load_format_xyzw v[0:3], {{v[0-9]+}}, s[0:3], 0 idxen
;CHECK: buffer_load_format_xyzw v[4:7], {{v[0-9]+}}, s[0:3], 0 idxen glc ;CHECK: buffer_load_format_xyzw v[4:7], {{v[0-9]+}}, s[0:3], 0 idxen glc
;CHECK: buffer_load_format_xyzw v[8:11], {{v[0-9]+}}, s[0:3], 0 idxen slc ;CHECK: buffer_load_format_xyzw v[8:11], {{v[0-9]+}}, s[0:3], 0 idxen slc
;CHECK: s_waitcnt ;CHECK: s_waitcnt
define amdgpu_ps {<4 x float>, <4 x float>, <4 x float>} @buffer_load(<4 x i32> inreg) { define amdgpu_ps {<4 x float>, <4 x float>, <4 x float>} @buffer_load(<4 x i32> inreg) {
main_body: main_body:
▲ Show 20 Lines • Show All 116 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.buffer.load.ll

;RUN: llc < %s -march=amdgcn -mcpu=verde -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=SICI ;RUN: llc < %s -march=amdgcn -mcpu=verde -verify-machineinstrs | FileCheck %s
;RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=VI ;RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK,VI
;CHECK-LABEL: {{^}}buffer_load: ;CHECK-LABEL: {{^}}buffer_load:
;CHECK: buffer_load_dwordx4 v[0:3], {{v[0-9]+}}, s[0:3], 0 idxen ;CHECK: buffer_load_dwordx4 v[0:3], {{v[0-9]+}}, s[0:3], 0 idxen
;CHECK: buffer_load_dwordx4 v[4:7], {{v[0-9]+}}, s[0:3], 0 idxen glc ;CHECK: buffer_load_dwordx4 v[4:7], {{v[0-9]+}}, s[0:3], 0 idxen glc
;CHECK: buffer_load_dwordx4 v[8:11], {{v[0-9]+}}, s[0:3], 0 idxen slc ;CHECK: buffer_load_dwordx4 v[8:11], {{v[0-9]+}}, s[0:3], 0 idxen slc
;CHECK: s_waitcnt ;CHECK: s_waitcnt
define amdgpu_ps {<4 x float>, <4 x float>, <4 x float>} @buffer_load(<4 x i32> inreg) { define amdgpu_ps {<4 x float>, <4 x float>, <4 x float>} @buffer_load(<4 x i32> inreg) {
main_body: main_body:
▲ Show 20 Lines • Show All 282 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.buffer.store.format.d16.ll

; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=tonga -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,UNPACKED %s ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=tonga -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,UNPACKED %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx810 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,PACKED,GFX81 %s ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx810 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,PACKED %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,PACKED,GFX9 %s ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,PACKED %s
; GCN-LABEL: {{^}}buffer_store_format_d16_x: ; GCN-LABEL: {{^}}buffer_store_format_d16_x:
; GCN: s_load_dword s[[LO:[0-9]+]] ; GCN: s_load_dword s[[LO:[0-9]+]]
; GCN: v_mov_b32_e32 v[[V_LO:[0-9]+]], s[[LO]] ; GCN: v_mov_b32_e32 v[[V_LO:[0-9]+]], s[[LO]]
; GCN: buffer_store_format_d16_x v[[V_LO]], v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 idxen ; GCN: buffer_store_format_d16_x v[[V_LO]], v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 idxen
define amdgpu_kernel void @buffer_store_format_d16_x(<4 x i32> %rsrc, [8 x i32], half %data, [8 x i32], i32 %index) { define amdgpu_kernel void @buffer_store_format_d16_x(<4 x i32> %rsrc, [8 x i32], half %data, [8 x i32], i32 %index) {
main_body: main_body:
call void @llvm.amdgcn.struct.buffer.store.format.f16(half %data, <4 x i32> %rsrc, i32 %index, i32 0, i32 0, i32 0) call void @llvm.amdgcn.struct.buffer.store.format.f16(half %data, <4 x i32> %rsrc, i32 %index, i32 0, i32 0, i32 0)
▲ Show 20 Lines • Show All 83 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.tbuffer.load.d16.ll

; RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs -show-mc-encoding | FileCheck -enable-var-scope -check-prefixes=GCN,UNPACKED,PREGFX10,PREGFX10-UNPACKED %s ; RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs -show-mc-encoding | FileCheck -enable-var-scope -check-prefixes=GCN,PREGFX10,PREGFX10-UNPACKED %s
; RUN: llc < %s -march=amdgcn -mcpu=gfx810 -verify-machineinstrs | FileCheck -enable-var-scope -check-prefixes=GCN,PACKED,PREGFX10,PREGFX10-PACKED %s ; RUN: llc < %s -march=amdgcn -mcpu=gfx810 -verify-machineinstrs | FileCheck -enable-var-scope -check-prefixes=GCN,PACKED,PREGFX10,PREGFX10-PACKED %s
; RUN: llc < %s -march=amdgcn -mcpu=gfx900 -verify-machineinstrs | FileCheck -enable-var-scope -check-prefixes=GCN,PACKED,PREGFX10,PREGFX10-PACKED %s ; RUN: llc < %s -march=amdgcn -mcpu=gfx900 -verify-machineinstrs | FileCheck -enable-var-scope -check-prefixes=GCN,PACKED,PREGFX10,PREGFX10-PACKED %s
; RUN: llc < %s -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs | FileCheck -enable-var-scope -check-prefixes=GCN,PACKED,GFX10,GFX10-PACKED %s ; RUN: llc < %s -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs | FileCheck -enable-var-scope -check-prefixes=GCN,PACKED,GFX10,GFX10-PACKED %s
; GCN-LABEL: {{^}}tbuffer_load_d16_x: ; GCN-LABEL: {{^}}tbuffer_load_d16_x:
; GCN: v_mov_b32_e32 [[ZEROREG:v[0-9]+]], 0 ; GCN: v_mov_b32_e32 [[ZEROREG:v[0-9]+]], 0
; PREGFX10: tbuffer_load_format_d16_x v{{[0-9]+}}, [[ZEROREG]], s[{{[0-9]+:[0-9]+}}], 0 format:[BUF_DATA_FORMAT_10_11_11,BUF_NUM_FORMAT_SNORM] idxen ; PREGFX10: tbuffer_load_format_d16_x v{{[0-9]+}}, [[ZEROREG]], s[{{[0-9]+:[0-9]+}}], 0 format:[BUF_DATA_FORMAT_10_11_11,BUF_NUM_FORMAT_SNORM] idxen
; GFX10: tbuffer_load_format_d16_x v{{[0-9]+}}, [[ZEROREG]], s[{{[0-9]+:[0-9]+}}], 0 format:[BUF_FMT_32_FLOAT] idxen ; GFX10: tbuffer_load_format_d16_x v{{[0-9]+}}, [[ZEROREG]], s[{{[0-9]+:[0-9]+}}], 0 format:[BUF_FMT_32_FLOAT] idxen
▲ Show 20 Lines • Show All 55 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.tbuffer.store.d16.ll

; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=tonga -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,PREGFX10,UNPACKED,PREGFX10-UNPACKED %s ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=tonga -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,PREGFX10,UNPACKED,PREGFX10-UNPACKED %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx810 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,PREGFX10,PACKED,GFX81,PREGFX10-PACKED %s ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx810 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,PREGFX10,PACKED,PREGFX10-PACKED %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,PREGFX10,PACKED,GFX9,PREGFX10-PACKED %s ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,PREGFX10,PACKED,PREGFX10-PACKED %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX10,PACKED,GFX10-PACKED %s ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX10,PACKED,GFX10-PACKED %s
; GCN-LABEL: {{^}}tbuffer_store_d16_x: ; GCN-LABEL: {{^}}tbuffer_store_d16_x:
; GCN-DAG: s_load_dwordx4 ; GCN-DAG: s_load_dwordx4
; GCN-DAG: s_load_dword{{[x0-2]*}} s{{\[}}[[S_LO:[0-9]+]] ; GCN-DAG: s_load_dword{{[x0-2]*}} s{{\[}}[[S_LO:[0-9]+]]
; GCN-DAG: v_mov_b32_e32 v[[V_LO:[0-9]+]], s[[S_LO]] ; GCN-DAG: v_mov_b32_e32 v[[V_LO:[0-9]+]], s[[S_LO]]
; PREGFX10: tbuffer_store_format_d16_x v[[V_LO]], v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 format:[BUF_NUM_FORMAT_USCALED] idxen ; PREGFX10: tbuffer_store_format_d16_x v[[V_LO]], v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 format:[BUF_NUM_FORMAT_USCALED] idxen
▲ Show 20 Lines • Show All 74 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.tbuffer.store.d16.ll

; RUN: llc -global-isel=0 -mtriple=amdgcn-amd-amdhsa -mcpu=tonga -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=UNPACKED %s ; RUN: llc -global-isel=0 -mtriple=amdgcn-amd-amdhsa -mcpu=tonga -verify-machineinstrs < %s | FileCheck -enable-var-scope --check-prefixes=GCN,UNPACKED %s
; RUN: llc -global-isel=0 -mtriple=amdgcn-amd-amdhsa -mcpu=gfx810 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=PACKED -check-prefix=GFX81 %s ; RUN: llc -global-isel=0 -mtriple=amdgcn-amd-amdhsa -mcpu=gfx810 -verify-machineinstrs < %s | FileCheck -enable-var-scope --check-prefixes=GCN,PACKED %s
; RUN: llc -global-isel=0 -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=PACKED -check-prefix=GFX9 %s ; RUN: llc -global-isel=0 -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -enable-var-scope --check-prefixes=GCN,PACKED %s
; GCN-LABEL: {{^}}tbuffer_store_d16_x: ; GCN-LABEL: {{^}}tbuffer_store_d16_x:
; GCN: s_load_dword s[[S_LO:[0-9]+]] ; GCN: s_load_dword s[[S_LO:[0-9]+]]
; GCN: v_mov_b32_e32 v[[V_LO:[0-9]+]], s[[S_LO]] ; GCN: v_mov_b32_e32 v[[V_LO:[0-9]+]], s[[S_LO]]
; GCN: tbuffer_store_format_d16_x v[[V_LO]], v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 format:[BUF_NUM_FORMAT_USCALED] idxen ; GCN: tbuffer_store_format_d16_x v[[V_LO]], v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 format:[BUF_NUM_FORMAT_USCALED] idxen
define amdgpu_kernel void @tbuffer_store_d16_x(<4 x i32> %rsrc, [8 x i32], half %data, [8 x i32], i32 %vindex) { define amdgpu_kernel void @tbuffer_store_d16_x(<4 x i32> %rsrc, [8 x i32], half %data, [8 x i32], i32 %vindex) {
main_body: main_body:
▲ Show 20 Lines • Show All 67 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.ubfe.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,SI %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -verify-machineinstrs < %s | FileCheck --check-prefix=SI %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,VI %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck --check-prefix=VI %s
define amdgpu_kernel void @bfe_u32_arg_arg_arg(i32 addrspace(1)* %out, i32 %src0, i32 %src1, i32 %src2) #0 { define amdgpu_kernel void @bfe_u32_arg_arg_arg(i32 addrspace(1)* %out, i32 %src0, i32 %src1, i32 %src2) #0 {
; SI-LABEL: bfe_u32_arg_arg_arg: ; SI-LABEL: bfe_u32_arg_arg_arg:
; SI: ; %bb.0: ; SI: ; %bb.0:
; SI-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0xb ; SI-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0xb
; SI-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x9 ; SI-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x9
; SI-NEXT: s_mov_b32 s7, 0xf000 ; SI-NEXT: s_mov_b32 s7, 0xf000
; SI-NEXT: s_mov_b32 s6, -1 ; SI-NEXT: s_mov_b32 s6, -1
▲ Show 20 Lines • Show All 1,733 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.workgroup.id.ll

; RUN: llc -march=amdgcn -mtriple=amdgcn-unknown-amdhsa --amdhsa-code-object-version=2 -mcpu=kaveri -verify-machineinstrs < %s | FileCheck -check-prefix=ALL -check-prefix=CO-V2 -check-prefix=CI-HSA %s ; RUN: llc -march=amdgcn -mtriple=amdgcn-unknown-amdhsa --amdhsa-code-object-version=2 -mcpu=kaveri -verify-machineinstrs < %s | FileCheck --check-prefixes=ALL,CO-V2 %s
; RUN: llc -march=amdgcn -mtriple=amdgcn-unknown-amdhsa --amdhsa-code-object-version=2 -mcpu=carrizo -verify-machineinstrs < %s | FileCheck -check-prefix=ALL -check-prefix=CO-V2 -check-prefix=VI-HSA %s ; RUN: llc -march=amdgcn -mtriple=amdgcn-unknown-amdhsa --amdhsa-code-object-version=2 -mcpu=carrizo -verify-machineinstrs < %s | FileCheck --check-prefixes=ALL,CO-V2 %s
; RUN: llc -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefix=ALL -check-prefix=UNKNOWN-OS -check-prefix=SI-MESA %s ; RUN: llc -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck --check-prefixes=ALL,UNKNOWN-OS %s
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=ALL -check-prefix=UNKNOWN-OS -check-prefix=VI-MESA %s ; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck --check-prefixes=ALL,UNKNOWN-OS %s
; RUN: llc -mtriple=amdgcn-unknown-mesa3d -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefixes=ALL,CO-V2,SI-MESA %s ; RUN: llc -mtriple=amdgcn-unknown-mesa3d -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefixes=ALL,CO-V2 %s
; RUN: llc -mtriple=amdgcn-unknown-mesa3d -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefixes=ALL,CO-V2,VI-MESA %s ; RUN: llc -mtriple=amdgcn-unknown-mesa3d -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefixes=ALL,CO-V2 %s
declare i32 @llvm.amdgcn.workgroup.id.x() #0 declare i32 @llvm.amdgcn.workgroup.id.x() #0
declare i32 @llvm.amdgcn.workgroup.id.y() #0 declare i32 @llvm.amdgcn.workgroup.id.y() #0
declare i32 @llvm.amdgcn.workgroup.id.z() #0 declare i32 @llvm.amdgcn.workgroup.id.z() #0
; ALL-LABEL: {{^}}test_workgroup_id_x: ; ALL-LABEL: {{^}}test_workgroup_id_x:
; CO-V2: .amd_kernel_code_t ; CO-V2: .amd_kernel_code_t
▲ Show 20 Lines • Show All 92 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.workitem.id.ll

; RUN: llc -march=amdgcn -mtriple=amdgcn-unknown-amdhsa --amdhsa-code-object-version=2 -mcpu=kaveri -verify-machineinstrs < %s | FileCheck -check-prefix=ALL -check-prefix=CO-V2 -check-prefix=CI-HSA %s ; RUN: llc -march=amdgcn -mtriple=amdgcn-unknown-amdhsa --amdhsa-code-object-version=2 -mcpu=kaveri -verify-machineinstrs < %s | FileCheck --check-prefixes=ALL,CO-V2 %s
; RUN: llc -march=amdgcn -mtriple=amdgcn-unknown-amdhsa --amdhsa-code-object-version=2 -mcpu=carrizo -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=ALL -check-prefix=CO-V2 -check-prefix=VI-HSA %s ; RUN: llc -march=amdgcn -mtriple=amdgcn-unknown-amdhsa --amdhsa-code-object-version=2 -mcpu=carrizo -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck --check-prefixes=ALL,CO-V2 %s
; RUN: llc -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefix=ALL -check-prefix=MESA -check-prefix=SI-MESA %s ; RUN: llc -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck --check-prefixes=ALL,MESA %s
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=ALL -check-prefix=MESA -check-prefix=VI-MESA %s ; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck --check-prefixes=ALL,MESA %s
; RUN: llc -mtriple=amdgcn-unknown-mesa3d -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefixes=ALL,CO-V2,SI-MESA %s ; RUN: llc -mtriple=amdgcn-unknown-mesa3d -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefixes=ALL,CO-V2 %s
; RUN: llc -mtriple=amdgcn-unknown-mesa3d -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefixes=ALL,CO-V2,VI-MESA %s ; RUN: llc -mtriple=amdgcn-unknown-mesa3d -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefixes=ALL,CO-V2 %s
declare i32 @llvm.amdgcn.workitem.id.x() #0 declare i32 @llvm.amdgcn.workitem.id.x() #0
declare i32 @llvm.amdgcn.workitem.id.y() #0 declare i32 @llvm.amdgcn.workitem.id.y() #0
declare i32 @llvm.amdgcn.workitem.id.z() #0 declare i32 @llvm.amdgcn.workitem.id.z() #0
; MESA: .section .AMDGPU.config ; MESA: .section .AMDGPU.config
; MESA: .long 47180 ; MESA: .long 47180
; MESA-NEXT: .long 132{{$}} ; MESA-NEXT: .long 132{{$}}
▲ Show 20 Lines • Show All 44 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.writelane.ll

; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=gfx700 -verify-machineinstrs < %s | FileCheck -check-prefixes=CHECK,CI,CIGFX9 %s ; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=gfx700 -verify-machineinstrs < %s | FileCheck -check-prefixes=CHECK,CIGFX9 %s
; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=gfx802 -verify-machineinstrs < %s | FileCheck -check-prefixes=CHECK,GFX9,CIGFX9 %s ; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=gfx802 -verify-machineinstrs < %s | FileCheck -check-prefixes=CHECK,CIGFX9 %s
; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=gfx1010 -verify-machineinstrs < %s | FileCheck -check-prefixes=CHECK,GFX10 %s ; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=gfx1010 -verify-machineinstrs < %s | FileCheck -check-prefixes=CHECK,GFX10 %s
declare i32 @llvm.amdgcn.writelane(i32, i32, i32) #0 declare i32 @llvm.amdgcn.writelane(i32, i32, i32) #0
; CHECK-LABEL: {{^}}test_writelane_sreg: ; CHECK-LABEL: {{^}}test_writelane_sreg:
; CIGFX9: v_writelane_b32 v{{[0-9]+}}, s{{[0-9]+}}, m0 ; CIGFX9: v_writelane_b32 v{{[0-9]+}}, s{{[0-9]+}}, m0
; GFX10: v_writelane_b32 v{{[0-9]+}}, s{{[0-9]+}}, s{{[0-9]+}} ; GFX10: v_writelane_b32 v{{[0-9]+}}, s{{[0-9]+}}, s{{[0-9]+}}
define amdgpu_kernel void @test_writelane_sreg(i32 addrspace(1)* %out, i32 %src0, i32 %src1) #1 { define amdgpu_kernel void @test_writelane_sreg(i32 addrspace(1)* %out, i32 %src0, i32 %src1) #1 {
▲ Show 20 Lines • Show All 76 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.cos.f16.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX6 %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -enable-var-scope --check-prefix=GFX6 %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=fiji -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX8 %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=fiji -verify-machineinstrs < %s | FileCheck -enable-var-scope --check-prefix=GFX8 %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9 %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -enable-var-scope --check-prefix=GFX9 %s
define amdgpu_kernel void @cos_f16(half addrspace(1)* %r, half addrspace(1)* %a) { define amdgpu_kernel void @cos_f16(half addrspace(1)* %r, half addrspace(1)* %a) {
; GFX6-LABEL: cos_f16: ; GFX6-LABEL: cos_f16:
; GFX6: ; %bb.0: ; GFX6: ; %bb.0:
; GFX6-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x9 ; GFX6-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x9
; GFX6-NEXT: s_mov_b32 s3, 0xf000 ; GFX6-NEXT: s_mov_b32 s3, 0xf000
; GFX6-NEXT: s_mov_b32 s2, -1 ; GFX6-NEXT: s_mov_b32 s2, -1
; GFX6-NEXT: s_mov_b32 s10, s2 ; GFX6-NEXT: s_mov_b32 s10, s2
▲ Show 20 Lines • Show All 126 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.fmuladd.f16.ll

; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tahiti -denormal-fp-math=preserve-sign -denormal-fp-math-f32=preserve-sign -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=SI -check-prefix=SI-FLUSH %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tahiti -denormal-fp-math=preserve-sign -denormal-fp-math-f32=preserve-sign -verify-machineinstrs < %s | FileCheck -enable-var-scope --check-prefixes=GCN,SI %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=fiji -denormal-fp-math=preserve-sign -denormal-fp-math-f32=preserve-sign -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=VI -check-prefix=VI-FLUSH %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=fiji -denormal-fp-math=preserve-sign -denormal-fp-math-f32=preserve-sign -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope --check-prefixes=GCN,VI-FLUSH %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tahiti -denormal-fp-math=ieee -denormal-fp-math-f32=preserve-sign -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=SI -check-prefix=SI-DENORM %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tahiti -denormal-fp-math=ieee -denormal-fp-math-f32=preserve-sign -verify-machineinstrs < %s | FileCheck -enable-var-scope --check-prefixes=GCN,SI %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=fiji -denormal-fp-math=ieee -denormal-fp-math-f32=preserve-sign -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=VI -check-prefix=VI-DENORM %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=fiji -denormal-fp-math=ieee -denormal-fp-math-f32=preserve-sign -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope --check-prefixes=GCN,VI-DENORM %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=gfx1010 -denormal-fp-math=preserve-sign -denormal-fp-math-f32=preserve-sign -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=GFX10 -check-prefix=GFX10-FLUSH %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=gfx1010 -denormal-fp-math=preserve-sign -denormal-fp-math-f32=preserve-sign -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope --check-prefixes=GCN,GFX10,GFX10-FLUSH %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=gfx1010 -denormal-fp-math=ieee -denormal-fp-math-f32=preserve-sign -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=GFX10 -check-prefix=GFX10-DENORM %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=gfx1010 -denormal-fp-math=ieee -denormal-fp-math-f32=preserve-sign -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope --check-prefixes=GCN,GFX10,GFX10-DENORM %s
declare half @llvm.fmuladd.f16(half %a, half %b, half %c) declare half @llvm.fmuladd.f16(half %a, half %b, half %c)
declare <2 x half> @llvm.fmuladd.v2f16(<2 x half> %a, <2 x half> %b, <2 x half> %c) declare <2 x half> @llvm.fmuladd.v2f16(<2 x half> %a, <2 x half> %b, <2 x half> %c)
; GCN-LABEL: {{^}}fmuladd_f16 ; GCN-LABEL: {{^}}fmuladd_f16
; GCN: buffer_load_ushort v[[A_F16:[0-9]+]] ; GCN: buffer_load_ushort v[[A_F16:[0-9]+]]
; GCN: buffer_load_ushort v[[B_F16:[0-9]+]] ; GCN: buffer_load_ushort v[[B_F16:[0-9]+]]
; GCN: buffer_load_ushort v[[C_F16:[0-9]+]] ; GCN: buffer_load_ushort v[[C_F16:[0-9]+]]
▲ Show 20 Lines • Show All 173 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.log.f16.ll

; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=SIVI -check-prefix=FUNC %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck --check-prefixes=SI,FUNC %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=fiji -verify-machineinstrs < %s | FileCheck -check-prefix=VI -check-prefix=SIVI -check-prefix=VIGFX9 -check-prefix=FUNC %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=fiji -verify-machineinstrs < %s | FileCheck --check-prefixes=VI,VIGFX9,FUNC %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefix=GFX9 -check-prefix=VIGFX9 -check-prefix=FUNC %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck --check-prefixes=GFX9,VIGFX9,FUNC %s
declare half @llvm.log.f16(half %a) declare half @llvm.log.f16(half %a)
declare <2 x half> @llvm.log.v2f16(<2 x half> %a) declare <2 x half> @llvm.log.v2f16(<2 x half> %a)
; FUNC-LABEL: {{^}}log_f16 ; FUNC-LABEL: {{^}}log_f16
; SI: buffer_load_ushort v[[A_F16_0:[0-9]+]] ; SI: buffer_load_ushort v[[A_F16_0:[0-9]+]]
; VI: flat_load_ushort v[[A_F16_0:[0-9]+]] ; VI: flat_load_ushort v[[A_F16_0:[0-9]+]]
; GFX9: global_load_ushort v[[A_F16_0:[0-9]+]] ; GFX9: global_load_ushort v[[A_F16_0:[0-9]+]]
▲ Show 20 Lines • Show All 60 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.log.ll

; RUN: llc -march=amdgcn < %s | FileCheck -allow-deprecated-dag-overlap -check-prefix=GCN -check-prefix=SI -check-prefix=FUNC %s ; RUN: llc -march=amdgcn < %s | FileCheck -allow-deprecated-dag-overlap --check-prefixes=GCN,FUNC %s
; RUN: llc -march=amdgcn -mcpu=tonga < %s | FileCheck -allow-deprecated-dag-overlap -check-prefix=GCN -check-prefix=GFX8 --check-prefix=FUNC %s ; RUN: llc -march=amdgcn -mcpu=tonga < %s | FileCheck -allow-deprecated-dag-overlap --check-prefixes=GCN,FUNC %s
; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -allow-deprecated-dag-overlap -check-prefix=EG -check-prefix=FUNC %s ; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -allow-deprecated-dag-overlap --check-prefixes=EG,FUNC %s
; RUN: llc -march=r600 -mcpu=cayman < %s | FileCheck -allow-deprecated-dag-overlap -check-prefix=CM -check-prefix=FUNC %s ; RUN: llc -march=r600 -mcpu=cayman < %s | FileCheck -allow-deprecated-dag-overlap --check-prefixes=CM,FUNC %s
; FUNC-LABEL: {{^}}test: ; FUNC-LABEL: {{^}}test:
; EG: LOG_IEEE ; EG: LOG_IEEE
; CM-DAG: LOG_IEEE T{{[0-9]+\.[XYZW]}} (MASKED) ; CM-DAG: LOG_IEEE T{{[0-9]+\.[XYZW]}} (MASKED)
; CM-DAG: LOG_IEEE T{{[0-9]+\.[XYZW]}} (MASKED) ; CM-DAG: LOG_IEEE T{{[0-9]+\.[XYZW]}} (MASKED)
; CM-DAG: LOG_IEEE T{{[0-9]+\.[XYZW]}} (MASKED) ; CM-DAG: LOG_IEEE T{{[0-9]+\.[XYZW]}} (MASKED)
; CM-DAG: LOG_IEEE T{{[0-9]+\.[XYZW]}} ; CM-DAG: LOG_IEEE T{{[0-9]+\.[XYZW]}}
; GCN: v_log_f32_e32 v{{[0-9]+}}, v{{[0-9]+}} ; GCN: v_log_f32_e32 v{{[0-9]+}}, v{{[0-9]+}}
▲ Show 20 Lines • Show All 75 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.log10.f16.ll

; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=SIVI -check-prefix=FUNC %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefix=SI %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=fiji -verify-machineinstrs < %s | FileCheck -check-prefix=VI -check-prefix=SIVI -check-prefix=VIGFX9 -check-prefix=FUNC %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=fiji -verify-machineinstrs < %s | FileCheck --check-prefixes=VI,VIGFX9 %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefix=GFX9 -check-prefix=VIGFX9 -check-prefix=FUNC %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck --check-prefixes=GFX9,VIGFX9 %s
declare half @llvm.log10.f16(half %a) declare half @llvm.log10.f16(half %a)
declare <2 x half> @llvm.log10.v2f16(<2 x half> %a) declare <2 x half> @llvm.log10.v2f16(<2 x half> %a)
; GCN-LABEL: {{^}}log10_f16 ; GCN-LABEL: {{^}}log10_f16
; SI: buffer_load_ushort v[[A_F16_0:[0-9]+]] ; SI: buffer_load_ushort v[[A_F16_0:[0-9]+]]
; VI: flat_load_ushort v[[A_F16_0:[0-9]+]] ; VI: flat_load_ushort v[[A_F16_0:[0-9]+]]
; GFX9: global_load_ushort v[[A_F16_0:[0-9]+]] ; GFX9: global_load_ushort v[[A_F16_0:[0-9]+]]
▲ Show 20 Lines • Show All 60 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.log10.ll

; RUN: llc -march=amdgcn < %s | FileCheck -allow-deprecated-dag-overlap -check-prefix=GCN -check-prefix=SI -check-prefix=FUNC %s ; RUN: llc -march=amdgcn < %s | FileCheck -allow-deprecated-dag-overlap --check-prefixes=GCN,FUNC %s
; RUN: llc -march=amdgcn -mcpu=tonga < %s | FileCheck -allow-deprecated-dag-overlap -check-prefix=GCN -check-prefix=GFX8 -check-prefix=FUNC %s ; RUN: llc -march=amdgcn -mcpu=tonga < %s | FileCheck -allow-deprecated-dag-overlap --check-prefixes=GCN,FUNC %s
; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -allow-deprecated-dag-overlap -check-prefix=EG -check-prefix=FUNC %s ; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -allow-deprecated-dag-overlap --check-prefixes=EG,FUNC %s
; RUN: llc -march=r600 -mcpu=cayman < %s | FileCheck -allow-deprecated-dag-overlap -check-prefix=CM -check-prefix=FUNC %s ; RUN: llc -march=r600 -mcpu=cayman < %s | FileCheck -allow-deprecated-dag-overlap --check-prefixes=CM,FUNC %s
; FUNC-LABEL: {{^}}test: ; FUNC-LABEL: {{^}}test:
; EG: LOG_IEEE ; EG: LOG_IEEE
; CM-DAG: LOG_IEEE T{{[0-9]+\.[XYZW]}} (MASKED) ; CM-DAG: LOG_IEEE T{{[0-9]+\.[XYZW]}} (MASKED)
; CM-DAG: LOG_IEEE T{{[0-9]+\.[XYZW]}} (MASKED) ; CM-DAG: LOG_IEEE T{{[0-9]+\.[XYZW]}} (MASKED)
; CM-DAG: LOG_IEEE T{{[0-9]+\.[XYZW]}} (MASKED) ; CM-DAG: LOG_IEEE T{{[0-9]+\.[XYZW]}} (MASKED)
; CM-DAG: LOG_IEEE T{{[0-9]+\.[XYZW]}} ; CM-DAG: LOG_IEEE T{{[0-9]+\.[XYZW]}}
; GCN: v_log_f32_e32 v{{[0-9]+}}, v{{[0-9]+}} ; GCN: v_log_f32_e32 v{{[0-9]+}}, v{{[0-9]+}}
▲ Show 20 Lines • Show All 75 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.maxnum.f16.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=amdgcn-- -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=SI %s ; RUN: llc -mtriple=amdgcn-- -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -enable-var-scope --check-prefix=SI %s
; RUN: llc -mtriple=amdgcn-- -mcpu=fiji -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=VI,SIVI %s ; RUN: llc -mtriple=amdgcn-- -mcpu=fiji -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope --check-prefix=VI %s
; RUN: llc -mtriple=amdgcn-- -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GFX9 %s ; RUN: llc -mtriple=amdgcn-- -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope --check-prefix=GFX9 %s
declare half @llvm.maxnum.f16(half %a, half %b) declare half @llvm.maxnum.f16(half %a, half %b)
declare <2 x half> @llvm.maxnum.v2f16(<2 x half> %a, <2 x half> %b) declare <2 x half> @llvm.maxnum.v2f16(<2 x half> %a, <2 x half> %b)
declare <3 x half> @llvm.maxnum.v3f16(<3 x half> %a, <3 x half> %b) declare <3 x half> @llvm.maxnum.v3f16(<3 x half> %a, <3 x half> %b)
declare <4 x half> @llvm.maxnum.v4f16(<4 x half> %a, <4 x half> %b) declare <4 x half> @llvm.maxnum.v4f16(<4 x half> %a, <4 x half> %b)
define amdgpu_kernel void @maxnum_f16( define amdgpu_kernel void @maxnum_f16(
; SI-LABEL: maxnum_f16: ; SI-LABEL: maxnum_f16:
▲ Show 20 Lines • Show All 745 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.mulo.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,SI %s ; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck --check-prefix=SI %s
; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX9 %s ; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck --check-prefix=GFX9 %s
define { i64, i1 } @umulo_i64_v_v(i64 %x, i64 %y) { define { i64, i1 } @umulo_i64_v_v(i64 %x, i64 %y) {
; SI-LABEL: umulo_i64_v_v: ; SI-LABEL: umulo_i64_v_v:
; SI: ; %bb.0: ; %bb ; SI: ; %bb.0: ; %bb
; SI-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) ; SI-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; SI-NEXT: v_mul_hi_u32 v4, v1, v2 ; SI-NEXT: v_mul_hi_u32 v4, v1, v2
; SI-NEXT: v_mul_lo_u32 v5, v1, v2 ; SI-NEXT: v_mul_lo_u32 v5, v1, v2
; SI-NEXT: v_mul_hi_u32 v6, v0, v3 ; SI-NEXT: v_mul_hi_u32 v6, v0, v3
▲ Show 20 Lines • Show All 354 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.r600.read.local.size.ll

; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=GCN -check-prefix=SI-NOHSA -check-prefix=GCN-NOHSA -check-prefix=FUNC %s ; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck --check-prefixes=SI,GCN,SI-NOHSA,FUNC %s
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=VI -check-prefix=VI-NOHSA -check-prefix=GCN -check-prefix=GCN-NOHSA -check-prefix=FUNC %s ; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck --check-prefixes=VI,VI-NOHSA,GCN,FUNC %s
; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s ; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck --check-prefixes=EG,FUNC %s
; FUNC-LABEL: {{^}}local_size_x: ; FUNC-LABEL: {{^}}local_size_x:
; EG: MEM_RAT_CACHELESS STORE_RAW [[VAL:T[0-9]+\.X]] ; EG: MEM_RAT_CACHELESS STORE_RAW [[VAL:T[0-9]+\.X]]
; EG: MOV * [[VAL]], KC0[1].Z ; EG: MOV * [[VAL]], KC0[1].Z
; SI-NOHSA: s_load_dword [[VAL:s[0-9]+]], s[0:1], 0x6 ; SI-NOHSA: s_load_dword [[VAL:s[0-9]+]], s[0:1], 0x6
; VI-NOHSA: s_load_dword [[VAL:s[0-9]+]], s[0:1], 0x18 ; VI-NOHSA: s_load_dword [[VAL:s[0-9]+]], s[0:1], 0x18
▲ Show 20 Lines • Show All 173 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.rint.f16.ll

; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=SI -check-prefix=SIVI %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,SI %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=fiji -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=SIVI -check-prefix=VI -check-prefix=GFX89 %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=fiji -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,VI,GFX89 %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GFX89 -check-prefix=GFX9 %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX89,GFX9 %s
declare half @llvm.rint.f16(half %a) declare half @llvm.rint.f16(half %a)
declare <2 x half> @llvm.rint.v2f16(<2 x half> %a) declare <2 x half> @llvm.rint.v2f16(<2 x half> %a)
; GCN-LABEL: {{^}}rint_f16 ; GCN-LABEL: {{^}}rint_f16
; GCN: buffer_load_ushort v[[A_F16:[0-9]+]] ; GCN: buffer_load_ushort v[[A_F16:[0-9]+]]
; SI: v_cvt_f32_f16_e32 v[[A_F32:[0-9]+]], v[[A_F16]] ; SI: v_cvt_f32_f16_e32 v[[A_F32:[0-9]+]], v[[A_F16]]
; SI: v_rndne_f32_e32 v[[R_F32:[0-9]+]], v[[A_F32]] ; SI: v_rndne_f32_e32 v[[R_F32:[0-9]+]], v[[A_F32]]
▲ Show 20 Lines • Show All 49 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.round.ll

; RUN: llc -march=amdgcn -mcpu=tahiti < %s | FileCheck -check-prefix=GCN -check-prefix=SI -check-prefix=FUNC %s ; RUN: llc -march=amdgcn -mcpu=tahiti < %s | FileCheck --check-prefixes=GCN,FUNC %s
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global < %s | FileCheck -check-prefix=GCN -check-prefix=GFX89 -check-prefix=FUNC %s ; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global < %s | FileCheck --check-prefixes=GCN,GFX89,FUNC %s
; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global < %s | FileCheck -check-prefix=GCN -check-prefix=GFX89 -check-prefix=GFX9 -check-prefix=FUNC %s ; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global < %s | FileCheck --check-prefixes=GCN,GFX89,GFX9,FUNC %s
; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=R600 -check-prefix=FUNC %s ; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck --check-prefixes=R600,FUNC %s
; FUNC-LABEL: {{^}}round_f32: ; FUNC-LABEL: {{^}}round_f32:
; GCN-DAG: s_load_dword [[SX:s[0-9]+]] ; GCN-DAG: s_load_dword [[SX:s[0-9]+]]
; GCN-DAG: s_brev_b32 [[K:s[0-9]+]], -2{{$}} ; GCN-DAG: s_brev_b32 [[K:s[0-9]+]], -2{{$}}
; GCN-DAG: v_trunc_f32_e32 [[TRUNC:v[0-9]+]], [[SX]] ; GCN-DAG: v_trunc_f32_e32 [[TRUNC:v[0-9]+]], [[SX]]
; GCN-DAG: v_sub_f32_e32 [[SUB:v[0-9]+]], [[SX]], [[TRUNC]] ; GCN-DAG: v_sub_f32_e32 [[SUB:v[0-9]+]], [[SX]], [[TRUNC]]
; GCN-DAG: v_mov_b32_e32 [[VX:v[0-9]+]], [[SX]] ; GCN-DAG: v_mov_b32_e32 [[VX:v[0-9]+]], [[SX]]
; GCN: v_bfi_b32 [[COPYSIGN:v[0-9]+]], [[K]], 1.0, [[VX]] ; GCN: v_bfi_b32 [[COPYSIGN:v[0-9]+]], [[K]], 1.0, [[VX]]
▲ Show 20 Lines • Show All 98 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/llvm.sin.f16.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX6 %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -enable-var-scope --check-prefix=GFX6 %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=fiji -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX8 %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=fiji -verify-machineinstrs < %s | FileCheck -enable-var-scope --check-prefix=GFX8 %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9 %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -enable-var-scope --check-prefix=GFX9 %s
define amdgpu_kernel void @sin_f16(half addrspace(1)* %r, half addrspace(1)* %a) { define amdgpu_kernel void @sin_f16(half addrspace(1)* %r, half addrspace(1)* %a) {
; GFX6-LABEL: sin_f16: ; GFX6-LABEL: sin_f16:
; GFX6: ; %bb.0: ; GFX6: ; %bb.0:
; GFX6-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x9 ; GFX6-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x9
; GFX6-NEXT: s_mov_b32 s3, 0xf000 ; GFX6-NEXT: s_mov_b32 s3, 0xf000
; GFX6-NEXT: s_mov_b32 s2, -1 ; GFX6-NEXT: s_mov_b32 s2, -1
; GFX6-NEXT: s_mov_b32 s10, s2 ; GFX6-NEXT: s_mov_b32 s10, s2
▲ Show 20 Lines • Show All 126 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/load-constant-i16.ll

  • This file is larger than 256 KB, so syntax highlighting is disabled by default.
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GCN-NOHSA,GCN-NOHSA-SI,FUNC %s ; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck --check-prefix=GCN-NOHSA-SI %s
; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck -check-prefixes=FUNC,GCN,GCN-HSA %s ; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck --check-prefix=GCN-HSA %s
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefixes=FUNC,GCN,GCN-NOHSA,GCN-NOHSA-VI %s ; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck --check-prefix=GCN-NOHSA-VI %s
; RUN: llc -march=r600 -mcpu=redwood -verify-machineinstrs < %s | FileCheck -check-prefixes=FUNC,EG %s ; RUN: llc -march=r600 -mcpu=redwood -verify-machineinstrs < %s | FileCheck --check-prefix=EG %s
define amdgpu_kernel void @constant_load_i16(i16 addrspace(1)* %out, i16 addrspace(4)* %in) { define amdgpu_kernel void @constant_load_i16(i16 addrspace(1)* %out, i16 addrspace(4)* %in) {
; GCN-NOHSA-SI-LABEL: constant_load_i16: ; GCN-NOHSA-SI-LABEL: constant_load_i16:
; GCN-NOHSA-SI: ; %bb.0: ; %entry ; GCN-NOHSA-SI: ; %bb.0: ; %entry
; GCN-NOHSA-SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9 ; GCN-NOHSA-SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
; GCN-NOHSA-SI-NEXT: s_mov_b32 s7, 0xf000 ; GCN-NOHSA-SI-NEXT: s_mov_b32 s7, 0xf000
; GCN-NOHSA-SI-NEXT: s_mov_b32 s6, -1 ; GCN-NOHSA-SI-NEXT: s_mov_b32 s6, -1
; GCN-NOHSA-SI-NEXT: s_mov_b32 s10, s6 ; GCN-NOHSA-SI-NEXT: s_mov_b32 s10, s6
▲ Show 20 Lines • Show All 7,310 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/load-constant-i64.ll

; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GCN-NOHSA -check-prefix=SI -check-prefix=FUNC %s ; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,FUNC %s
; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GCN-HSA -check-prefix=SI -check-prefix=FUNC %s ; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,FUNC %s
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GCN-NOHSA -check-prefix=VI -check-prefix=FUNC %s ; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,FUNC %s
; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s ; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck --check-prefixes=EG,FUNC %s
; FUNC-LABEL: {{^}}constant_load_i64: ; FUNC-LABEL: {{^}}constant_load_i64:
; GCN: s_load_dwordx2 {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, 0x0{{$}} ; GCN: s_load_dwordx2 {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, 0x0{{$}}
; EG: VTX_READ_64 ; EG: VTX_READ_64
define amdgpu_kernel void @constant_load_i64(i64 addrspace(1)* %out, i64 addrspace(4)* %in) #0 { define amdgpu_kernel void @constant_load_i64(i64 addrspace(1)* %out, i64 addrspace(4)* %in) #0 {
%ld = load i64, i64 addrspace(4)* %in %ld = load i64, i64 addrspace(4)* %in
store i64 %ld, i64 addrspace(1)* %out store i64 %ld, i64 addrspace(1)* %out
▲ Show 20 Lines • Show All 72 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/load-global-f32.ll

; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GCN-NOHSA -check-prefix=FUNC -check-prefix=SI-NOHSA %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN-NOHSA,FUNC,SI-NOHSA %s
; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn-amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GCN-HSA -check-prefix=FUNC -check-prefix=GCNX3-HSA %s ; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn-amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN-HSA,FUNC,GCNX3-HSA %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GCN-NOHSA -check-prefix=FUNC -check-prefix=GCNX3-NOHSA %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN-NOHSA,FUNC,GCNX3-NOHSA %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=R600 -check-prefix=FUNC %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=r600 -mcpu=redwood < %s | FileCheck --check-prefixes=R600,FUNC %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=r600 -mcpu=cayman < %s | FileCheck -check-prefix=R600 -check-prefix=FUNC %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=r600 -mcpu=cayman < %s | FileCheck --check-prefixes=R600,FUNC %s
; FUNC-LABEL: {{^}}global_load_f32: ; FUNC-LABEL: {{^}}global_load_f32:
; GCN-NOHSA: buffer_load_dword v{{[0-9]+}} ; GCN-NOHSA: buffer_load_dword v{{[0-9]+}}
; GCN-HSA: flat_load_dword ; GCN-HSA: flat_load_dword
; R600: VTX_READ_32 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 0 ; R600: VTX_READ_32 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 0
define amdgpu_kernel void @global_load_f32(float addrspace(1)* %out, float addrspace(1)* %in) #0 { define amdgpu_kernel void @global_load_f32(float addrspace(1)* %out, float addrspace(1)* %in) #0 {
entry: entry:
▲ Show 20 Lines • Show All 80 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/load-global-f64.ll

; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GCN-NOHSA -check-prefix=FUNC %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN-NOHSA,FUNC %s
; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn-amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GCN-HSA -check-prefix=FUNC %s ; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn-amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN-HSA,FUNC %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GCN-NOHSA -check-prefix=FUNC %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN-NOHSA,FUNC %s
; FUNC-LABEL: {{^}}global_load_f64: ; FUNC-LABEL: {{^}}global_load_f64:
; GCN-NOHSA: buffer_load_dwordx2 [[VAL:v\[[0-9]+:[0-9]+\]]] ; GCN-NOHSA: buffer_load_dwordx2 [[VAL:v\[[0-9]+:[0-9]+\]]]
; GCN-NOHSA: buffer_store_dwordx2 [[VAL]] ; GCN-NOHSA: buffer_store_dwordx2 [[VAL]]
; GCN-HSA: flat_load_dwordx2 [[VAL:v\[[0-9]+:[0-9]+\]]] ; GCN-HSA: flat_load_dwordx2 [[VAL:v\[[0-9]+:[0-9]+\]]]
; GCN-HSA: flat_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, [[VAL]] ; GCN-HSA: flat_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, [[VAL]]
define amdgpu_kernel void @global_load_f64(double addrspace(1)* %out, double addrspace(1)* %in) #0 { define amdgpu_kernel void @global_load_f64(double addrspace(1)* %out, double addrspace(1)* %in) #0 {
▲ Show 20 Lines • Show All 83 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/load-global-i16.ll

  • This file is larger than 256 KB, so syntax highlighting is disabled by default.
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -verify-machineinstrs < %s | FileCheck -allow-deprecated-dag-overlap -check-prefixes=FUNC,GCN,GCN-NOHSA,GCN-NOHSA-SI %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -verify-machineinstrs < %s | FileCheck -allow-deprecated-dag-overlap --check-prefix=GCN-NOHSA-SI %s
; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn--amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck -allow-deprecated-dag-overlap -check-prefixes=FUNC,GCN,GCN-HSA %s ; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn--amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck -allow-deprecated-dag-overlap --check-prefix=GCN-HSA %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -allow-deprecated-dag-overlap -check-prefixes=FUNC,GCN,GCN-NOHSA,GCN-NOHSA-VI %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -allow-deprecated-dag-overlap --check-prefix=GCN-NOHSA-VI %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=r600 -mcpu=redwood -verify-machineinstrs < %s | FileCheck -allow-deprecated-dag-overlap -check-prefixes=FUNC,EGCM,EG %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=r600 -mcpu=redwood -verify-machineinstrs < %s | FileCheck -allow-deprecated-dag-overlap --check-prefix=EG %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=r600 -mcpu=cayman -verify-machineinstrs < %s | FileCheck -allow-deprecated-dag-overlap -check-prefixes=FUNC,EGCM,CM %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=r600 -mcpu=cayman -verify-machineinstrs < %s | FileCheck -allow-deprecated-dag-overlap --check-prefix=CM %s
; FIXME: r600 is broken because the bigger testcases spill and it's not implemented ; FIXME: r600 is broken because the bigger testcases spill and it's not implemented
define amdgpu_kernel void @global_load_i16(i16 addrspace(1)* %out, i16 addrspace(1)* %in) { define amdgpu_kernel void @global_load_i16(i16 addrspace(1)* %out, i16 addrspace(1)* %in) {
; GCN-NOHSA-SI-LABEL: global_load_i16: ; GCN-NOHSA-SI-LABEL: global_load_i16:
; GCN-NOHSA-SI: ; %bb.0: ; %entry ; GCN-NOHSA-SI: ; %bb.0: ; %entry
; GCN-NOHSA-SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9 ; GCN-NOHSA-SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
; GCN-NOHSA-SI-NEXT: s_mov_b32 s7, 0xf000 ; GCN-NOHSA-SI-NEXT: s_mov_b32 s7, 0xf000
▲ Show 20 Lines • Show All 8,741 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/load-global-i64.ll

; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GCN-NOHSA -check-prefix=FUNC %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN-NOHSA,FUNC %s
; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn--amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GCN-HSA -check-prefix=FUNC %s ; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn--amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN-HSA,FUNC %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GCN-NOHSA -check-prefix=FUNC %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN-NOHSA,FUNC %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=r600 -mcpu=redwood < %s | FileCheck --check-prefixes=EG,FUNC %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=r600 -mcpu=cayman < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=r600 -mcpu=cayman < %s | FileCheck --check-prefixes=EG,FUNC %s
; FUNC-LABEL: {{^}}global_load_i64: ; FUNC-LABEL: {{^}}global_load_i64:
; GCN-NOHSA: buffer_load_dwordx2 [[VAL:v\[[0-9]+:[0-9]+\]]] ; GCN-NOHSA: buffer_load_dwordx2 [[VAL:v\[[0-9]+:[0-9]+\]]]
; GCN-NOHSA: buffer_store_dwordx2 [[VAL]] ; GCN-NOHSA: buffer_store_dwordx2 [[VAL]]
; GCN-HSA: flat_load_dwordx2 [[VAL:v\[[0-9]+:[0-9]+\]]] ; GCN-HSA: flat_load_dwordx2 [[VAL:v\[[0-9]+:[0-9]+\]]]
; GCN-HSA: flat_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, [[VAL]] ; GCN-HSA: flat_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, [[VAL]]
▲ Show 20 Lines • Show All 108 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/load-lo16.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -march=amdgcn -mcpu=gfx900 -amdgpu-sroa=0 -mattr=-promote-alloca -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX900,GFX900-MUBUF %s ; RUN: llc -march=amdgcn -mcpu=gfx900 -amdgpu-sroa=0 -mattr=-promote-alloca -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX900,GFX900-MUBUF %s
; RUN: llc -march=amdgcn -mcpu=gfx906 -amdgpu-sroa=0 -mattr=-promote-alloca,+sram-ecc -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX906,NO-D16-HI %s ; RUN: llc -march=amdgcn -mcpu=gfx906 -amdgpu-sroa=0 -mattr=-promote-alloca,+sram-ecc -verify-machineinstrs < %s | FileCheck --check-prefix=GFX906 %s
; RUN: llc -march=amdgcn -mcpu=fiji -amdgpu-sroa=0 -mattr=-promote-alloca -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX803,NO-D16-HI %s ; RUN: llc -march=amdgcn -mcpu=fiji -amdgpu-sroa=0 -mattr=-promote-alloca -verify-machineinstrs < %s | FileCheck --check-prefix=GFX803 %s
; RUN: llc -march=amdgcn -mcpu=gfx900 -amdgpu-sroa=0 -mattr=-promote-alloca -verify-machineinstrs --amdgpu-enable-flat-scratch < %s | FileCheck -check-prefixes=GCN,GFX900,GFX900-FLATSCR %s ; RUN: llc -march=amdgcn -mcpu=gfx900 -amdgpu-sroa=0 -mattr=-promote-alloca -verify-machineinstrs --amdgpu-enable-flat-scratch < %s | FileCheck -check-prefixes=GFX900,GFX900-FLATSCR %s
define <2 x i16> @load_local_lo_v2i16_undeflo(i16 addrspace(3)* %in) #0 { define <2 x i16> @load_local_lo_v2i16_undeflo(i16 addrspace(3)* %in) #0 {
; GFX900-LABEL: load_local_lo_v2i16_undeflo: ; GFX900-LABEL: load_local_lo_v2i16_undeflo:
; GFX900: ; %bb.0: ; %entry ; GFX900: ; %bb.0: ; %entry
; GFX900-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) ; GFX900-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX900-NEXT: ds_read_u16_d16 v0, v0 ; GFX900-NEXT: ds_read_u16_d16 v0, v0
; GFX900-NEXT: s_waitcnt lgkmcnt(0) ; GFX900-NEXT: s_waitcnt lgkmcnt(0)
; GFX900-NEXT: s_setpc_b64 s[30:31] ; GFX900-NEXT: s_setpc_b64 s[30:31]
▲ Show 20 Lines • Show All 2,213 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/load-local-f64.ll

; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,SICIVI,FUNC %s ; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,FUNC %s
; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=kaveri -mattr=-enable-ds128 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,SICIVI,FUNC %s ; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=kaveri -mattr=-enable-ds128 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,FUNC %s
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-enable-ds128 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,SICIVI,FUNC %s ; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-enable-ds128 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,FUNC %s
; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-enable-ds128 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX9,FUNC %s ; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-enable-ds128 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX9,FUNC %s
; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefixes=EG,FUNC %s ; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefixes=EG,FUNC %s
; Testing for ds_read_b128 ; Testing for ds_read_b128
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs -mattr=+enable-ds128 < %s | FileCheck -check-prefixes=CIVI,FUNC %s ; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs -mattr=+enable-ds128 < %s | FileCheck -check-prefixes=CIVI,FUNC %s
; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs -mattr=+enable-ds128 < %s | FileCheck -check-prefixes=CIVI,FUNC %s ; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs -mattr=+enable-ds128 < %s | FileCheck -check-prefixes=CIVI,FUNC %s
; FUNC-LABEL: {{^}}local_load_f64: ; FUNC-LABEL: {{^}}local_load_f64:
▲ Show 20 Lines • Show All 183 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/load-local-i32.ll

; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,SICIVI,FUNC %s ; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,SICIVI,FUNC %s
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global,-enable-ds128 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,SICIVI,FUNC %s ; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global,-enable-ds128 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,SICIVI,FUNC %s
; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global,-enable-ds128 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,VI,FUNC %s ; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global,-enable-ds128 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,FUNC %s
; RUN: llc -march=amdgcn -mcpu=gfx908 -mattr=-flat-for-global,-enable-ds128 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,VI,FUNC %s ; RUN: llc -march=amdgcn -mcpu=gfx908 -mattr=-flat-for-global,-enable-ds128 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,FUNC %s
; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s ; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck --check-prefixes=EG,FUNC %s
; Testing for ds_read/write_128 ; Testing for ds_read/write_128
; RUN: llc -march=amdgcn -mcpu=tahiti -mattr=+enable-ds128 < %s | FileCheck -check-prefixes=SI,FUNC %s ; RUN: llc -march=amdgcn -mcpu=tahiti -mattr=+enable-ds128 < %s | FileCheck -check-prefixes=SI,FUNC %s
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=+enable-ds128 < %s | FileCheck -check-prefixes=CIVI,FUNC %s ; RUN: llc -march=amdgcn -mcpu=tonga -mattr=+enable-ds128 < %s | FileCheck -check-prefixes=CIVI,FUNC %s
; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=+enable-ds128 < %s | FileCheck -check-prefixes=CIVI,FUNC %s ; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=+enable-ds128 < %s | FileCheck -check-prefixes=CIVI,FUNC %s
; FUNC-LABEL: {{^}}local_load_i32: ; FUNC-LABEL: {{^}}local_load_i32:
; GCN-NOT: s_wqm_b64 ; GCN-NOT: s_wqm_b64
▲ Show 20 Lines • Show All 268 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/load-local.128.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX9 %s ; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck --check-prefix=GFX9 %s
; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=hawaii -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX7 %s ; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=hawaii -verify-machineinstrs < %s | FileCheck --check-prefix=GFX7 %s
; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX6 %s ; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=tahiti -verify-machineinstrs < %s | FileCheck --check-prefix=GFX6 %s
define <4 x i32> @load_lds_v4i32(<4 x i32> addrspace(3)* %ptr) { define <4 x i32> @load_lds_v4i32(<4 x i32> addrspace(3)* %ptr) {
; GFX9-LABEL: load_lds_v4i32: ; GFX9-LABEL: load_lds_v4i32:
; GFX9: ; %bb.0: ; GFX9: ; %bb.0:
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) ; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT: ds_read_b128 v[0:3], v0 ; GFX9-NEXT: ds_read_b128 v[0:3], v0
; GFX9-NEXT: s_waitcnt lgkmcnt(0) ; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: s_setpc_b64 s[30:31] ; GFX9-NEXT: s_setpc_b64 s[30:31]
▲ Show 20 Lines • Show All 368 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/load-local.96.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX9 %s ; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck --check-prefix=GFX9 %s
; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=hawaii -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX7 %s ; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=hawaii -verify-machineinstrs < %s | FileCheck --check-prefix=GFX7 %s
; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX6 %s ; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=tahiti -verify-machineinstrs < %s | FileCheck --check-prefix=GFX6 %s
define <3 x i32> @load_lds_v3i32(<3 x i32> addrspace(3)* %ptr) { define <3 x i32> @load_lds_v3i32(<3 x i32> addrspace(3)* %ptr) {
; GFX9-LABEL: load_lds_v3i32: ; GFX9-LABEL: load_lds_v3i32:
; GFX9: ; %bb.0: ; GFX9: ; %bb.0:
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) ; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT: ds_read_b96 v[0:2], v0 ; GFX9-NEXT: ds_read_b96 v[0:2], v0
; GFX9-NEXT: s_waitcnt lgkmcnt(0) ; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: s_setpc_b64 s[30:31] ; GFX9-NEXT: s_setpc_b64 s[30:31]
▲ Show 20 Lines • Show All 323 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/load-weird-sizes.ll

; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=SI-NOHSA -check-prefix=SI -check-prefix=FUNC %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -verify-machineinstrs < %s | FileCheck --check-prefixes=SI-NOHSA,SI,FUNC %s
; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn-amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck -check-prefix=FUNC -check-prefix=CI-HSA -check-prefix=SI %s ; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn-amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck --check-prefixes=FUNC,CI-HSA,SI %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=SI-NOHSA -check-prefix=SI -check-prefix=FUNC %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck --check-prefixes=SI-NOHSA,SI,FUNC %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=R600 -check-prefix=EG -check-prefix=FUNC %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=FUNC %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=r600 -mcpu=cayman < %s | FileCheck -check-prefix=R600 -check-prefix=CM -check-prefix=FUNC %s ; RUN: llc -amdgpu-scalarize-global-loads=false -march=r600 -mcpu=cayman < %s | FileCheck -check-prefix=FUNC %s
; FUNC-LABEL: {{^}}load_i24: ; FUNC-LABEL: {{^}}load_i24:
; SI-DAG: {{flat|buffer}}_load_ubyte ; SI-DAG: {{flat|buffer}}_load_ubyte
; SI-DAG: {{flat|buffer}}_load_ushort ; SI-DAG: {{flat|buffer}}_load_ushort
; SI: {{flat|buffer}}_store_dword ; SI: {{flat|buffer}}_store_dword
define amdgpu_kernel void @load_i24(i32 addrspace(1)* %out, i24 addrspace(1)* %in) #0 { define amdgpu_kernel void @load_i24(i32 addrspace(1)* %out, i24 addrspace(1)* %in) #0 {
%1 = load i24, i24 addrspace(1)* %in %1 = load i24, i24 addrspace(1)* %in
%2 = zext i24 %1 to i32 %2 = zext i24 %1 to i32
Show All 18 Lines

llvm/test/CodeGen/AMDGPU/local-atomics64.ll

; RUN: llc -march=amdgcn -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -strict-whitespace -check-prefixes=GCN,SI,SICIVI %s ; RUN: llc -march=amdgcn -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -strict-whitespace -check-prefixes=GCN,SI,SICIVI %s
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -strict-whitespace -check-prefixes=GCN,VI,SICIVI,GFX89 %s ; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -strict-whitespace -check-prefixes=GCN,SICIVI,GFX89 %s
; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -strict-whitespace -check-prefixes=GCN,GFX9,GFX89 %s ; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-atomic-optimizations=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -strict-whitespace -check-prefixes=GCN,GFX9,GFX89 %s
; GCN-LABEL: {{^}}lds_atomic_xchg_ret_i64: ; GCN-LABEL: {{^}}lds_atomic_xchg_ret_i64:
; SICIVI: s_mov_b32 m0 ; SICIVI: s_mov_b32 m0
; GFX9-NOT: m0 ; GFX9-NOT: m0
; GCN: ds_wrxchg_rtn_b64 ; GCN: ds_wrxchg_rtn_b64
; GCN: s_endpgm ; GCN: s_endpgm
▲ Show 20 Lines • Show All 618 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/local-memory.ll

; RUN: llc -march=amdgcn -mcpu=verde -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=FUNC %s ; RUN: llc -march=amdgcn -mcpu=verde -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,FUNC %s
; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=FUNC %s ; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,FUNC %s
; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s ; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=FUNC %s
@local_memory.local_mem = internal unnamed_addr addrspace(3) global [128 x i32] undef, align 4 @local_memory.local_mem = internal unnamed_addr addrspace(3) global [128 x i32] undef, align 4
@lds = addrspace(3) global [512 x i32] undef, align 4 @lds = addrspace(3) global [512 x i32] undef, align 4
; On SI we need to make sure that the base offset is a register and ; On SI we need to make sure that the base offset is a register and
; not an immediate. ; not an immediate.
Show All 33 Lines

llvm/test/CodeGen/AMDGPU/local-stack-alloc-block-sp-reference.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx906 < %s | FileCheck -check-prefixes=GCN,GFX9,MUBUF %s ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx906 < %s | FileCheck --check-prefix=MUBUF %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx906 --amdgpu-enable-flat-scratch < %s | FileCheck -check-prefixes=GCN,GFX9,FLATSCR %s ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx906 --amdgpu-enable-flat-scratch < %s | FileCheck --check-prefix=FLATSCR %s
; Make sure we use the correct frame offset is used with the local ; Make sure we use the correct frame offset is used with the local
; frame area. ; frame area.
; ;
; %pin.low is allocated to offset 0. ; %pin.low is allocated to offset 0.
; ;
; %local.area is assigned to the local frame offset by the ; %local.area is assigned to the local frame offset by the
; LocalStackSlotAllocation pass at offset 4096. ; LocalStackSlotAllocation pass at offset 4096.
▲ Show 20 Lines • Show All 178 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/lshr.v2i16.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9 %s ; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -enable-var-scope --check-prefix=GFX9 %s
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,VI,CIVI %s ; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -enable-var-scope --check-prefix=VI %s
; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,CI,CIVI %s ; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs < %s | FileCheck -enable-var-scope --check-prefix=CI %s
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,CIVI,VI %s ; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -enable-var-scope --check-prefix=VI %s
; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,CIVI,CI %s ; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs < %s | FileCheck -enable-var-scope --check-prefix=CI %s
define amdgpu_kernel void @s_lshr_v2i16(<2 x i16> addrspace(1)* %out, <2 x i16> %lhs, <2 x i16> %rhs) #0 { define amdgpu_kernel void @s_lshr_v2i16(<2 x i16> addrspace(1)* %out, <2 x i16> %lhs, <2 x i16> %rhs) #0 {
; GFX9-LABEL: s_lshr_v2i16: ; GFX9-LABEL: s_lshr_v2i16:
; GFX9: ; %bb.0: ; GFX9: ; %bb.0:
; GFX9-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x24 ; GFX9-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x24
; GFX9-NEXT: s_load_dword s4, s[0:1], 0x2c ; GFX9-NEXT: s_load_dword s4, s[0:1], 0x2c
; GFX9-NEXT: s_load_dword s0, s[0:1], 0x30 ; GFX9-NEXT: s_load_dword s0, s[0:1], 0x30
; GFX9-NEXT: v_mov_b32_e32 v0, 0 ; GFX9-NEXT: v_mov_b32_e32 v0, 0
▲ Show 20 Lines • Show All 533 Lines • Show Last 20 Lines