derek/TheRock
1
0 Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
Files
1a182e2dac58879f215c0fad0f5f78c76dcafe56
TheRock/compiler/amd-llvm/llvm/test/CodeGen/AMDGPU/a-v-global-atomic-cmpxchg.ll
T
derek.holloway 7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
Details
CodeQL / Analyze (python) (push) Canceled after 0s
Details
pre-commit / pre-commit (push) Canceled after 0s
Details
Multi-Arch CI / setup (push) Canceled after 0s
Details
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Details
Setup (Multi-Arch) / setup (push) Canceled after 0s
Details
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Details
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
Details
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Details
Multi-Arch CI / CI Summary (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Details
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Details
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
Details
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

746 lines
28 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc -mtriple=amdgcn -mcpu=gfx90a < %s | FileCheck %s
;---------------------------------------------------------------------
; i32 cases
;---------------------------------------------------------------------
define void @global_atomic_cmpxchg_i32_ret_av_av__av(ptr addrspace(1) %ptr) #0 {
; CHECK-LABEL: global_atomic_cmpxchg_i32_ret_av_av__av:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def v3
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def v2
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: buffer_wbl2
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: global_atomic_cmpswap v0, v[0:1], v[2:3], off offset:40 glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: buffer_invl2
; CHECK-NEXT: buffer_wbinvl1_vol
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; use v0
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: s_setpc_b64 s[30:31]
%gep.0 = getelementptr inbounds [512 x i32], ptr addrspace(1) %ptr, i64 0, i64 10
%data0 = call i32 asm "; def $0", "=^VA"()
%data1 = call i32 asm "; def $0", "=^VA"()
%pair = cmpxchg ptr addrspace(1) %gep.0, i32 %data0, i32 %data1 seq_cst monotonic
%result = extractvalue { i32, i1 } %pair, 0
call void asm "; use $0", "^VA"(i32 %result)
ret void
}
define void @global_atomic_cmpxchg_i32_ret_av_av__v(ptr addrspace(1) %ptr) #0 {
; CHECK-LABEL: global_atomic_cmpxchg_i32_ret_av_av__v:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def v3
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def v2
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: buffer_wbl2
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: global_atomic_cmpswap v0, v[0:1], v[2:3], off offset:40 glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: buffer_invl2
; CHECK-NEXT: buffer_wbinvl1_vol
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; use v0
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: s_setpc_b64 s[30:31]
%gep.0 = getelementptr inbounds [512 x i32], ptr addrspace(1) %ptr, i64 0, i64 10
%data0 = call i32 asm "; def $0", "=^VA"()
%data1 = call i32 asm "; def $0", "=^VA"()
%pair = cmpxchg ptr addrspace(1) %gep.0, i32 %data0, i32 %data1 seq_cst monotonic
%result = extractvalue { i32, i1 } %pair, 0
call void asm "; use $0", "v"(i32 %result)
ret void
}
define void @global_atomic_cmpxchg_i32_ret_av_av__a(ptr addrspace(1) %ptr) #0 {
; CHECK-LABEL: global_atomic_cmpxchg_i32_ret_av_av__a:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def v3
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def v2
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: buffer_wbl2
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: global_atomic_cmpswap v0, v[0:1], v[2:3], off offset:40 glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: buffer_invl2
; CHECK-NEXT: buffer_wbinvl1_vol
; CHECK-NEXT: v_accvgpr_write_b32 a0, v0
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; use a0
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: s_setpc_b64 s[30:31]
%gep.0 = getelementptr inbounds [512 x i32], ptr addrspace(1) %ptr, i64 0, i64 10
%data0 = call i32 asm "; def $0", "=^VA"()
%data1 = call i32 asm "; def $0", "=^VA"()
%pair = cmpxchg ptr addrspace(1) %gep.0, i32 %data0, i32 %data1 seq_cst monotonic
%result = extractvalue { i32, i1 } %pair, 0
call void asm "; use $0", "a"(i32 %result)
ret void
}
define void @global_atomic_cmpxchg_i32_ret_a_a__a(ptr addrspace(1) %ptr) #0 {
; CHECK-LABEL: global_atomic_cmpxchg_i32_ret_a_a__a:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def a1
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def a0
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: v_accvgpr_read_b32 v3, a1
; CHECK-NEXT: v_accvgpr_read_b32 v2, a0
; CHECK-NEXT: buffer_wbl2
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: global_atomic_cmpswap v0, v[0:1], v[2:3], off offset:40 glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: buffer_invl2
; CHECK-NEXT: buffer_wbinvl1_vol
; CHECK-NEXT: v_accvgpr_write_b32 a0, v0
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; use a0
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: s_setpc_b64 s[30:31]
%gep.0 = getelementptr inbounds [512 x i32], ptr addrspace(1) %ptr, i64 0, i64 10
%data0 = call i32 asm "; def $0", "=a"()
%data1 = call i32 asm "; def $0", "=a"()
%pair = cmpxchg ptr addrspace(1) %gep.0, i32 %data0, i32 %data1 seq_cst monotonic
%result = extractvalue { i32, i1 } %pair, 0
call void asm "; use $0", "a"(i32 %result)
ret void
}
define void @global_atomic_cmpxchg_i32_ret_a_a__v(ptr addrspace(1) %ptr) #0 {
; CHECK-LABEL: global_atomic_cmpxchg_i32_ret_a_a__v:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def a1
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def a0
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: v_accvgpr_read_b32 v3, a1
; CHECK-NEXT: v_accvgpr_read_b32 v2, a0
; CHECK-NEXT: buffer_wbl2
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: global_atomic_cmpswap v0, v[0:1], v[2:3], off offset:40 glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: buffer_invl2
; CHECK-NEXT: buffer_wbinvl1_vol
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; use v0
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: s_setpc_b64 s[30:31]
%gep.0 = getelementptr inbounds [512 x i32], ptr addrspace(1) %ptr, i64 0, i64 10
%data0 = call i32 asm "; def $0", "=a"()
%data1 = call i32 asm "; def $0", "=a"()
%pair = cmpxchg ptr addrspace(1) %gep.0, i32 %data0, i32 %data1 seq_cst monotonic
%result = extractvalue { i32, i1 } %pair, 0
call void asm "; use $0", "v"(i32 %result)
ret void
}
define void @global_atomic_cmpxchg_i32_ret_v_a__v(ptr addrspace(1) %ptr) #0 {
; CHECK-LABEL: global_atomic_cmpxchg_i32_ret_v_a__v:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def v2
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: v_accvgpr_write_b32 a1, v2
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def a0
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: v_accvgpr_read_b32 v3, a1
; CHECK-NEXT: v_accvgpr_read_b32 v2, a0
; CHECK-NEXT: buffer_wbl2
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: global_atomic_cmpswap v0, v[0:1], v[2:3], off offset:40 glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: buffer_invl2
; CHECK-NEXT: buffer_wbinvl1_vol
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; use v0
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: s_setpc_b64 s[30:31]
%gep.0 = getelementptr inbounds [512 x i32], ptr addrspace(1) %ptr, i64 0, i64 10
%data0 = call i32 asm "; def $0", "=v"()
%data1 = call i32 asm "; def $0", "=a"()
%pair = cmpxchg ptr addrspace(1) %gep.0, i32 %data0, i32 %data1 seq_cst monotonic
%result = extractvalue { i32, i1 } %pair, 0
call void asm "; use $0", "v"(i32 %result)
ret void
}
define void @global_atomic_cmpxchg_i32_ret_a_v__v(ptr addrspace(1) %ptr) #0 {
; CHECK-LABEL: global_atomic_cmpxchg_i32_ret_a_v__v:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def a0
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: v_accvgpr_read_b32 v3, a0
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def v2
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: buffer_wbl2
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: global_atomic_cmpswap v0, v[0:1], v[2:3], off offset:40 glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: buffer_invl2
; CHECK-NEXT: buffer_wbinvl1_vol
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; use v0
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: s_setpc_b64 s[30:31]
%gep.0 = getelementptr inbounds [512 x i32], ptr addrspace(1) %ptr, i64 0, i64 10
%data0 = call i32 asm "; def $0", "=a"()
%data1 = call i32 asm "; def $0", "=v"()
%pair = cmpxchg ptr addrspace(1) %gep.0, i32 %data0, i32 %data1 seq_cst monotonic
%result = extractvalue { i32, i1 } %pair, 0
call void asm "; use $0", "v"(i32 %result)
ret void
}
define void @global_atomic_cmpxchg_i32_ret_v_v__a(ptr addrspace(1) %ptr) #0 {
; CHECK-LABEL: global_atomic_cmpxchg_i32_ret_v_v__a:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def v3
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def v2
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: buffer_wbl2
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: global_atomic_cmpswap v0, v[0:1], v[2:3], off offset:40 glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: buffer_invl2
; CHECK-NEXT: buffer_wbinvl1_vol
; CHECK-NEXT: v_accvgpr_write_b32 a0, v0
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; use a0
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: s_setpc_b64 s[30:31]
%gep.0 = getelementptr inbounds [512 x i32], ptr addrspace(1) %ptr, i64 0, i64 10
%data0 = call i32 asm "; def $0", "=v"()
%data1 = call i32 asm "; def $0", "=v"()
%pair = cmpxchg ptr addrspace(1) %gep.0, i32 %data0, i32 %data1 seq_cst monotonic
%result = extractvalue { i32, i1 } %pair, 0
call void asm "; use $0", "a"(i32 %result)
ret void
}
define void @global_atomic_cmpxchg_i32_ret_av_v__av(ptr addrspace(1) %ptr) #0 {
; CHECK-LABEL: global_atomic_cmpxchg_i32_ret_av_v__av:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def v3
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def v2
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: buffer_wbl2
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: global_atomic_cmpswap v0, v[0:1], v[2:3], off offset:40 glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: buffer_invl2
; CHECK-NEXT: buffer_wbinvl1_vol
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; use v0
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: s_setpc_b64 s[30:31]
%gep.0 = getelementptr inbounds [512 x i32], ptr addrspace(1) %ptr, i64 0, i64 10
%data0 = call i32 asm "; def $0", "=^VA"()
%data1 = call i32 asm "; def $0", "=v"()
%pair = cmpxchg ptr addrspace(1) %gep.0, i32 %data0, i32 %data1 seq_cst monotonic
%result = extractvalue { i32, i1 } %pair, 0
call void asm "; use $0", "^VA"(i32 %result)
ret void
}
define void @global_atomic_cmpxchg_i32_ret_v_av__av(ptr addrspace(1) %ptr) #0 {
; CHECK-LABEL: global_atomic_cmpxchg_i32_ret_v_av__av:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def v3
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def v2
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: buffer_wbl2
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: global_atomic_cmpswap v0, v[0:1], v[2:3], off offset:40 glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: buffer_invl2
; CHECK-NEXT: buffer_wbinvl1_vol
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; use v0
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: s_setpc_b64 s[30:31]
%gep.0 = getelementptr inbounds [512 x i32], ptr addrspace(1) %ptr, i64 0, i64 10
%data0 = call i32 asm "; def $0", "=v"()
%data1 = call i32 asm "; def $0", "=^VA"()
%pair = cmpxchg ptr addrspace(1) %gep.0, i32 %data0, i32 %data1 seq_cst monotonic
%result = extractvalue { i32, i1 } %pair, 0
call void asm "; use $0", "^VA"(i32 %result)
ret void
}
define void @global_atomic_cmpxchg_i32_ret_av_a__av(ptr addrspace(1) %ptr) #0 {
; CHECK-LABEL: global_atomic_cmpxchg_i32_ret_av_a__av:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def a1
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def a0
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: v_accvgpr_read_b32 v3, a1
; CHECK-NEXT: v_accvgpr_read_b32 v2, a0
; CHECK-NEXT: buffer_wbl2
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: global_atomic_cmpswap v0, v[0:1], v[2:3], off offset:40 glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: buffer_invl2
; CHECK-NEXT: buffer_wbinvl1_vol
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; use v0
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: s_setpc_b64 s[30:31]
%gep.0 = getelementptr inbounds [512 x i32], ptr addrspace(1) %ptr, i64 0, i64 10
%data0 = call i32 asm "; def $0", "=^VA"()
%data1 = call i32 asm "; def $0", "=a"()
%pair = cmpxchg ptr addrspace(1) %gep.0, i32 %data0, i32 %data1 seq_cst monotonic
%result = extractvalue { i32, i1 } %pair, 0
call void asm "; use $0", "^VA"(i32 %result)
ret void
}
define void @global_atomic_cmpxchg_i32_ret_a_av__av(ptr addrspace(1) %ptr) #0 {
; CHECK-LABEL: global_atomic_cmpxchg_i32_ret_a_av__av:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def a1
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def a0
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: v_accvgpr_read_b32 v3, a1
; CHECK-NEXT: v_accvgpr_read_b32 v2, a0
; CHECK-NEXT: buffer_wbl2
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: global_atomic_cmpswap v0, v[0:1], v[2:3], off offset:40 glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: buffer_invl2
; CHECK-NEXT: buffer_wbinvl1_vol
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; use v0
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: s_setpc_b64 s[30:31]
%gep.0 = getelementptr inbounds [512 x i32], ptr addrspace(1) %ptr, i64 0, i64 10
%data0 = call i32 asm "; def $0", "=a"()
%data1 = call i32 asm "; def $0", "=^VA"()
%pair = cmpxchg ptr addrspace(1) %gep.0, i32 %data0, i32 %data1 seq_cst monotonic
%result = extractvalue { i32, i1 } %pair, 0
call void asm "; use $0", "^VA"(i32 %result)
ret void
}
;---------------------------------------------------------------------
; i64 cases
;---------------------------------------------------------------------
define void @global_atomic_cmpxchg_i64_ret_av_av__av(ptr addrspace(1) %ptr) #0 {
; CHECK-LABEL: global_atomic_cmpxchg_i64_ret_av_av__av:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def v[4:5]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def v[2:3]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: buffer_wbl2
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: global_atomic_cmpswap_x2 v[0:1], v[0:1], v[2:5], off offset:80 glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: buffer_invl2
; CHECK-NEXT: buffer_wbinvl1_vol
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; use v[0:1]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: s_setpc_b64 s[30:31]
%gep.0 = getelementptr inbounds [512 x i64], ptr addrspace(1) %ptr, i64 0, i64 10
%data0 = call i64 asm "; def $0", "=^VA"()
%data1 = call i64 asm "; def $0", "=^VA"()
%pair = cmpxchg ptr addrspace(1) %gep.0, i64 %data0, i64 %data1 seq_cst monotonic
%result = extractvalue { i64, i1 } %pair, 0
call void asm "; use $0", "^VA"(i64 %result)
ret void
}
define void @global_atomic_cmpxchg_i64_ret_av_av__v(ptr addrspace(1) %ptr) #0 {
; CHECK-LABEL: global_atomic_cmpxchg_i64_ret_av_av__v:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def v[4:5]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def v[2:3]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: buffer_wbl2
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: global_atomic_cmpswap_x2 v[0:1], v[0:1], v[2:5], off offset:80 glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: buffer_invl2
; CHECK-NEXT: buffer_wbinvl1_vol
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; use v[0:1]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: s_setpc_b64 s[30:31]
%gep.0 = getelementptr inbounds [512 x i64], ptr addrspace(1) %ptr, i64 0, i64 10
%data0 = call i64 asm "; def $0", "=^VA"()
%data1 = call i64 asm "; def $0", "=^VA"()
%pair = cmpxchg ptr addrspace(1) %gep.0, i64 %data0, i64 %data1 seq_cst monotonic
%result = extractvalue { i64, i1 } %pair, 0
call void asm "; use $0", "v"(i64 %result)
ret void
}
define void @global_atomic_cmpxchg_i64_ret_av_av__a(ptr addrspace(1) %ptr) #0 {
; CHECK-LABEL: global_atomic_cmpxchg_i64_ret_av_av__a:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def v[4:5]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def v[2:3]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: buffer_wbl2
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: global_atomic_cmpswap_x2 v[0:1], v[0:1], v[2:5], off offset:80 glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: buffer_invl2
; CHECK-NEXT: buffer_wbinvl1_vol
; CHECK-NEXT: v_accvgpr_write_b32 a0, v0
; CHECK-NEXT: v_accvgpr_write_b32 a1, v1
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; use a[0:1]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: s_setpc_b64 s[30:31]
%gep.0 = getelementptr inbounds [512 x i64], ptr addrspace(1) %ptr, i64 0, i64 10
%data0 = call i64 asm "; def $0", "=^VA"()
%data1 = call i64 asm "; def $0", "=^VA"()
%pair = cmpxchg ptr addrspace(1) %gep.0, i64 %data0, i64 %data1 seq_cst monotonic
%result = extractvalue { i64, i1 } %pair, 0
call void asm "; use $0", "a"(i64 %result)
ret void
}
define void @global_atomic_cmpxchg_i64_ret_a_a__a(ptr addrspace(1) %ptr) #0 {
; CHECK-LABEL: global_atomic_cmpxchg_i64_ret_a_a__a:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def a[0:1]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def a[2:3]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: v_accvgpr_read_b32 v2, a2
; CHECK-NEXT: v_accvgpr_read_b32 v3, a3
; CHECK-NEXT: v_accvgpr_read_b32 v4, a0
; CHECK-NEXT: v_accvgpr_read_b32 v5, a1
; CHECK-NEXT: buffer_wbl2
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: global_atomic_cmpswap_x2 v[0:1], v[0:1], v[2:5], off offset:80 glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: buffer_invl2
; CHECK-NEXT: buffer_wbinvl1_vol
; CHECK-NEXT: v_accvgpr_write_b32 a0, v0
; CHECK-NEXT: v_accvgpr_write_b32 a1, v1
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; use a[0:1]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: s_setpc_b64 s[30:31]
%gep.0 = getelementptr inbounds [512 x i64], ptr addrspace(1) %ptr, i64 0, i64 10
%data0 = call i64 asm "; def $0", "=a"()
%data1 = call i64 asm "; def $0", "=a"()
%pair = cmpxchg ptr addrspace(1) %gep.0, i64 %data0, i64 %data1 seq_cst monotonic
%result = extractvalue { i64, i1 } %pair, 0
call void asm "; use $0", "a"(i64 %result)
ret void
}
define void @global_atomic_cmpxchg_i64_ret_a_a__v(ptr addrspace(1) %ptr) #0 {
; CHECK-LABEL: global_atomic_cmpxchg_i64_ret_a_a__v:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def a[0:1]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def a[2:3]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: v_accvgpr_read_b32 v2, a2
; CHECK-NEXT: v_accvgpr_read_b32 v3, a3
; CHECK-NEXT: v_accvgpr_read_b32 v4, a0
; CHECK-NEXT: v_accvgpr_read_b32 v5, a1
; CHECK-NEXT: buffer_wbl2
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: global_atomic_cmpswap_x2 v[0:1], v[0:1], v[2:5], off offset:80 glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: buffer_invl2
; CHECK-NEXT: buffer_wbinvl1_vol
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; use v[0:1]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: s_setpc_b64 s[30:31]
%gep.0 = getelementptr inbounds [512 x i64], ptr addrspace(1) %ptr, i64 0, i64 10
%data0 = call i64 asm "; def $0", "=a"()
%data1 = call i64 asm "; def $0", "=a"()
%pair = cmpxchg ptr addrspace(1) %gep.0, i64 %data0, i64 %data1 seq_cst monotonic
%result = extractvalue { i64, i1 } %pair, 0
call void asm "; use $0", "v"(i64 %result)
ret void
}
define void @global_atomic_cmpxchg_i64_ret_v_a__v(ptr addrspace(1) %ptr) #0 {
; CHECK-LABEL: global_atomic_cmpxchg_i64_ret_v_a__v:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def a[0:1]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: v_accvgpr_read_b32 v2, a0
; CHECK-NEXT: v_accvgpr_read_b32 v3, a1
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def v[4:5]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: buffer_wbl2
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: global_atomic_cmpswap_x2 v[0:1], v[0:1], v[2:5], off offset:80 glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: buffer_invl2
; CHECK-NEXT: buffer_wbinvl1_vol
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; use v[0:1]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: s_setpc_b64 s[30:31]
%gep.0 = getelementptr inbounds [512 x i64], ptr addrspace(1) %ptr, i64 0, i64 10
%data0 = call i64 asm "; def $0", "=v"()
%data1 = call i64 asm "; def $0", "=a"()
%pair = cmpxchg ptr addrspace(1) %gep.0, i64 %data0, i64 %data1 seq_cst monotonic
%result = extractvalue { i64, i1 } %pair, 0
call void asm "; use $0", "v"(i64 %result)
ret void
}
define void @global_atomic_cmpxchg_i64_ret_a_v__v(ptr addrspace(1) %ptr) #0 {
; CHECK-LABEL: global_atomic_cmpxchg_i64_ret_a_v__v:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def a[0:1]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: v_accvgpr_read_b32 v4, a0
; CHECK-NEXT: v_accvgpr_read_b32 v5, a1
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def v[2:3]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: buffer_wbl2
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: global_atomic_cmpswap_x2 v[0:1], v[0:1], v[2:5], off offset:80 glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: buffer_invl2
; CHECK-NEXT: buffer_wbinvl1_vol
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; use v[0:1]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: s_setpc_b64 s[30:31]
%gep.0 = getelementptr inbounds [512 x i64], ptr addrspace(1) %ptr, i64 0, i64 10
%data0 = call i64 asm "; def $0", "=a"()
%data1 = call i64 asm "; def $0", "=v"()
%pair = cmpxchg ptr addrspace(1) %gep.0, i64 %data0, i64 %data1 seq_cst monotonic
%result = extractvalue { i64, i1 } %pair, 0
call void asm "; use $0", "v"(i64 %result)
ret void
}
define void @global_atomic_cmpxchg_i64_ret_v_v__a(ptr addrspace(1) %ptr) #0 {
; CHECK-LABEL: global_atomic_cmpxchg_i64_ret_v_v__a:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def v[4:5]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def v[2:3]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: buffer_wbl2
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: global_atomic_cmpswap_x2 v[0:1], v[0:1], v[2:5], off offset:80 glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: buffer_invl2
; CHECK-NEXT: buffer_wbinvl1_vol
; CHECK-NEXT: v_accvgpr_write_b32 a0, v0
; CHECK-NEXT: v_accvgpr_write_b32 a1, v1
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; use a[0:1]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: s_setpc_b64 s[30:31]
%gep.0 = getelementptr inbounds [512 x i64], ptr addrspace(1) %ptr, i64 0, i64 10
%data0 = call i64 asm "; def $0", "=v"()
%data1 = call i64 asm "; def $0", "=v"()
%pair = cmpxchg ptr addrspace(1) %gep.0, i64 %data0, i64 %data1 seq_cst monotonic
%result = extractvalue { i64, i1 } %pair, 0
call void asm "; use $0", "a"(i64 %result)
ret void
}
define void @global_atomic_cmpxchg_i64_ret_av_v__av(ptr addrspace(1) %ptr) #0 {
; CHECK-LABEL: global_atomic_cmpxchg_i64_ret_av_v__av:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def v[4:5]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def v[2:3]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: buffer_wbl2
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: global_atomic_cmpswap_x2 v[0:1], v[0:1], v[2:5], off offset:80 glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: buffer_invl2
; CHECK-NEXT: buffer_wbinvl1_vol
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; use v[0:1]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: s_setpc_b64 s[30:31]
%gep.0 = getelementptr inbounds [512 x i64], ptr addrspace(1) %ptr, i64 0, i64 10
%data0 = call i64 asm "; def $0", "=^VA"()
%data1 = call i64 asm "; def $0", "=v"()
%pair = cmpxchg ptr addrspace(1) %gep.0, i64 %data0, i64 %data1 seq_cst monotonic
%result = extractvalue { i64, i1 } %pair, 0
call void asm "; use $0", "^VA"(i64 %result)
ret void
}
define void @global_atomic_cmpxchg_i64_ret_v_av__av(ptr addrspace(1) %ptr) #0 {
; CHECK-LABEL: global_atomic_cmpxchg_i64_ret_v_av__av:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def v[4:5]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def v[2:3]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: buffer_wbl2
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: global_atomic_cmpswap_x2 v[0:1], v[0:1], v[2:5], off offset:80 glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: buffer_invl2
; CHECK-NEXT: buffer_wbinvl1_vol
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; use v[0:1]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: s_setpc_b64 s[30:31]
%gep.0 = getelementptr inbounds [512 x i64], ptr addrspace(1) %ptr, i64 0, i64 10
%data0 = call i64 asm "; def $0", "=v"()
%data1 = call i64 asm "; def $0", "=^VA"()
%pair = cmpxchg ptr addrspace(1) %gep.0, i64 %data0, i64 %data1 seq_cst monotonic
%result = extractvalue { i64, i1 } %pair, 0
call void asm "; use $0", "^VA"(i64 %result)
ret void
}
define void @global_atomic_cmpxchg_i64_ret_av_a__av(ptr addrspace(1) %ptr) #0 {
; CHECK-LABEL: global_atomic_cmpxchg_i64_ret_av_a__av:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def a[0:1]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: v_accvgpr_read_b32 v2, a0
; CHECK-NEXT: v_accvgpr_read_b32 v3, a1
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def v[4:5]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: buffer_wbl2
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: global_atomic_cmpswap_x2 v[0:1], v[0:1], v[2:5], off offset:80 glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: buffer_invl2
; CHECK-NEXT: buffer_wbinvl1_vol
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; use v[0:1]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: s_setpc_b64 s[30:31]
%gep.0 = getelementptr inbounds [512 x i64], ptr addrspace(1) %ptr, i64 0, i64 10
%data0 = call i64 asm "; def $0", "=^VA"()
%data1 = call i64 asm "; def $0", "=a"()
%pair = cmpxchg ptr addrspace(1) %gep.0, i64 %data0, i64 %data1 seq_cst monotonic
%result = extractvalue { i64, i1 } %pair, 0
call void asm "; use $0", "^VA"(i64 %result)
ret void
}
define void @global_atomic_cmpxchg_i64_ret_a_av__av(ptr addrspace(1) %ptr) #0 {
; CHECK-LABEL: global_atomic_cmpxchg_i64_ret_a_av__av:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def a[0:1]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: v_accvgpr_read_b32 v4, a0
; CHECK-NEXT: v_accvgpr_read_b32 v5, a1
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; def v[2:3]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: buffer_wbl2
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: global_atomic_cmpswap_x2 v[0:1], v[0:1], v[2:5], off offset:80 glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: buffer_invl2
; CHECK-NEXT: buffer_wbinvl1_vol
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; use v[0:1]
; CHECK-NEXT: ;;#ASMEND
; CHECK-NEXT: s_setpc_b64 s[30:31]
%gep.0 = getelementptr inbounds [512 x i64], ptr addrspace(1) %ptr, i64 0, i64 10
%data0 = call i64 asm "; def $0", "=a"()
%data1 = call i64 asm "; def $0", "=^VA"()
%pair = cmpxchg ptr addrspace(1) %gep.0, i64 %data0, i64 %data1 seq_cst monotonic
%result = extractvalue { i64, i1 } %pair, 0
call void asm "; use $0", "^VA"(i64 %result)
ret void
}
attributes #0 = { nounwind "amdgpu-waves-per-eu"="10,10" }
Reference in new issue View Git Blame Copy Permalink