forked from OSchip/llvm-project
5203 lines
217 KiB
LLVM
5203 lines
217 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GFX7LESS %s
|
|
; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=tonga -mattr=-flat-for-global -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GFX8 %s
|
|
; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GFX9 %s
|
|
; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=gfx1010 -mattr=-wavefrontsize32,+wavefrontsize64 -mattr=-flat-for-global -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GFX1064 %s
|
|
; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=gfx1010 -mattr=+wavefrontsize32,-wavefrontsize64 -mattr=-flat-for-global -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GFX1032 %s
|
|
|
|
declare i32 @llvm.amdgcn.workitem.id.x()
|
|
|
|
@local_var32 = addrspace(3) global i32 undef, align 4
|
|
@local_var64 = addrspace(3) global i64 undef, align 8
|
|
|
|
; Show that what the atomic optimization pass will do for local pointers.
|
|
|
|
define amdgpu_kernel void @add_i32_constant(i32 addrspace(1)* %out) {
|
|
;
|
|
;
|
|
; GFX7LESS-LABEL: add_i32_constant:
|
|
; GFX7LESS: ; %bb.0: ; %entry
|
|
; GFX7LESS-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; GFX7LESS-NEXT: v_cmp_ne_u32_e64 s[4:5], 1, 0
|
|
; GFX7LESS-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s4, 0
|
|
; GFX7LESS-NEXT: v_mbcnt_hi_u32_b32_e32 v0, s5, v0
|
|
; GFX7LESS-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX7LESS-NEXT: ; implicit-def: $vgpr1
|
|
; GFX7LESS-NEXT: s_and_saveexec_b64 s[2:3], vcc
|
|
; GFX7LESS-NEXT: ; mask branch BB0_2
|
|
; GFX7LESS-NEXT: s_cbranch_execz BB0_2
|
|
; GFX7LESS-NEXT: BB0_1:
|
|
; GFX7LESS-NEXT: s_bcnt1_i32_b64 s4, s[4:5]
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v1, local_var32@abs32@lo
|
|
; GFX7LESS-NEXT: v_mul_u32_u24_e64 v2, s4, 5
|
|
; GFX7LESS-NEXT: s_mov_b32 m0, -1
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: ds_add_rtn_u32 v1, v1, v2
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: buffer_wbinvl1
|
|
; GFX7LESS-NEXT: BB0_2:
|
|
; GFX7LESS-NEXT: s_or_b64 exec, exec, s[2:3]
|
|
; GFX7LESS-NEXT: v_readfirstlane_b32 s2, v1
|
|
; GFX7LESS-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX7LESS-NEXT: v_mad_u32_u24 v0, v0, 5, s2
|
|
; GFX7LESS-NEXT: s_mov_b32 s2, -1
|
|
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7LESS-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX7LESS-NEXT: s_endpgm
|
|
;
|
|
; GFX8-LABEL: add_i32_constant:
|
|
; GFX8: ; %bb.0: ; %entry
|
|
; GFX8-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX8-NEXT: v_cmp_ne_u32_e64 s[4:5], 1, 0
|
|
; GFX8-NEXT: v_mbcnt_lo_u32_b32 v0, s4, 0
|
|
; GFX8-NEXT: v_mbcnt_hi_u32_b32 v0, s5, v0
|
|
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX8-NEXT: ; implicit-def: $vgpr1
|
|
; GFX8-NEXT: s_and_saveexec_b64 s[2:3], vcc
|
|
; GFX8-NEXT: ; mask branch BB0_2
|
|
; GFX8-NEXT: s_cbranch_execz BB0_2
|
|
; GFX8-NEXT: BB0_1:
|
|
; GFX8-NEXT: s_bcnt1_i32_b64 s4, s[4:5]
|
|
; GFX8-NEXT: v_mul_u32_u24_e64 v1, s4, 5
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, local_var32@abs32@lo
|
|
; GFX8-NEXT: s_mov_b32 m0, -1
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: ds_add_rtn_u32 v1, v2, v1
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_wbinvl1_vol
|
|
; GFX8-NEXT: BB0_2:
|
|
; GFX8-NEXT: s_or_b64 exec, exec, s[2:3]
|
|
; GFX8-NEXT: v_readfirstlane_b32 s2, v1
|
|
; GFX8-NEXT: v_mad_u32_u24 v0, v0, 5, s2
|
|
; GFX8-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX8-NEXT: s_mov_b32 s2, -1
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX8-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: add_i32_constant:
|
|
; GFX9: ; %bb.0: ; %entry
|
|
; GFX9-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX9-NEXT: v_cmp_ne_u32_e64 s[4:5], 1, 0
|
|
; GFX9-NEXT: v_mbcnt_lo_u32_b32 v0, s4, 0
|
|
; GFX9-NEXT: v_mbcnt_hi_u32_b32 v0, s5, v0
|
|
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX9-NEXT: ; implicit-def: $vgpr1
|
|
; GFX9-NEXT: s_and_saveexec_b64 s[2:3], vcc
|
|
; GFX9-NEXT: ; mask branch BB0_2
|
|
; GFX9-NEXT: s_cbranch_execz BB0_2
|
|
; GFX9-NEXT: BB0_1:
|
|
; GFX9-NEXT: s_bcnt1_i32_b64 s4, s[4:5]
|
|
; GFX9-NEXT: v_mul_u32_u24_e64 v1, s4, 5
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, local_var32@abs32@lo
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: ds_add_rtn_u32 v1, v2, v1
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_wbinvl1_vol
|
|
; GFX9-NEXT: BB0_2:
|
|
; GFX9-NEXT: s_or_b64 exec, exec, s[2:3]
|
|
; GFX9-NEXT: v_readfirstlane_b32 s2, v1
|
|
; GFX9-NEXT: v_mad_u32_u24 v0, v0, 5, s2
|
|
; GFX9-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX9-NEXT: s_mov_b32 s2, -1
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX1064-LABEL: add_i32_constant:
|
|
; GFX1064: ; %bb.0: ; %entry
|
|
; GFX1064-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX1064-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1064-NEXT: ; implicit-def: $vgpr1
|
|
; GFX1064-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s2, 0
|
|
; GFX1064-NEXT: v_mbcnt_hi_u32_b32_e64 v0, s3, v0
|
|
; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX1064-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX1064-NEXT: ; mask branch BB0_2
|
|
; GFX1064-NEXT: s_cbranch_execz BB0_2
|
|
; GFX1064-NEXT: BB0_1:
|
|
; GFX1064-NEXT: s_bcnt1_i32_b64 s2, s[2:3]
|
|
; GFX1064-NEXT: v_mov_b32_e32 v2, local_var32@abs32@lo
|
|
; GFX1064-NEXT: v_mul_u32_u24_e64 v1, s2, 5
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1064-NEXT: ds_add_rtn_u32 v1, v2, v1
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_gl0_inv
|
|
; GFX1064-NEXT: buffer_gl1_inv
|
|
; GFX1064-NEXT: BB0_2:
|
|
; GFX1064-NEXT: v_nop
|
|
; GFX1064-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX1064-NEXT: v_readfirstlane_b32 s2, v1
|
|
; GFX1064-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1064-NEXT: v_mad_u32_u24 v0, v0, 5, s2
|
|
; GFX1064-NEXT: s_mov_b32 s2, -1
|
|
; GFX1064-NEXT: s_nop 1
|
|
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX1064-NEXT: s_endpgm
|
|
;
|
|
; GFX1032-LABEL: add_i32_constant:
|
|
; GFX1032: ; %bb.0: ; %entry
|
|
; GFX1032-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1032-NEXT: v_cmp_ne_u32_e64 s3, 1, 0
|
|
; GFX1032-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX1032-NEXT: ; implicit-def: $vgpr1
|
|
; GFX1032-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s3, 0
|
|
; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v0
|
|
; GFX1032-NEXT: s_and_saveexec_b32 s2, vcc_lo
|
|
; GFX1032-NEXT: ; mask branch BB0_2
|
|
; GFX1032-NEXT: s_cbranch_execz BB0_2
|
|
; GFX1032-NEXT: BB0_1:
|
|
; GFX1032-NEXT: s_bcnt1_i32_b32 s3, s3
|
|
; GFX1032-NEXT: v_mov_b32_e32 v2, local_var32@abs32@lo
|
|
; GFX1032-NEXT: v_mul_u32_u24_e64 v1, s3, 5
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1032-NEXT: ds_add_rtn_u32 v1, v2, v1
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_gl0_inv
|
|
; GFX1032-NEXT: buffer_gl1_inv
|
|
; GFX1032-NEXT: BB0_2:
|
|
; GFX1032-NEXT: v_nop
|
|
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s2
|
|
; GFX1032-NEXT: v_readfirstlane_b32 s2, v1
|
|
; GFX1032-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1032-NEXT: v_mad_u32_u24 v0, v0, 5, s2
|
|
; GFX1032-NEXT: s_mov_b32 s2, -1
|
|
; GFX1032-NEXT: s_nop 1
|
|
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX1032-NEXT: s_endpgm
|
|
entry:
|
|
%old = atomicrmw add i32 addrspace(3)* @local_var32, i32 5 acq_rel
|
|
store i32 %old, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @add_i32_uniform(i32 addrspace(1)* %out, i32 %additive) {
|
|
;
|
|
;
|
|
; GFX7LESS-LABEL: add_i32_uniform:
|
|
; GFX7LESS: ; %bb.0: ; %entry
|
|
; GFX7LESS-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x9
|
|
; GFX7LESS-NEXT: s_load_dword s2, s[0:1], 0xb
|
|
; GFX7LESS-NEXT: v_cmp_ne_u32_e64 s[6:7], 1, 0
|
|
; GFX7LESS-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s6, 0
|
|
; GFX7LESS-NEXT: v_mbcnt_hi_u32_b32_e32 v0, s7, v0
|
|
; GFX7LESS-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX7LESS-NEXT: ; implicit-def: $vgpr1
|
|
; GFX7LESS-NEXT: s_and_saveexec_b64 s[0:1], vcc
|
|
; GFX7LESS-NEXT: ; mask branch BB1_2
|
|
; GFX7LESS-NEXT: s_cbranch_execz BB1_2
|
|
; GFX7LESS-NEXT: BB1_1:
|
|
; GFX7LESS-NEXT: s_bcnt1_i32_b64 s3, s[6:7]
|
|
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7LESS-NEXT: s_mul_i32 s3, s2, s3
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v1, local_var32@abs32@lo
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v2, s3
|
|
; GFX7LESS-NEXT: s_mov_b32 m0, -1
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: ds_add_rtn_u32 v1, v1, v2
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: buffer_wbinvl1
|
|
; GFX7LESS-NEXT: BB1_2:
|
|
; GFX7LESS-NEXT: s_or_b64 exec, exec, s[0:1]
|
|
; GFX7LESS-NEXT: v_readfirstlane_b32 s0, v1
|
|
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7LESS-NEXT: v_mul_lo_u32 v0, s2, v0
|
|
; GFX7LESS-NEXT: s_mov_b32 s7, 0xf000
|
|
; GFX7LESS-NEXT: v_add_i32_e32 v0, vcc, s0, v0
|
|
; GFX7LESS-NEXT: s_mov_b32 s6, -1
|
|
; GFX7LESS-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; GFX7LESS-NEXT: s_endpgm
|
|
;
|
|
; GFX8-LABEL: add_i32_uniform:
|
|
; GFX8: ; %bb.0: ; %entry
|
|
; GFX8-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x24
|
|
; GFX8-NEXT: s_load_dword s0, s[0:1], 0x2c
|
|
; GFX8-NEXT: v_cmp_ne_u32_e64 s[6:7], 1, 0
|
|
; GFX8-NEXT: v_mbcnt_lo_u32_b32 v0, s6, 0
|
|
; GFX8-NEXT: v_mbcnt_hi_u32_b32 v0, s7, v0
|
|
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX8-NEXT: ; implicit-def: $vgpr1
|
|
; GFX8-NEXT: s_and_saveexec_b64 s[2:3], vcc
|
|
; GFX8-NEXT: ; mask branch BB1_2
|
|
; GFX8-NEXT: s_cbranch_execz BB1_2
|
|
; GFX8-NEXT: BB1_1:
|
|
; GFX8-NEXT: s_bcnt1_i32_b64 s1, s[6:7]
|
|
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX8-NEXT: s_mul_i32 s1, s0, s1
|
|
; GFX8-NEXT: v_mov_b32_e32 v1, local_var32@abs32@lo
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, s1
|
|
; GFX8-NEXT: s_mov_b32 m0, -1
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: ds_add_rtn_u32 v1, v1, v2
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_wbinvl1_vol
|
|
; GFX8-NEXT: BB1_2:
|
|
; GFX8-NEXT: s_or_b64 exec, exec, s[2:3]
|
|
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX8-NEXT: v_mul_lo_u32 v0, s0, v0
|
|
; GFX8-NEXT: v_readfirstlane_b32 s0, v1
|
|
; GFX8-NEXT: s_mov_b32 s7, 0xf000
|
|
; GFX8-NEXT: s_mov_b32 s6, -1
|
|
; GFX8-NEXT: v_add_u32_e32 v0, vcc, s0, v0
|
|
; GFX8-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; GFX8-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: add_i32_uniform:
|
|
; GFX9: ; %bb.0: ; %entry
|
|
; GFX9-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x24
|
|
; GFX9-NEXT: s_load_dword s0, s[0:1], 0x2c
|
|
; GFX9-NEXT: v_cmp_ne_u32_e64 s[6:7], 1, 0
|
|
; GFX9-NEXT: v_mbcnt_lo_u32_b32 v0, s6, 0
|
|
; GFX9-NEXT: v_mbcnt_hi_u32_b32 v0, s7, v0
|
|
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX9-NEXT: ; implicit-def: $vgpr1
|
|
; GFX9-NEXT: s_and_saveexec_b64 s[2:3], vcc
|
|
; GFX9-NEXT: ; mask branch BB1_2
|
|
; GFX9-NEXT: s_cbranch_execz BB1_2
|
|
; GFX9-NEXT: BB1_1:
|
|
; GFX9-NEXT: s_bcnt1_i32_b64 s1, s[6:7]
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: s_mul_i32 s1, s0, s1
|
|
; GFX9-NEXT: v_mov_b32_e32 v1, local_var32@abs32@lo
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, s1
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: ds_add_rtn_u32 v1, v1, v2
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_wbinvl1_vol
|
|
; GFX9-NEXT: BB1_2:
|
|
; GFX9-NEXT: s_or_b64 exec, exec, s[2:3]
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: v_mul_lo_u32 v0, s0, v0
|
|
; GFX9-NEXT: v_readfirstlane_b32 s0, v1
|
|
; GFX9-NEXT: s_mov_b32 s7, 0xf000
|
|
; GFX9-NEXT: s_mov_b32 s6, -1
|
|
; GFX9-NEXT: v_add_u32_e32 v0, s0, v0
|
|
; GFX9-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX1064-LABEL: add_i32_uniform:
|
|
; GFX1064: ; %bb.0: ; %entry
|
|
; GFX1064-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x24
|
|
; GFX1064-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX1064-NEXT: s_load_dword s0, s[0:1], 0x2c
|
|
; GFX1064-NEXT: ; implicit-def: $vgpr1
|
|
; GFX1064-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s2, 0
|
|
; GFX1064-NEXT: v_mbcnt_hi_u32_b32_e64 v0, s3, v0
|
|
; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX1064-NEXT: s_and_saveexec_b64 s[6:7], vcc
|
|
; GFX1064-NEXT: ; mask branch BB1_2
|
|
; GFX1064-NEXT: s_cbranch_execz BB1_2
|
|
; GFX1064-NEXT: BB1_1:
|
|
; GFX1064-NEXT: s_bcnt1_i32_b64 s1, s[2:3]
|
|
; GFX1064-NEXT: v_mov_b32_e32 v1, local_var32@abs32@lo
|
|
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1064-NEXT: s_mul_i32 s1, s0, s1
|
|
; GFX1064-NEXT: v_mov_b32_e32 v2, s1
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1064-NEXT: ds_add_rtn_u32 v1, v1, v2
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_gl0_inv
|
|
; GFX1064-NEXT: buffer_gl1_inv
|
|
; GFX1064-NEXT: BB1_2:
|
|
; GFX1064-NEXT: v_nop
|
|
; GFX1064-NEXT: s_or_b64 exec, exec, s[6:7]
|
|
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1064-NEXT: v_mul_lo_u32 v0, s0, v0
|
|
; GFX1064-NEXT: v_readfirstlane_b32 s0, v1
|
|
; GFX1064-NEXT: s_mov_b32 s7, 0x31016000
|
|
; GFX1064-NEXT: s_mov_b32 s6, -1
|
|
; GFX1064-NEXT: v_add_nc_u32_e32 v0, s0, v0
|
|
; GFX1064-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; GFX1064-NEXT: s_endpgm
|
|
;
|
|
; GFX1032-LABEL: add_i32_uniform:
|
|
; GFX1032: ; %bb.0: ; %entry
|
|
; GFX1032-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x24
|
|
; GFX1032-NEXT: s_load_dword s0, s[0:1], 0x2c
|
|
; GFX1032-NEXT: v_cmp_ne_u32_e64 s2, 1, 0
|
|
; GFX1032-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX1032-NEXT: ; implicit-def: $vgpr1
|
|
; GFX1032-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s2, 0
|
|
; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v0
|
|
; GFX1032-NEXT: s_and_saveexec_b32 s1, vcc_lo
|
|
; GFX1032-NEXT: ; mask branch BB1_2
|
|
; GFX1032-NEXT: s_cbranch_execz BB1_2
|
|
; GFX1032-NEXT: BB1_1:
|
|
; GFX1032-NEXT: s_bcnt1_i32_b32 s2, s2
|
|
; GFX1032-NEXT: v_mov_b32_e32 v1, local_var32@abs32@lo
|
|
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1032-NEXT: s_mul_i32 s2, s0, s2
|
|
; GFX1032-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1032-NEXT: ds_add_rtn_u32 v1, v1, v2
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_gl0_inv
|
|
; GFX1032-NEXT: buffer_gl1_inv
|
|
; GFX1032-NEXT: BB1_2:
|
|
; GFX1032-NEXT: v_nop
|
|
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s1
|
|
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1032-NEXT: v_mul_lo_u32 v0, s0, v0
|
|
; GFX1032-NEXT: v_readfirstlane_b32 s0, v1
|
|
; GFX1032-NEXT: s_mov_b32 s7, 0x31016000
|
|
; GFX1032-NEXT: s_mov_b32 s6, -1
|
|
; GFX1032-NEXT: v_add_nc_u32_e32 v0, s0, v0
|
|
; GFX1032-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; GFX1032-NEXT: s_endpgm
|
|
entry:
|
|
%old = atomicrmw add i32 addrspace(3)* @local_var32, i32 %additive acq_rel
|
|
store i32 %old, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; GFX7LESS-NOT: v_mbcnt_lo_u32_b32
|
|
; GFX7LESS-NOT: v_mbcnt_hi_u32_b32
|
|
; GFX7LESS-NOT: s_bcnt1_i32_b64
|
|
; DPPCOMB: v_add_u32_dpp
|
|
; DPPCOMB: v_add_u32_dpp
|
|
; GFX8MORE32: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 31
|
|
; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
|
|
; GFX8MORE: ds_add_rtn_u32 v{{[0-9]+}}, v{{[0-9]+}}, v[[value]]
|
|
define amdgpu_kernel void @add_i32_varying(i32 addrspace(1)* %out) {
|
|
;
|
|
;
|
|
; GFX7LESS-LABEL: add_i32_varying:
|
|
; GFX7LESS: ; %bb.0: ; %entry
|
|
; GFX7LESS-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v1, local_var32@abs32@lo
|
|
; GFX7LESS-NEXT: s_mov_b32 m0, -1
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: ds_add_rtn_u32 v0, v1, v0
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: buffer_wbinvl1
|
|
; GFX7LESS-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX7LESS-NEXT: s_mov_b32 s2, -1
|
|
; GFX7LESS-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX7LESS-NEXT: s_endpgm
|
|
;
|
|
; GFX8-LABEL: add_i32_varying:
|
|
; GFX8: ; %bb.0: ; %entry
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX8-NEXT: s_or_saveexec_b64 s[2:3], -1
|
|
; GFX8-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX8-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX8-NEXT: s_mov_b64 exec, s[2:3]
|
|
; GFX8-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX8-NEXT: v_mbcnt_lo_u32_b32 v0, s2, 0
|
|
; GFX8-NEXT: v_mbcnt_hi_u32_b32 v0, s3, v0
|
|
; GFX8-NEXT: s_not_b64 exec, exec
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX8-NEXT: s_not_b64 exec, exec
|
|
; GFX8-NEXT: s_or_saveexec_b64 s[4:5], -1
|
|
; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_bcast:31 row_mask:0xc bank_mask:0xf
|
|
; GFX8-NEXT: v_readlane_b32 s2, v2, 63
|
|
; GFX8-NEXT: s_nop 0
|
|
; GFX8-NEXT: v_mov_b32_dpp v1, v2 wave_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX8-NEXT: s_mov_b64 exec, s[4:5]
|
|
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX8-NEXT: ; implicit-def: $vgpr0
|
|
; GFX8-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX8-NEXT: ; mask branch BB2_2
|
|
; GFX8-NEXT: s_cbranch_execz BB2_2
|
|
; GFX8-NEXT: BB2_1:
|
|
; GFX8-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX8-NEXT: v_mov_b32_e32 v3, s2
|
|
; GFX8-NEXT: s_mov_b32 m0, -1
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: ds_add_rtn_u32 v0, v0, v3
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_wbinvl1_vol
|
|
; GFX8-NEXT: BB2_2:
|
|
; GFX8-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX8-NEXT: v_readfirstlane_b32 s2, v0
|
|
; GFX8-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX8-NEXT: v_add_u32_e32 v0, vcc, s2, v0
|
|
; GFX8-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX8-NEXT: s_mov_b32 s2, -1
|
|
; GFX8-NEXT: s_nop 0
|
|
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX8-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: add_i32_varying:
|
|
; GFX9: ; %bb.0: ; %entry
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX9-NEXT: s_or_saveexec_b64 s[2:3], -1
|
|
; GFX9-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX9-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX9-NEXT: s_mov_b64 exec, s[2:3]
|
|
; GFX9-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX9-NEXT: v_mbcnt_lo_u32_b32 v0, s2, 0
|
|
; GFX9-NEXT: v_mbcnt_hi_u32_b32 v0, s3, v0
|
|
; GFX9-NEXT: s_not_b64 exec, exec
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX9-NEXT: s_not_b64 exec, exec
|
|
; GFX9-NEXT: s_or_saveexec_b64 s[4:5], -1
|
|
; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_bcast:31 row_mask:0xc bank_mask:0xf
|
|
; GFX9-NEXT: v_readlane_b32 s2, v2, 63
|
|
; GFX9-NEXT: s_nop 0
|
|
; GFX9-NEXT: v_mov_b32_dpp v1, v2 wave_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX9-NEXT: s_mov_b64 exec, s[4:5]
|
|
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX9-NEXT: ; implicit-def: $vgpr0
|
|
; GFX9-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX9-NEXT: ; mask branch BB2_2
|
|
; GFX9-NEXT: s_cbranch_execz BB2_2
|
|
; GFX9-NEXT: BB2_1:
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX9-NEXT: v_mov_b32_e32 v3, s2
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: ds_add_rtn_u32 v0, v0, v3
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_wbinvl1_vol
|
|
; GFX9-NEXT: BB2_2:
|
|
; GFX9-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX9-NEXT: v_readfirstlane_b32 s2, v0
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX9-NEXT: v_add_u32_e32 v0, s2, v0
|
|
; GFX9-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX9-NEXT: s_mov_b32 s2, -1
|
|
; GFX9-NEXT: s_nop 0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX1064-LABEL: add_i32_varying:
|
|
; GFX1064: ; %bb.0: ; %entry
|
|
; GFX1064-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX1064-NEXT: s_or_saveexec_b64 s[2:3], -1
|
|
; GFX1064-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1064-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX1064-NEXT: s_mov_b64 exec, s[2:3]
|
|
; GFX1064-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX1064-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s2, 0
|
|
; GFX1064-NEXT: v_mbcnt_hi_u32_b32_e64 v0, s3, v0
|
|
; GFX1064-NEXT: s_not_b64 exec, exec
|
|
; GFX1064-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX1064-NEXT: s_not_b64 exec, exec
|
|
; GFX1064-NEXT: s_or_saveexec_b64 s[4:5], -1
|
|
; GFX1064-NEXT: v_add_nc_u32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1064-NEXT: v_add_nc_u32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1064-NEXT: v_add_nc_u32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1064-NEXT: v_add_nc_u32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1064-NEXT: v_mov_b32_e32 v3, v2
|
|
; GFX1064-NEXT: v_permlanex16_b32 v3, v3, -1, -1
|
|
; GFX1064-NEXT: v_add_nc_u32_dpp v2, v3, v2 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf
|
|
; GFX1064-NEXT: v_readlane_b32 s2, v2, 31
|
|
; GFX1064-NEXT: v_mov_b32_e32 v3, s2
|
|
; GFX1064-NEXT: v_add_nc_u32_dpp v2, v3, v2 quad_perm:[0,1,2,3] row_mask:0xc bank_mask:0xf
|
|
; GFX1064-NEXT: v_readlane_b32 s2, v2, 15
|
|
; GFX1064-NEXT: v_mov_b32_dpp v1, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX1064-NEXT: v_readlane_b32 s3, v2, 31
|
|
; GFX1064-NEXT: v_readlane_b32 s6, v2, 47
|
|
; GFX1064-NEXT: v_writelane_b32 v1, s2, 16
|
|
; GFX1064-NEXT: s_mov_b32 s2, -1
|
|
; GFX1064-NEXT: v_writelane_b32 v1, s3, 32
|
|
; GFX1064-NEXT: v_readlane_b32 s3, v2, 63
|
|
; GFX1064-NEXT: v_writelane_b32 v1, s6, 48
|
|
; GFX1064-NEXT: s_mov_b64 exec, s[4:5]
|
|
; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX1064-NEXT: ; implicit-def: $vgpr0
|
|
; GFX1064-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX1064-NEXT: ; mask branch BB2_2
|
|
; GFX1064-NEXT: s_cbranch_execz BB2_2
|
|
; GFX1064-NEXT: BB2_1:
|
|
; GFX1064-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX1064-NEXT: v_mov_b32_e32 v7, s3
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1064-NEXT: ds_add_rtn_u32 v0, v0, v7
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_gl0_inv
|
|
; GFX1064-NEXT: buffer_gl1_inv
|
|
; GFX1064-NEXT: BB2_2:
|
|
; GFX1064-NEXT: v_nop
|
|
; GFX1064-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX1064-NEXT: v_readfirstlane_b32 s3, v0
|
|
; GFX1064-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX1064-NEXT: v_add_nc_u32_e32 v0, s3, v0
|
|
; GFX1064-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1064-NEXT: s_nop 1
|
|
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX1064-NEXT: s_endpgm
|
|
;
|
|
; GFX1032-LABEL: add_i32_varying:
|
|
; GFX1032: ; %bb.0: ; %entry
|
|
; GFX1032-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX1032-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX1032-NEXT: s_or_saveexec_b32 s2, -1
|
|
; GFX1032-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1032-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX1032-NEXT: s_mov_b32 exec_lo, s2
|
|
; GFX1032-NEXT: v_cmp_ne_u32_e64 s2, 1, 0
|
|
; GFX1032-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s2, 0
|
|
; GFX1032-NEXT: s_not_b32 exec_lo, exec_lo
|
|
; GFX1032-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX1032-NEXT: s_not_b32 exec_lo, exec_lo
|
|
; GFX1032-NEXT: s_or_saveexec_b32 s4, -1
|
|
; GFX1032-NEXT: v_add_nc_u32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1032-NEXT: s_mov_b32 s2, -1
|
|
; GFX1032-NEXT: v_add_nc_u32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1032-NEXT: v_add_nc_u32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1032-NEXT: v_add_nc_u32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1032-NEXT: v_mov_b32_e32 v3, v2
|
|
; GFX1032-NEXT: v_permlanex16_b32 v3, v3, -1, -1
|
|
; GFX1032-NEXT: v_add_nc_u32_dpp v2, v3, v2 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf
|
|
; GFX1032-NEXT: v_readlane_b32 s3, v2, 31
|
|
; GFX1032-NEXT: v_mov_b32_dpp v1, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX1032-NEXT: v_readlane_b32 s5, v2, 15
|
|
; GFX1032-NEXT: v_writelane_b32 v1, s5, 16
|
|
; GFX1032-NEXT: s_mov_b32 exec_lo, s4
|
|
; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v0
|
|
; GFX1032-NEXT: ; implicit-def: $vgpr0
|
|
; GFX1032-NEXT: s_and_saveexec_b32 s4, vcc_lo
|
|
; GFX1032-NEXT: ; mask branch BB2_2
|
|
; GFX1032-NEXT: s_cbranch_execz BB2_2
|
|
; GFX1032-NEXT: BB2_1:
|
|
; GFX1032-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX1032-NEXT: v_mov_b32_e32 v7, s3
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1032-NEXT: ds_add_rtn_u32 v0, v0, v7
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_gl0_inv
|
|
; GFX1032-NEXT: buffer_gl1_inv
|
|
; GFX1032-NEXT: BB2_2:
|
|
; GFX1032-NEXT: v_nop
|
|
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s4
|
|
; GFX1032-NEXT: v_readfirstlane_b32 s3, v0
|
|
; GFX1032-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX1032-NEXT: v_add_nc_u32_e32 v0, s3, v0
|
|
; GFX1032-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1032-NEXT: s_nop 1
|
|
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX1032-NEXT: s_endpgm
|
|
entry:
|
|
%lane = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%old = atomicrmw add i32 addrspace(3)* @local_var32, i32 %lane acq_rel
|
|
store i32 %old, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @add_i32_varying_gfx1032(i32 addrspace(1)* %out) {
|
|
;
|
|
;
|
|
; GFX7LESS-LABEL: add_i32_varying_gfx1032:
|
|
; GFX7LESS: ; %bb.0: ; %entry
|
|
; GFX7LESS-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v1, local_var32@abs32@lo
|
|
; GFX7LESS-NEXT: s_mov_b32 m0, -1
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: ds_add_rtn_u32 v0, v1, v0
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: buffer_wbinvl1
|
|
; GFX7LESS-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX7LESS-NEXT: s_mov_b32 s2, -1
|
|
; GFX7LESS-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX7LESS-NEXT: s_endpgm
|
|
;
|
|
; GFX8-LABEL: add_i32_varying_gfx1032:
|
|
; GFX8: ; %bb.0: ; %entry
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX8-NEXT: s_or_saveexec_b64 s[2:3], -1
|
|
; GFX8-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX8-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX8-NEXT: s_mov_b64 exec, s[2:3]
|
|
; GFX8-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX8-NEXT: v_mbcnt_lo_u32_b32 v0, s2, 0
|
|
; GFX8-NEXT: v_mbcnt_hi_u32_b32 v0, s3, v0
|
|
; GFX8-NEXT: s_not_b64 exec, exec
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX8-NEXT: s_not_b64 exec, exec
|
|
; GFX8-NEXT: s_or_saveexec_b64 s[4:5], -1
|
|
; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_bcast:31 row_mask:0xc bank_mask:0xf
|
|
; GFX8-NEXT: v_readlane_b32 s2, v2, 63
|
|
; GFX8-NEXT: s_nop 0
|
|
; GFX8-NEXT: v_mov_b32_dpp v1, v2 wave_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX8-NEXT: s_mov_b64 exec, s[4:5]
|
|
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX8-NEXT: ; implicit-def: $vgpr0
|
|
; GFX8-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX8-NEXT: ; mask branch BB3_2
|
|
; GFX8-NEXT: s_cbranch_execz BB3_2
|
|
; GFX8-NEXT: BB3_1:
|
|
; GFX8-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX8-NEXT: v_mov_b32_e32 v3, s2
|
|
; GFX8-NEXT: s_mov_b32 m0, -1
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: ds_add_rtn_u32 v0, v0, v3
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_wbinvl1_vol
|
|
; GFX8-NEXT: BB3_2:
|
|
; GFX8-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX8-NEXT: v_readfirstlane_b32 s2, v0
|
|
; GFX8-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX8-NEXT: v_add_u32_e32 v0, vcc, s2, v0
|
|
; GFX8-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX8-NEXT: s_mov_b32 s2, -1
|
|
; GFX8-NEXT: s_nop 0
|
|
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX8-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: add_i32_varying_gfx1032:
|
|
; GFX9: ; %bb.0: ; %entry
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX9-NEXT: s_or_saveexec_b64 s[2:3], -1
|
|
; GFX9-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX9-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX9-NEXT: s_mov_b64 exec, s[2:3]
|
|
; GFX9-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX9-NEXT: v_mbcnt_lo_u32_b32 v0, s2, 0
|
|
; GFX9-NEXT: v_mbcnt_hi_u32_b32 v0, s3, v0
|
|
; GFX9-NEXT: s_not_b64 exec, exec
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX9-NEXT: s_not_b64 exec, exec
|
|
; GFX9-NEXT: s_or_saveexec_b64 s[4:5], -1
|
|
; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_bcast:31 row_mask:0xc bank_mask:0xf
|
|
; GFX9-NEXT: v_readlane_b32 s2, v2, 63
|
|
; GFX9-NEXT: s_nop 0
|
|
; GFX9-NEXT: v_mov_b32_dpp v1, v2 wave_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX9-NEXT: s_mov_b64 exec, s[4:5]
|
|
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX9-NEXT: ; implicit-def: $vgpr0
|
|
; GFX9-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX9-NEXT: ; mask branch BB3_2
|
|
; GFX9-NEXT: s_cbranch_execz BB3_2
|
|
; GFX9-NEXT: BB3_1:
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX9-NEXT: v_mov_b32_e32 v3, s2
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: ds_add_rtn_u32 v0, v0, v3
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_wbinvl1_vol
|
|
; GFX9-NEXT: BB3_2:
|
|
; GFX9-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX9-NEXT: v_readfirstlane_b32 s2, v0
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX9-NEXT: v_add_u32_e32 v0, s2, v0
|
|
; GFX9-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX9-NEXT: s_mov_b32 s2, -1
|
|
; GFX9-NEXT: s_nop 0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX1064-LABEL: add_i32_varying_gfx1032:
|
|
; GFX1064: ; %bb.0: ; %entry
|
|
; GFX1064-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX1064-NEXT: s_or_saveexec_b64 s[2:3], -1
|
|
; GFX1064-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1064-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX1064-NEXT: s_mov_b64 exec, s[2:3]
|
|
; GFX1064-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX1064-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s2, 0
|
|
; GFX1064-NEXT: v_mbcnt_hi_u32_b32_e64 v0, s3, v0
|
|
; GFX1064-NEXT: s_not_b64 exec, exec
|
|
; GFX1064-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX1064-NEXT: s_not_b64 exec, exec
|
|
; GFX1064-NEXT: s_or_saveexec_b64 s[4:5], -1
|
|
; GFX1064-NEXT: v_add_nc_u32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1064-NEXT: v_add_nc_u32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1064-NEXT: v_add_nc_u32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1064-NEXT: v_add_nc_u32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1064-NEXT: v_mov_b32_e32 v3, v2
|
|
; GFX1064-NEXT: v_permlanex16_b32 v3, v3, -1, -1
|
|
; GFX1064-NEXT: v_add_nc_u32_dpp v2, v3, v2 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf
|
|
; GFX1064-NEXT: v_readlane_b32 s2, v2, 31
|
|
; GFX1064-NEXT: v_mov_b32_e32 v3, s2
|
|
; GFX1064-NEXT: v_add_nc_u32_dpp v2, v3, v2 quad_perm:[0,1,2,3] row_mask:0xc bank_mask:0xf
|
|
; GFX1064-NEXT: v_readlane_b32 s2, v2, 15
|
|
; GFX1064-NEXT: v_mov_b32_dpp v1, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX1064-NEXT: v_readlane_b32 s3, v2, 31
|
|
; GFX1064-NEXT: v_readlane_b32 s6, v2, 47
|
|
; GFX1064-NEXT: v_writelane_b32 v1, s2, 16
|
|
; GFX1064-NEXT: s_mov_b32 s2, -1
|
|
; GFX1064-NEXT: v_writelane_b32 v1, s3, 32
|
|
; GFX1064-NEXT: v_readlane_b32 s3, v2, 63
|
|
; GFX1064-NEXT: v_writelane_b32 v1, s6, 48
|
|
; GFX1064-NEXT: s_mov_b64 exec, s[4:5]
|
|
; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX1064-NEXT: ; implicit-def: $vgpr0
|
|
; GFX1064-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX1064-NEXT: ; mask branch BB3_2
|
|
; GFX1064-NEXT: s_cbranch_execz BB3_2
|
|
; GFX1064-NEXT: BB3_1:
|
|
; GFX1064-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX1064-NEXT: v_mov_b32_e32 v7, s3
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1064-NEXT: ds_add_rtn_u32 v0, v0, v7
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_gl0_inv
|
|
; GFX1064-NEXT: buffer_gl1_inv
|
|
; GFX1064-NEXT: BB3_2:
|
|
; GFX1064-NEXT: v_nop
|
|
; GFX1064-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX1064-NEXT: v_readfirstlane_b32 s3, v0
|
|
; GFX1064-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX1064-NEXT: v_add_nc_u32_e32 v0, s3, v0
|
|
; GFX1064-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1064-NEXT: s_nop 1
|
|
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX1064-NEXT: s_endpgm
|
|
;
|
|
; GFX1032-LABEL: add_i32_varying_gfx1032:
|
|
; GFX1032: ; %bb.0: ; %entry
|
|
; GFX1032-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX1032-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX1032-NEXT: s_or_saveexec_b32 s2, -1
|
|
; GFX1032-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1032-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX1032-NEXT: s_mov_b32 exec_lo, s2
|
|
; GFX1032-NEXT: v_cmp_ne_u32_e64 s2, 1, 0
|
|
; GFX1032-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s2, 0
|
|
; GFX1032-NEXT: s_not_b32 exec_lo, exec_lo
|
|
; GFX1032-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX1032-NEXT: s_not_b32 exec_lo, exec_lo
|
|
; GFX1032-NEXT: s_or_saveexec_b32 s4, -1
|
|
; GFX1032-NEXT: v_add_nc_u32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1032-NEXT: s_mov_b32 s2, -1
|
|
; GFX1032-NEXT: v_add_nc_u32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1032-NEXT: v_add_nc_u32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1032-NEXT: v_add_nc_u32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1032-NEXT: v_mov_b32_e32 v3, v2
|
|
; GFX1032-NEXT: v_permlanex16_b32 v3, v3, -1, -1
|
|
; GFX1032-NEXT: v_add_nc_u32_dpp v2, v3, v2 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf
|
|
; GFX1032-NEXT: v_readlane_b32 s3, v2, 31
|
|
; GFX1032-NEXT: v_mov_b32_dpp v1, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX1032-NEXT: v_readlane_b32 s5, v2, 15
|
|
; GFX1032-NEXT: v_writelane_b32 v1, s5, 16
|
|
; GFX1032-NEXT: s_mov_b32 exec_lo, s4
|
|
; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v0
|
|
; GFX1032-NEXT: ; implicit-def: $vgpr0
|
|
; GFX1032-NEXT: s_and_saveexec_b32 s4, vcc_lo
|
|
; GFX1032-NEXT: ; mask branch BB3_2
|
|
; GFX1032-NEXT: s_cbranch_execz BB3_2
|
|
; GFX1032-NEXT: BB3_1:
|
|
; GFX1032-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX1032-NEXT: v_mov_b32_e32 v7, s3
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1032-NEXT: ds_add_rtn_u32 v0, v0, v7
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_gl0_inv
|
|
; GFX1032-NEXT: buffer_gl1_inv
|
|
; GFX1032-NEXT: BB3_2:
|
|
; GFX1032-NEXT: v_nop
|
|
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s4
|
|
; GFX1032-NEXT: v_readfirstlane_b32 s3, v0
|
|
; GFX1032-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX1032-NEXT: v_add_nc_u32_e32 v0, s3, v0
|
|
; GFX1032-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1032-NEXT: s_nop 1
|
|
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX1032-NEXT: s_endpgm
|
|
entry:
|
|
%lane = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%old = atomicrmw add i32 addrspace(3)* @local_var32, i32 %lane acq_rel
|
|
store i32 %old, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @add_i32_varying_gfx1064(i32 addrspace(1)* %out) {
|
|
;
|
|
;
|
|
; GFX7LESS-LABEL: add_i32_varying_gfx1064:
|
|
; GFX7LESS: ; %bb.0: ; %entry
|
|
; GFX7LESS-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v1, local_var32@abs32@lo
|
|
; GFX7LESS-NEXT: s_mov_b32 m0, -1
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: ds_add_rtn_u32 v0, v1, v0
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: buffer_wbinvl1
|
|
; GFX7LESS-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX7LESS-NEXT: s_mov_b32 s2, -1
|
|
; GFX7LESS-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX7LESS-NEXT: s_endpgm
|
|
;
|
|
; GFX8-LABEL: add_i32_varying_gfx1064:
|
|
; GFX8: ; %bb.0: ; %entry
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX8-NEXT: s_or_saveexec_b64 s[2:3], -1
|
|
; GFX8-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX8-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX8-NEXT: s_mov_b64 exec, s[2:3]
|
|
; GFX8-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX8-NEXT: v_mbcnt_lo_u32_b32 v0, s2, 0
|
|
; GFX8-NEXT: v_mbcnt_hi_u32_b32 v0, s3, v0
|
|
; GFX8-NEXT: s_not_b64 exec, exec
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX8-NEXT: s_not_b64 exec, exec
|
|
; GFX8-NEXT: s_or_saveexec_b64 s[4:5], -1
|
|
; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_bcast:31 row_mask:0xc bank_mask:0xf
|
|
; GFX8-NEXT: v_readlane_b32 s2, v2, 63
|
|
; GFX8-NEXT: s_nop 0
|
|
; GFX8-NEXT: v_mov_b32_dpp v1, v2 wave_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX8-NEXT: s_mov_b64 exec, s[4:5]
|
|
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX8-NEXT: ; implicit-def: $vgpr0
|
|
; GFX8-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX8-NEXT: ; mask branch BB4_2
|
|
; GFX8-NEXT: s_cbranch_execz BB4_2
|
|
; GFX8-NEXT: BB4_1:
|
|
; GFX8-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX8-NEXT: v_mov_b32_e32 v3, s2
|
|
; GFX8-NEXT: s_mov_b32 m0, -1
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: ds_add_rtn_u32 v0, v0, v3
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_wbinvl1_vol
|
|
; GFX8-NEXT: BB4_2:
|
|
; GFX8-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX8-NEXT: v_readfirstlane_b32 s2, v0
|
|
; GFX8-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX8-NEXT: v_add_u32_e32 v0, vcc, s2, v0
|
|
; GFX8-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX8-NEXT: s_mov_b32 s2, -1
|
|
; GFX8-NEXT: s_nop 0
|
|
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX8-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: add_i32_varying_gfx1064:
|
|
; GFX9: ; %bb.0: ; %entry
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX9-NEXT: s_or_saveexec_b64 s[2:3], -1
|
|
; GFX9-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX9-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX9-NEXT: s_mov_b64 exec, s[2:3]
|
|
; GFX9-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX9-NEXT: v_mbcnt_lo_u32_b32 v0, s2, 0
|
|
; GFX9-NEXT: v_mbcnt_hi_u32_b32 v0, s3, v0
|
|
; GFX9-NEXT: s_not_b64 exec, exec
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX9-NEXT: s_not_b64 exec, exec
|
|
; GFX9-NEXT: s_or_saveexec_b64 s[4:5], -1
|
|
; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_bcast:31 row_mask:0xc bank_mask:0xf
|
|
; GFX9-NEXT: v_readlane_b32 s2, v2, 63
|
|
; GFX9-NEXT: s_nop 0
|
|
; GFX9-NEXT: v_mov_b32_dpp v1, v2 wave_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX9-NEXT: s_mov_b64 exec, s[4:5]
|
|
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX9-NEXT: ; implicit-def: $vgpr0
|
|
; GFX9-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX9-NEXT: ; mask branch BB4_2
|
|
; GFX9-NEXT: s_cbranch_execz BB4_2
|
|
; GFX9-NEXT: BB4_1:
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX9-NEXT: v_mov_b32_e32 v3, s2
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: ds_add_rtn_u32 v0, v0, v3
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_wbinvl1_vol
|
|
; GFX9-NEXT: BB4_2:
|
|
; GFX9-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX9-NEXT: v_readfirstlane_b32 s2, v0
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX9-NEXT: v_add_u32_e32 v0, s2, v0
|
|
; GFX9-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX9-NEXT: s_mov_b32 s2, -1
|
|
; GFX9-NEXT: s_nop 0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX1064-LABEL: add_i32_varying_gfx1064:
|
|
; GFX1064: ; %bb.0: ; %entry
|
|
; GFX1064-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX1064-NEXT: s_or_saveexec_b64 s[2:3], -1
|
|
; GFX1064-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1064-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX1064-NEXT: s_mov_b64 exec, s[2:3]
|
|
; GFX1064-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX1064-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s2, 0
|
|
; GFX1064-NEXT: v_mbcnt_hi_u32_b32_e64 v0, s3, v0
|
|
; GFX1064-NEXT: s_not_b64 exec, exec
|
|
; GFX1064-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX1064-NEXT: s_not_b64 exec, exec
|
|
; GFX1064-NEXT: s_or_saveexec_b64 s[4:5], -1
|
|
; GFX1064-NEXT: v_add_nc_u32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1064-NEXT: v_add_nc_u32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1064-NEXT: v_add_nc_u32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1064-NEXT: v_add_nc_u32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1064-NEXT: v_mov_b32_e32 v3, v2
|
|
; GFX1064-NEXT: v_permlanex16_b32 v3, v3, -1, -1
|
|
; GFX1064-NEXT: v_add_nc_u32_dpp v2, v3, v2 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf
|
|
; GFX1064-NEXT: v_readlane_b32 s2, v2, 31
|
|
; GFX1064-NEXT: v_mov_b32_e32 v3, s2
|
|
; GFX1064-NEXT: v_add_nc_u32_dpp v2, v3, v2 quad_perm:[0,1,2,3] row_mask:0xc bank_mask:0xf
|
|
; GFX1064-NEXT: v_readlane_b32 s2, v2, 15
|
|
; GFX1064-NEXT: v_mov_b32_dpp v1, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX1064-NEXT: v_readlane_b32 s3, v2, 31
|
|
; GFX1064-NEXT: v_readlane_b32 s6, v2, 47
|
|
; GFX1064-NEXT: v_writelane_b32 v1, s2, 16
|
|
; GFX1064-NEXT: s_mov_b32 s2, -1
|
|
; GFX1064-NEXT: v_writelane_b32 v1, s3, 32
|
|
; GFX1064-NEXT: v_readlane_b32 s3, v2, 63
|
|
; GFX1064-NEXT: v_writelane_b32 v1, s6, 48
|
|
; GFX1064-NEXT: s_mov_b64 exec, s[4:5]
|
|
; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX1064-NEXT: ; implicit-def: $vgpr0
|
|
; GFX1064-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX1064-NEXT: ; mask branch BB4_2
|
|
; GFX1064-NEXT: s_cbranch_execz BB4_2
|
|
; GFX1064-NEXT: BB4_1:
|
|
; GFX1064-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX1064-NEXT: v_mov_b32_e32 v7, s3
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1064-NEXT: ds_add_rtn_u32 v0, v0, v7
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_gl0_inv
|
|
; GFX1064-NEXT: buffer_gl1_inv
|
|
; GFX1064-NEXT: BB4_2:
|
|
; GFX1064-NEXT: v_nop
|
|
; GFX1064-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX1064-NEXT: v_readfirstlane_b32 s3, v0
|
|
; GFX1064-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX1064-NEXT: v_add_nc_u32_e32 v0, s3, v0
|
|
; GFX1064-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1064-NEXT: s_nop 1
|
|
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX1064-NEXT: s_endpgm
|
|
;
|
|
; GFX1032-LABEL: add_i32_varying_gfx1064:
|
|
; GFX1032: ; %bb.0: ; %entry
|
|
; GFX1032-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX1032-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX1032-NEXT: s_or_saveexec_b32 s2, -1
|
|
; GFX1032-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1032-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX1032-NEXT: s_mov_b32 exec_lo, s2
|
|
; GFX1032-NEXT: v_cmp_ne_u32_e64 s2, 1, 0
|
|
; GFX1032-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s2, 0
|
|
; GFX1032-NEXT: s_not_b32 exec_lo, exec_lo
|
|
; GFX1032-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX1032-NEXT: s_not_b32 exec_lo, exec_lo
|
|
; GFX1032-NEXT: s_or_saveexec_b32 s4, -1
|
|
; GFX1032-NEXT: v_add_nc_u32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1032-NEXT: s_mov_b32 s2, -1
|
|
; GFX1032-NEXT: v_add_nc_u32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1032-NEXT: v_add_nc_u32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1032-NEXT: v_add_nc_u32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1032-NEXT: v_mov_b32_e32 v3, v2
|
|
; GFX1032-NEXT: v_permlanex16_b32 v3, v3, -1, -1
|
|
; GFX1032-NEXT: v_add_nc_u32_dpp v2, v3, v2 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf
|
|
; GFX1032-NEXT: v_readlane_b32 s3, v2, 31
|
|
; GFX1032-NEXT: v_mov_b32_dpp v1, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX1032-NEXT: v_readlane_b32 s5, v2, 15
|
|
; GFX1032-NEXT: v_writelane_b32 v1, s5, 16
|
|
; GFX1032-NEXT: s_mov_b32 exec_lo, s4
|
|
; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v0
|
|
; GFX1032-NEXT: ; implicit-def: $vgpr0
|
|
; GFX1032-NEXT: s_and_saveexec_b32 s4, vcc_lo
|
|
; GFX1032-NEXT: ; mask branch BB4_2
|
|
; GFX1032-NEXT: s_cbranch_execz BB4_2
|
|
; GFX1032-NEXT: BB4_1:
|
|
; GFX1032-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX1032-NEXT: v_mov_b32_e32 v7, s3
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1032-NEXT: ds_add_rtn_u32 v0, v0, v7
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_gl0_inv
|
|
; GFX1032-NEXT: buffer_gl1_inv
|
|
; GFX1032-NEXT: BB4_2:
|
|
; GFX1032-NEXT: v_nop
|
|
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s4
|
|
; GFX1032-NEXT: v_readfirstlane_b32 s3, v0
|
|
; GFX1032-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX1032-NEXT: v_add_nc_u32_e32 v0, s3, v0
|
|
; GFX1032-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1032-NEXT: s_nop 1
|
|
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX1032-NEXT: s_endpgm
|
|
entry:
|
|
%lane = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%old = atomicrmw add i32 addrspace(3)* @local_var32, i32 %lane acq_rel
|
|
store i32 %old, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @add_i64_constant(i64 addrspace(1)* %out) {
|
|
;
|
|
;
|
|
; GFX7LESS-LABEL: add_i64_constant:
|
|
; GFX7LESS: ; %bb.0: ; %entry
|
|
; GFX7LESS-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; GFX7LESS-NEXT: v_cmp_ne_u32_e64 s[4:5], 1, 0
|
|
; GFX7LESS-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s4, 0
|
|
; GFX7LESS-NEXT: v_mbcnt_hi_u32_b32_e32 v0, s5, v0
|
|
; GFX7LESS-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX7LESS-NEXT: ; implicit-def: $vgpr1_vgpr2
|
|
; GFX7LESS-NEXT: s_and_saveexec_b64 s[2:3], vcc
|
|
; GFX7LESS-NEXT: ; mask branch BB5_2
|
|
; GFX7LESS-NEXT: s_cbranch_execz BB5_2
|
|
; GFX7LESS-NEXT: BB5_1:
|
|
; GFX7LESS-NEXT: s_bcnt1_i32_b64 s4, s[4:5]
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v3, local_var64@abs32@lo
|
|
; GFX7LESS-NEXT: v_mul_hi_u32_u24_e64 v2, s4, 5
|
|
; GFX7LESS-NEXT: v_mul_u32_u24_e64 v1, s4, 5
|
|
; GFX7LESS-NEXT: s_mov_b32 m0, -1
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: ds_add_rtn_u64 v[1:2], v3, v[1:2]
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: buffer_wbinvl1
|
|
; GFX7LESS-NEXT: BB5_2:
|
|
; GFX7LESS-NEXT: s_or_b64 exec, exec, s[2:3]
|
|
; GFX7LESS-NEXT: v_readfirstlane_b32 s2, v1
|
|
; GFX7LESS-NEXT: v_readfirstlane_b32 s4, v2
|
|
; GFX7LESS-NEXT: v_mul_hi_u32_u24_e32 v1, 5, v0
|
|
; GFX7LESS-NEXT: v_mul_u32_u24_e32 v0, 5, v0
|
|
; GFX7LESS-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v2, s4
|
|
; GFX7LESS-NEXT: v_add_i32_e32 v0, vcc, s2, v0
|
|
; GFX7LESS-NEXT: v_addc_u32_e32 v1, vcc, v2, v1, vcc
|
|
; GFX7LESS-NEXT: s_mov_b32 s2, -1
|
|
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7LESS-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX7LESS-NEXT: s_endpgm
|
|
;
|
|
; GFX8-LABEL: add_i64_constant:
|
|
; GFX8: ; %bb.0: ; %entry
|
|
; GFX8-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX8-NEXT: v_cmp_ne_u32_e64 s[4:5], 1, 0
|
|
; GFX8-NEXT: v_mbcnt_lo_u32_b32 v0, s4, 0
|
|
; GFX8-NEXT: v_mbcnt_hi_u32_b32 v0, s5, v0
|
|
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX8-NEXT: ; implicit-def: $vgpr1_vgpr2
|
|
; GFX8-NEXT: s_and_saveexec_b64 s[2:3], vcc
|
|
; GFX8-NEXT: ; mask branch BB5_2
|
|
; GFX8-NEXT: s_cbranch_execz BB5_2
|
|
; GFX8-NEXT: BB5_1:
|
|
; GFX8-NEXT: s_bcnt1_i32_b64 s4, s[4:5]
|
|
; GFX8-NEXT: v_mul_hi_u32_u24_e64 v2, s4, 5
|
|
; GFX8-NEXT: v_mul_u32_u24_e64 v1, s4, 5
|
|
; GFX8-NEXT: v_mov_b32_e32 v3, local_var64@abs32@lo
|
|
; GFX8-NEXT: s_mov_b32 m0, -1
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: ds_add_rtn_u64 v[1:2], v3, v[1:2]
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_wbinvl1_vol
|
|
; GFX8-NEXT: BB5_2:
|
|
; GFX8-NEXT: s_or_b64 exec, exec, s[2:3]
|
|
; GFX8-NEXT: v_readfirstlane_b32 s2, v1
|
|
; GFX8-NEXT: v_readfirstlane_b32 s3, v2
|
|
; GFX8-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, s3
|
|
; GFX8-NEXT: v_mad_u64_u32 v[0:1], s[2:3], v0, 5, v[1:2]
|
|
; GFX8-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX8-NEXT: s_mov_b32 s2, -1
|
|
; GFX8-NEXT: s_nop 2
|
|
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX8-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: add_i64_constant:
|
|
; GFX9: ; %bb.0: ; %entry
|
|
; GFX9-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX9-NEXT: v_cmp_ne_u32_e64 s[4:5], 1, 0
|
|
; GFX9-NEXT: v_mbcnt_lo_u32_b32 v0, s4, 0
|
|
; GFX9-NEXT: v_mbcnt_hi_u32_b32 v0, s5, v0
|
|
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX9-NEXT: ; implicit-def: $vgpr1_vgpr2
|
|
; GFX9-NEXT: s_and_saveexec_b64 s[2:3], vcc
|
|
; GFX9-NEXT: ; mask branch BB5_2
|
|
; GFX9-NEXT: s_cbranch_execz BB5_2
|
|
; GFX9-NEXT: BB5_1:
|
|
; GFX9-NEXT: s_bcnt1_i32_b64 s4, s[4:5]
|
|
; GFX9-NEXT: v_mul_hi_u32_u24_e64 v2, s4, 5
|
|
; GFX9-NEXT: v_mul_u32_u24_e64 v1, s4, 5
|
|
; GFX9-NEXT: v_mov_b32_e32 v3, local_var64@abs32@lo
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: ds_add_rtn_u64 v[1:2], v3, v[1:2]
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_wbinvl1_vol
|
|
; GFX9-NEXT: BB5_2:
|
|
; GFX9-NEXT: s_or_b64 exec, exec, s[2:3]
|
|
; GFX9-NEXT: v_readfirstlane_b32 s2, v1
|
|
; GFX9-NEXT: v_readfirstlane_b32 s3, v2
|
|
; GFX9-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, s3
|
|
; GFX9-NEXT: v_mad_u64_u32 v[0:1], s[2:3], v0, 5, v[1:2]
|
|
; GFX9-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX9-NEXT: s_mov_b32 s2, -1
|
|
; GFX9-NEXT: s_nop 2
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX1064-LABEL: add_i64_constant:
|
|
; GFX1064: ; %bb.0: ; %entry
|
|
; GFX1064-NEXT: v_cmp_ne_u32_e64 s[4:5], 1, 0
|
|
; GFX1064-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1064-NEXT: ; implicit-def: $vgpr1_vgpr2
|
|
; GFX1064-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s4, 0
|
|
; GFX1064-NEXT: v_mbcnt_hi_u32_b32_e64 v0, s5, v0
|
|
; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX1064-NEXT: s_and_saveexec_b64 s[2:3], vcc
|
|
; GFX1064-NEXT: ; mask branch BB5_2
|
|
; GFX1064-NEXT: s_cbranch_execz BB5_2
|
|
; GFX1064-NEXT: BB5_1:
|
|
; GFX1064-NEXT: s_bcnt1_i32_b64 s4, s[4:5]
|
|
; GFX1064-NEXT: v_mov_b32_e32 v3, local_var64@abs32@lo
|
|
; GFX1064-NEXT: v_mul_hi_u32_u24_e64 v2, s4, 5
|
|
; GFX1064-NEXT: v_mul_u32_u24_e64 v1, s4, 5
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1064-NEXT: ds_add_rtn_u64 v[1:2], v3, v[1:2]
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_gl0_inv
|
|
; GFX1064-NEXT: buffer_gl1_inv
|
|
; GFX1064-NEXT: BB5_2:
|
|
; GFX1064-NEXT: v_nop
|
|
; GFX1064-NEXT: s_or_b64 exec, exec, s[2:3]
|
|
; GFX1064-NEXT: v_readfirstlane_b32 s2, v1
|
|
; GFX1064-NEXT: v_readfirstlane_b32 s3, v2
|
|
; GFX1064-NEXT: v_mad_u64_u32 v[0:1], s[2:3], v0, 5, s[2:3]
|
|
; GFX1064-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1064-NEXT: s_mov_b32 s2, -1
|
|
; GFX1064-NEXT: s_nop 2
|
|
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX1064-NEXT: s_endpgm
|
|
;
|
|
; GFX1032-LABEL: add_i64_constant:
|
|
; GFX1032: ; %bb.0: ; %entry
|
|
; GFX1032-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1032-NEXT: v_cmp_ne_u32_e64 s3, 1, 0
|
|
; GFX1032-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX1032-NEXT: ; implicit-def: $vgpr1_vgpr2
|
|
; GFX1032-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s3, 0
|
|
; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v0
|
|
; GFX1032-NEXT: s_and_saveexec_b32 s2, vcc_lo
|
|
; GFX1032-NEXT: ; mask branch BB5_2
|
|
; GFX1032-NEXT: s_cbranch_execz BB5_2
|
|
; GFX1032-NEXT: BB5_1:
|
|
; GFX1032-NEXT: s_bcnt1_i32_b32 s3, s3
|
|
; GFX1032-NEXT: v_mov_b32_e32 v3, local_var64@abs32@lo
|
|
; GFX1032-NEXT: v_mul_hi_u32_u24_e64 v2, s3, 5
|
|
; GFX1032-NEXT: v_mul_u32_u24_e64 v1, s3, 5
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1032-NEXT: ds_add_rtn_u64 v[1:2], v3, v[1:2]
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_gl0_inv
|
|
; GFX1032-NEXT: buffer_gl1_inv
|
|
; GFX1032-NEXT: BB5_2:
|
|
; GFX1032-NEXT: v_nop
|
|
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s2
|
|
; GFX1032-NEXT: v_readfirstlane_b32 s2, v1
|
|
; GFX1032-NEXT: v_readfirstlane_b32 s3, v2
|
|
; GFX1032-NEXT: v_mad_u64_u32 v[0:1], s2, v0, 5, s[2:3]
|
|
; GFX1032-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1032-NEXT: s_mov_b32 s2, -1
|
|
; GFX1032-NEXT: s_nop 2
|
|
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX1032-NEXT: s_endpgm
|
|
entry:
|
|
%old = atomicrmw add i64 addrspace(3)* @local_var64, i64 5 acq_rel
|
|
store i64 %old, i64 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @add_i64_uniform(i64 addrspace(1)* %out, i64 %additive) {
|
|
;
|
|
;
|
|
; GFX7LESS-LABEL: add_i64_uniform:
|
|
; GFX7LESS: ; %bb.0: ; %entry
|
|
; GFX7LESS-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; GFX7LESS-NEXT: v_cmp_ne_u32_e64 s[6:7], 1, 0
|
|
; GFX7LESS-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s6, 0
|
|
; GFX7LESS-NEXT: v_mbcnt_hi_u32_b32_e32 v0, s7, v0
|
|
; GFX7LESS-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX7LESS-NEXT: ; implicit-def: $vgpr1_vgpr2
|
|
; GFX7LESS-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX7LESS-NEXT: ; mask branch BB6_2
|
|
; GFX7LESS-NEXT: s_cbranch_execz BB6_2
|
|
; GFX7LESS-NEXT: BB6_1:
|
|
; GFX7LESS-NEXT: s_bcnt1_i32_b64 s6, s[6:7]
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v3, local_var64@abs32@lo
|
|
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7LESS-NEXT: s_mul_i32 s7, s3, s6
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v1, s6
|
|
; GFX7LESS-NEXT: v_mul_hi_u32 v1, s2, v1
|
|
; GFX7LESS-NEXT: s_mul_i32 s6, s2, s6
|
|
; GFX7LESS-NEXT: v_add_i32_e32 v2, vcc, s7, v1
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v1, s6
|
|
; GFX7LESS-NEXT: s_mov_b32 m0, -1
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: ds_add_rtn_u64 v[1:2], v3, v[1:2]
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: buffer_wbinvl1
|
|
; GFX7LESS-NEXT: BB6_2:
|
|
; GFX7LESS-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX7LESS-NEXT: s_mov_b32 s7, 0xf000
|
|
; GFX7LESS-NEXT: s_mov_b32 s6, -1
|
|
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7LESS-NEXT: s_mov_b32 s4, s0
|
|
; GFX7LESS-NEXT: s_mov_b32 s5, s1
|
|
; GFX7LESS-NEXT: v_readfirstlane_b32 s0, v1
|
|
; GFX7LESS-NEXT: v_readfirstlane_b32 s1, v2
|
|
; GFX7LESS-NEXT: v_mul_lo_u32 v1, s3, v0
|
|
; GFX7LESS-NEXT: v_mul_hi_u32 v2, s2, v0
|
|
; GFX7LESS-NEXT: v_mul_lo_u32 v0, s2, v0
|
|
; GFX7LESS-NEXT: v_add_i32_e32 v1, vcc, v2, v1
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v2, s1
|
|
; GFX7LESS-NEXT: v_add_i32_e32 v0, vcc, s0, v0
|
|
; GFX7LESS-NEXT: v_addc_u32_e32 v1, vcc, v2, v1, vcc
|
|
; GFX7LESS-NEXT: buffer_store_dwordx2 v[0:1], off, s[4:7], 0
|
|
; GFX7LESS-NEXT: s_endpgm
|
|
;
|
|
; GFX8-LABEL: add_i64_uniform:
|
|
; GFX8: ; %bb.0: ; %entry
|
|
; GFX8-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX8-NEXT: v_cmp_ne_u32_e64 s[6:7], 1, 0
|
|
; GFX8-NEXT: v_mbcnt_lo_u32_b32 v0, s6, 0
|
|
; GFX8-NEXT: v_mbcnt_hi_u32_b32 v0, s7, v0
|
|
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX8-NEXT: ; implicit-def: $vgpr1_vgpr2
|
|
; GFX8-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX8-NEXT: ; mask branch BB6_2
|
|
; GFX8-NEXT: s_cbranch_execz BB6_2
|
|
; GFX8-NEXT: BB6_1:
|
|
; GFX8-NEXT: s_bcnt1_i32_b64 s6, s[6:7]
|
|
; GFX8-NEXT: v_mov_b32_e32 v1, s6
|
|
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX8-NEXT: v_mul_hi_u32 v1, s2, v1
|
|
; GFX8-NEXT: s_mul_i32 s7, s3, s6
|
|
; GFX8-NEXT: s_mul_i32 s6, s2, s6
|
|
; GFX8-NEXT: v_mov_b32_e32 v3, local_var64@abs32@lo
|
|
; GFX8-NEXT: v_add_u32_e32 v2, vcc, s7, v1
|
|
; GFX8-NEXT: v_mov_b32_e32 v1, s6
|
|
; GFX8-NEXT: s_mov_b32 m0, -1
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: ds_add_rtn_u64 v[1:2], v3, v[1:2]
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_wbinvl1_vol
|
|
; GFX8-NEXT: BB6_2:
|
|
; GFX8-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX8-NEXT: s_mov_b32 s4, s0
|
|
; GFX8-NEXT: v_readfirstlane_b32 s0, v1
|
|
; GFX8-NEXT: v_mul_lo_u32 v1, s3, v0
|
|
; GFX8-NEXT: v_mul_hi_u32 v3, s2, v0
|
|
; GFX8-NEXT: v_mul_lo_u32 v0, s2, v0
|
|
; GFX8-NEXT: s_mov_b32 s5, s1
|
|
; GFX8-NEXT: v_readfirstlane_b32 s1, v2
|
|
; GFX8-NEXT: v_add_u32_e32 v1, vcc, v3, v1
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, s1
|
|
; GFX8-NEXT: v_add_u32_e32 v0, vcc, s0, v0
|
|
; GFX8-NEXT: s_mov_b32 s7, 0xf000
|
|
; GFX8-NEXT: s_mov_b32 s6, -1
|
|
; GFX8-NEXT: v_addc_u32_e32 v1, vcc, v2, v1, vcc
|
|
; GFX8-NEXT: buffer_store_dwordx2 v[0:1], off, s[4:7], 0
|
|
; GFX8-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: add_i64_uniform:
|
|
; GFX9: ; %bb.0: ; %entry
|
|
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX9-NEXT: v_cmp_ne_u32_e64 s[6:7], 1, 0
|
|
; GFX9-NEXT: v_mbcnt_lo_u32_b32 v0, s6, 0
|
|
; GFX9-NEXT: v_mbcnt_hi_u32_b32 v0, s7, v0
|
|
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX9-NEXT: ; implicit-def: $vgpr1_vgpr2
|
|
; GFX9-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX9-NEXT: ; mask branch BB6_2
|
|
; GFX9-NEXT: s_cbranch_execz BB6_2
|
|
; GFX9-NEXT: BB6_1:
|
|
; GFX9-NEXT: s_bcnt1_i32_b64 s6, s[6:7]
|
|
; GFX9-NEXT: v_mov_b32_e32 v1, s6
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: v_mul_hi_u32 v2, s2, v1
|
|
; GFX9-NEXT: s_mul_i32 s7, s3, s6
|
|
; GFX9-NEXT: s_mul_i32 s6, s2, s6
|
|
; GFX9-NEXT: v_mov_b32_e32 v1, s6
|
|
; GFX9-NEXT: v_add_u32_e32 v2, s7, v2
|
|
; GFX9-NEXT: v_mov_b32_e32 v3, local_var64@abs32@lo
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: ds_add_rtn_u64 v[1:2], v3, v[1:2]
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_wbinvl1_vol
|
|
; GFX9-NEXT: BB6_2:
|
|
; GFX9-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: v_mul_lo_u32 v3, s3, v0
|
|
; GFX9-NEXT: v_mul_hi_u32 v4, s2, v0
|
|
; GFX9-NEXT: v_mul_lo_u32 v0, s2, v0
|
|
; GFX9-NEXT: s_mov_b32 s4, s0
|
|
; GFX9-NEXT: v_readfirstlane_b32 s0, v1
|
|
; GFX9-NEXT: s_mov_b32 s5, s1
|
|
; GFX9-NEXT: v_readfirstlane_b32 s1, v2
|
|
; GFX9-NEXT: v_add_u32_e32 v1, v4, v3
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, s1
|
|
; GFX9-NEXT: v_add_co_u32_e32 v0, vcc, s0, v0
|
|
; GFX9-NEXT: s_mov_b32 s7, 0xf000
|
|
; GFX9-NEXT: s_mov_b32 s6, -1
|
|
; GFX9-NEXT: v_addc_co_u32_e32 v1, vcc, v2, v1, vcc
|
|
; GFX9-NEXT: buffer_store_dwordx2 v[0:1], off, s[4:7], 0
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX1064-LABEL: add_i64_uniform:
|
|
; GFX1064: ; %bb.0: ; %entry
|
|
; GFX1064-NEXT: v_cmp_ne_u32_e64 s[6:7], 1, 0
|
|
; GFX1064-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX1064-NEXT: ; implicit-def: $vgpr1_vgpr2
|
|
; GFX1064-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s6, 0
|
|
; GFX1064-NEXT: v_mbcnt_hi_u32_b32_e64 v0, s7, v0
|
|
; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX1064-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX1064-NEXT: ; mask branch BB6_2
|
|
; GFX1064-NEXT: s_cbranch_execz BB6_2
|
|
; GFX1064-NEXT: BB6_1:
|
|
; GFX1064-NEXT: s_bcnt1_i32_b64 s6, s[6:7]
|
|
; GFX1064-NEXT: v_mov_b32_e32 v3, local_var64@abs32@lo
|
|
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1064-NEXT: v_mul_hi_u32 v2, s2, s6
|
|
; GFX1064-NEXT: s_mul_i32 s7, s2, s6
|
|
; GFX1064-NEXT: s_mul_i32 s6, s3, s6
|
|
; GFX1064-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX1064-NEXT: v_add_nc_u32_e32 v2, s6, v2
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1064-NEXT: ds_add_rtn_u64 v[1:2], v3, v[1:2]
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_gl0_inv
|
|
; GFX1064-NEXT: buffer_gl1_inv
|
|
; GFX1064-NEXT: BB6_2:
|
|
; GFX1064-NEXT: v_nop
|
|
; GFX1064-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1064-NEXT: v_mul_lo_u32 v3, s3, v0
|
|
; GFX1064-NEXT: v_mul_hi_u32 v4, s2, v0
|
|
; GFX1064-NEXT: v_mul_lo_u32 v0, s2, v0
|
|
; GFX1064-NEXT: v_readfirstlane_b32 s4, v1
|
|
; GFX1064-NEXT: v_readfirstlane_b32 s5, v2
|
|
; GFX1064-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1064-NEXT: s_mov_b32 s2, -1
|
|
; GFX1064-NEXT: v_add_nc_u32_e32 v1, v4, v3
|
|
; GFX1064-NEXT: v_add_co_u32_e64 v0, vcc, s4, v0
|
|
; GFX1064-NEXT: v_add_co_ci_u32_e32 v1, vcc, s5, v1, vcc
|
|
; GFX1064-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX1064-NEXT: s_endpgm
|
|
;
|
|
; GFX1032-LABEL: add_i64_uniform:
|
|
; GFX1032: ; %bb.0: ; %entry
|
|
; GFX1032-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX1032-NEXT: v_cmp_ne_u32_e64 s5, 1, 0
|
|
; GFX1032-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX1032-NEXT: ; implicit-def: $vgpr1_vgpr2
|
|
; GFX1032-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s5, 0
|
|
; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v0
|
|
; GFX1032-NEXT: s_and_saveexec_b32 s4, vcc_lo
|
|
; GFX1032-NEXT: ; mask branch BB6_2
|
|
; GFX1032-NEXT: s_cbranch_execz BB6_2
|
|
; GFX1032-NEXT: BB6_1:
|
|
; GFX1032-NEXT: s_bcnt1_i32_b32 s5, s5
|
|
; GFX1032-NEXT: v_mov_b32_e32 v3, local_var64@abs32@lo
|
|
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1032-NEXT: v_mul_hi_u32 v2, s2, s5
|
|
; GFX1032-NEXT: s_mul_i32 s6, s2, s5
|
|
; GFX1032-NEXT: s_mul_i32 s5, s3, s5
|
|
; GFX1032-NEXT: v_mov_b32_e32 v1, s6
|
|
; GFX1032-NEXT: v_add_nc_u32_e32 v2, s5, v2
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1032-NEXT: ds_add_rtn_u64 v[1:2], v3, v[1:2]
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_gl0_inv
|
|
; GFX1032-NEXT: buffer_gl1_inv
|
|
; GFX1032-NEXT: BB6_2:
|
|
; GFX1032-NEXT: v_nop
|
|
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s4
|
|
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1032-NEXT: v_mul_lo_u32 v3, s3, v0
|
|
; GFX1032-NEXT: v_mul_hi_u32 v4, s2, v0
|
|
; GFX1032-NEXT: v_mul_lo_u32 v0, s2, v0
|
|
; GFX1032-NEXT: v_readfirstlane_b32 s4, v1
|
|
; GFX1032-NEXT: v_readfirstlane_b32 s5, v2
|
|
; GFX1032-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1032-NEXT: s_mov_b32 s2, -1
|
|
; GFX1032-NEXT: v_add_nc_u32_e32 v1, v4, v3
|
|
; GFX1032-NEXT: v_add_co_u32_e64 v0, vcc_lo, s4, v0
|
|
; GFX1032-NEXT: v_add_co_ci_u32_e32 v1, vcc_lo, s5, v1, vcc_lo
|
|
; GFX1032-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX1032-NEXT: s_endpgm
|
|
entry:
|
|
%old = atomicrmw add i64 addrspace(3)* @local_var64, i64 %additive acq_rel
|
|
store i64 %old, i64 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; GCN-NOT: v_mbcnt_lo_u32_b32
|
|
; GCN-NOT: v_mbcnt_hi_u32_b32
|
|
; GCN-NOT: s_bcnt1_i32_b64
|
|
define amdgpu_kernel void @add_i64_varying(i64 addrspace(1)* %out) {
|
|
;
|
|
;
|
|
; GFX7LESS-LABEL: add_i64_varying:
|
|
; GFX7LESS: ; %bb.0: ; %entry
|
|
; GFX7LESS-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
|
|
; GFX7LESS-NEXT: s_mov_b32 m0, -1
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: ds_add_rtn_u64 v[0:1], v2, v[0:1]
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: buffer_wbinvl1
|
|
; GFX7LESS-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX7LESS-NEXT: s_mov_b32 s2, -1
|
|
; GFX7LESS-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX7LESS-NEXT: s_endpgm
|
|
;
|
|
; GFX8-LABEL: add_i64_varying:
|
|
; GFX8: ; %bb.0: ; %entry
|
|
; GFX8-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
|
|
; GFX8-NEXT: s_mov_b32 m0, -1
|
|
; GFX8-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: ds_add_rtn_u64 v[0:1], v2, v[0:1]
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_wbinvl1_vol
|
|
; GFX8-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX8-NEXT: s_mov_b32 s2, -1
|
|
; GFX8-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX8-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: add_i64_varying:
|
|
; GFX9: ; %bb.0: ; %entry
|
|
; GFX9-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
|
|
; GFX9-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: ds_add_rtn_u64 v[0:1], v2, v[0:1]
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_wbinvl1_vol
|
|
; GFX9-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX9-NEXT: s_mov_b32 s2, -1
|
|
; GFX9-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX1064-LABEL: add_i64_varying:
|
|
; GFX1064: ; %bb.0: ; %entry
|
|
; GFX1064-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX1064-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
|
|
; GFX1064-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1064-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1064-NEXT: s_mov_b32 s2, -1
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1064-NEXT: ds_add_rtn_u64 v[0:1], v2, v[0:1]
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_gl0_inv
|
|
; GFX1064-NEXT: buffer_gl1_inv
|
|
; GFX1064-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX1064-NEXT: s_endpgm
|
|
;
|
|
; GFX1032-LABEL: add_i64_varying:
|
|
; GFX1032: ; %bb.0: ; %entry
|
|
; GFX1032-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX1032-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
|
|
; GFX1032-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1032-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1032-NEXT: s_mov_b32 s2, -1
|
|
; GFX1032-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1032-NEXT: ds_add_rtn_u64 v[0:1], v2, v[0:1]
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_gl0_inv
|
|
; GFX1032-NEXT: buffer_gl1_inv
|
|
; GFX1032-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX1032-NEXT: s_endpgm
|
|
entry:
|
|
%lane = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%zext = zext i32 %lane to i64
|
|
%old = atomicrmw add i64 addrspace(3)* @local_var64, i64 %zext acq_rel
|
|
store i64 %old, i64 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @sub_i32_constant(i32 addrspace(1)* %out) {
|
|
;
|
|
;
|
|
; GFX7LESS-LABEL: sub_i32_constant:
|
|
; GFX7LESS: ; %bb.0: ; %entry
|
|
; GFX7LESS-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; GFX7LESS-NEXT: v_cmp_ne_u32_e64 s[4:5], 1, 0
|
|
; GFX7LESS-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s4, 0
|
|
; GFX7LESS-NEXT: v_mbcnt_hi_u32_b32_e32 v0, s5, v0
|
|
; GFX7LESS-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX7LESS-NEXT: ; implicit-def: $vgpr1
|
|
; GFX7LESS-NEXT: s_and_saveexec_b64 s[2:3], vcc
|
|
; GFX7LESS-NEXT: ; mask branch BB8_2
|
|
; GFX7LESS-NEXT: s_cbranch_execz BB8_2
|
|
; GFX7LESS-NEXT: BB8_1:
|
|
; GFX7LESS-NEXT: s_bcnt1_i32_b64 s4, s[4:5]
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v1, local_var32@abs32@lo
|
|
; GFX7LESS-NEXT: v_mul_u32_u24_e64 v2, s4, 5
|
|
; GFX7LESS-NEXT: s_mov_b32 m0, -1
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: ds_sub_rtn_u32 v1, v1, v2
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: buffer_wbinvl1
|
|
; GFX7LESS-NEXT: BB8_2:
|
|
; GFX7LESS-NEXT: s_or_b64 exec, exec, s[2:3]
|
|
; GFX7LESS-NEXT: v_readfirstlane_b32 s2, v1
|
|
; GFX7LESS-NEXT: v_mul_u32_u24_e32 v0, 5, v0
|
|
; GFX7LESS-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX7LESS-NEXT: v_sub_i32_e32 v0, vcc, s2, v0
|
|
; GFX7LESS-NEXT: s_mov_b32 s2, -1
|
|
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7LESS-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX7LESS-NEXT: s_endpgm
|
|
;
|
|
; GFX8-LABEL: sub_i32_constant:
|
|
; GFX8: ; %bb.0: ; %entry
|
|
; GFX8-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX8-NEXT: v_cmp_ne_u32_e64 s[4:5], 1, 0
|
|
; GFX8-NEXT: v_mbcnt_lo_u32_b32 v0, s4, 0
|
|
; GFX8-NEXT: v_mbcnt_hi_u32_b32 v0, s5, v0
|
|
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX8-NEXT: ; implicit-def: $vgpr1
|
|
; GFX8-NEXT: s_and_saveexec_b64 s[2:3], vcc
|
|
; GFX8-NEXT: ; mask branch BB8_2
|
|
; GFX8-NEXT: s_cbranch_execz BB8_2
|
|
; GFX8-NEXT: BB8_1:
|
|
; GFX8-NEXT: s_bcnt1_i32_b64 s4, s[4:5]
|
|
; GFX8-NEXT: v_mul_u32_u24_e64 v1, s4, 5
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, local_var32@abs32@lo
|
|
; GFX8-NEXT: s_mov_b32 m0, -1
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: ds_sub_rtn_u32 v1, v2, v1
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_wbinvl1_vol
|
|
; GFX8-NEXT: BB8_2:
|
|
; GFX8-NEXT: s_or_b64 exec, exec, s[2:3]
|
|
; GFX8-NEXT: v_readfirstlane_b32 s2, v1
|
|
; GFX8-NEXT: v_mul_u32_u24_e32 v0, 5, v0
|
|
; GFX8-NEXT: v_sub_u32_e32 v0, vcc, s2, v0
|
|
; GFX8-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX8-NEXT: s_mov_b32 s2, -1
|
|
; GFX8-NEXT: s_nop 0
|
|
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX8-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: sub_i32_constant:
|
|
; GFX9: ; %bb.0: ; %entry
|
|
; GFX9-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX9-NEXT: v_cmp_ne_u32_e64 s[4:5], 1, 0
|
|
; GFX9-NEXT: v_mbcnt_lo_u32_b32 v0, s4, 0
|
|
; GFX9-NEXT: v_mbcnt_hi_u32_b32 v0, s5, v0
|
|
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX9-NEXT: ; implicit-def: $vgpr1
|
|
; GFX9-NEXT: s_and_saveexec_b64 s[2:3], vcc
|
|
; GFX9-NEXT: ; mask branch BB8_2
|
|
; GFX9-NEXT: s_cbranch_execz BB8_2
|
|
; GFX9-NEXT: BB8_1:
|
|
; GFX9-NEXT: s_bcnt1_i32_b64 s4, s[4:5]
|
|
; GFX9-NEXT: v_mul_u32_u24_e64 v1, s4, 5
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, local_var32@abs32@lo
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: ds_sub_rtn_u32 v1, v2, v1
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_wbinvl1_vol
|
|
; GFX9-NEXT: BB8_2:
|
|
; GFX9-NEXT: s_or_b64 exec, exec, s[2:3]
|
|
; GFX9-NEXT: v_readfirstlane_b32 s2, v1
|
|
; GFX9-NEXT: v_mul_u32_u24_e32 v0, 5, v0
|
|
; GFX9-NEXT: v_sub_u32_e32 v0, s2, v0
|
|
; GFX9-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX9-NEXT: s_mov_b32 s2, -1
|
|
; GFX9-NEXT: s_nop 0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX1064-LABEL: sub_i32_constant:
|
|
; GFX1064: ; %bb.0: ; %entry
|
|
; GFX1064-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX1064-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1064-NEXT: ; implicit-def: $vgpr1
|
|
; GFX1064-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s2, 0
|
|
; GFX1064-NEXT: v_mbcnt_hi_u32_b32_e64 v0, s3, v0
|
|
; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX1064-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX1064-NEXT: ; mask branch BB8_2
|
|
; GFX1064-NEXT: s_cbranch_execz BB8_2
|
|
; GFX1064-NEXT: BB8_1:
|
|
; GFX1064-NEXT: s_bcnt1_i32_b64 s2, s[2:3]
|
|
; GFX1064-NEXT: v_mov_b32_e32 v2, local_var32@abs32@lo
|
|
; GFX1064-NEXT: v_mul_u32_u24_e64 v1, s2, 5
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1064-NEXT: ds_sub_rtn_u32 v1, v2, v1
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_gl0_inv
|
|
; GFX1064-NEXT: buffer_gl1_inv
|
|
; GFX1064-NEXT: BB8_2:
|
|
; GFX1064-NEXT: v_nop
|
|
; GFX1064-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX1064-NEXT: v_readfirstlane_b32 s2, v1
|
|
; GFX1064-NEXT: v_mul_u32_u24_e32 v0, 5, v0
|
|
; GFX1064-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1064-NEXT: v_sub_nc_u32_e32 v0, s2, v0
|
|
; GFX1064-NEXT: s_mov_b32 s2, -1
|
|
; GFX1064-NEXT: s_nop 0
|
|
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX1064-NEXT: s_endpgm
|
|
;
|
|
; GFX1032-LABEL: sub_i32_constant:
|
|
; GFX1032: ; %bb.0: ; %entry
|
|
; GFX1032-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1032-NEXT: v_cmp_ne_u32_e64 s3, 1, 0
|
|
; GFX1032-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX1032-NEXT: ; implicit-def: $vgpr1
|
|
; GFX1032-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s3, 0
|
|
; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v0
|
|
; GFX1032-NEXT: s_and_saveexec_b32 s2, vcc_lo
|
|
; GFX1032-NEXT: ; mask branch BB8_2
|
|
; GFX1032-NEXT: s_cbranch_execz BB8_2
|
|
; GFX1032-NEXT: BB8_1:
|
|
; GFX1032-NEXT: s_bcnt1_i32_b32 s3, s3
|
|
; GFX1032-NEXT: v_mov_b32_e32 v2, local_var32@abs32@lo
|
|
; GFX1032-NEXT: v_mul_u32_u24_e64 v1, s3, 5
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1032-NEXT: ds_sub_rtn_u32 v1, v2, v1
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_gl0_inv
|
|
; GFX1032-NEXT: buffer_gl1_inv
|
|
; GFX1032-NEXT: BB8_2:
|
|
; GFX1032-NEXT: v_nop
|
|
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s2
|
|
; GFX1032-NEXT: v_readfirstlane_b32 s2, v1
|
|
; GFX1032-NEXT: v_mul_u32_u24_e32 v0, 5, v0
|
|
; GFX1032-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1032-NEXT: v_sub_nc_u32_e32 v0, s2, v0
|
|
; GFX1032-NEXT: s_mov_b32 s2, -1
|
|
; GFX1032-NEXT: s_nop 0
|
|
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX1032-NEXT: s_endpgm
|
|
entry:
|
|
%old = atomicrmw sub i32 addrspace(3)* @local_var32, i32 5 acq_rel
|
|
store i32 %old, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @sub_i32_uniform(i32 addrspace(1)* %out, i32 %subitive) {
|
|
;
|
|
;
|
|
; GFX7LESS-LABEL: sub_i32_uniform:
|
|
; GFX7LESS: ; %bb.0: ; %entry
|
|
; GFX7LESS-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x9
|
|
; GFX7LESS-NEXT: s_load_dword s2, s[0:1], 0xb
|
|
; GFX7LESS-NEXT: v_cmp_ne_u32_e64 s[6:7], 1, 0
|
|
; GFX7LESS-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s6, 0
|
|
; GFX7LESS-NEXT: v_mbcnt_hi_u32_b32_e32 v0, s7, v0
|
|
; GFX7LESS-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX7LESS-NEXT: ; implicit-def: $vgpr1
|
|
; GFX7LESS-NEXT: s_and_saveexec_b64 s[0:1], vcc
|
|
; GFX7LESS-NEXT: ; mask branch BB9_2
|
|
; GFX7LESS-NEXT: s_cbranch_execz BB9_2
|
|
; GFX7LESS-NEXT: BB9_1:
|
|
; GFX7LESS-NEXT: s_bcnt1_i32_b64 s3, s[6:7]
|
|
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7LESS-NEXT: s_mul_i32 s3, s2, s3
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v1, local_var32@abs32@lo
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v2, s3
|
|
; GFX7LESS-NEXT: s_mov_b32 m0, -1
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: ds_sub_rtn_u32 v1, v1, v2
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: buffer_wbinvl1
|
|
; GFX7LESS-NEXT: BB9_2:
|
|
; GFX7LESS-NEXT: s_or_b64 exec, exec, s[0:1]
|
|
; GFX7LESS-NEXT: v_readfirstlane_b32 s0, v1
|
|
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7LESS-NEXT: v_mul_lo_u32 v0, s2, v0
|
|
; GFX7LESS-NEXT: s_mov_b32 s7, 0xf000
|
|
; GFX7LESS-NEXT: v_sub_i32_e32 v0, vcc, s0, v0
|
|
; GFX7LESS-NEXT: s_mov_b32 s6, -1
|
|
; GFX7LESS-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; GFX7LESS-NEXT: s_endpgm
|
|
;
|
|
; GFX8-LABEL: sub_i32_uniform:
|
|
; GFX8: ; %bb.0: ; %entry
|
|
; GFX8-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x24
|
|
; GFX8-NEXT: s_load_dword s0, s[0:1], 0x2c
|
|
; GFX8-NEXT: v_cmp_ne_u32_e64 s[6:7], 1, 0
|
|
; GFX8-NEXT: v_mbcnt_lo_u32_b32 v0, s6, 0
|
|
; GFX8-NEXT: v_mbcnt_hi_u32_b32 v0, s7, v0
|
|
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX8-NEXT: ; implicit-def: $vgpr1
|
|
; GFX8-NEXT: s_and_saveexec_b64 s[2:3], vcc
|
|
; GFX8-NEXT: ; mask branch BB9_2
|
|
; GFX8-NEXT: s_cbranch_execz BB9_2
|
|
; GFX8-NEXT: BB9_1:
|
|
; GFX8-NEXT: s_bcnt1_i32_b64 s1, s[6:7]
|
|
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX8-NEXT: s_mul_i32 s1, s0, s1
|
|
; GFX8-NEXT: v_mov_b32_e32 v1, local_var32@abs32@lo
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, s1
|
|
; GFX8-NEXT: s_mov_b32 m0, -1
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: ds_sub_rtn_u32 v1, v1, v2
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_wbinvl1_vol
|
|
; GFX8-NEXT: BB9_2:
|
|
; GFX8-NEXT: s_or_b64 exec, exec, s[2:3]
|
|
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX8-NEXT: v_mul_lo_u32 v0, s0, v0
|
|
; GFX8-NEXT: v_readfirstlane_b32 s0, v1
|
|
; GFX8-NEXT: s_mov_b32 s7, 0xf000
|
|
; GFX8-NEXT: s_mov_b32 s6, -1
|
|
; GFX8-NEXT: v_sub_u32_e32 v0, vcc, s0, v0
|
|
; GFX8-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; GFX8-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: sub_i32_uniform:
|
|
; GFX9: ; %bb.0: ; %entry
|
|
; GFX9-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x24
|
|
; GFX9-NEXT: s_load_dword s0, s[0:1], 0x2c
|
|
; GFX9-NEXT: v_cmp_ne_u32_e64 s[6:7], 1, 0
|
|
; GFX9-NEXT: v_mbcnt_lo_u32_b32 v0, s6, 0
|
|
; GFX9-NEXT: v_mbcnt_hi_u32_b32 v0, s7, v0
|
|
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX9-NEXT: ; implicit-def: $vgpr1
|
|
; GFX9-NEXT: s_and_saveexec_b64 s[2:3], vcc
|
|
; GFX9-NEXT: ; mask branch BB9_2
|
|
; GFX9-NEXT: s_cbranch_execz BB9_2
|
|
; GFX9-NEXT: BB9_1:
|
|
; GFX9-NEXT: s_bcnt1_i32_b64 s1, s[6:7]
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: s_mul_i32 s1, s0, s1
|
|
; GFX9-NEXT: v_mov_b32_e32 v1, local_var32@abs32@lo
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, s1
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: ds_sub_rtn_u32 v1, v1, v2
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_wbinvl1_vol
|
|
; GFX9-NEXT: BB9_2:
|
|
; GFX9-NEXT: s_or_b64 exec, exec, s[2:3]
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: v_mul_lo_u32 v0, s0, v0
|
|
; GFX9-NEXT: v_readfirstlane_b32 s0, v1
|
|
; GFX9-NEXT: s_mov_b32 s7, 0xf000
|
|
; GFX9-NEXT: s_mov_b32 s6, -1
|
|
; GFX9-NEXT: v_sub_u32_e32 v0, s0, v0
|
|
; GFX9-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX1064-LABEL: sub_i32_uniform:
|
|
; GFX1064: ; %bb.0: ; %entry
|
|
; GFX1064-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x24
|
|
; GFX1064-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX1064-NEXT: s_load_dword s0, s[0:1], 0x2c
|
|
; GFX1064-NEXT: ; implicit-def: $vgpr1
|
|
; GFX1064-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s2, 0
|
|
; GFX1064-NEXT: v_mbcnt_hi_u32_b32_e64 v0, s3, v0
|
|
; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX1064-NEXT: s_and_saveexec_b64 s[6:7], vcc
|
|
; GFX1064-NEXT: ; mask branch BB9_2
|
|
; GFX1064-NEXT: s_cbranch_execz BB9_2
|
|
; GFX1064-NEXT: BB9_1:
|
|
; GFX1064-NEXT: s_bcnt1_i32_b64 s1, s[2:3]
|
|
; GFX1064-NEXT: v_mov_b32_e32 v1, local_var32@abs32@lo
|
|
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1064-NEXT: s_mul_i32 s1, s0, s1
|
|
; GFX1064-NEXT: v_mov_b32_e32 v2, s1
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1064-NEXT: ds_sub_rtn_u32 v1, v1, v2
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_gl0_inv
|
|
; GFX1064-NEXT: buffer_gl1_inv
|
|
; GFX1064-NEXT: BB9_2:
|
|
; GFX1064-NEXT: v_nop
|
|
; GFX1064-NEXT: s_or_b64 exec, exec, s[6:7]
|
|
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1064-NEXT: v_mul_lo_u32 v0, s0, v0
|
|
; GFX1064-NEXT: v_readfirstlane_b32 s0, v1
|
|
; GFX1064-NEXT: s_mov_b32 s7, 0x31016000
|
|
; GFX1064-NEXT: s_mov_b32 s6, -1
|
|
; GFX1064-NEXT: v_sub_nc_u32_e32 v0, s0, v0
|
|
; GFX1064-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; GFX1064-NEXT: s_endpgm
|
|
;
|
|
; GFX1032-LABEL: sub_i32_uniform:
|
|
; GFX1032: ; %bb.0: ; %entry
|
|
; GFX1032-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x24
|
|
; GFX1032-NEXT: s_load_dword s0, s[0:1], 0x2c
|
|
; GFX1032-NEXT: v_cmp_ne_u32_e64 s2, 1, 0
|
|
; GFX1032-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX1032-NEXT: ; implicit-def: $vgpr1
|
|
; GFX1032-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s2, 0
|
|
; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v0
|
|
; GFX1032-NEXT: s_and_saveexec_b32 s1, vcc_lo
|
|
; GFX1032-NEXT: ; mask branch BB9_2
|
|
; GFX1032-NEXT: s_cbranch_execz BB9_2
|
|
; GFX1032-NEXT: BB9_1:
|
|
; GFX1032-NEXT: s_bcnt1_i32_b32 s2, s2
|
|
; GFX1032-NEXT: v_mov_b32_e32 v1, local_var32@abs32@lo
|
|
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1032-NEXT: s_mul_i32 s2, s0, s2
|
|
; GFX1032-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1032-NEXT: ds_sub_rtn_u32 v1, v1, v2
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_gl0_inv
|
|
; GFX1032-NEXT: buffer_gl1_inv
|
|
; GFX1032-NEXT: BB9_2:
|
|
; GFX1032-NEXT: v_nop
|
|
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s1
|
|
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1032-NEXT: v_mul_lo_u32 v0, s0, v0
|
|
; GFX1032-NEXT: v_readfirstlane_b32 s0, v1
|
|
; GFX1032-NEXT: s_mov_b32 s7, 0x31016000
|
|
; GFX1032-NEXT: s_mov_b32 s6, -1
|
|
; GFX1032-NEXT: v_sub_nc_u32_e32 v0, s0, v0
|
|
; GFX1032-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; GFX1032-NEXT: s_endpgm
|
|
entry:
|
|
%old = atomicrmw sub i32 addrspace(3)* @local_var32, i32 %subitive acq_rel
|
|
store i32 %old, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; GFX7LESS-NOT: v_mbcnt_lo_u32_b32
|
|
; GFX7LESS-NOT: v_mbcnt_hi_u32_b32
|
|
; GFX7LESS-NOT: s_bcnt1_i32_b64
|
|
; DPPCOMB: v_add_u32_dpp
|
|
; DPPCOMB: v_add_u32_dpp
|
|
; GFX8MORE32: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 31
|
|
; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
|
|
; GFX8MORE: ds_sub_rtn_u32 v{{[0-9]+}}, v{{[0-9]+}}, v[[value]]
|
|
define amdgpu_kernel void @sub_i32_varying(i32 addrspace(1)* %out) {
|
|
;
|
|
;
|
|
; GFX7LESS-LABEL: sub_i32_varying:
|
|
; GFX7LESS: ; %bb.0: ; %entry
|
|
; GFX7LESS-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v1, local_var32@abs32@lo
|
|
; GFX7LESS-NEXT: s_mov_b32 m0, -1
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: ds_sub_rtn_u32 v0, v1, v0
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: buffer_wbinvl1
|
|
; GFX7LESS-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX7LESS-NEXT: s_mov_b32 s2, -1
|
|
; GFX7LESS-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX7LESS-NEXT: s_endpgm
|
|
;
|
|
; GFX8-LABEL: sub_i32_varying:
|
|
; GFX8: ; %bb.0: ; %entry
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX8-NEXT: s_or_saveexec_b64 s[2:3], -1
|
|
; GFX8-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX8-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX8-NEXT: s_mov_b64 exec, s[2:3]
|
|
; GFX8-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX8-NEXT: v_mbcnt_lo_u32_b32 v0, s2, 0
|
|
; GFX8-NEXT: v_mbcnt_hi_u32_b32 v0, s3, v0
|
|
; GFX8-NEXT: s_not_b64 exec, exec
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX8-NEXT: s_not_b64 exec, exec
|
|
; GFX8-NEXT: s_or_saveexec_b64 s[4:5], -1
|
|
; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_bcast:31 row_mask:0xc bank_mask:0xf
|
|
; GFX8-NEXT: v_readlane_b32 s2, v2, 63
|
|
; GFX8-NEXT: s_nop 0
|
|
; GFX8-NEXT: v_mov_b32_dpp v1, v2 wave_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX8-NEXT: s_mov_b64 exec, s[4:5]
|
|
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX8-NEXT: ; implicit-def: $vgpr0
|
|
; GFX8-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX8-NEXT: ; mask branch BB10_2
|
|
; GFX8-NEXT: s_cbranch_execz BB10_2
|
|
; GFX8-NEXT: BB10_1:
|
|
; GFX8-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX8-NEXT: v_mov_b32_e32 v3, s2
|
|
; GFX8-NEXT: s_mov_b32 m0, -1
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: ds_sub_rtn_u32 v0, v0, v3
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_wbinvl1_vol
|
|
; GFX8-NEXT: BB10_2:
|
|
; GFX8-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX8-NEXT: v_readfirstlane_b32 s2, v0
|
|
; GFX8-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX8-NEXT: v_sub_u32_e32 v0, vcc, s2, v0
|
|
; GFX8-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX8-NEXT: s_mov_b32 s2, -1
|
|
; GFX8-NEXT: s_nop 0
|
|
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX8-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: sub_i32_varying:
|
|
; GFX9: ; %bb.0: ; %entry
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX9-NEXT: s_or_saveexec_b64 s[2:3], -1
|
|
; GFX9-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX9-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX9-NEXT: s_mov_b64 exec, s[2:3]
|
|
; GFX9-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX9-NEXT: v_mbcnt_lo_u32_b32 v0, s2, 0
|
|
; GFX9-NEXT: v_mbcnt_hi_u32_b32 v0, s3, v0
|
|
; GFX9-NEXT: s_not_b64 exec, exec
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX9-NEXT: s_not_b64 exec, exec
|
|
; GFX9-NEXT: s_or_saveexec_b64 s[4:5], -1
|
|
; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_bcast:31 row_mask:0xc bank_mask:0xf
|
|
; GFX9-NEXT: v_readlane_b32 s2, v2, 63
|
|
; GFX9-NEXT: s_nop 0
|
|
; GFX9-NEXT: v_mov_b32_dpp v1, v2 wave_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX9-NEXT: s_mov_b64 exec, s[4:5]
|
|
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX9-NEXT: ; implicit-def: $vgpr0
|
|
; GFX9-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX9-NEXT: ; mask branch BB10_2
|
|
; GFX9-NEXT: s_cbranch_execz BB10_2
|
|
; GFX9-NEXT: BB10_1:
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX9-NEXT: v_mov_b32_e32 v3, s2
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: ds_sub_rtn_u32 v0, v0, v3
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_wbinvl1_vol
|
|
; GFX9-NEXT: BB10_2:
|
|
; GFX9-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX9-NEXT: v_readfirstlane_b32 s2, v0
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX9-NEXT: v_sub_u32_e32 v0, s2, v0
|
|
; GFX9-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX9-NEXT: s_mov_b32 s2, -1
|
|
; GFX9-NEXT: s_nop 0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX1064-LABEL: sub_i32_varying:
|
|
; GFX1064: ; %bb.0: ; %entry
|
|
; GFX1064-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX1064-NEXT: s_or_saveexec_b64 s[2:3], -1
|
|
; GFX1064-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1064-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX1064-NEXT: s_mov_b64 exec, s[2:3]
|
|
; GFX1064-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX1064-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s2, 0
|
|
; GFX1064-NEXT: v_mbcnt_hi_u32_b32_e64 v0, s3, v0
|
|
; GFX1064-NEXT: s_not_b64 exec, exec
|
|
; GFX1064-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX1064-NEXT: s_not_b64 exec, exec
|
|
; GFX1064-NEXT: s_or_saveexec_b64 s[4:5], -1
|
|
; GFX1064-NEXT: v_add_nc_u32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1064-NEXT: v_add_nc_u32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1064-NEXT: v_add_nc_u32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1064-NEXT: v_add_nc_u32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1064-NEXT: v_mov_b32_e32 v3, v2
|
|
; GFX1064-NEXT: v_permlanex16_b32 v3, v3, -1, -1
|
|
; GFX1064-NEXT: v_add_nc_u32_dpp v2, v3, v2 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf
|
|
; GFX1064-NEXT: v_readlane_b32 s2, v2, 31
|
|
; GFX1064-NEXT: v_mov_b32_e32 v3, s2
|
|
; GFX1064-NEXT: v_add_nc_u32_dpp v2, v3, v2 quad_perm:[0,1,2,3] row_mask:0xc bank_mask:0xf
|
|
; GFX1064-NEXT: v_readlane_b32 s2, v2, 15
|
|
; GFX1064-NEXT: v_mov_b32_dpp v1, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX1064-NEXT: v_readlane_b32 s3, v2, 31
|
|
; GFX1064-NEXT: v_readlane_b32 s6, v2, 47
|
|
; GFX1064-NEXT: v_writelane_b32 v1, s2, 16
|
|
; GFX1064-NEXT: s_mov_b32 s2, -1
|
|
; GFX1064-NEXT: v_writelane_b32 v1, s3, 32
|
|
; GFX1064-NEXT: v_readlane_b32 s3, v2, 63
|
|
; GFX1064-NEXT: v_writelane_b32 v1, s6, 48
|
|
; GFX1064-NEXT: s_mov_b64 exec, s[4:5]
|
|
; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX1064-NEXT: ; implicit-def: $vgpr0
|
|
; GFX1064-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX1064-NEXT: ; mask branch BB10_2
|
|
; GFX1064-NEXT: s_cbranch_execz BB10_2
|
|
; GFX1064-NEXT: BB10_1:
|
|
; GFX1064-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX1064-NEXT: v_mov_b32_e32 v7, s3
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1064-NEXT: ds_sub_rtn_u32 v0, v0, v7
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_gl0_inv
|
|
; GFX1064-NEXT: buffer_gl1_inv
|
|
; GFX1064-NEXT: BB10_2:
|
|
; GFX1064-NEXT: v_nop
|
|
; GFX1064-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX1064-NEXT: v_readfirstlane_b32 s3, v0
|
|
; GFX1064-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX1064-NEXT: v_sub_nc_u32_e32 v0, s3, v0
|
|
; GFX1064-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1064-NEXT: s_nop 1
|
|
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX1064-NEXT: s_endpgm
|
|
;
|
|
; GFX1032-LABEL: sub_i32_varying:
|
|
; GFX1032: ; %bb.0: ; %entry
|
|
; GFX1032-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX1032-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX1032-NEXT: s_or_saveexec_b32 s2, -1
|
|
; GFX1032-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1032-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX1032-NEXT: s_mov_b32 exec_lo, s2
|
|
; GFX1032-NEXT: v_cmp_ne_u32_e64 s2, 1, 0
|
|
; GFX1032-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s2, 0
|
|
; GFX1032-NEXT: s_not_b32 exec_lo, exec_lo
|
|
; GFX1032-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX1032-NEXT: s_not_b32 exec_lo, exec_lo
|
|
; GFX1032-NEXT: s_or_saveexec_b32 s4, -1
|
|
; GFX1032-NEXT: v_add_nc_u32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1032-NEXT: s_mov_b32 s2, -1
|
|
; GFX1032-NEXT: v_add_nc_u32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1032-NEXT: v_add_nc_u32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1032-NEXT: v_add_nc_u32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1032-NEXT: v_mov_b32_e32 v3, v2
|
|
; GFX1032-NEXT: v_permlanex16_b32 v3, v3, -1, -1
|
|
; GFX1032-NEXT: v_add_nc_u32_dpp v2, v3, v2 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf
|
|
; GFX1032-NEXT: v_readlane_b32 s3, v2, 31
|
|
; GFX1032-NEXT: v_mov_b32_dpp v1, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX1032-NEXT: v_readlane_b32 s5, v2, 15
|
|
; GFX1032-NEXT: v_writelane_b32 v1, s5, 16
|
|
; GFX1032-NEXT: s_mov_b32 exec_lo, s4
|
|
; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v0
|
|
; GFX1032-NEXT: ; implicit-def: $vgpr0
|
|
; GFX1032-NEXT: s_and_saveexec_b32 s4, vcc_lo
|
|
; GFX1032-NEXT: ; mask branch BB10_2
|
|
; GFX1032-NEXT: s_cbranch_execz BB10_2
|
|
; GFX1032-NEXT: BB10_1:
|
|
; GFX1032-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX1032-NEXT: v_mov_b32_e32 v7, s3
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1032-NEXT: ds_sub_rtn_u32 v0, v0, v7
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_gl0_inv
|
|
; GFX1032-NEXT: buffer_gl1_inv
|
|
; GFX1032-NEXT: BB10_2:
|
|
; GFX1032-NEXT: v_nop
|
|
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s4
|
|
; GFX1032-NEXT: v_readfirstlane_b32 s3, v0
|
|
; GFX1032-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX1032-NEXT: v_sub_nc_u32_e32 v0, s3, v0
|
|
; GFX1032-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1032-NEXT: s_nop 1
|
|
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX1032-NEXT: s_endpgm
|
|
entry:
|
|
%lane = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%old = atomicrmw sub i32 addrspace(3)* @local_var32, i32 %lane acq_rel
|
|
store i32 %old, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @sub_i64_constant(i64 addrspace(1)* %out) {
|
|
;
|
|
;
|
|
; GFX7LESS-LABEL: sub_i64_constant:
|
|
; GFX7LESS: ; %bb.0: ; %entry
|
|
; GFX7LESS-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; GFX7LESS-NEXT: v_cmp_ne_u32_e64 s[4:5], 1, 0
|
|
; GFX7LESS-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s4, 0
|
|
; GFX7LESS-NEXT: v_mbcnt_hi_u32_b32_e32 v0, s5, v0
|
|
; GFX7LESS-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX7LESS-NEXT: ; implicit-def: $vgpr1_vgpr2
|
|
; GFX7LESS-NEXT: s_and_saveexec_b64 s[2:3], vcc
|
|
; GFX7LESS-NEXT: ; mask branch BB11_2
|
|
; GFX7LESS-NEXT: s_cbranch_execz BB11_2
|
|
; GFX7LESS-NEXT: BB11_1:
|
|
; GFX7LESS-NEXT: s_bcnt1_i32_b64 s4, s[4:5]
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v3, local_var64@abs32@lo
|
|
; GFX7LESS-NEXT: v_mul_hi_u32_u24_e64 v2, s4, 5
|
|
; GFX7LESS-NEXT: v_mul_u32_u24_e64 v1, s4, 5
|
|
; GFX7LESS-NEXT: s_mov_b32 m0, -1
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: ds_sub_rtn_u64 v[1:2], v3, v[1:2]
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: buffer_wbinvl1
|
|
; GFX7LESS-NEXT: BB11_2:
|
|
; GFX7LESS-NEXT: s_or_b64 exec, exec, s[2:3]
|
|
; GFX7LESS-NEXT: v_readfirstlane_b32 s2, v1
|
|
; GFX7LESS-NEXT: v_readfirstlane_b32 s4, v2
|
|
; GFX7LESS-NEXT: v_mul_hi_u32_u24_e32 v1, 5, v0
|
|
; GFX7LESS-NEXT: v_mul_u32_u24_e32 v0, 5, v0
|
|
; GFX7LESS-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v2, s4
|
|
; GFX7LESS-NEXT: v_sub_i32_e32 v0, vcc, s2, v0
|
|
; GFX7LESS-NEXT: v_subb_u32_e32 v1, vcc, v2, v1, vcc
|
|
; GFX7LESS-NEXT: s_mov_b32 s2, -1
|
|
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7LESS-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX7LESS-NEXT: s_endpgm
|
|
;
|
|
; GFX8-LABEL: sub_i64_constant:
|
|
; GFX8: ; %bb.0: ; %entry
|
|
; GFX8-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX8-NEXT: v_cmp_ne_u32_e64 s[4:5], 1, 0
|
|
; GFX8-NEXT: v_mbcnt_lo_u32_b32 v0, s4, 0
|
|
; GFX8-NEXT: v_mbcnt_hi_u32_b32 v0, s5, v0
|
|
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX8-NEXT: ; implicit-def: $vgpr1_vgpr2
|
|
; GFX8-NEXT: s_and_saveexec_b64 s[2:3], vcc
|
|
; GFX8-NEXT: ; mask branch BB11_2
|
|
; GFX8-NEXT: s_cbranch_execz BB11_2
|
|
; GFX8-NEXT: BB11_1:
|
|
; GFX8-NEXT: s_bcnt1_i32_b64 s4, s[4:5]
|
|
; GFX8-NEXT: v_mul_hi_u32_u24_e64 v2, s4, 5
|
|
; GFX8-NEXT: v_mul_u32_u24_e64 v1, s4, 5
|
|
; GFX8-NEXT: v_mov_b32_e32 v3, local_var64@abs32@lo
|
|
; GFX8-NEXT: s_mov_b32 m0, -1
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: ds_sub_rtn_u64 v[1:2], v3, v[1:2]
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_wbinvl1_vol
|
|
; GFX8-NEXT: BB11_2:
|
|
; GFX8-NEXT: s_or_b64 exec, exec, s[2:3]
|
|
; GFX8-NEXT: v_readfirstlane_b32 s3, v2
|
|
; GFX8-NEXT: v_readfirstlane_b32 s2, v1
|
|
; GFX8-NEXT: v_mul_hi_u32_u24_e32 v1, 5, v0
|
|
; GFX8-NEXT: v_mul_u32_u24_e32 v0, 5, v0
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, s3
|
|
; GFX8-NEXT: v_sub_u32_e32 v0, vcc, s2, v0
|
|
; GFX8-NEXT: v_subb_u32_e32 v1, vcc, v2, v1, vcc
|
|
; GFX8-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX8-NEXT: s_mov_b32 s2, -1
|
|
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX8-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: sub_i64_constant:
|
|
; GFX9: ; %bb.0: ; %entry
|
|
; GFX9-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX9-NEXT: v_cmp_ne_u32_e64 s[4:5], 1, 0
|
|
; GFX9-NEXT: v_mbcnt_lo_u32_b32 v0, s4, 0
|
|
; GFX9-NEXT: v_mbcnt_hi_u32_b32 v0, s5, v0
|
|
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX9-NEXT: ; implicit-def: $vgpr1_vgpr2
|
|
; GFX9-NEXT: s_and_saveexec_b64 s[2:3], vcc
|
|
; GFX9-NEXT: ; mask branch BB11_2
|
|
; GFX9-NEXT: s_cbranch_execz BB11_2
|
|
; GFX9-NEXT: BB11_1:
|
|
; GFX9-NEXT: s_bcnt1_i32_b64 s4, s[4:5]
|
|
; GFX9-NEXT: v_mul_hi_u32_u24_e64 v2, s4, 5
|
|
; GFX9-NEXT: v_mul_u32_u24_e64 v1, s4, 5
|
|
; GFX9-NEXT: v_mov_b32_e32 v3, local_var64@abs32@lo
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: ds_sub_rtn_u64 v[1:2], v3, v[1:2]
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_wbinvl1_vol
|
|
; GFX9-NEXT: BB11_2:
|
|
; GFX9-NEXT: s_or_b64 exec, exec, s[2:3]
|
|
; GFX9-NEXT: v_readfirstlane_b32 s3, v2
|
|
; GFX9-NEXT: v_readfirstlane_b32 s2, v1
|
|
; GFX9-NEXT: v_mul_hi_u32_u24_e32 v1, 5, v0
|
|
; GFX9-NEXT: v_mul_u32_u24_e32 v0, 5, v0
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, s3
|
|
; GFX9-NEXT: v_sub_co_u32_e32 v0, vcc, s2, v0
|
|
; GFX9-NEXT: v_subb_co_u32_e32 v1, vcc, v2, v1, vcc
|
|
; GFX9-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX9-NEXT: s_mov_b32 s2, -1
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX1064-LABEL: sub_i64_constant:
|
|
; GFX1064: ; %bb.0: ; %entry
|
|
; GFX1064-NEXT: v_cmp_ne_u32_e64 s[4:5], 1, 0
|
|
; GFX1064-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1064-NEXT: ; implicit-def: $vgpr1_vgpr2
|
|
; GFX1064-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s4, 0
|
|
; GFX1064-NEXT: v_mbcnt_hi_u32_b32_e64 v0, s5, v0
|
|
; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX1064-NEXT: s_and_saveexec_b64 s[2:3], vcc
|
|
; GFX1064-NEXT: ; mask branch BB11_2
|
|
; GFX1064-NEXT: s_cbranch_execz BB11_2
|
|
; GFX1064-NEXT: BB11_1:
|
|
; GFX1064-NEXT: s_bcnt1_i32_b64 s4, s[4:5]
|
|
; GFX1064-NEXT: v_mov_b32_e32 v3, local_var64@abs32@lo
|
|
; GFX1064-NEXT: v_mul_hi_u32_u24_e64 v2, s4, 5
|
|
; GFX1064-NEXT: v_mul_u32_u24_e64 v1, s4, 5
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1064-NEXT: ds_sub_rtn_u64 v[1:2], v3, v[1:2]
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_gl0_inv
|
|
; GFX1064-NEXT: buffer_gl1_inv
|
|
; GFX1064-NEXT: BB11_2:
|
|
; GFX1064-NEXT: v_nop
|
|
; GFX1064-NEXT: s_or_b64 exec, exec, s[2:3]
|
|
; GFX1064-NEXT: v_readfirstlane_b32 s2, v1
|
|
; GFX1064-NEXT: v_mul_u32_u24_e32 v1, 5, v0
|
|
; GFX1064-NEXT: v_readfirstlane_b32 s3, v2
|
|
; GFX1064-NEXT: v_mul_hi_u32_u24_e32 v2, 5, v0
|
|
; GFX1064-NEXT: v_sub_co_u32_e64 v0, vcc, s2, v1
|
|
; GFX1064-NEXT: s_mov_b32 s2, -1
|
|
; GFX1064-NEXT: v_sub_co_ci_u32_e32 v1, vcc, s3, v2, vcc
|
|
; GFX1064-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX1064-NEXT: s_endpgm
|
|
;
|
|
; GFX1032-LABEL: sub_i64_constant:
|
|
; GFX1032: ; %bb.0: ; %entry
|
|
; GFX1032-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1032-NEXT: v_cmp_ne_u32_e64 s3, 1, 0
|
|
; GFX1032-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX1032-NEXT: ; implicit-def: $vgpr1_vgpr2
|
|
; GFX1032-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s3, 0
|
|
; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v0
|
|
; GFX1032-NEXT: s_and_saveexec_b32 s2, vcc_lo
|
|
; GFX1032-NEXT: ; mask branch BB11_2
|
|
; GFX1032-NEXT: s_cbranch_execz BB11_2
|
|
; GFX1032-NEXT: BB11_1:
|
|
; GFX1032-NEXT: s_bcnt1_i32_b32 s3, s3
|
|
; GFX1032-NEXT: v_mov_b32_e32 v3, local_var64@abs32@lo
|
|
; GFX1032-NEXT: v_mul_hi_u32_u24_e64 v2, s3, 5
|
|
; GFX1032-NEXT: v_mul_u32_u24_e64 v1, s3, 5
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1032-NEXT: ds_sub_rtn_u64 v[1:2], v3, v[1:2]
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_gl0_inv
|
|
; GFX1032-NEXT: buffer_gl1_inv
|
|
; GFX1032-NEXT: BB11_2:
|
|
; GFX1032-NEXT: v_nop
|
|
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s2
|
|
; GFX1032-NEXT: v_readfirstlane_b32 s2, v1
|
|
; GFX1032-NEXT: v_mul_u32_u24_e32 v1, 5, v0
|
|
; GFX1032-NEXT: v_readfirstlane_b32 s3, v2
|
|
; GFX1032-NEXT: v_mul_hi_u32_u24_e32 v2, 5, v0
|
|
; GFX1032-NEXT: v_sub_co_u32_e64 v0, vcc_lo, s2, v1
|
|
; GFX1032-NEXT: s_mov_b32 s2, -1
|
|
; GFX1032-NEXT: v_sub_co_ci_u32_e32 v1, vcc_lo, s3, v2, vcc_lo
|
|
; GFX1032-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX1032-NEXT: s_endpgm
|
|
entry:
|
|
%old = atomicrmw sub i64 addrspace(3)* @local_var64, i64 5 acq_rel
|
|
store i64 %old, i64 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @sub_i64_uniform(i64 addrspace(1)* %out, i64 %subitive) {
|
|
;
|
|
;
|
|
; GFX7LESS-LABEL: sub_i64_uniform:
|
|
; GFX7LESS: ; %bb.0: ; %entry
|
|
; GFX7LESS-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; GFX7LESS-NEXT: v_cmp_ne_u32_e64 s[6:7], 1, 0
|
|
; GFX7LESS-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s6, 0
|
|
; GFX7LESS-NEXT: v_mbcnt_hi_u32_b32_e32 v0, s7, v0
|
|
; GFX7LESS-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX7LESS-NEXT: ; implicit-def: $vgpr1_vgpr2
|
|
; GFX7LESS-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX7LESS-NEXT: ; mask branch BB12_2
|
|
; GFX7LESS-NEXT: s_cbranch_execz BB12_2
|
|
; GFX7LESS-NEXT: BB12_1:
|
|
; GFX7LESS-NEXT: s_bcnt1_i32_b64 s6, s[6:7]
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v3, local_var64@abs32@lo
|
|
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7LESS-NEXT: s_mul_i32 s7, s3, s6
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v1, s6
|
|
; GFX7LESS-NEXT: v_mul_hi_u32 v1, s2, v1
|
|
; GFX7LESS-NEXT: s_mul_i32 s6, s2, s6
|
|
; GFX7LESS-NEXT: v_add_i32_e32 v2, vcc, s7, v1
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v1, s6
|
|
; GFX7LESS-NEXT: s_mov_b32 m0, -1
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: ds_sub_rtn_u64 v[1:2], v3, v[1:2]
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: buffer_wbinvl1
|
|
; GFX7LESS-NEXT: BB12_2:
|
|
; GFX7LESS-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX7LESS-NEXT: s_mov_b32 s7, 0xf000
|
|
; GFX7LESS-NEXT: s_mov_b32 s6, -1
|
|
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7LESS-NEXT: s_mov_b32 s4, s0
|
|
; GFX7LESS-NEXT: s_mov_b32 s5, s1
|
|
; GFX7LESS-NEXT: v_readfirstlane_b32 s0, v1
|
|
; GFX7LESS-NEXT: v_readfirstlane_b32 s1, v2
|
|
; GFX7LESS-NEXT: v_mul_lo_u32 v1, s3, v0
|
|
; GFX7LESS-NEXT: v_mul_hi_u32 v2, s2, v0
|
|
; GFX7LESS-NEXT: v_mul_lo_u32 v0, s2, v0
|
|
; GFX7LESS-NEXT: v_add_i32_e32 v1, vcc, v2, v1
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v2, s1
|
|
; GFX7LESS-NEXT: v_sub_i32_e32 v0, vcc, s0, v0
|
|
; GFX7LESS-NEXT: v_subb_u32_e32 v1, vcc, v2, v1, vcc
|
|
; GFX7LESS-NEXT: buffer_store_dwordx2 v[0:1], off, s[4:7], 0
|
|
; GFX7LESS-NEXT: s_endpgm
|
|
;
|
|
; GFX8-LABEL: sub_i64_uniform:
|
|
; GFX8: ; %bb.0: ; %entry
|
|
; GFX8-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX8-NEXT: v_cmp_ne_u32_e64 s[6:7], 1, 0
|
|
; GFX8-NEXT: v_mbcnt_lo_u32_b32 v0, s6, 0
|
|
; GFX8-NEXT: v_mbcnt_hi_u32_b32 v0, s7, v0
|
|
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX8-NEXT: ; implicit-def: $vgpr1_vgpr2
|
|
; GFX8-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX8-NEXT: ; mask branch BB12_2
|
|
; GFX8-NEXT: s_cbranch_execz BB12_2
|
|
; GFX8-NEXT: BB12_1:
|
|
; GFX8-NEXT: s_bcnt1_i32_b64 s6, s[6:7]
|
|
; GFX8-NEXT: v_mov_b32_e32 v1, s6
|
|
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX8-NEXT: v_mul_hi_u32 v1, s2, v1
|
|
; GFX8-NEXT: s_mul_i32 s7, s3, s6
|
|
; GFX8-NEXT: s_mul_i32 s6, s2, s6
|
|
; GFX8-NEXT: v_mov_b32_e32 v3, local_var64@abs32@lo
|
|
; GFX8-NEXT: v_add_u32_e32 v2, vcc, s7, v1
|
|
; GFX8-NEXT: v_mov_b32_e32 v1, s6
|
|
; GFX8-NEXT: s_mov_b32 m0, -1
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: ds_sub_rtn_u64 v[1:2], v3, v[1:2]
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_wbinvl1_vol
|
|
; GFX8-NEXT: BB12_2:
|
|
; GFX8-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX8-NEXT: s_mov_b32 s4, s0
|
|
; GFX8-NEXT: v_readfirstlane_b32 s0, v1
|
|
; GFX8-NEXT: v_mul_lo_u32 v1, s3, v0
|
|
; GFX8-NEXT: v_mul_hi_u32 v3, s2, v0
|
|
; GFX8-NEXT: v_mul_lo_u32 v0, s2, v0
|
|
; GFX8-NEXT: s_mov_b32 s5, s1
|
|
; GFX8-NEXT: v_readfirstlane_b32 s1, v2
|
|
; GFX8-NEXT: v_add_u32_e32 v1, vcc, v3, v1
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, s1
|
|
; GFX8-NEXT: v_sub_u32_e32 v0, vcc, s0, v0
|
|
; GFX8-NEXT: s_mov_b32 s7, 0xf000
|
|
; GFX8-NEXT: s_mov_b32 s6, -1
|
|
; GFX8-NEXT: v_subb_u32_e32 v1, vcc, v2, v1, vcc
|
|
; GFX8-NEXT: buffer_store_dwordx2 v[0:1], off, s[4:7], 0
|
|
; GFX8-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: sub_i64_uniform:
|
|
; GFX9: ; %bb.0: ; %entry
|
|
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX9-NEXT: v_cmp_ne_u32_e64 s[6:7], 1, 0
|
|
; GFX9-NEXT: v_mbcnt_lo_u32_b32 v0, s6, 0
|
|
; GFX9-NEXT: v_mbcnt_hi_u32_b32 v0, s7, v0
|
|
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX9-NEXT: ; implicit-def: $vgpr1_vgpr2
|
|
; GFX9-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX9-NEXT: ; mask branch BB12_2
|
|
; GFX9-NEXT: s_cbranch_execz BB12_2
|
|
; GFX9-NEXT: BB12_1:
|
|
; GFX9-NEXT: s_bcnt1_i32_b64 s6, s[6:7]
|
|
; GFX9-NEXT: v_mov_b32_e32 v1, s6
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: v_mul_hi_u32 v2, s2, v1
|
|
; GFX9-NEXT: s_mul_i32 s7, s3, s6
|
|
; GFX9-NEXT: s_mul_i32 s6, s2, s6
|
|
; GFX9-NEXT: v_mov_b32_e32 v1, s6
|
|
; GFX9-NEXT: v_add_u32_e32 v2, s7, v2
|
|
; GFX9-NEXT: v_mov_b32_e32 v3, local_var64@abs32@lo
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: ds_sub_rtn_u64 v[1:2], v3, v[1:2]
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_wbinvl1_vol
|
|
; GFX9-NEXT: BB12_2:
|
|
; GFX9-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: v_mul_lo_u32 v3, s3, v0
|
|
; GFX9-NEXT: v_mul_hi_u32 v4, s2, v0
|
|
; GFX9-NEXT: v_mul_lo_u32 v0, s2, v0
|
|
; GFX9-NEXT: s_mov_b32 s4, s0
|
|
; GFX9-NEXT: v_readfirstlane_b32 s0, v1
|
|
; GFX9-NEXT: s_mov_b32 s5, s1
|
|
; GFX9-NEXT: v_readfirstlane_b32 s1, v2
|
|
; GFX9-NEXT: v_add_u32_e32 v1, v4, v3
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, s1
|
|
; GFX9-NEXT: v_sub_co_u32_e32 v0, vcc, s0, v0
|
|
; GFX9-NEXT: s_mov_b32 s7, 0xf000
|
|
; GFX9-NEXT: s_mov_b32 s6, -1
|
|
; GFX9-NEXT: v_subb_co_u32_e32 v1, vcc, v2, v1, vcc
|
|
; GFX9-NEXT: buffer_store_dwordx2 v[0:1], off, s[4:7], 0
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX1064-LABEL: sub_i64_uniform:
|
|
; GFX1064: ; %bb.0: ; %entry
|
|
; GFX1064-NEXT: v_cmp_ne_u32_e64 s[6:7], 1, 0
|
|
; GFX1064-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX1064-NEXT: ; implicit-def: $vgpr1_vgpr2
|
|
; GFX1064-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s6, 0
|
|
; GFX1064-NEXT: v_mbcnt_hi_u32_b32_e64 v0, s7, v0
|
|
; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX1064-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX1064-NEXT: ; mask branch BB12_2
|
|
; GFX1064-NEXT: s_cbranch_execz BB12_2
|
|
; GFX1064-NEXT: BB12_1:
|
|
; GFX1064-NEXT: s_bcnt1_i32_b64 s6, s[6:7]
|
|
; GFX1064-NEXT: v_mov_b32_e32 v3, local_var64@abs32@lo
|
|
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1064-NEXT: v_mul_hi_u32 v2, s2, s6
|
|
; GFX1064-NEXT: s_mul_i32 s7, s2, s6
|
|
; GFX1064-NEXT: s_mul_i32 s6, s3, s6
|
|
; GFX1064-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX1064-NEXT: v_add_nc_u32_e32 v2, s6, v2
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1064-NEXT: ds_sub_rtn_u64 v[1:2], v3, v[1:2]
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_gl0_inv
|
|
; GFX1064-NEXT: buffer_gl1_inv
|
|
; GFX1064-NEXT: BB12_2:
|
|
; GFX1064-NEXT: v_nop
|
|
; GFX1064-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1064-NEXT: v_mul_lo_u32 v3, s3, v0
|
|
; GFX1064-NEXT: v_mul_hi_u32 v4, s2, v0
|
|
; GFX1064-NEXT: v_mul_lo_u32 v0, s2, v0
|
|
; GFX1064-NEXT: v_readfirstlane_b32 s4, v1
|
|
; GFX1064-NEXT: v_readfirstlane_b32 s5, v2
|
|
; GFX1064-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1064-NEXT: s_mov_b32 s2, -1
|
|
; GFX1064-NEXT: v_add_nc_u32_e32 v1, v4, v3
|
|
; GFX1064-NEXT: v_sub_co_u32_e64 v0, vcc, s4, v0
|
|
; GFX1064-NEXT: v_sub_co_ci_u32_e32 v1, vcc, s5, v1, vcc
|
|
; GFX1064-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX1064-NEXT: s_endpgm
|
|
;
|
|
; GFX1032-LABEL: sub_i64_uniform:
|
|
; GFX1032: ; %bb.0: ; %entry
|
|
; GFX1032-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX1032-NEXT: v_cmp_ne_u32_e64 s5, 1, 0
|
|
; GFX1032-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX1032-NEXT: ; implicit-def: $vgpr1_vgpr2
|
|
; GFX1032-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s5, 0
|
|
; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v0
|
|
; GFX1032-NEXT: s_and_saveexec_b32 s4, vcc_lo
|
|
; GFX1032-NEXT: ; mask branch BB12_2
|
|
; GFX1032-NEXT: s_cbranch_execz BB12_2
|
|
; GFX1032-NEXT: BB12_1:
|
|
; GFX1032-NEXT: s_bcnt1_i32_b32 s5, s5
|
|
; GFX1032-NEXT: v_mov_b32_e32 v3, local_var64@abs32@lo
|
|
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1032-NEXT: v_mul_hi_u32 v2, s2, s5
|
|
; GFX1032-NEXT: s_mul_i32 s6, s2, s5
|
|
; GFX1032-NEXT: s_mul_i32 s5, s3, s5
|
|
; GFX1032-NEXT: v_mov_b32_e32 v1, s6
|
|
; GFX1032-NEXT: v_add_nc_u32_e32 v2, s5, v2
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1032-NEXT: ds_sub_rtn_u64 v[1:2], v3, v[1:2]
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_gl0_inv
|
|
; GFX1032-NEXT: buffer_gl1_inv
|
|
; GFX1032-NEXT: BB12_2:
|
|
; GFX1032-NEXT: v_nop
|
|
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s4
|
|
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1032-NEXT: v_mul_lo_u32 v3, s3, v0
|
|
; GFX1032-NEXT: v_mul_hi_u32 v4, s2, v0
|
|
; GFX1032-NEXT: v_mul_lo_u32 v0, s2, v0
|
|
; GFX1032-NEXT: v_readfirstlane_b32 s4, v1
|
|
; GFX1032-NEXT: v_readfirstlane_b32 s5, v2
|
|
; GFX1032-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1032-NEXT: s_mov_b32 s2, -1
|
|
; GFX1032-NEXT: v_add_nc_u32_e32 v1, v4, v3
|
|
; GFX1032-NEXT: v_sub_co_u32_e64 v0, vcc_lo, s4, v0
|
|
; GFX1032-NEXT: v_sub_co_ci_u32_e32 v1, vcc_lo, s5, v1, vcc_lo
|
|
; GFX1032-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX1032-NEXT: s_endpgm
|
|
entry:
|
|
%old = atomicrmw sub i64 addrspace(3)* @local_var64, i64 %subitive acq_rel
|
|
store i64 %old, i64 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; GCN-NOT: v_mbcnt_lo_u32_b32
|
|
; GCN-NOT: v_mbcnt_hi_u32_b32
|
|
; GCN-NOT: s_bcnt1_i32_b64
|
|
define amdgpu_kernel void @sub_i64_varying(i64 addrspace(1)* %out) {
|
|
;
|
|
;
|
|
; GFX7LESS-LABEL: sub_i64_varying:
|
|
; GFX7LESS: ; %bb.0: ; %entry
|
|
; GFX7LESS-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
|
|
; GFX7LESS-NEXT: s_mov_b32 m0, -1
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: ds_sub_rtn_u64 v[0:1], v2, v[0:1]
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: buffer_wbinvl1
|
|
; GFX7LESS-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX7LESS-NEXT: s_mov_b32 s2, -1
|
|
; GFX7LESS-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX7LESS-NEXT: s_endpgm
|
|
;
|
|
; GFX8-LABEL: sub_i64_varying:
|
|
; GFX8: ; %bb.0: ; %entry
|
|
; GFX8-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
|
|
; GFX8-NEXT: s_mov_b32 m0, -1
|
|
; GFX8-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: ds_sub_rtn_u64 v[0:1], v2, v[0:1]
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_wbinvl1_vol
|
|
; GFX8-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX8-NEXT: s_mov_b32 s2, -1
|
|
; GFX8-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX8-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: sub_i64_varying:
|
|
; GFX9: ; %bb.0: ; %entry
|
|
; GFX9-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
|
|
; GFX9-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: ds_sub_rtn_u64 v[0:1], v2, v[0:1]
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_wbinvl1_vol
|
|
; GFX9-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX9-NEXT: s_mov_b32 s2, -1
|
|
; GFX9-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX1064-LABEL: sub_i64_varying:
|
|
; GFX1064: ; %bb.0: ; %entry
|
|
; GFX1064-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX1064-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
|
|
; GFX1064-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1064-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1064-NEXT: s_mov_b32 s2, -1
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1064-NEXT: ds_sub_rtn_u64 v[0:1], v2, v[0:1]
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_gl0_inv
|
|
; GFX1064-NEXT: buffer_gl1_inv
|
|
; GFX1064-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX1064-NEXT: s_endpgm
|
|
;
|
|
; GFX1032-LABEL: sub_i64_varying:
|
|
; GFX1032: ; %bb.0: ; %entry
|
|
; GFX1032-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX1032-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
|
|
; GFX1032-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1032-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1032-NEXT: s_mov_b32 s2, -1
|
|
; GFX1032-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1032-NEXT: ds_sub_rtn_u64 v[0:1], v2, v[0:1]
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_gl0_inv
|
|
; GFX1032-NEXT: buffer_gl1_inv
|
|
; GFX1032-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX1032-NEXT: s_endpgm
|
|
entry:
|
|
%lane = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%zext = zext i32 %lane to i64
|
|
%old = atomicrmw sub i64 addrspace(3)* @local_var64, i64 %zext acq_rel
|
|
store i64 %old, i64 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; GFX8MORE32: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 31
|
|
; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
|
|
; GFX8MORE: ds_and_rtn_b32 v{{[0-9]+}}, v{{[0-9]+}}, v[[value]]
|
|
define amdgpu_kernel void @and_i32_varying(i32 addrspace(1)* %out) {
|
|
;
|
|
;
|
|
; GFX7LESS-LABEL: and_i32_varying:
|
|
; GFX7LESS: ; %bb.0: ; %entry
|
|
; GFX7LESS-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v1, local_var32@abs32@lo
|
|
; GFX7LESS-NEXT: s_mov_b32 m0, -1
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: ds_and_rtn_b32 v0, v1, v0
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: buffer_wbinvl1
|
|
; GFX7LESS-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX7LESS-NEXT: s_mov_b32 s2, -1
|
|
; GFX7LESS-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX7LESS-NEXT: s_endpgm
|
|
;
|
|
; GFX8-LABEL: and_i32_varying:
|
|
; GFX8: ; %bb.0: ; %entry
|
|
; GFX8-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX8-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX8-NEXT: v_mbcnt_lo_u32_b32 v3, s2, 0
|
|
; GFX8-NEXT: v_mbcnt_hi_u32_b32 v3, s3, v3
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX8-NEXT: s_or_saveexec_b64 s[2:3], -1
|
|
; GFX8-NEXT: v_mov_b32_e32 v1, -1
|
|
; GFX8-NEXT: s_mov_b64 exec, s[2:3]
|
|
; GFX8-NEXT: s_not_b64 exec, exec
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, -1
|
|
; GFX8-NEXT: s_not_b64 exec, exec
|
|
; GFX8-NEXT: s_or_saveexec_b64 s[4:5], -1
|
|
; GFX8-NEXT: v_and_b32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_and_b32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_and_b32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_and_b32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_and_b32_dpp v2, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_and_b32_dpp v2, v2, v2 row_bcast:31 row_mask:0xc bank_mask:0xf
|
|
; GFX8-NEXT: v_readlane_b32 s2, v2, 63
|
|
; GFX8-NEXT: s_nop 0
|
|
; GFX8-NEXT: v_mov_b32_dpp v1, v2 wave_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX8-NEXT: s_mov_b64 exec, s[4:5]
|
|
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v3
|
|
; GFX8-NEXT: ; implicit-def: $vgpr0
|
|
; GFX8-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX8-NEXT: ; mask branch BB14_2
|
|
; GFX8-NEXT: s_cbranch_execz BB14_2
|
|
; GFX8-NEXT: BB14_1:
|
|
; GFX8-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX8-NEXT: v_mov_b32_e32 v3, s2
|
|
; GFX8-NEXT: s_mov_b32 m0, -1
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: ds_and_rtn_b32 v0, v0, v3
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_wbinvl1_vol
|
|
; GFX8-NEXT: BB14_2:
|
|
; GFX8-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX8-NEXT: v_readfirstlane_b32 s2, v0
|
|
; GFX8-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX8-NEXT: v_and_b32_e32 v0, s2, v0
|
|
; GFX8-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX8-NEXT: s_mov_b32 s2, -1
|
|
; GFX8-NEXT: s_nop 0
|
|
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX8-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: and_i32_varying:
|
|
; GFX9: ; %bb.0: ; %entry
|
|
; GFX9-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX9-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX9-NEXT: v_mbcnt_lo_u32_b32 v3, s2, 0
|
|
; GFX9-NEXT: v_mbcnt_hi_u32_b32 v3, s3, v3
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX9-NEXT: s_or_saveexec_b64 s[2:3], -1
|
|
; GFX9-NEXT: v_mov_b32_e32 v1, -1
|
|
; GFX9-NEXT: s_mov_b64 exec, s[2:3]
|
|
; GFX9-NEXT: s_not_b64 exec, exec
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, -1
|
|
; GFX9-NEXT: s_not_b64 exec, exec
|
|
; GFX9-NEXT: s_or_saveexec_b64 s[4:5], -1
|
|
; GFX9-NEXT: v_and_b32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_and_b32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_and_b32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_and_b32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_and_b32_dpp v2, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_and_b32_dpp v2, v2, v2 row_bcast:31 row_mask:0xc bank_mask:0xf
|
|
; GFX9-NEXT: v_readlane_b32 s2, v2, 63
|
|
; GFX9-NEXT: s_nop 0
|
|
; GFX9-NEXT: v_mov_b32_dpp v1, v2 wave_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX9-NEXT: s_mov_b64 exec, s[4:5]
|
|
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v3
|
|
; GFX9-NEXT: ; implicit-def: $vgpr0
|
|
; GFX9-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX9-NEXT: ; mask branch BB14_2
|
|
; GFX9-NEXT: s_cbranch_execz BB14_2
|
|
; GFX9-NEXT: BB14_1:
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX9-NEXT: v_mov_b32_e32 v3, s2
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: ds_and_rtn_b32 v0, v0, v3
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_wbinvl1_vol
|
|
; GFX9-NEXT: BB14_2:
|
|
; GFX9-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX9-NEXT: v_readfirstlane_b32 s2, v0
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX9-NEXT: v_and_b32_e32 v0, s2, v0
|
|
; GFX9-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX9-NEXT: s_mov_b32 s2, -1
|
|
; GFX9-NEXT: s_nop 0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX1064-LABEL: and_i32_varying:
|
|
; GFX1064: ; %bb.0: ; %entry
|
|
; GFX1064-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1064-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX1064-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX1064-NEXT: v_mbcnt_lo_u32_b32_e64 v4, s2, 0
|
|
; GFX1064-NEXT: v_mbcnt_hi_u32_b32_e64 v4, s3, v4
|
|
; GFX1064-NEXT: s_or_saveexec_b64 s[2:3], -1
|
|
; GFX1064-NEXT: v_mov_b32_e32 v1, -1
|
|
; GFX1064-NEXT: s_mov_b64 exec, s[2:3]
|
|
; GFX1064-NEXT: s_not_b64 exec, exec
|
|
; GFX1064-NEXT: v_mov_b32_e32 v2, -1
|
|
; GFX1064-NEXT: s_not_b64 exec, exec
|
|
; GFX1064-NEXT: s_or_saveexec_b64 s[4:5], -1
|
|
; GFX1064-NEXT: v_and_b32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX1064-NEXT: v_and_b32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf
|
|
; GFX1064-NEXT: v_and_b32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf
|
|
; GFX1064-NEXT: v_and_b32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf
|
|
; GFX1064-NEXT: v_mov_b32_e32 v3, v2
|
|
; GFX1064-NEXT: v_permlanex16_b32 v3, v3, -1, -1
|
|
; GFX1064-NEXT: v_and_b32_dpp v2, v3, v2 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf
|
|
; GFX1064-NEXT: v_readlane_b32 s2, v2, 31
|
|
; GFX1064-NEXT: v_mov_b32_e32 v3, s2
|
|
; GFX1064-NEXT: v_and_b32_dpp v2, v3, v2 quad_perm:[0,1,2,3] row_mask:0xc bank_mask:0xf
|
|
; GFX1064-NEXT: v_readlane_b32 s2, v2, 15
|
|
; GFX1064-NEXT: v_mov_b32_dpp v1, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX1064-NEXT: v_readlane_b32 s3, v2, 31
|
|
; GFX1064-NEXT: v_readlane_b32 s6, v2, 47
|
|
; GFX1064-NEXT: v_writelane_b32 v1, s2, 16
|
|
; GFX1064-NEXT: s_mov_b32 s2, -1
|
|
; GFX1064-NEXT: v_writelane_b32 v1, s3, 32
|
|
; GFX1064-NEXT: v_readlane_b32 s3, v2, 63
|
|
; GFX1064-NEXT: v_writelane_b32 v1, s6, 48
|
|
; GFX1064-NEXT: s_mov_b64 exec, s[4:5]
|
|
; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v4
|
|
; GFX1064-NEXT: ; implicit-def: $vgpr0
|
|
; GFX1064-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX1064-NEXT: ; mask branch BB14_2
|
|
; GFX1064-NEXT: s_cbranch_execz BB14_2
|
|
; GFX1064-NEXT: BB14_1:
|
|
; GFX1064-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX1064-NEXT: v_mov_b32_e32 v7, s3
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1064-NEXT: ds_and_rtn_b32 v0, v0, v7
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_gl0_inv
|
|
; GFX1064-NEXT: buffer_gl1_inv
|
|
; GFX1064-NEXT: BB14_2:
|
|
; GFX1064-NEXT: v_nop
|
|
; GFX1064-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX1064-NEXT: v_readfirstlane_b32 s3, v0
|
|
; GFX1064-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX1064-NEXT: v_and_b32_e32 v0, s3, v0
|
|
; GFX1064-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1064-NEXT: s_nop 1
|
|
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX1064-NEXT: s_endpgm
|
|
;
|
|
; GFX1032-LABEL: and_i32_varying:
|
|
; GFX1032: ; %bb.0: ; %entry
|
|
; GFX1032-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1032-NEXT: v_cmp_ne_u32_e64 s2, 1, 0
|
|
; GFX1032-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX1032-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX1032-NEXT: v_mbcnt_lo_u32_b32_e64 v4, s2, 0
|
|
; GFX1032-NEXT: s_or_saveexec_b32 s2, -1
|
|
; GFX1032-NEXT: v_mov_b32_e32 v1, -1
|
|
; GFX1032-NEXT: s_mov_b32 exec_lo, s2
|
|
; GFX1032-NEXT: s_not_b32 exec_lo, exec_lo
|
|
; GFX1032-NEXT: v_mov_b32_e32 v2, -1
|
|
; GFX1032-NEXT: s_not_b32 exec_lo, exec_lo
|
|
; GFX1032-NEXT: s_or_saveexec_b32 s4, -1
|
|
; GFX1032-NEXT: v_and_b32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX1032-NEXT: s_mov_b32 s2, -1
|
|
; GFX1032-NEXT: v_and_b32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf
|
|
; GFX1032-NEXT: v_and_b32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf
|
|
; GFX1032-NEXT: v_and_b32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf
|
|
; GFX1032-NEXT: v_mov_b32_e32 v3, v2
|
|
; GFX1032-NEXT: v_permlanex16_b32 v3, v3, -1, -1
|
|
; GFX1032-NEXT: v_and_b32_dpp v2, v3, v2 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf
|
|
; GFX1032-NEXT: v_readlane_b32 s3, v2, 31
|
|
; GFX1032-NEXT: v_mov_b32_dpp v1, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX1032-NEXT: v_readlane_b32 s5, v2, 15
|
|
; GFX1032-NEXT: v_writelane_b32 v1, s5, 16
|
|
; GFX1032-NEXT: s_mov_b32 exec_lo, s4
|
|
; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v4
|
|
; GFX1032-NEXT: ; implicit-def: $vgpr0
|
|
; GFX1032-NEXT: s_and_saveexec_b32 s4, vcc_lo
|
|
; GFX1032-NEXT: ; mask branch BB14_2
|
|
; GFX1032-NEXT: s_cbranch_execz BB14_2
|
|
; GFX1032-NEXT: BB14_1:
|
|
; GFX1032-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX1032-NEXT: v_mov_b32_e32 v7, s3
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1032-NEXT: ds_and_rtn_b32 v0, v0, v7
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_gl0_inv
|
|
; GFX1032-NEXT: buffer_gl1_inv
|
|
; GFX1032-NEXT: BB14_2:
|
|
; GFX1032-NEXT: v_nop
|
|
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s4
|
|
; GFX1032-NEXT: v_readfirstlane_b32 s3, v0
|
|
; GFX1032-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX1032-NEXT: v_and_b32_e32 v0, s3, v0
|
|
; GFX1032-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1032-NEXT: s_nop 1
|
|
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX1032-NEXT: s_endpgm
|
|
entry:
|
|
%lane = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%old = atomicrmw and i32 addrspace(3)* @local_var32, i32 %lane acq_rel
|
|
store i32 %old, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; GFX8MORE32: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 31
|
|
; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
|
|
; GFX8MORE: ds_or_rtn_b32 v{{[0-9]+}}, v{{[0-9]+}}, v[[value]]
|
|
define amdgpu_kernel void @or_i32_varying(i32 addrspace(1)* %out) {
|
|
;
|
|
;
|
|
; GFX7LESS-LABEL: or_i32_varying:
|
|
; GFX7LESS: ; %bb.0: ; %entry
|
|
; GFX7LESS-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v1, local_var32@abs32@lo
|
|
; GFX7LESS-NEXT: s_mov_b32 m0, -1
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: ds_or_rtn_b32 v0, v1, v0
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: buffer_wbinvl1
|
|
; GFX7LESS-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX7LESS-NEXT: s_mov_b32 s2, -1
|
|
; GFX7LESS-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX7LESS-NEXT: s_endpgm
|
|
;
|
|
; GFX8-LABEL: or_i32_varying:
|
|
; GFX8: ; %bb.0: ; %entry
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX8-NEXT: s_or_saveexec_b64 s[2:3], -1
|
|
; GFX8-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX8-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX8-NEXT: s_mov_b64 exec, s[2:3]
|
|
; GFX8-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX8-NEXT: v_mbcnt_lo_u32_b32 v0, s2, 0
|
|
; GFX8-NEXT: v_mbcnt_hi_u32_b32 v0, s3, v0
|
|
; GFX8-NEXT: s_not_b64 exec, exec
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX8-NEXT: s_not_b64 exec, exec
|
|
; GFX8-NEXT: s_or_saveexec_b64 s[4:5], -1
|
|
; GFX8-NEXT: v_or_b32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_or_b32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_or_b32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_or_b32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_or_b32_dpp v2, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_or_b32_dpp v2, v2, v2 row_bcast:31 row_mask:0xc bank_mask:0xf
|
|
; GFX8-NEXT: v_readlane_b32 s2, v2, 63
|
|
; GFX8-NEXT: s_nop 0
|
|
; GFX8-NEXT: v_mov_b32_dpp v1, v2 wave_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX8-NEXT: s_mov_b64 exec, s[4:5]
|
|
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX8-NEXT: ; implicit-def: $vgpr0
|
|
; GFX8-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX8-NEXT: ; mask branch BB15_2
|
|
; GFX8-NEXT: s_cbranch_execz BB15_2
|
|
; GFX8-NEXT: BB15_1:
|
|
; GFX8-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX8-NEXT: v_mov_b32_e32 v3, s2
|
|
; GFX8-NEXT: s_mov_b32 m0, -1
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: ds_or_rtn_b32 v0, v0, v3
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_wbinvl1_vol
|
|
; GFX8-NEXT: BB15_2:
|
|
; GFX8-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX8-NEXT: v_readfirstlane_b32 s2, v0
|
|
; GFX8-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX8-NEXT: v_or_b32_e32 v0, s2, v0
|
|
; GFX8-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX8-NEXT: s_mov_b32 s2, -1
|
|
; GFX8-NEXT: s_nop 0
|
|
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX8-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: or_i32_varying:
|
|
; GFX9: ; %bb.0: ; %entry
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX9-NEXT: s_or_saveexec_b64 s[2:3], -1
|
|
; GFX9-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX9-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX9-NEXT: s_mov_b64 exec, s[2:3]
|
|
; GFX9-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX9-NEXT: v_mbcnt_lo_u32_b32 v0, s2, 0
|
|
; GFX9-NEXT: v_mbcnt_hi_u32_b32 v0, s3, v0
|
|
; GFX9-NEXT: s_not_b64 exec, exec
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX9-NEXT: s_not_b64 exec, exec
|
|
; GFX9-NEXT: s_or_saveexec_b64 s[4:5], -1
|
|
; GFX9-NEXT: v_or_b32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_or_b32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_or_b32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_or_b32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_or_b32_dpp v2, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_or_b32_dpp v2, v2, v2 row_bcast:31 row_mask:0xc bank_mask:0xf
|
|
; GFX9-NEXT: v_readlane_b32 s2, v2, 63
|
|
; GFX9-NEXT: s_nop 0
|
|
; GFX9-NEXT: v_mov_b32_dpp v1, v2 wave_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX9-NEXT: s_mov_b64 exec, s[4:5]
|
|
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX9-NEXT: ; implicit-def: $vgpr0
|
|
; GFX9-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX9-NEXT: ; mask branch BB15_2
|
|
; GFX9-NEXT: s_cbranch_execz BB15_2
|
|
; GFX9-NEXT: BB15_1:
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX9-NEXT: v_mov_b32_e32 v3, s2
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: ds_or_rtn_b32 v0, v0, v3
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_wbinvl1_vol
|
|
; GFX9-NEXT: BB15_2:
|
|
; GFX9-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX9-NEXT: v_readfirstlane_b32 s2, v0
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX9-NEXT: v_or_b32_e32 v0, s2, v0
|
|
; GFX9-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX9-NEXT: s_mov_b32 s2, -1
|
|
; GFX9-NEXT: s_nop 0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX1064-LABEL: or_i32_varying:
|
|
; GFX1064: ; %bb.0: ; %entry
|
|
; GFX1064-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX1064-NEXT: s_or_saveexec_b64 s[2:3], -1
|
|
; GFX1064-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1064-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX1064-NEXT: s_mov_b64 exec, s[2:3]
|
|
; GFX1064-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX1064-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s2, 0
|
|
; GFX1064-NEXT: v_mbcnt_hi_u32_b32_e64 v0, s3, v0
|
|
; GFX1064-NEXT: s_not_b64 exec, exec
|
|
; GFX1064-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX1064-NEXT: s_not_b64 exec, exec
|
|
; GFX1064-NEXT: s_or_saveexec_b64 s[4:5], -1
|
|
; GFX1064-NEXT: v_or_b32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1064-NEXT: v_or_b32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1064-NEXT: v_or_b32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1064-NEXT: v_or_b32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1064-NEXT: v_mov_b32_e32 v3, v2
|
|
; GFX1064-NEXT: v_permlanex16_b32 v3, v3, -1, -1
|
|
; GFX1064-NEXT: v_or_b32_dpp v2, v3, v2 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf
|
|
; GFX1064-NEXT: v_readlane_b32 s2, v2, 31
|
|
; GFX1064-NEXT: v_mov_b32_e32 v3, s2
|
|
; GFX1064-NEXT: v_or_b32_dpp v2, v3, v2 quad_perm:[0,1,2,3] row_mask:0xc bank_mask:0xf
|
|
; GFX1064-NEXT: v_readlane_b32 s2, v2, 15
|
|
; GFX1064-NEXT: v_mov_b32_dpp v1, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX1064-NEXT: v_readlane_b32 s3, v2, 31
|
|
; GFX1064-NEXT: v_readlane_b32 s6, v2, 47
|
|
; GFX1064-NEXT: v_writelane_b32 v1, s2, 16
|
|
; GFX1064-NEXT: s_mov_b32 s2, -1
|
|
; GFX1064-NEXT: v_writelane_b32 v1, s3, 32
|
|
; GFX1064-NEXT: v_readlane_b32 s3, v2, 63
|
|
; GFX1064-NEXT: v_writelane_b32 v1, s6, 48
|
|
; GFX1064-NEXT: s_mov_b64 exec, s[4:5]
|
|
; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX1064-NEXT: ; implicit-def: $vgpr0
|
|
; GFX1064-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX1064-NEXT: ; mask branch BB15_2
|
|
; GFX1064-NEXT: s_cbranch_execz BB15_2
|
|
; GFX1064-NEXT: BB15_1:
|
|
; GFX1064-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX1064-NEXT: v_mov_b32_e32 v7, s3
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1064-NEXT: ds_or_rtn_b32 v0, v0, v7
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_gl0_inv
|
|
; GFX1064-NEXT: buffer_gl1_inv
|
|
; GFX1064-NEXT: BB15_2:
|
|
; GFX1064-NEXT: v_nop
|
|
; GFX1064-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX1064-NEXT: v_readfirstlane_b32 s3, v0
|
|
; GFX1064-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX1064-NEXT: v_or_b32_e32 v0, s3, v0
|
|
; GFX1064-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1064-NEXT: s_nop 1
|
|
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX1064-NEXT: s_endpgm
|
|
;
|
|
; GFX1032-LABEL: or_i32_varying:
|
|
; GFX1032: ; %bb.0: ; %entry
|
|
; GFX1032-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX1032-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX1032-NEXT: s_or_saveexec_b32 s2, -1
|
|
; GFX1032-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1032-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX1032-NEXT: s_mov_b32 exec_lo, s2
|
|
; GFX1032-NEXT: v_cmp_ne_u32_e64 s2, 1, 0
|
|
; GFX1032-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s2, 0
|
|
; GFX1032-NEXT: s_not_b32 exec_lo, exec_lo
|
|
; GFX1032-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX1032-NEXT: s_not_b32 exec_lo, exec_lo
|
|
; GFX1032-NEXT: s_or_saveexec_b32 s4, -1
|
|
; GFX1032-NEXT: v_or_b32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1032-NEXT: s_mov_b32 s2, -1
|
|
; GFX1032-NEXT: v_or_b32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1032-NEXT: v_or_b32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1032-NEXT: v_or_b32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1032-NEXT: v_mov_b32_e32 v3, v2
|
|
; GFX1032-NEXT: v_permlanex16_b32 v3, v3, -1, -1
|
|
; GFX1032-NEXT: v_or_b32_dpp v2, v3, v2 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf
|
|
; GFX1032-NEXT: v_readlane_b32 s3, v2, 31
|
|
; GFX1032-NEXT: v_mov_b32_dpp v1, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX1032-NEXT: v_readlane_b32 s5, v2, 15
|
|
; GFX1032-NEXT: v_writelane_b32 v1, s5, 16
|
|
; GFX1032-NEXT: s_mov_b32 exec_lo, s4
|
|
; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v0
|
|
; GFX1032-NEXT: ; implicit-def: $vgpr0
|
|
; GFX1032-NEXT: s_and_saveexec_b32 s4, vcc_lo
|
|
; GFX1032-NEXT: ; mask branch BB15_2
|
|
; GFX1032-NEXT: s_cbranch_execz BB15_2
|
|
; GFX1032-NEXT: BB15_1:
|
|
; GFX1032-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX1032-NEXT: v_mov_b32_e32 v7, s3
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1032-NEXT: ds_or_rtn_b32 v0, v0, v7
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_gl0_inv
|
|
; GFX1032-NEXT: buffer_gl1_inv
|
|
; GFX1032-NEXT: BB15_2:
|
|
; GFX1032-NEXT: v_nop
|
|
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s4
|
|
; GFX1032-NEXT: v_readfirstlane_b32 s3, v0
|
|
; GFX1032-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX1032-NEXT: v_or_b32_e32 v0, s3, v0
|
|
; GFX1032-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1032-NEXT: s_nop 1
|
|
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX1032-NEXT: s_endpgm
|
|
entry:
|
|
%lane = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%old = atomicrmw or i32 addrspace(3)* @local_var32, i32 %lane acq_rel
|
|
store i32 %old, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; GFX8MORE32: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 31
|
|
; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
|
|
; GFX8MORE: ds_xor_rtn_b32 v{{[0-9]+}}, v{{[0-9]+}}, v[[value]]
|
|
define amdgpu_kernel void @xor_i32_varying(i32 addrspace(1)* %out) {
|
|
;
|
|
;
|
|
; GFX7LESS-LABEL: xor_i32_varying:
|
|
; GFX7LESS: ; %bb.0: ; %entry
|
|
; GFX7LESS-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v1, local_var32@abs32@lo
|
|
; GFX7LESS-NEXT: s_mov_b32 m0, -1
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: ds_xor_rtn_b32 v0, v1, v0
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: buffer_wbinvl1
|
|
; GFX7LESS-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX7LESS-NEXT: s_mov_b32 s2, -1
|
|
; GFX7LESS-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX7LESS-NEXT: s_endpgm
|
|
;
|
|
; GFX8-LABEL: xor_i32_varying:
|
|
; GFX8: ; %bb.0: ; %entry
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX8-NEXT: s_or_saveexec_b64 s[2:3], -1
|
|
; GFX8-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX8-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX8-NEXT: s_mov_b64 exec, s[2:3]
|
|
; GFX8-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX8-NEXT: v_mbcnt_lo_u32_b32 v0, s2, 0
|
|
; GFX8-NEXT: v_mbcnt_hi_u32_b32 v0, s3, v0
|
|
; GFX8-NEXT: s_not_b64 exec, exec
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX8-NEXT: s_not_b64 exec, exec
|
|
; GFX8-NEXT: s_or_saveexec_b64 s[4:5], -1
|
|
; GFX8-NEXT: v_xor_b32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_xor_b32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_xor_b32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_xor_b32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_xor_b32_dpp v2, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_xor_b32_dpp v2, v2, v2 row_bcast:31 row_mask:0xc bank_mask:0xf
|
|
; GFX8-NEXT: v_readlane_b32 s2, v2, 63
|
|
; GFX8-NEXT: s_nop 0
|
|
; GFX8-NEXT: v_mov_b32_dpp v1, v2 wave_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX8-NEXT: s_mov_b64 exec, s[4:5]
|
|
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX8-NEXT: ; implicit-def: $vgpr0
|
|
; GFX8-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX8-NEXT: ; mask branch BB16_2
|
|
; GFX8-NEXT: s_cbranch_execz BB16_2
|
|
; GFX8-NEXT: BB16_1:
|
|
; GFX8-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX8-NEXT: v_mov_b32_e32 v3, s2
|
|
; GFX8-NEXT: s_mov_b32 m0, -1
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: ds_xor_rtn_b32 v0, v0, v3
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_wbinvl1_vol
|
|
; GFX8-NEXT: BB16_2:
|
|
; GFX8-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX8-NEXT: v_readfirstlane_b32 s2, v0
|
|
; GFX8-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX8-NEXT: v_xor_b32_e32 v0, s2, v0
|
|
; GFX8-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX8-NEXT: s_mov_b32 s2, -1
|
|
; GFX8-NEXT: s_nop 0
|
|
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX8-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: xor_i32_varying:
|
|
; GFX9: ; %bb.0: ; %entry
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX9-NEXT: s_or_saveexec_b64 s[2:3], -1
|
|
; GFX9-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX9-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX9-NEXT: s_mov_b64 exec, s[2:3]
|
|
; GFX9-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX9-NEXT: v_mbcnt_lo_u32_b32 v0, s2, 0
|
|
; GFX9-NEXT: v_mbcnt_hi_u32_b32 v0, s3, v0
|
|
; GFX9-NEXT: s_not_b64 exec, exec
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX9-NEXT: s_not_b64 exec, exec
|
|
; GFX9-NEXT: s_or_saveexec_b64 s[4:5], -1
|
|
; GFX9-NEXT: v_xor_b32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_xor_b32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_xor_b32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_xor_b32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_xor_b32_dpp v2, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_xor_b32_dpp v2, v2, v2 row_bcast:31 row_mask:0xc bank_mask:0xf
|
|
; GFX9-NEXT: v_readlane_b32 s2, v2, 63
|
|
; GFX9-NEXT: s_nop 0
|
|
; GFX9-NEXT: v_mov_b32_dpp v1, v2 wave_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX9-NEXT: s_mov_b64 exec, s[4:5]
|
|
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX9-NEXT: ; implicit-def: $vgpr0
|
|
; GFX9-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX9-NEXT: ; mask branch BB16_2
|
|
; GFX9-NEXT: s_cbranch_execz BB16_2
|
|
; GFX9-NEXT: BB16_1:
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX9-NEXT: v_mov_b32_e32 v3, s2
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: ds_xor_rtn_b32 v0, v0, v3
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_wbinvl1_vol
|
|
; GFX9-NEXT: BB16_2:
|
|
; GFX9-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX9-NEXT: v_readfirstlane_b32 s2, v0
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX9-NEXT: v_xor_b32_e32 v0, s2, v0
|
|
; GFX9-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX9-NEXT: s_mov_b32 s2, -1
|
|
; GFX9-NEXT: s_nop 0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX1064-LABEL: xor_i32_varying:
|
|
; GFX1064: ; %bb.0: ; %entry
|
|
; GFX1064-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX1064-NEXT: s_or_saveexec_b64 s[2:3], -1
|
|
; GFX1064-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1064-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX1064-NEXT: s_mov_b64 exec, s[2:3]
|
|
; GFX1064-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX1064-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s2, 0
|
|
; GFX1064-NEXT: v_mbcnt_hi_u32_b32_e64 v0, s3, v0
|
|
; GFX1064-NEXT: s_not_b64 exec, exec
|
|
; GFX1064-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX1064-NEXT: s_not_b64 exec, exec
|
|
; GFX1064-NEXT: s_or_saveexec_b64 s[4:5], -1
|
|
; GFX1064-NEXT: v_xor_b32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1064-NEXT: v_xor_b32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1064-NEXT: v_xor_b32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1064-NEXT: v_xor_b32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1064-NEXT: v_mov_b32_e32 v3, v2
|
|
; GFX1064-NEXT: v_permlanex16_b32 v3, v3, -1, -1
|
|
; GFX1064-NEXT: v_xor_b32_dpp v2, v3, v2 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf
|
|
; GFX1064-NEXT: v_readlane_b32 s2, v2, 31
|
|
; GFX1064-NEXT: v_mov_b32_e32 v3, s2
|
|
; GFX1064-NEXT: v_xor_b32_dpp v2, v3, v2 quad_perm:[0,1,2,3] row_mask:0xc bank_mask:0xf
|
|
; GFX1064-NEXT: v_readlane_b32 s2, v2, 15
|
|
; GFX1064-NEXT: v_mov_b32_dpp v1, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX1064-NEXT: v_readlane_b32 s3, v2, 31
|
|
; GFX1064-NEXT: v_readlane_b32 s6, v2, 47
|
|
; GFX1064-NEXT: v_writelane_b32 v1, s2, 16
|
|
; GFX1064-NEXT: s_mov_b32 s2, -1
|
|
; GFX1064-NEXT: v_writelane_b32 v1, s3, 32
|
|
; GFX1064-NEXT: v_readlane_b32 s3, v2, 63
|
|
; GFX1064-NEXT: v_writelane_b32 v1, s6, 48
|
|
; GFX1064-NEXT: s_mov_b64 exec, s[4:5]
|
|
; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX1064-NEXT: ; implicit-def: $vgpr0
|
|
; GFX1064-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX1064-NEXT: ; mask branch BB16_2
|
|
; GFX1064-NEXT: s_cbranch_execz BB16_2
|
|
; GFX1064-NEXT: BB16_1:
|
|
; GFX1064-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX1064-NEXT: v_mov_b32_e32 v7, s3
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1064-NEXT: ds_xor_rtn_b32 v0, v0, v7
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_gl0_inv
|
|
; GFX1064-NEXT: buffer_gl1_inv
|
|
; GFX1064-NEXT: BB16_2:
|
|
; GFX1064-NEXT: v_nop
|
|
; GFX1064-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX1064-NEXT: v_readfirstlane_b32 s3, v0
|
|
; GFX1064-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX1064-NEXT: v_xor_b32_e32 v0, s3, v0
|
|
; GFX1064-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1064-NEXT: s_nop 1
|
|
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX1064-NEXT: s_endpgm
|
|
;
|
|
; GFX1032-LABEL: xor_i32_varying:
|
|
; GFX1032: ; %bb.0: ; %entry
|
|
; GFX1032-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX1032-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX1032-NEXT: s_or_saveexec_b32 s2, -1
|
|
; GFX1032-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1032-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX1032-NEXT: s_mov_b32 exec_lo, s2
|
|
; GFX1032-NEXT: v_cmp_ne_u32_e64 s2, 1, 0
|
|
; GFX1032-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s2, 0
|
|
; GFX1032-NEXT: s_not_b32 exec_lo, exec_lo
|
|
; GFX1032-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX1032-NEXT: s_not_b32 exec_lo, exec_lo
|
|
; GFX1032-NEXT: s_or_saveexec_b32 s4, -1
|
|
; GFX1032-NEXT: v_xor_b32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1032-NEXT: s_mov_b32 s2, -1
|
|
; GFX1032-NEXT: v_xor_b32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1032-NEXT: v_xor_b32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1032-NEXT: v_xor_b32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1032-NEXT: v_mov_b32_e32 v3, v2
|
|
; GFX1032-NEXT: v_permlanex16_b32 v3, v3, -1, -1
|
|
; GFX1032-NEXT: v_xor_b32_dpp v2, v3, v2 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf
|
|
; GFX1032-NEXT: v_readlane_b32 s3, v2, 31
|
|
; GFX1032-NEXT: v_mov_b32_dpp v1, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX1032-NEXT: v_readlane_b32 s5, v2, 15
|
|
; GFX1032-NEXT: v_writelane_b32 v1, s5, 16
|
|
; GFX1032-NEXT: s_mov_b32 exec_lo, s4
|
|
; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v0
|
|
; GFX1032-NEXT: ; implicit-def: $vgpr0
|
|
; GFX1032-NEXT: s_and_saveexec_b32 s4, vcc_lo
|
|
; GFX1032-NEXT: ; mask branch BB16_2
|
|
; GFX1032-NEXT: s_cbranch_execz BB16_2
|
|
; GFX1032-NEXT: BB16_1:
|
|
; GFX1032-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX1032-NEXT: v_mov_b32_e32 v7, s3
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1032-NEXT: ds_xor_rtn_b32 v0, v0, v7
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_gl0_inv
|
|
; GFX1032-NEXT: buffer_gl1_inv
|
|
; GFX1032-NEXT: BB16_2:
|
|
; GFX1032-NEXT: v_nop
|
|
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s4
|
|
; GFX1032-NEXT: v_readfirstlane_b32 s3, v0
|
|
; GFX1032-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX1032-NEXT: v_xor_b32_e32 v0, s3, v0
|
|
; GFX1032-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1032-NEXT: s_nop 1
|
|
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX1032-NEXT: s_endpgm
|
|
entry:
|
|
%lane = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%old = atomicrmw xor i32 addrspace(3)* @local_var32, i32 %lane acq_rel
|
|
store i32 %old, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; GFX8MORE32: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 31
|
|
; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
|
|
; GFX8MORE: ds_max_rtn_i32 v{{[0-9]+}}, v{{[0-9]+}}, v[[value]]
|
|
define amdgpu_kernel void @max_i32_varying(i32 addrspace(1)* %out) {
|
|
;
|
|
;
|
|
; GFX7LESS-LABEL: max_i32_varying:
|
|
; GFX7LESS: ; %bb.0: ; %entry
|
|
; GFX7LESS-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v1, local_var32@abs32@lo
|
|
; GFX7LESS-NEXT: s_mov_b32 m0, -1
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: ds_max_rtn_i32 v0, v1, v0
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: buffer_wbinvl1
|
|
; GFX7LESS-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX7LESS-NEXT: s_mov_b32 s2, -1
|
|
; GFX7LESS-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX7LESS-NEXT: s_endpgm
|
|
;
|
|
; GFX8-LABEL: max_i32_varying:
|
|
; GFX8: ; %bb.0: ; %entry
|
|
; GFX8-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX8-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX8-NEXT: v_mbcnt_lo_u32_b32 v3, s2, 0
|
|
; GFX8-NEXT: v_mbcnt_hi_u32_b32 v3, s3, v3
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX8-NEXT: s_or_saveexec_b64 s[2:3], -1
|
|
; GFX8-NEXT: v_bfrev_b32_e32 v1, 1
|
|
; GFX8-NEXT: s_mov_b64 exec, s[2:3]
|
|
; GFX8-NEXT: s_not_b64 exec, exec
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, v1
|
|
; GFX8-NEXT: s_not_b64 exec, exec
|
|
; GFX8-NEXT: s_or_saveexec_b64 s[4:5], -1
|
|
; GFX8-NEXT: v_max_i32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_max_i32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_max_i32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_max_i32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_max_i32_dpp v2, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_max_i32_dpp v2, v2, v2 row_bcast:31 row_mask:0xc bank_mask:0xf
|
|
; GFX8-NEXT: v_readlane_b32 s2, v2, 63
|
|
; GFX8-NEXT: s_nop 0
|
|
; GFX8-NEXT: v_mov_b32_dpp v1, v2 wave_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX8-NEXT: s_mov_b64 exec, s[4:5]
|
|
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v3
|
|
; GFX8-NEXT: ; implicit-def: $vgpr0
|
|
; GFX8-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX8-NEXT: ; mask branch BB17_2
|
|
; GFX8-NEXT: s_cbranch_execz BB17_2
|
|
; GFX8-NEXT: BB17_1:
|
|
; GFX8-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX8-NEXT: v_mov_b32_e32 v3, s2
|
|
; GFX8-NEXT: s_mov_b32 m0, -1
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: ds_max_rtn_i32 v0, v0, v3
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_wbinvl1_vol
|
|
; GFX8-NEXT: BB17_2:
|
|
; GFX8-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX8-NEXT: v_readfirstlane_b32 s2, v0
|
|
; GFX8-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX8-NEXT: v_max_i32_e32 v0, s2, v0
|
|
; GFX8-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX8-NEXT: s_mov_b32 s2, -1
|
|
; GFX8-NEXT: s_nop 0
|
|
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX8-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: max_i32_varying:
|
|
; GFX9: ; %bb.0: ; %entry
|
|
; GFX9-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX9-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX9-NEXT: v_mbcnt_lo_u32_b32 v3, s2, 0
|
|
; GFX9-NEXT: v_mbcnt_hi_u32_b32 v3, s3, v3
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX9-NEXT: s_or_saveexec_b64 s[2:3], -1
|
|
; GFX9-NEXT: v_bfrev_b32_e32 v1, 1
|
|
; GFX9-NEXT: s_mov_b64 exec, s[2:3]
|
|
; GFX9-NEXT: s_not_b64 exec, exec
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, v1
|
|
; GFX9-NEXT: s_not_b64 exec, exec
|
|
; GFX9-NEXT: s_or_saveexec_b64 s[4:5], -1
|
|
; GFX9-NEXT: v_max_i32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_max_i32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_max_i32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_max_i32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_max_i32_dpp v2, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_max_i32_dpp v2, v2, v2 row_bcast:31 row_mask:0xc bank_mask:0xf
|
|
; GFX9-NEXT: v_readlane_b32 s2, v2, 63
|
|
; GFX9-NEXT: s_nop 0
|
|
; GFX9-NEXT: v_mov_b32_dpp v1, v2 wave_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX9-NEXT: s_mov_b64 exec, s[4:5]
|
|
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v3
|
|
; GFX9-NEXT: ; implicit-def: $vgpr0
|
|
; GFX9-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX9-NEXT: ; mask branch BB17_2
|
|
; GFX9-NEXT: s_cbranch_execz BB17_2
|
|
; GFX9-NEXT: BB17_1:
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX9-NEXT: v_mov_b32_e32 v3, s2
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: ds_max_rtn_i32 v0, v0, v3
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_wbinvl1_vol
|
|
; GFX9-NEXT: BB17_2:
|
|
; GFX9-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX9-NEXT: v_readfirstlane_b32 s2, v0
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX9-NEXT: v_max_i32_e32 v0, s2, v0
|
|
; GFX9-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX9-NEXT: s_mov_b32 s2, -1
|
|
; GFX9-NEXT: s_nop 0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX1064-LABEL: max_i32_varying:
|
|
; GFX1064: ; %bb.0: ; %entry
|
|
; GFX1064-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1064-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX1064-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX1064-NEXT: v_mbcnt_lo_u32_b32_e64 v4, s2, 0
|
|
; GFX1064-NEXT: v_mbcnt_hi_u32_b32_e64 v4, s3, v4
|
|
; GFX1064-NEXT: s_or_saveexec_b64 s[2:3], -1
|
|
; GFX1064-NEXT: v_bfrev_b32_e32 v1, 1
|
|
; GFX1064-NEXT: s_mov_b64 exec, s[2:3]
|
|
; GFX1064-NEXT: s_not_b64 exec, exec
|
|
; GFX1064-NEXT: v_mov_b32_e32 v2, v1
|
|
; GFX1064-NEXT: s_not_b64 exec, exec
|
|
; GFX1064-NEXT: s_or_saveexec_b64 s[4:5], -1
|
|
; GFX1064-NEXT: v_max_i32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX1064-NEXT: v_max_i32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf
|
|
; GFX1064-NEXT: v_max_i32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf
|
|
; GFX1064-NEXT: v_max_i32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf
|
|
; GFX1064-NEXT: v_mov_b32_e32 v3, v2
|
|
; GFX1064-NEXT: v_permlanex16_b32 v3, v3, -1, -1
|
|
; GFX1064-NEXT: v_max_i32_dpp v2, v3, v2 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf
|
|
; GFX1064-NEXT: v_readlane_b32 s2, v2, 31
|
|
; GFX1064-NEXT: v_mov_b32_e32 v3, s2
|
|
; GFX1064-NEXT: v_max_i32_dpp v2, v3, v2 quad_perm:[0,1,2,3] row_mask:0xc bank_mask:0xf
|
|
; GFX1064-NEXT: v_readlane_b32 s2, v2, 15
|
|
; GFX1064-NEXT: v_mov_b32_dpp v1, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX1064-NEXT: v_readlane_b32 s3, v2, 31
|
|
; GFX1064-NEXT: v_readlane_b32 s6, v2, 47
|
|
; GFX1064-NEXT: v_writelane_b32 v1, s2, 16
|
|
; GFX1064-NEXT: s_mov_b32 s2, -1
|
|
; GFX1064-NEXT: v_writelane_b32 v1, s3, 32
|
|
; GFX1064-NEXT: v_readlane_b32 s3, v2, 63
|
|
; GFX1064-NEXT: v_writelane_b32 v1, s6, 48
|
|
; GFX1064-NEXT: s_mov_b64 exec, s[4:5]
|
|
; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v4
|
|
; GFX1064-NEXT: ; implicit-def: $vgpr0
|
|
; GFX1064-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX1064-NEXT: ; mask branch BB17_2
|
|
; GFX1064-NEXT: s_cbranch_execz BB17_2
|
|
; GFX1064-NEXT: BB17_1:
|
|
; GFX1064-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX1064-NEXT: v_mov_b32_e32 v7, s3
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1064-NEXT: ds_max_rtn_i32 v0, v0, v7
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_gl0_inv
|
|
; GFX1064-NEXT: buffer_gl1_inv
|
|
; GFX1064-NEXT: BB17_2:
|
|
; GFX1064-NEXT: v_nop
|
|
; GFX1064-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX1064-NEXT: v_readfirstlane_b32 s3, v0
|
|
; GFX1064-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX1064-NEXT: v_max_i32_e32 v0, s3, v0
|
|
; GFX1064-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1064-NEXT: s_nop 1
|
|
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX1064-NEXT: s_endpgm
|
|
;
|
|
; GFX1032-LABEL: max_i32_varying:
|
|
; GFX1032: ; %bb.0: ; %entry
|
|
; GFX1032-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1032-NEXT: v_cmp_ne_u32_e64 s2, 1, 0
|
|
; GFX1032-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX1032-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX1032-NEXT: v_mbcnt_lo_u32_b32_e64 v4, s2, 0
|
|
; GFX1032-NEXT: s_or_saveexec_b32 s2, -1
|
|
; GFX1032-NEXT: v_bfrev_b32_e32 v1, 1
|
|
; GFX1032-NEXT: s_mov_b32 exec_lo, s2
|
|
; GFX1032-NEXT: s_not_b32 exec_lo, exec_lo
|
|
; GFX1032-NEXT: v_mov_b32_e32 v2, v1
|
|
; GFX1032-NEXT: s_not_b32 exec_lo, exec_lo
|
|
; GFX1032-NEXT: s_or_saveexec_b32 s4, -1
|
|
; GFX1032-NEXT: v_max_i32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX1032-NEXT: s_mov_b32 s2, -1
|
|
; GFX1032-NEXT: v_max_i32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf
|
|
; GFX1032-NEXT: v_max_i32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf
|
|
; GFX1032-NEXT: v_max_i32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf
|
|
; GFX1032-NEXT: v_mov_b32_e32 v3, v2
|
|
; GFX1032-NEXT: v_permlanex16_b32 v3, v3, -1, -1
|
|
; GFX1032-NEXT: v_max_i32_dpp v2, v3, v2 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf
|
|
; GFX1032-NEXT: v_readlane_b32 s3, v2, 31
|
|
; GFX1032-NEXT: v_mov_b32_dpp v1, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX1032-NEXT: v_readlane_b32 s5, v2, 15
|
|
; GFX1032-NEXT: v_writelane_b32 v1, s5, 16
|
|
; GFX1032-NEXT: s_mov_b32 exec_lo, s4
|
|
; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v4
|
|
; GFX1032-NEXT: ; implicit-def: $vgpr0
|
|
; GFX1032-NEXT: s_and_saveexec_b32 s4, vcc_lo
|
|
; GFX1032-NEXT: ; mask branch BB17_2
|
|
; GFX1032-NEXT: s_cbranch_execz BB17_2
|
|
; GFX1032-NEXT: BB17_1:
|
|
; GFX1032-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX1032-NEXT: v_mov_b32_e32 v7, s3
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1032-NEXT: ds_max_rtn_i32 v0, v0, v7
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_gl0_inv
|
|
; GFX1032-NEXT: buffer_gl1_inv
|
|
; GFX1032-NEXT: BB17_2:
|
|
; GFX1032-NEXT: v_nop
|
|
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s4
|
|
; GFX1032-NEXT: v_readfirstlane_b32 s3, v0
|
|
; GFX1032-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX1032-NEXT: v_max_i32_e32 v0, s3, v0
|
|
; GFX1032-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1032-NEXT: s_nop 1
|
|
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX1032-NEXT: s_endpgm
|
|
entry:
|
|
%lane = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%old = atomicrmw max i32 addrspace(3)* @local_var32, i32 %lane acq_rel
|
|
store i32 %old, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @max_i64_constant(i64 addrspace(1)* %out) {
|
|
;
|
|
;
|
|
; GFX7LESS-LABEL: max_i64_constant:
|
|
; GFX7LESS: ; %bb.0: ; %entry
|
|
; GFX7LESS-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; GFX7LESS-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX7LESS-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s2, 0
|
|
; GFX7LESS-NEXT: v_mbcnt_hi_u32_b32_e32 v0, s3, v0
|
|
; GFX7LESS-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX7LESS-NEXT: ; implicit-def: $vgpr0_vgpr1
|
|
; GFX7LESS-NEXT: s_and_saveexec_b64 s[2:3], vcc
|
|
; GFX7LESS-NEXT: ; mask branch BB18_2
|
|
; GFX7LESS-NEXT: s_cbranch_execz BB18_2
|
|
; GFX7LESS-NEXT: BB18_1:
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v0, 5
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX7LESS-NEXT: s_mov_b32 m0, -1
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: ds_max_rtn_i64 v[0:1], v2, v[0:1]
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: buffer_wbinvl1
|
|
; GFX7LESS-NEXT: BB18_2:
|
|
; GFX7LESS-NEXT: s_or_b64 exec, exec, s[2:3]
|
|
; GFX7LESS-NEXT: v_readfirstlane_b32 s4, v0
|
|
; GFX7LESS-NEXT: v_readfirstlane_b32 s5, v1
|
|
; GFX7LESS-NEXT: v_bfrev_b32_e32 v1, 1
|
|
; GFX7LESS-NEXT: v_cndmask_b32_e64 v0, 5, 0, vcc
|
|
; GFX7LESS-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX7LESS-NEXT: v_cndmask_b32_e32 v1, 0, v1, vcc
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v2, s5
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v3, s4
|
|
; GFX7LESS-NEXT: v_cmp_gt_i64_e32 vcc, s[4:5], v[0:1]
|
|
; GFX7LESS-NEXT: v_cndmask_b32_e32 v1, v1, v2, vcc
|
|
; GFX7LESS-NEXT: v_cndmask_b32_e32 v0, v0, v3, vcc
|
|
; GFX7LESS-NEXT: s_mov_b32 s2, -1
|
|
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7LESS-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX7LESS-NEXT: s_endpgm
|
|
;
|
|
; GFX8-LABEL: max_i64_constant:
|
|
; GFX8: ; %bb.0: ; %entry
|
|
; GFX8-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX8-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX8-NEXT: v_mbcnt_lo_u32_b32 v0, s2, 0
|
|
; GFX8-NEXT: v_mbcnt_hi_u32_b32 v0, s3, v0
|
|
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX8-NEXT: ; implicit-def: $vgpr0_vgpr1
|
|
; GFX8-NEXT: s_and_saveexec_b64 s[2:3], vcc
|
|
; GFX8-NEXT: ; mask branch BB18_2
|
|
; GFX8-NEXT: s_cbranch_execz BB18_2
|
|
; GFX8-NEXT: BB18_1:
|
|
; GFX8-NEXT: v_mov_b32_e32 v0, 5
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
|
|
; GFX8-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX8-NEXT: s_mov_b32 m0, -1
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: ds_max_rtn_i64 v[0:1], v2, v[0:1]
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_wbinvl1_vol
|
|
; GFX8-NEXT: BB18_2:
|
|
; GFX8-NEXT: s_or_b64 exec, exec, s[2:3]
|
|
; GFX8-NEXT: v_readfirstlane_b32 s2, v0
|
|
; GFX8-NEXT: v_bfrev_b32_e32 v0, 1
|
|
; GFX8-NEXT: v_readfirstlane_b32 s3, v1
|
|
; GFX8-NEXT: v_cndmask_b32_e32 v1, 0, v0, vcc
|
|
; GFX8-NEXT: v_cndmask_b32_e64 v0, 5, 0, vcc
|
|
; GFX8-NEXT: v_cmp_gt_i64_e32 vcc, s[2:3], v[0:1]
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, s3
|
|
; GFX8-NEXT: v_cndmask_b32_e32 v1, v1, v2, vcc
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX8-NEXT: v_cndmask_b32_e32 v0, v0, v2, vcc
|
|
; GFX8-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX8-NEXT: s_mov_b32 s2, -1
|
|
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX8-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: max_i64_constant:
|
|
; GFX9: ; %bb.0: ; %entry
|
|
; GFX9-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX9-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX9-NEXT: v_mbcnt_lo_u32_b32 v0, s2, 0
|
|
; GFX9-NEXT: v_mbcnt_hi_u32_b32 v0, s3, v0
|
|
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX9-NEXT: ; implicit-def: $vgpr0_vgpr1
|
|
; GFX9-NEXT: s_and_saveexec_b64 s[2:3], vcc
|
|
; GFX9-NEXT: ; mask branch BB18_2
|
|
; GFX9-NEXT: s_cbranch_execz BB18_2
|
|
; GFX9-NEXT: BB18_1:
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, 5
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
|
|
; GFX9-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: ds_max_rtn_i64 v[0:1], v2, v[0:1]
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_wbinvl1_vol
|
|
; GFX9-NEXT: BB18_2:
|
|
; GFX9-NEXT: s_or_b64 exec, exec, s[2:3]
|
|
; GFX9-NEXT: v_readfirstlane_b32 s2, v0
|
|
; GFX9-NEXT: v_bfrev_b32_e32 v0, 1
|
|
; GFX9-NEXT: v_readfirstlane_b32 s3, v1
|
|
; GFX9-NEXT: v_cndmask_b32_e32 v1, 0, v0, vcc
|
|
; GFX9-NEXT: v_cndmask_b32_e64 v0, 5, 0, vcc
|
|
; GFX9-NEXT: v_cmp_gt_i64_e32 vcc, s[2:3], v[0:1]
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, s3
|
|
; GFX9-NEXT: v_cndmask_b32_e32 v1, v1, v2, vcc
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX9-NEXT: v_cndmask_b32_e32 v0, v0, v2, vcc
|
|
; GFX9-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX9-NEXT: s_mov_b32 s2, -1
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX1064-LABEL: max_i64_constant:
|
|
; GFX1064: ; %bb.0: ; %entry
|
|
; GFX1064-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX1064-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1064-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s2, 0
|
|
; GFX1064-NEXT: v_mbcnt_hi_u32_b32_e64 v0, s3, v0
|
|
; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX1064-NEXT: ; implicit-def: $vgpr0_vgpr1
|
|
; GFX1064-NEXT: s_and_saveexec_b64 s[2:3], vcc
|
|
; GFX1064-NEXT: ; mask branch BB18_2
|
|
; GFX1064-NEXT: s_cbranch_execz BB18_2
|
|
; GFX1064-NEXT: BB18_1:
|
|
; GFX1064-NEXT: v_mov_b32_e32 v0, 5
|
|
; GFX1064-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
|
|
; GFX1064-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1064-NEXT: ds_max_rtn_i64 v[0:1], v2, v[0:1]
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_gl0_inv
|
|
; GFX1064-NEXT: buffer_gl1_inv
|
|
; GFX1064-NEXT: BB18_2:
|
|
; GFX1064-NEXT: v_nop
|
|
; GFX1064-NEXT: s_or_b64 exec, exec, s[2:3]
|
|
; GFX1064-NEXT: v_readfirstlane_b32 s4, v0
|
|
; GFX1064-NEXT: v_readfirstlane_b32 s5, v1
|
|
; GFX1064-NEXT: v_cndmask_b32_e64 v1, 0, 0x80000000, vcc
|
|
; GFX1064-NEXT: v_cndmask_b32_e64 v0, 5, 0, vcc
|
|
; GFX1064-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1064-NEXT: s_mov_b32 s2, -1
|
|
; GFX1064-NEXT: v_cmp_gt_i64_e32 vcc, s[4:5], v[0:1]
|
|
; GFX1064-NEXT: v_cndmask_b32_e64 v1, v1, s5, vcc
|
|
; GFX1064-NEXT: v_cndmask_b32_e64 v0, v0, s4, vcc
|
|
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX1064-NEXT: s_endpgm
|
|
;
|
|
; GFX1032-LABEL: max_i64_constant:
|
|
; GFX1032: ; %bb.0: ; %entry
|
|
; GFX1032-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1032-NEXT: v_cmp_ne_u32_e64 s2, 1, 0
|
|
; GFX1032-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX1032-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s2, 0
|
|
; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v0
|
|
; GFX1032-NEXT: ; implicit-def: $vgpr0_vgpr1
|
|
; GFX1032-NEXT: s_and_saveexec_b32 s2, vcc_lo
|
|
; GFX1032-NEXT: ; mask branch BB18_2
|
|
; GFX1032-NEXT: s_cbranch_execz BB18_2
|
|
; GFX1032-NEXT: BB18_1:
|
|
; GFX1032-NEXT: v_mov_b32_e32 v0, 5
|
|
; GFX1032-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
|
|
; GFX1032-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1032-NEXT: ds_max_rtn_i64 v[0:1], v2, v[0:1]
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_gl0_inv
|
|
; GFX1032-NEXT: buffer_gl1_inv
|
|
; GFX1032-NEXT: BB18_2:
|
|
; GFX1032-NEXT: v_nop
|
|
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s2
|
|
; GFX1032-NEXT: v_readfirstlane_b32 s4, v0
|
|
; GFX1032-NEXT: v_readfirstlane_b32 s5, v1
|
|
; GFX1032-NEXT: v_cndmask_b32_e64 v1, 0, 0x80000000, vcc_lo
|
|
; GFX1032-NEXT: v_cndmask_b32_e64 v0, 5, 0, vcc_lo
|
|
; GFX1032-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1032-NEXT: s_mov_b32 s2, -1
|
|
; GFX1032-NEXT: v_cmp_gt_i64_e32 vcc_lo, s[4:5], v[0:1]
|
|
; GFX1032-NEXT: v_cndmask_b32_e64 v1, v1, s5, vcc_lo
|
|
; GFX1032-NEXT: v_cndmask_b32_e64 v0, v0, s4, vcc_lo
|
|
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX1032-NEXT: s_endpgm
|
|
entry:
|
|
%old = atomicrmw max i64 addrspace(3)* @local_var64, i64 5 acq_rel
|
|
store i64 %old, i64 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; GFX8MORE32: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 31
|
|
; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
|
|
; GFX8MORE: ds_min_rtn_i32 v{{[0-9]+}}, v{{[0-9]+}}, v[[value]]
|
|
define amdgpu_kernel void @min_i32_varying(i32 addrspace(1)* %out) {
|
|
;
|
|
;
|
|
; GFX7LESS-LABEL: min_i32_varying:
|
|
; GFX7LESS: ; %bb.0: ; %entry
|
|
; GFX7LESS-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v1, local_var32@abs32@lo
|
|
; GFX7LESS-NEXT: s_mov_b32 m0, -1
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: ds_min_rtn_i32 v0, v1, v0
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: buffer_wbinvl1
|
|
; GFX7LESS-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX7LESS-NEXT: s_mov_b32 s2, -1
|
|
; GFX7LESS-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX7LESS-NEXT: s_endpgm
|
|
;
|
|
; GFX8-LABEL: min_i32_varying:
|
|
; GFX8: ; %bb.0: ; %entry
|
|
; GFX8-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX8-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX8-NEXT: v_mbcnt_lo_u32_b32 v3, s2, 0
|
|
; GFX8-NEXT: v_mbcnt_hi_u32_b32 v3, s3, v3
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX8-NEXT: s_or_saveexec_b64 s[2:3], -1
|
|
; GFX8-NEXT: v_bfrev_b32_e32 v1, -2
|
|
; GFX8-NEXT: s_mov_b64 exec, s[2:3]
|
|
; GFX8-NEXT: s_not_b64 exec, exec
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, v1
|
|
; GFX8-NEXT: s_not_b64 exec, exec
|
|
; GFX8-NEXT: s_or_saveexec_b64 s[4:5], -1
|
|
; GFX8-NEXT: v_min_i32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_min_i32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_min_i32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_min_i32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_min_i32_dpp v2, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_min_i32_dpp v2, v2, v2 row_bcast:31 row_mask:0xc bank_mask:0xf
|
|
; GFX8-NEXT: v_readlane_b32 s2, v2, 63
|
|
; GFX8-NEXT: s_nop 0
|
|
; GFX8-NEXT: v_mov_b32_dpp v1, v2 wave_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX8-NEXT: s_mov_b64 exec, s[4:5]
|
|
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v3
|
|
; GFX8-NEXT: ; implicit-def: $vgpr0
|
|
; GFX8-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX8-NEXT: ; mask branch BB19_2
|
|
; GFX8-NEXT: s_cbranch_execz BB19_2
|
|
; GFX8-NEXT: BB19_1:
|
|
; GFX8-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX8-NEXT: v_mov_b32_e32 v3, s2
|
|
; GFX8-NEXT: s_mov_b32 m0, -1
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: ds_min_rtn_i32 v0, v0, v3
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_wbinvl1_vol
|
|
; GFX8-NEXT: BB19_2:
|
|
; GFX8-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX8-NEXT: v_readfirstlane_b32 s2, v0
|
|
; GFX8-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX8-NEXT: v_min_i32_e32 v0, s2, v0
|
|
; GFX8-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX8-NEXT: s_mov_b32 s2, -1
|
|
; GFX8-NEXT: s_nop 0
|
|
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX8-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: min_i32_varying:
|
|
; GFX9: ; %bb.0: ; %entry
|
|
; GFX9-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX9-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX9-NEXT: v_mbcnt_lo_u32_b32 v3, s2, 0
|
|
; GFX9-NEXT: v_mbcnt_hi_u32_b32 v3, s3, v3
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX9-NEXT: s_or_saveexec_b64 s[2:3], -1
|
|
; GFX9-NEXT: v_bfrev_b32_e32 v1, -2
|
|
; GFX9-NEXT: s_mov_b64 exec, s[2:3]
|
|
; GFX9-NEXT: s_not_b64 exec, exec
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, v1
|
|
; GFX9-NEXT: s_not_b64 exec, exec
|
|
; GFX9-NEXT: s_or_saveexec_b64 s[4:5], -1
|
|
; GFX9-NEXT: v_min_i32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_min_i32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_min_i32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_min_i32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_min_i32_dpp v2, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_min_i32_dpp v2, v2, v2 row_bcast:31 row_mask:0xc bank_mask:0xf
|
|
; GFX9-NEXT: v_readlane_b32 s2, v2, 63
|
|
; GFX9-NEXT: s_nop 0
|
|
; GFX9-NEXT: v_mov_b32_dpp v1, v2 wave_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX9-NEXT: s_mov_b64 exec, s[4:5]
|
|
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v3
|
|
; GFX9-NEXT: ; implicit-def: $vgpr0
|
|
; GFX9-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX9-NEXT: ; mask branch BB19_2
|
|
; GFX9-NEXT: s_cbranch_execz BB19_2
|
|
; GFX9-NEXT: BB19_1:
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX9-NEXT: v_mov_b32_e32 v3, s2
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: ds_min_rtn_i32 v0, v0, v3
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_wbinvl1_vol
|
|
; GFX9-NEXT: BB19_2:
|
|
; GFX9-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX9-NEXT: v_readfirstlane_b32 s2, v0
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX9-NEXT: v_min_i32_e32 v0, s2, v0
|
|
; GFX9-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX9-NEXT: s_mov_b32 s2, -1
|
|
; GFX9-NEXT: s_nop 0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX1064-LABEL: min_i32_varying:
|
|
; GFX1064: ; %bb.0: ; %entry
|
|
; GFX1064-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1064-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX1064-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX1064-NEXT: v_mbcnt_lo_u32_b32_e64 v4, s2, 0
|
|
; GFX1064-NEXT: v_mbcnt_hi_u32_b32_e64 v4, s3, v4
|
|
; GFX1064-NEXT: s_or_saveexec_b64 s[2:3], -1
|
|
; GFX1064-NEXT: v_bfrev_b32_e32 v1, -2
|
|
; GFX1064-NEXT: s_mov_b64 exec, s[2:3]
|
|
; GFX1064-NEXT: s_not_b64 exec, exec
|
|
; GFX1064-NEXT: v_mov_b32_e32 v2, v1
|
|
; GFX1064-NEXT: s_not_b64 exec, exec
|
|
; GFX1064-NEXT: s_or_saveexec_b64 s[4:5], -1
|
|
; GFX1064-NEXT: v_min_i32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX1064-NEXT: v_min_i32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf
|
|
; GFX1064-NEXT: v_min_i32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf
|
|
; GFX1064-NEXT: v_min_i32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf
|
|
; GFX1064-NEXT: v_mov_b32_e32 v3, v2
|
|
; GFX1064-NEXT: v_permlanex16_b32 v3, v3, -1, -1
|
|
; GFX1064-NEXT: v_min_i32_dpp v2, v3, v2 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf
|
|
; GFX1064-NEXT: v_readlane_b32 s2, v2, 31
|
|
; GFX1064-NEXT: v_mov_b32_e32 v3, s2
|
|
; GFX1064-NEXT: v_min_i32_dpp v2, v3, v2 quad_perm:[0,1,2,3] row_mask:0xc bank_mask:0xf
|
|
; GFX1064-NEXT: v_readlane_b32 s2, v2, 15
|
|
; GFX1064-NEXT: v_mov_b32_dpp v1, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX1064-NEXT: v_readlane_b32 s3, v2, 31
|
|
; GFX1064-NEXT: v_readlane_b32 s6, v2, 47
|
|
; GFX1064-NEXT: v_writelane_b32 v1, s2, 16
|
|
; GFX1064-NEXT: s_mov_b32 s2, -1
|
|
; GFX1064-NEXT: v_writelane_b32 v1, s3, 32
|
|
; GFX1064-NEXT: v_readlane_b32 s3, v2, 63
|
|
; GFX1064-NEXT: v_writelane_b32 v1, s6, 48
|
|
; GFX1064-NEXT: s_mov_b64 exec, s[4:5]
|
|
; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v4
|
|
; GFX1064-NEXT: ; implicit-def: $vgpr0
|
|
; GFX1064-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX1064-NEXT: ; mask branch BB19_2
|
|
; GFX1064-NEXT: s_cbranch_execz BB19_2
|
|
; GFX1064-NEXT: BB19_1:
|
|
; GFX1064-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX1064-NEXT: v_mov_b32_e32 v7, s3
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1064-NEXT: ds_min_rtn_i32 v0, v0, v7
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_gl0_inv
|
|
; GFX1064-NEXT: buffer_gl1_inv
|
|
; GFX1064-NEXT: BB19_2:
|
|
; GFX1064-NEXT: v_nop
|
|
; GFX1064-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX1064-NEXT: v_readfirstlane_b32 s3, v0
|
|
; GFX1064-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX1064-NEXT: v_min_i32_e32 v0, s3, v0
|
|
; GFX1064-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1064-NEXT: s_nop 1
|
|
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX1064-NEXT: s_endpgm
|
|
;
|
|
; GFX1032-LABEL: min_i32_varying:
|
|
; GFX1032: ; %bb.0: ; %entry
|
|
; GFX1032-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1032-NEXT: v_cmp_ne_u32_e64 s2, 1, 0
|
|
; GFX1032-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX1032-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX1032-NEXT: v_mbcnt_lo_u32_b32_e64 v4, s2, 0
|
|
; GFX1032-NEXT: s_or_saveexec_b32 s2, -1
|
|
; GFX1032-NEXT: v_bfrev_b32_e32 v1, -2
|
|
; GFX1032-NEXT: s_mov_b32 exec_lo, s2
|
|
; GFX1032-NEXT: s_not_b32 exec_lo, exec_lo
|
|
; GFX1032-NEXT: v_mov_b32_e32 v2, v1
|
|
; GFX1032-NEXT: s_not_b32 exec_lo, exec_lo
|
|
; GFX1032-NEXT: s_or_saveexec_b32 s4, -1
|
|
; GFX1032-NEXT: v_min_i32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX1032-NEXT: s_mov_b32 s2, -1
|
|
; GFX1032-NEXT: v_min_i32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf
|
|
; GFX1032-NEXT: v_min_i32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf
|
|
; GFX1032-NEXT: v_min_i32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf
|
|
; GFX1032-NEXT: v_mov_b32_e32 v3, v2
|
|
; GFX1032-NEXT: v_permlanex16_b32 v3, v3, -1, -1
|
|
; GFX1032-NEXT: v_min_i32_dpp v2, v3, v2 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf
|
|
; GFX1032-NEXT: v_readlane_b32 s3, v2, 31
|
|
; GFX1032-NEXT: v_mov_b32_dpp v1, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX1032-NEXT: v_readlane_b32 s5, v2, 15
|
|
; GFX1032-NEXT: v_writelane_b32 v1, s5, 16
|
|
; GFX1032-NEXT: s_mov_b32 exec_lo, s4
|
|
; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v4
|
|
; GFX1032-NEXT: ; implicit-def: $vgpr0
|
|
; GFX1032-NEXT: s_and_saveexec_b32 s4, vcc_lo
|
|
; GFX1032-NEXT: ; mask branch BB19_2
|
|
; GFX1032-NEXT: s_cbranch_execz BB19_2
|
|
; GFX1032-NEXT: BB19_1:
|
|
; GFX1032-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX1032-NEXT: v_mov_b32_e32 v7, s3
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1032-NEXT: ds_min_rtn_i32 v0, v0, v7
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_gl0_inv
|
|
; GFX1032-NEXT: buffer_gl1_inv
|
|
; GFX1032-NEXT: BB19_2:
|
|
; GFX1032-NEXT: v_nop
|
|
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s4
|
|
; GFX1032-NEXT: v_readfirstlane_b32 s3, v0
|
|
; GFX1032-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX1032-NEXT: v_min_i32_e32 v0, s3, v0
|
|
; GFX1032-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1032-NEXT: s_nop 1
|
|
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX1032-NEXT: s_endpgm
|
|
entry:
|
|
%lane = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%old = atomicrmw min i32 addrspace(3)* @local_var32, i32 %lane acq_rel
|
|
store i32 %old, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @min_i64_constant(i64 addrspace(1)* %out) {
|
|
;
|
|
;
|
|
; GFX7LESS-LABEL: min_i64_constant:
|
|
; GFX7LESS: ; %bb.0: ; %entry
|
|
; GFX7LESS-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; GFX7LESS-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX7LESS-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s2, 0
|
|
; GFX7LESS-NEXT: v_mbcnt_hi_u32_b32_e32 v0, s3, v0
|
|
; GFX7LESS-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX7LESS-NEXT: ; implicit-def: $vgpr0_vgpr1
|
|
; GFX7LESS-NEXT: s_and_saveexec_b64 s[2:3], vcc
|
|
; GFX7LESS-NEXT: ; mask branch BB20_2
|
|
; GFX7LESS-NEXT: s_cbranch_execz BB20_2
|
|
; GFX7LESS-NEXT: BB20_1:
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v0, 5
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX7LESS-NEXT: s_mov_b32 m0, -1
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: ds_min_rtn_i64 v[0:1], v2, v[0:1]
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: buffer_wbinvl1
|
|
; GFX7LESS-NEXT: BB20_2:
|
|
; GFX7LESS-NEXT: s_or_b64 exec, exec, s[2:3]
|
|
; GFX7LESS-NEXT: v_readfirstlane_b32 s4, v0
|
|
; GFX7LESS-NEXT: v_readfirstlane_b32 s5, v1
|
|
; GFX7LESS-NEXT: v_bfrev_b32_e32 v1, -2
|
|
; GFX7LESS-NEXT: s_mov_b32 s2, -1
|
|
; GFX7LESS-NEXT: v_cndmask_b32_e64 v0, 5, -1, vcc
|
|
; GFX7LESS-NEXT: v_cndmask_b32_e32 v1, 0, v1, vcc
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v2, s5
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v3, s4
|
|
; GFX7LESS-NEXT: v_cmp_lt_i64_e32 vcc, s[4:5], v[0:1]
|
|
; GFX7LESS-NEXT: v_cndmask_b32_e32 v1, v1, v2, vcc
|
|
; GFX7LESS-NEXT: v_cndmask_b32_e32 v0, v0, v3, vcc
|
|
; GFX7LESS-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7LESS-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX7LESS-NEXT: s_endpgm
|
|
;
|
|
; GFX8-LABEL: min_i64_constant:
|
|
; GFX8: ; %bb.0: ; %entry
|
|
; GFX8-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX8-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX8-NEXT: v_mbcnt_lo_u32_b32 v0, s2, 0
|
|
; GFX8-NEXT: v_mbcnt_hi_u32_b32 v0, s3, v0
|
|
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX8-NEXT: ; implicit-def: $vgpr0_vgpr1
|
|
; GFX8-NEXT: s_and_saveexec_b64 s[2:3], vcc
|
|
; GFX8-NEXT: ; mask branch BB20_2
|
|
; GFX8-NEXT: s_cbranch_execz BB20_2
|
|
; GFX8-NEXT: BB20_1:
|
|
; GFX8-NEXT: v_mov_b32_e32 v0, 5
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
|
|
; GFX8-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX8-NEXT: s_mov_b32 m0, -1
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: ds_min_rtn_i64 v[0:1], v2, v[0:1]
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_wbinvl1_vol
|
|
; GFX8-NEXT: BB20_2:
|
|
; GFX8-NEXT: s_or_b64 exec, exec, s[2:3]
|
|
; GFX8-NEXT: v_readfirstlane_b32 s4, v0
|
|
; GFX8-NEXT: v_bfrev_b32_e32 v0, -2
|
|
; GFX8-NEXT: v_readfirstlane_b32 s5, v1
|
|
; GFX8-NEXT: v_cndmask_b32_e32 v1, 0, v0, vcc
|
|
; GFX8-NEXT: v_cndmask_b32_e64 v0, 5, -1, vcc
|
|
; GFX8-NEXT: v_cmp_lt_i64_e32 vcc, s[4:5], v[0:1]
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, s5
|
|
; GFX8-NEXT: v_cndmask_b32_e32 v1, v1, v2, vcc
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, s4
|
|
; GFX8-NEXT: s_mov_b32 s2, -1
|
|
; GFX8-NEXT: v_cndmask_b32_e32 v0, v0, v2, vcc
|
|
; GFX8-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX8-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: min_i64_constant:
|
|
; GFX9: ; %bb.0: ; %entry
|
|
; GFX9-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX9-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX9-NEXT: v_mbcnt_lo_u32_b32 v0, s2, 0
|
|
; GFX9-NEXT: v_mbcnt_hi_u32_b32 v0, s3, v0
|
|
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX9-NEXT: ; implicit-def: $vgpr0_vgpr1
|
|
; GFX9-NEXT: s_and_saveexec_b64 s[2:3], vcc
|
|
; GFX9-NEXT: ; mask branch BB20_2
|
|
; GFX9-NEXT: s_cbranch_execz BB20_2
|
|
; GFX9-NEXT: BB20_1:
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, 5
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
|
|
; GFX9-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: ds_min_rtn_i64 v[0:1], v2, v[0:1]
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_wbinvl1_vol
|
|
; GFX9-NEXT: BB20_2:
|
|
; GFX9-NEXT: s_or_b64 exec, exec, s[2:3]
|
|
; GFX9-NEXT: v_readfirstlane_b32 s4, v0
|
|
; GFX9-NEXT: v_bfrev_b32_e32 v0, -2
|
|
; GFX9-NEXT: v_readfirstlane_b32 s5, v1
|
|
; GFX9-NEXT: v_cndmask_b32_e32 v1, 0, v0, vcc
|
|
; GFX9-NEXT: v_cndmask_b32_e64 v0, 5, -1, vcc
|
|
; GFX9-NEXT: v_cmp_lt_i64_e32 vcc, s[4:5], v[0:1]
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, s5
|
|
; GFX9-NEXT: v_cndmask_b32_e32 v1, v1, v2, vcc
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, s4
|
|
; GFX9-NEXT: s_mov_b32 s2, -1
|
|
; GFX9-NEXT: v_cndmask_b32_e32 v0, v0, v2, vcc
|
|
; GFX9-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX1064-LABEL: min_i64_constant:
|
|
; GFX1064: ; %bb.0: ; %entry
|
|
; GFX1064-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX1064-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1064-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s2, 0
|
|
; GFX1064-NEXT: v_mbcnt_hi_u32_b32_e64 v0, s3, v0
|
|
; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX1064-NEXT: ; implicit-def: $vgpr0_vgpr1
|
|
; GFX1064-NEXT: s_and_saveexec_b64 s[2:3], vcc
|
|
; GFX1064-NEXT: ; mask branch BB20_2
|
|
; GFX1064-NEXT: s_cbranch_execz BB20_2
|
|
; GFX1064-NEXT: BB20_1:
|
|
; GFX1064-NEXT: v_mov_b32_e32 v0, 5
|
|
; GFX1064-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
|
|
; GFX1064-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1064-NEXT: ds_min_rtn_i64 v[0:1], v2, v[0:1]
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_gl0_inv
|
|
; GFX1064-NEXT: buffer_gl1_inv
|
|
; GFX1064-NEXT: BB20_2:
|
|
; GFX1064-NEXT: v_nop
|
|
; GFX1064-NEXT: s_or_b64 exec, exec, s[2:3]
|
|
; GFX1064-NEXT: v_readfirstlane_b32 s4, v0
|
|
; GFX1064-NEXT: v_readfirstlane_b32 s5, v1
|
|
; GFX1064-NEXT: v_cndmask_b32_e64 v1, 0, 0x7fffffff, vcc
|
|
; GFX1064-NEXT: v_cndmask_b32_e64 v0, 5, -1, vcc
|
|
; GFX1064-NEXT: s_mov_b32 s2, -1
|
|
; GFX1064-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1064-NEXT: v_cmp_lt_i64_e32 vcc, s[4:5], v[0:1]
|
|
; GFX1064-NEXT: v_cndmask_b32_e64 v1, v1, s5, vcc
|
|
; GFX1064-NEXT: v_cndmask_b32_e64 v0, v0, s4, vcc
|
|
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX1064-NEXT: s_endpgm
|
|
;
|
|
; GFX1032-LABEL: min_i64_constant:
|
|
; GFX1032: ; %bb.0: ; %entry
|
|
; GFX1032-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1032-NEXT: v_cmp_ne_u32_e64 s2, 1, 0
|
|
; GFX1032-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX1032-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s2, 0
|
|
; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v0
|
|
; GFX1032-NEXT: ; implicit-def: $vgpr0_vgpr1
|
|
; GFX1032-NEXT: s_and_saveexec_b32 s2, vcc_lo
|
|
; GFX1032-NEXT: ; mask branch BB20_2
|
|
; GFX1032-NEXT: s_cbranch_execz BB20_2
|
|
; GFX1032-NEXT: BB20_1:
|
|
; GFX1032-NEXT: v_mov_b32_e32 v0, 5
|
|
; GFX1032-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
|
|
; GFX1032-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1032-NEXT: ds_min_rtn_i64 v[0:1], v2, v[0:1]
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_gl0_inv
|
|
; GFX1032-NEXT: buffer_gl1_inv
|
|
; GFX1032-NEXT: BB20_2:
|
|
; GFX1032-NEXT: v_nop
|
|
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s2
|
|
; GFX1032-NEXT: v_readfirstlane_b32 s4, v0
|
|
; GFX1032-NEXT: v_readfirstlane_b32 s5, v1
|
|
; GFX1032-NEXT: v_cndmask_b32_e64 v1, 0, 0x7fffffff, vcc_lo
|
|
; GFX1032-NEXT: v_cndmask_b32_e64 v0, 5, -1, vcc_lo
|
|
; GFX1032-NEXT: s_mov_b32 s2, -1
|
|
; GFX1032-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1032-NEXT: v_cmp_lt_i64_e32 vcc_lo, s[4:5], v[0:1]
|
|
; GFX1032-NEXT: v_cndmask_b32_e64 v1, v1, s5, vcc_lo
|
|
; GFX1032-NEXT: v_cndmask_b32_e64 v0, v0, s4, vcc_lo
|
|
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX1032-NEXT: s_endpgm
|
|
entry:
|
|
%old = atomicrmw min i64 addrspace(3)* @local_var64, i64 5 acq_rel
|
|
store i64 %old, i64 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; GFX8MORE32: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 31
|
|
; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
|
|
; GFX8MORE: ds_max_rtn_u32 v{{[0-9]+}}, v{{[0-9]+}}, v[[value]]
|
|
define amdgpu_kernel void @umax_i32_varying(i32 addrspace(1)* %out) {
|
|
;
|
|
;
|
|
; GFX7LESS-LABEL: umax_i32_varying:
|
|
; GFX7LESS: ; %bb.0: ; %entry
|
|
; GFX7LESS-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v1, local_var32@abs32@lo
|
|
; GFX7LESS-NEXT: s_mov_b32 m0, -1
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: ds_max_rtn_u32 v0, v1, v0
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: buffer_wbinvl1
|
|
; GFX7LESS-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX7LESS-NEXT: s_mov_b32 s2, -1
|
|
; GFX7LESS-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX7LESS-NEXT: s_endpgm
|
|
;
|
|
; GFX8-LABEL: umax_i32_varying:
|
|
; GFX8: ; %bb.0: ; %entry
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX8-NEXT: s_or_saveexec_b64 s[2:3], -1
|
|
; GFX8-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX8-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX8-NEXT: s_mov_b64 exec, s[2:3]
|
|
; GFX8-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX8-NEXT: v_mbcnt_lo_u32_b32 v0, s2, 0
|
|
; GFX8-NEXT: v_mbcnt_hi_u32_b32 v0, s3, v0
|
|
; GFX8-NEXT: s_not_b64 exec, exec
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX8-NEXT: s_not_b64 exec, exec
|
|
; GFX8-NEXT: s_or_saveexec_b64 s[4:5], -1
|
|
; GFX8-NEXT: v_max_u32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_max_u32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_max_u32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_max_u32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_max_u32_dpp v2, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_max_u32_dpp v2, v2, v2 row_bcast:31 row_mask:0xc bank_mask:0xf
|
|
; GFX8-NEXT: v_readlane_b32 s2, v2, 63
|
|
; GFX8-NEXT: s_nop 0
|
|
; GFX8-NEXT: v_mov_b32_dpp v1, v2 wave_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX8-NEXT: s_mov_b64 exec, s[4:5]
|
|
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX8-NEXT: ; implicit-def: $vgpr0
|
|
; GFX8-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX8-NEXT: ; mask branch BB21_2
|
|
; GFX8-NEXT: s_cbranch_execz BB21_2
|
|
; GFX8-NEXT: BB21_1:
|
|
; GFX8-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX8-NEXT: v_mov_b32_e32 v3, s2
|
|
; GFX8-NEXT: s_mov_b32 m0, -1
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: ds_max_rtn_u32 v0, v0, v3
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_wbinvl1_vol
|
|
; GFX8-NEXT: BB21_2:
|
|
; GFX8-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX8-NEXT: v_readfirstlane_b32 s2, v0
|
|
; GFX8-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX8-NEXT: v_max_u32_e32 v0, s2, v0
|
|
; GFX8-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX8-NEXT: s_mov_b32 s2, -1
|
|
; GFX8-NEXT: s_nop 0
|
|
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX8-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: umax_i32_varying:
|
|
; GFX9: ; %bb.0: ; %entry
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX9-NEXT: s_or_saveexec_b64 s[2:3], -1
|
|
; GFX9-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX9-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX9-NEXT: s_mov_b64 exec, s[2:3]
|
|
; GFX9-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX9-NEXT: v_mbcnt_lo_u32_b32 v0, s2, 0
|
|
; GFX9-NEXT: v_mbcnt_hi_u32_b32 v0, s3, v0
|
|
; GFX9-NEXT: s_not_b64 exec, exec
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX9-NEXT: s_not_b64 exec, exec
|
|
; GFX9-NEXT: s_or_saveexec_b64 s[4:5], -1
|
|
; GFX9-NEXT: v_max_u32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_max_u32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_max_u32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_max_u32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_max_u32_dpp v2, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_max_u32_dpp v2, v2, v2 row_bcast:31 row_mask:0xc bank_mask:0xf
|
|
; GFX9-NEXT: v_readlane_b32 s2, v2, 63
|
|
; GFX9-NEXT: s_nop 0
|
|
; GFX9-NEXT: v_mov_b32_dpp v1, v2 wave_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX9-NEXT: s_mov_b64 exec, s[4:5]
|
|
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX9-NEXT: ; implicit-def: $vgpr0
|
|
; GFX9-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX9-NEXT: ; mask branch BB21_2
|
|
; GFX9-NEXT: s_cbranch_execz BB21_2
|
|
; GFX9-NEXT: BB21_1:
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX9-NEXT: v_mov_b32_e32 v3, s2
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: ds_max_rtn_u32 v0, v0, v3
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_wbinvl1_vol
|
|
; GFX9-NEXT: BB21_2:
|
|
; GFX9-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX9-NEXT: v_readfirstlane_b32 s2, v0
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX9-NEXT: v_max_u32_e32 v0, s2, v0
|
|
; GFX9-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX9-NEXT: s_mov_b32 s2, -1
|
|
; GFX9-NEXT: s_nop 0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX1064-LABEL: umax_i32_varying:
|
|
; GFX1064: ; %bb.0: ; %entry
|
|
; GFX1064-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX1064-NEXT: s_or_saveexec_b64 s[2:3], -1
|
|
; GFX1064-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1064-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX1064-NEXT: s_mov_b64 exec, s[2:3]
|
|
; GFX1064-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX1064-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s2, 0
|
|
; GFX1064-NEXT: v_mbcnt_hi_u32_b32_e64 v0, s3, v0
|
|
; GFX1064-NEXT: s_not_b64 exec, exec
|
|
; GFX1064-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX1064-NEXT: s_not_b64 exec, exec
|
|
; GFX1064-NEXT: s_or_saveexec_b64 s[4:5], -1
|
|
; GFX1064-NEXT: v_max_u32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1064-NEXT: v_max_u32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1064-NEXT: v_max_u32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1064-NEXT: v_max_u32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1064-NEXT: v_mov_b32_e32 v3, v2
|
|
; GFX1064-NEXT: v_permlanex16_b32 v3, v3, -1, -1
|
|
; GFX1064-NEXT: v_max_u32_dpp v2, v3, v2 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf
|
|
; GFX1064-NEXT: v_readlane_b32 s2, v2, 31
|
|
; GFX1064-NEXT: v_mov_b32_e32 v3, s2
|
|
; GFX1064-NEXT: v_max_u32_dpp v2, v3, v2 quad_perm:[0,1,2,3] row_mask:0xc bank_mask:0xf
|
|
; GFX1064-NEXT: v_readlane_b32 s2, v2, 15
|
|
; GFX1064-NEXT: v_mov_b32_dpp v1, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX1064-NEXT: v_readlane_b32 s3, v2, 31
|
|
; GFX1064-NEXT: v_readlane_b32 s6, v2, 47
|
|
; GFX1064-NEXT: v_writelane_b32 v1, s2, 16
|
|
; GFX1064-NEXT: s_mov_b32 s2, -1
|
|
; GFX1064-NEXT: v_writelane_b32 v1, s3, 32
|
|
; GFX1064-NEXT: v_readlane_b32 s3, v2, 63
|
|
; GFX1064-NEXT: v_writelane_b32 v1, s6, 48
|
|
; GFX1064-NEXT: s_mov_b64 exec, s[4:5]
|
|
; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX1064-NEXT: ; implicit-def: $vgpr0
|
|
; GFX1064-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX1064-NEXT: ; mask branch BB21_2
|
|
; GFX1064-NEXT: s_cbranch_execz BB21_2
|
|
; GFX1064-NEXT: BB21_1:
|
|
; GFX1064-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX1064-NEXT: v_mov_b32_e32 v7, s3
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1064-NEXT: ds_max_rtn_u32 v0, v0, v7
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_gl0_inv
|
|
; GFX1064-NEXT: buffer_gl1_inv
|
|
; GFX1064-NEXT: BB21_2:
|
|
; GFX1064-NEXT: v_nop
|
|
; GFX1064-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX1064-NEXT: v_readfirstlane_b32 s3, v0
|
|
; GFX1064-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX1064-NEXT: v_max_u32_e32 v0, s3, v0
|
|
; GFX1064-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1064-NEXT: s_nop 1
|
|
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX1064-NEXT: s_endpgm
|
|
;
|
|
; GFX1032-LABEL: umax_i32_varying:
|
|
; GFX1032: ; %bb.0: ; %entry
|
|
; GFX1032-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX1032-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX1032-NEXT: s_or_saveexec_b32 s2, -1
|
|
; GFX1032-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1032-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX1032-NEXT: s_mov_b32 exec_lo, s2
|
|
; GFX1032-NEXT: v_cmp_ne_u32_e64 s2, 1, 0
|
|
; GFX1032-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s2, 0
|
|
; GFX1032-NEXT: s_not_b32 exec_lo, exec_lo
|
|
; GFX1032-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX1032-NEXT: s_not_b32 exec_lo, exec_lo
|
|
; GFX1032-NEXT: s_or_saveexec_b32 s4, -1
|
|
; GFX1032-NEXT: v_max_u32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1032-NEXT: s_mov_b32 s2, -1
|
|
; GFX1032-NEXT: v_max_u32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1032-NEXT: v_max_u32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1032-NEXT: v_max_u32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0
|
|
; GFX1032-NEXT: v_mov_b32_e32 v3, v2
|
|
; GFX1032-NEXT: v_permlanex16_b32 v3, v3, -1, -1
|
|
; GFX1032-NEXT: v_max_u32_dpp v2, v3, v2 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf
|
|
; GFX1032-NEXT: v_readlane_b32 s3, v2, 31
|
|
; GFX1032-NEXT: v_mov_b32_dpp v1, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX1032-NEXT: v_readlane_b32 s5, v2, 15
|
|
; GFX1032-NEXT: v_writelane_b32 v1, s5, 16
|
|
; GFX1032-NEXT: s_mov_b32 exec_lo, s4
|
|
; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v0
|
|
; GFX1032-NEXT: ; implicit-def: $vgpr0
|
|
; GFX1032-NEXT: s_and_saveexec_b32 s4, vcc_lo
|
|
; GFX1032-NEXT: ; mask branch BB21_2
|
|
; GFX1032-NEXT: s_cbranch_execz BB21_2
|
|
; GFX1032-NEXT: BB21_1:
|
|
; GFX1032-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX1032-NEXT: v_mov_b32_e32 v7, s3
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1032-NEXT: ds_max_rtn_u32 v0, v0, v7
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_gl0_inv
|
|
; GFX1032-NEXT: buffer_gl1_inv
|
|
; GFX1032-NEXT: BB21_2:
|
|
; GFX1032-NEXT: v_nop
|
|
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s4
|
|
; GFX1032-NEXT: v_readfirstlane_b32 s3, v0
|
|
; GFX1032-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX1032-NEXT: v_max_u32_e32 v0, s3, v0
|
|
; GFX1032-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1032-NEXT: s_nop 1
|
|
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX1032-NEXT: s_endpgm
|
|
entry:
|
|
%lane = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%old = atomicrmw umax i32 addrspace(3)* @local_var32, i32 %lane acq_rel
|
|
store i32 %old, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @umax_i64_constant(i64 addrspace(1)* %out) {
|
|
;
|
|
;
|
|
; GFX7LESS-LABEL: umax_i64_constant:
|
|
; GFX7LESS: ; %bb.0: ; %entry
|
|
; GFX7LESS-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; GFX7LESS-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX7LESS-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s2, 0
|
|
; GFX7LESS-NEXT: v_mbcnt_hi_u32_b32_e32 v0, s3, v0
|
|
; GFX7LESS-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX7LESS-NEXT: ; implicit-def: $vgpr0_vgpr1
|
|
; GFX7LESS-NEXT: s_and_saveexec_b64 s[2:3], vcc
|
|
; GFX7LESS-NEXT: ; mask branch BB22_2
|
|
; GFX7LESS-NEXT: s_cbranch_execz BB22_2
|
|
; GFX7LESS-NEXT: BB22_1:
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v0, 5
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX7LESS-NEXT: s_mov_b32 m0, -1
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: ds_max_rtn_u64 v[0:1], v2, v[0:1]
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: buffer_wbinvl1
|
|
; GFX7LESS-NEXT: BB22_2:
|
|
; GFX7LESS-NEXT: s_or_b64 exec, exec, s[2:3]
|
|
; GFX7LESS-NEXT: v_readfirstlane_b32 s4, v0
|
|
; GFX7LESS-NEXT: v_readfirstlane_b32 s5, v1
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX7LESS-NEXT: v_cndmask_b32_e64 v0, 5, 0, vcc
|
|
; GFX7LESS-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v2, s4
|
|
; GFX7LESS-NEXT: v_cmp_gt_u64_e32 vcc, s[4:5], v[0:1]
|
|
; GFX7LESS-NEXT: v_cndmask_b32_e32 v0, v0, v2, vcc
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX7LESS-NEXT: v_cndmask_b32_e32 v1, 0, v1, vcc
|
|
; GFX7LESS-NEXT: s_mov_b32 s2, -1
|
|
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7LESS-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX7LESS-NEXT: s_endpgm
|
|
;
|
|
; GFX8-LABEL: umax_i64_constant:
|
|
; GFX8: ; %bb.0: ; %entry
|
|
; GFX8-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX8-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX8-NEXT: v_mbcnt_lo_u32_b32 v0, s2, 0
|
|
; GFX8-NEXT: v_mbcnt_hi_u32_b32 v0, s3, v0
|
|
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX8-NEXT: ; implicit-def: $vgpr0_vgpr1
|
|
; GFX8-NEXT: s_and_saveexec_b64 s[2:3], vcc
|
|
; GFX8-NEXT: ; mask branch BB22_2
|
|
; GFX8-NEXT: s_cbranch_execz BB22_2
|
|
; GFX8-NEXT: BB22_1:
|
|
; GFX8-NEXT: v_mov_b32_e32 v0, 5
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
|
|
; GFX8-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX8-NEXT: s_mov_b32 m0, -1
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: ds_max_rtn_u64 v[0:1], v2, v[0:1]
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_wbinvl1_vol
|
|
; GFX8-NEXT: BB22_2:
|
|
; GFX8-NEXT: s_or_b64 exec, exec, s[2:3]
|
|
; GFX8-NEXT: v_readfirstlane_b32 s2, v0
|
|
; GFX8-NEXT: v_readfirstlane_b32 s3, v1
|
|
; GFX8-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX8-NEXT: v_cndmask_b32_e64 v0, 5, 0, vcc
|
|
; GFX8-NEXT: v_cmp_gt_u64_e32 vcc, s[2:3], v[0:1]
|
|
; GFX8-NEXT: v_mov_b32_e32 v1, s3
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX8-NEXT: v_cndmask_b32_e32 v0, v0, v2, vcc
|
|
; GFX8-NEXT: v_cndmask_b32_e32 v1, 0, v1, vcc
|
|
; GFX8-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX8-NEXT: s_mov_b32 s2, -1
|
|
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX8-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: umax_i64_constant:
|
|
; GFX9: ; %bb.0: ; %entry
|
|
; GFX9-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX9-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX9-NEXT: v_mbcnt_lo_u32_b32 v0, s2, 0
|
|
; GFX9-NEXT: v_mbcnt_hi_u32_b32 v0, s3, v0
|
|
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX9-NEXT: ; implicit-def: $vgpr0_vgpr1
|
|
; GFX9-NEXT: s_and_saveexec_b64 s[2:3], vcc
|
|
; GFX9-NEXT: ; mask branch BB22_2
|
|
; GFX9-NEXT: s_cbranch_execz BB22_2
|
|
; GFX9-NEXT: BB22_1:
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, 5
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
|
|
; GFX9-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: ds_max_rtn_u64 v[0:1], v2, v[0:1]
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_wbinvl1_vol
|
|
; GFX9-NEXT: BB22_2:
|
|
; GFX9-NEXT: s_or_b64 exec, exec, s[2:3]
|
|
; GFX9-NEXT: v_readfirstlane_b32 s2, v0
|
|
; GFX9-NEXT: v_readfirstlane_b32 s3, v1
|
|
; GFX9-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX9-NEXT: v_cndmask_b32_e64 v0, 5, 0, vcc
|
|
; GFX9-NEXT: v_cmp_gt_u64_e32 vcc, s[2:3], v[0:1]
|
|
; GFX9-NEXT: v_mov_b32_e32 v1, s3
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX9-NEXT: v_cndmask_b32_e32 v0, v0, v2, vcc
|
|
; GFX9-NEXT: v_cndmask_b32_e32 v1, 0, v1, vcc
|
|
; GFX9-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX9-NEXT: s_mov_b32 s2, -1
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX1064-LABEL: umax_i64_constant:
|
|
; GFX1064: ; %bb.0: ; %entry
|
|
; GFX1064-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX1064-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1064-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s2, 0
|
|
; GFX1064-NEXT: v_mbcnt_hi_u32_b32_e64 v0, s3, v0
|
|
; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX1064-NEXT: ; implicit-def: $vgpr0_vgpr1
|
|
; GFX1064-NEXT: s_and_saveexec_b64 s[2:3], vcc
|
|
; GFX1064-NEXT: ; mask branch BB22_2
|
|
; GFX1064-NEXT: s_cbranch_execz BB22_2
|
|
; GFX1064-NEXT: BB22_1:
|
|
; GFX1064-NEXT: v_mov_b32_e32 v0, 5
|
|
; GFX1064-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
|
|
; GFX1064-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1064-NEXT: ds_max_rtn_u64 v[0:1], v2, v[0:1]
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_gl0_inv
|
|
; GFX1064-NEXT: buffer_gl1_inv
|
|
; GFX1064-NEXT: BB22_2:
|
|
; GFX1064-NEXT: v_nop
|
|
; GFX1064-NEXT: s_or_b64 exec, exec, s[2:3]
|
|
; GFX1064-NEXT: v_readfirstlane_b32 s4, v0
|
|
; GFX1064-NEXT: v_readfirstlane_b32 s5, v1
|
|
; GFX1064-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX1064-NEXT: v_cndmask_b32_e64 v0, 5, 0, vcc
|
|
; GFX1064-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1064-NEXT: s_mov_b32 s2, -1
|
|
; GFX1064-NEXT: v_cmp_gt_u64_e32 vcc, s[4:5], v[0:1]
|
|
; GFX1064-NEXT: v_cndmask_b32_e64 v0, v0, s4, vcc
|
|
; GFX1064-NEXT: v_cndmask_b32_e64 v1, 0, s5, vcc
|
|
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX1064-NEXT: s_endpgm
|
|
;
|
|
; GFX1032-LABEL: umax_i64_constant:
|
|
; GFX1032: ; %bb.0: ; %entry
|
|
; GFX1032-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1032-NEXT: v_cmp_ne_u32_e64 s2, 1, 0
|
|
; GFX1032-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX1032-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s2, 0
|
|
; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v0
|
|
; GFX1032-NEXT: ; implicit-def: $vgpr0_vgpr1
|
|
; GFX1032-NEXT: s_and_saveexec_b32 s2, vcc_lo
|
|
; GFX1032-NEXT: ; mask branch BB22_2
|
|
; GFX1032-NEXT: s_cbranch_execz BB22_2
|
|
; GFX1032-NEXT: BB22_1:
|
|
; GFX1032-NEXT: v_mov_b32_e32 v0, 5
|
|
; GFX1032-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
|
|
; GFX1032-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1032-NEXT: ds_max_rtn_u64 v[0:1], v2, v[0:1]
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_gl0_inv
|
|
; GFX1032-NEXT: buffer_gl1_inv
|
|
; GFX1032-NEXT: BB22_2:
|
|
; GFX1032-NEXT: v_nop
|
|
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s2
|
|
; GFX1032-NEXT: v_readfirstlane_b32 s4, v0
|
|
; GFX1032-NEXT: v_readfirstlane_b32 s5, v1
|
|
; GFX1032-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX1032-NEXT: v_cndmask_b32_e64 v0, 5, 0, vcc_lo
|
|
; GFX1032-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1032-NEXT: s_mov_b32 s2, -1
|
|
; GFX1032-NEXT: v_cmp_gt_u64_e32 vcc_lo, s[4:5], v[0:1]
|
|
; GFX1032-NEXT: v_cndmask_b32_e64 v0, v0, s4, vcc_lo
|
|
; GFX1032-NEXT: v_cndmask_b32_e64 v1, 0, s5, vcc_lo
|
|
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX1032-NEXT: s_endpgm
|
|
entry:
|
|
%old = atomicrmw umax i64 addrspace(3)* @local_var64, i64 5 acq_rel
|
|
store i64 %old, i64 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; GFX8MORE32: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 31
|
|
; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
|
|
; GFX8MORE: ds_min_rtn_u32 v{{[0-9]+}}, v{{[0-9]+}}, v[[value]]
|
|
define amdgpu_kernel void @umin_i32_varying(i32 addrspace(1)* %out) {
|
|
;
|
|
;
|
|
; GFX7LESS-LABEL: umin_i32_varying:
|
|
; GFX7LESS: ; %bb.0: ; %entry
|
|
; GFX7LESS-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v1, local_var32@abs32@lo
|
|
; GFX7LESS-NEXT: s_mov_b32 m0, -1
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: ds_min_rtn_u32 v0, v1, v0
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: buffer_wbinvl1
|
|
; GFX7LESS-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX7LESS-NEXT: s_mov_b32 s2, -1
|
|
; GFX7LESS-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX7LESS-NEXT: s_endpgm
|
|
;
|
|
; GFX8-LABEL: umin_i32_varying:
|
|
; GFX8: ; %bb.0: ; %entry
|
|
; GFX8-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX8-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX8-NEXT: v_mbcnt_lo_u32_b32 v3, s2, 0
|
|
; GFX8-NEXT: v_mbcnt_hi_u32_b32 v3, s3, v3
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX8-NEXT: s_or_saveexec_b64 s[2:3], -1
|
|
; GFX8-NEXT: v_mov_b32_e32 v1, -1
|
|
; GFX8-NEXT: s_mov_b64 exec, s[2:3]
|
|
; GFX8-NEXT: s_not_b64 exec, exec
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, -1
|
|
; GFX8-NEXT: s_not_b64 exec, exec
|
|
; GFX8-NEXT: s_or_saveexec_b64 s[4:5], -1
|
|
; GFX8-NEXT: v_min_u32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_min_u32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_min_u32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_min_u32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_min_u32_dpp v2, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf
|
|
; GFX8-NEXT: s_nop 1
|
|
; GFX8-NEXT: v_min_u32_dpp v2, v2, v2 row_bcast:31 row_mask:0xc bank_mask:0xf
|
|
; GFX8-NEXT: v_readlane_b32 s2, v2, 63
|
|
; GFX8-NEXT: s_nop 0
|
|
; GFX8-NEXT: v_mov_b32_dpp v1, v2 wave_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX8-NEXT: s_mov_b64 exec, s[4:5]
|
|
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v3
|
|
; GFX8-NEXT: ; implicit-def: $vgpr0
|
|
; GFX8-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX8-NEXT: ; mask branch BB23_2
|
|
; GFX8-NEXT: s_cbranch_execz BB23_2
|
|
; GFX8-NEXT: BB23_1:
|
|
; GFX8-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX8-NEXT: v_mov_b32_e32 v3, s2
|
|
; GFX8-NEXT: s_mov_b32 m0, -1
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: ds_min_rtn_u32 v0, v0, v3
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_wbinvl1_vol
|
|
; GFX8-NEXT: BB23_2:
|
|
; GFX8-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX8-NEXT: v_readfirstlane_b32 s2, v0
|
|
; GFX8-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX8-NEXT: v_min_u32_e32 v0, s2, v0
|
|
; GFX8-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX8-NEXT: s_mov_b32 s2, -1
|
|
; GFX8-NEXT: s_nop 0
|
|
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX8-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: umin_i32_varying:
|
|
; GFX9: ; %bb.0: ; %entry
|
|
; GFX9-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX9-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX9-NEXT: v_mbcnt_lo_u32_b32 v3, s2, 0
|
|
; GFX9-NEXT: v_mbcnt_hi_u32_b32 v3, s3, v3
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX9-NEXT: s_or_saveexec_b64 s[2:3], -1
|
|
; GFX9-NEXT: v_mov_b32_e32 v1, -1
|
|
; GFX9-NEXT: s_mov_b64 exec, s[2:3]
|
|
; GFX9-NEXT: s_not_b64 exec, exec
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, -1
|
|
; GFX9-NEXT: s_not_b64 exec, exec
|
|
; GFX9-NEXT: s_or_saveexec_b64 s[4:5], -1
|
|
; GFX9-NEXT: v_min_u32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_min_u32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_min_u32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_min_u32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_min_u32_dpp v2, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf
|
|
; GFX9-NEXT: s_nop 1
|
|
; GFX9-NEXT: v_min_u32_dpp v2, v2, v2 row_bcast:31 row_mask:0xc bank_mask:0xf
|
|
; GFX9-NEXT: v_readlane_b32 s2, v2, 63
|
|
; GFX9-NEXT: s_nop 0
|
|
; GFX9-NEXT: v_mov_b32_dpp v1, v2 wave_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX9-NEXT: s_mov_b64 exec, s[4:5]
|
|
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v3
|
|
; GFX9-NEXT: ; implicit-def: $vgpr0
|
|
; GFX9-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX9-NEXT: ; mask branch BB23_2
|
|
; GFX9-NEXT: s_cbranch_execz BB23_2
|
|
; GFX9-NEXT: BB23_1:
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX9-NEXT: v_mov_b32_e32 v3, s2
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: ds_min_rtn_u32 v0, v0, v3
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_wbinvl1_vol
|
|
; GFX9-NEXT: BB23_2:
|
|
; GFX9-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX9-NEXT: v_readfirstlane_b32 s2, v0
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX9-NEXT: v_min_u32_e32 v0, s2, v0
|
|
; GFX9-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX9-NEXT: s_mov_b32 s2, -1
|
|
; GFX9-NEXT: s_nop 0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX1064-LABEL: umin_i32_varying:
|
|
; GFX1064: ; %bb.0: ; %entry
|
|
; GFX1064-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1064-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX1064-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX1064-NEXT: v_mbcnt_lo_u32_b32_e64 v4, s2, 0
|
|
; GFX1064-NEXT: v_mbcnt_hi_u32_b32_e64 v4, s3, v4
|
|
; GFX1064-NEXT: s_or_saveexec_b64 s[2:3], -1
|
|
; GFX1064-NEXT: v_mov_b32_e32 v1, -1
|
|
; GFX1064-NEXT: s_mov_b64 exec, s[2:3]
|
|
; GFX1064-NEXT: s_not_b64 exec, exec
|
|
; GFX1064-NEXT: v_mov_b32_e32 v2, -1
|
|
; GFX1064-NEXT: s_not_b64 exec, exec
|
|
; GFX1064-NEXT: s_or_saveexec_b64 s[4:5], -1
|
|
; GFX1064-NEXT: v_min_u32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX1064-NEXT: v_min_u32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf
|
|
; GFX1064-NEXT: v_min_u32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf
|
|
; GFX1064-NEXT: v_min_u32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf
|
|
; GFX1064-NEXT: v_mov_b32_e32 v3, v2
|
|
; GFX1064-NEXT: v_permlanex16_b32 v3, v3, -1, -1
|
|
; GFX1064-NEXT: v_min_u32_dpp v2, v3, v2 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf
|
|
; GFX1064-NEXT: v_readlane_b32 s2, v2, 31
|
|
; GFX1064-NEXT: v_mov_b32_e32 v3, s2
|
|
; GFX1064-NEXT: v_min_u32_dpp v2, v3, v2 quad_perm:[0,1,2,3] row_mask:0xc bank_mask:0xf
|
|
; GFX1064-NEXT: v_readlane_b32 s2, v2, 15
|
|
; GFX1064-NEXT: v_mov_b32_dpp v1, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX1064-NEXT: v_readlane_b32 s3, v2, 31
|
|
; GFX1064-NEXT: v_readlane_b32 s6, v2, 47
|
|
; GFX1064-NEXT: v_writelane_b32 v1, s2, 16
|
|
; GFX1064-NEXT: s_mov_b32 s2, -1
|
|
; GFX1064-NEXT: v_writelane_b32 v1, s3, 32
|
|
; GFX1064-NEXT: v_readlane_b32 s3, v2, 63
|
|
; GFX1064-NEXT: v_writelane_b32 v1, s6, 48
|
|
; GFX1064-NEXT: s_mov_b64 exec, s[4:5]
|
|
; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v4
|
|
; GFX1064-NEXT: ; implicit-def: $vgpr0
|
|
; GFX1064-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GFX1064-NEXT: ; mask branch BB23_2
|
|
; GFX1064-NEXT: s_cbranch_execz BB23_2
|
|
; GFX1064-NEXT: BB23_1:
|
|
; GFX1064-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX1064-NEXT: v_mov_b32_e32 v7, s3
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1064-NEXT: ds_min_rtn_u32 v0, v0, v7
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_gl0_inv
|
|
; GFX1064-NEXT: buffer_gl1_inv
|
|
; GFX1064-NEXT: BB23_2:
|
|
; GFX1064-NEXT: v_nop
|
|
; GFX1064-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GFX1064-NEXT: v_readfirstlane_b32 s3, v0
|
|
; GFX1064-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX1064-NEXT: v_min_u32_e32 v0, s3, v0
|
|
; GFX1064-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1064-NEXT: s_nop 1
|
|
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX1064-NEXT: s_endpgm
|
|
;
|
|
; GFX1032-LABEL: umin_i32_varying:
|
|
; GFX1032: ; %bb.0: ; %entry
|
|
; GFX1032-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1032-NEXT: v_cmp_ne_u32_e64 s2, 1, 0
|
|
; GFX1032-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX1032-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX1032-NEXT: v_mbcnt_lo_u32_b32_e64 v4, s2, 0
|
|
; GFX1032-NEXT: s_or_saveexec_b32 s2, -1
|
|
; GFX1032-NEXT: v_mov_b32_e32 v1, -1
|
|
; GFX1032-NEXT: s_mov_b32 exec_lo, s2
|
|
; GFX1032-NEXT: s_not_b32 exec_lo, exec_lo
|
|
; GFX1032-NEXT: v_mov_b32_e32 v2, -1
|
|
; GFX1032-NEXT: s_not_b32 exec_lo, exec_lo
|
|
; GFX1032-NEXT: s_or_saveexec_b32 s4, -1
|
|
; GFX1032-NEXT: v_min_u32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX1032-NEXT: s_mov_b32 s2, -1
|
|
; GFX1032-NEXT: v_min_u32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf
|
|
; GFX1032-NEXT: v_min_u32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf
|
|
; GFX1032-NEXT: v_min_u32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf
|
|
; GFX1032-NEXT: v_mov_b32_e32 v3, v2
|
|
; GFX1032-NEXT: v_permlanex16_b32 v3, v3, -1, -1
|
|
; GFX1032-NEXT: v_min_u32_dpp v2, v3, v2 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf
|
|
; GFX1032-NEXT: v_readlane_b32 s3, v2, 31
|
|
; GFX1032-NEXT: v_mov_b32_dpp v1, v2 row_shr:1 row_mask:0xf bank_mask:0xf
|
|
; GFX1032-NEXT: v_readlane_b32 s5, v2, 15
|
|
; GFX1032-NEXT: v_writelane_b32 v1, s5, 16
|
|
; GFX1032-NEXT: s_mov_b32 exec_lo, s4
|
|
; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v4
|
|
; GFX1032-NEXT: ; implicit-def: $vgpr0
|
|
; GFX1032-NEXT: s_and_saveexec_b32 s4, vcc_lo
|
|
; GFX1032-NEXT: ; mask branch BB23_2
|
|
; GFX1032-NEXT: s_cbranch_execz BB23_2
|
|
; GFX1032-NEXT: BB23_1:
|
|
; GFX1032-NEXT: v_mov_b32_e32 v0, local_var32@abs32@lo
|
|
; GFX1032-NEXT: v_mov_b32_e32 v7, s3
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1032-NEXT: ds_min_rtn_u32 v0, v0, v7
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_gl0_inv
|
|
; GFX1032-NEXT: buffer_gl1_inv
|
|
; GFX1032-NEXT: BB23_2:
|
|
; GFX1032-NEXT: v_nop
|
|
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s4
|
|
; GFX1032-NEXT: v_readfirstlane_b32 s3, v0
|
|
; GFX1032-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX1032-NEXT: v_min_u32_e32 v0, s3, v0
|
|
; GFX1032-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1032-NEXT: s_nop 1
|
|
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX1032-NEXT: s_endpgm
|
|
entry:
|
|
%lane = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%old = atomicrmw umin i32 addrspace(3)* @local_var32, i32 %lane acq_rel
|
|
store i32 %old, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @umin_i64_constant(i64 addrspace(1)* %out) {
|
|
;
|
|
;
|
|
; GFX7LESS-LABEL: umin_i64_constant:
|
|
; GFX7LESS: ; %bb.0: ; %entry
|
|
; GFX7LESS-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; GFX7LESS-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX7LESS-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s2, 0
|
|
; GFX7LESS-NEXT: v_mbcnt_hi_u32_b32_e32 v0, s3, v0
|
|
; GFX7LESS-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX7LESS-NEXT: ; implicit-def: $vgpr0_vgpr1
|
|
; GFX7LESS-NEXT: s_and_saveexec_b64 s[2:3], vcc
|
|
; GFX7LESS-NEXT: ; mask branch BB24_2
|
|
; GFX7LESS-NEXT: s_cbranch_execz BB24_2
|
|
; GFX7LESS-NEXT: BB24_1:
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v0, 5
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX7LESS-NEXT: s_mov_b32 m0, -1
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: ds_min_rtn_u64 v[0:1], v2, v[0:1]
|
|
; GFX7LESS-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX7LESS-NEXT: buffer_wbinvl1
|
|
; GFX7LESS-NEXT: BB24_2:
|
|
; GFX7LESS-NEXT: s_or_b64 exec, exec, s[2:3]
|
|
; GFX7LESS-NEXT: v_readfirstlane_b32 s4, v0
|
|
; GFX7LESS-NEXT: v_readfirstlane_b32 s5, v1
|
|
; GFX7LESS-NEXT: s_mov_b32 s2, -1
|
|
; GFX7LESS-NEXT: v_cndmask_b32_e64 v1, 0, -1, vcc
|
|
; GFX7LESS-NEXT: v_cndmask_b32_e64 v0, 5, -1, vcc
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v2, s5
|
|
; GFX7LESS-NEXT: v_cmp_lt_u64_e32 vcc, s[4:5], v[0:1]
|
|
; GFX7LESS-NEXT: v_cndmask_b32_e32 v1, v1, v2, vcc
|
|
; GFX7LESS-NEXT: v_mov_b32_e32 v2, s4
|
|
; GFX7LESS-NEXT: v_cndmask_b32_e32 v0, v0, v2, vcc
|
|
; GFX7LESS-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX7LESS-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7LESS-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX7LESS-NEXT: s_endpgm
|
|
;
|
|
; GFX8-LABEL: umin_i64_constant:
|
|
; GFX8: ; %bb.0: ; %entry
|
|
; GFX8-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX8-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX8-NEXT: v_mbcnt_lo_u32_b32 v0, s2, 0
|
|
; GFX8-NEXT: v_mbcnt_hi_u32_b32 v0, s3, v0
|
|
; GFX8-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX8-NEXT: ; implicit-def: $vgpr0_vgpr1
|
|
; GFX8-NEXT: s_and_saveexec_b64 s[2:3], vcc
|
|
; GFX8-NEXT: ; mask branch BB24_2
|
|
; GFX8-NEXT: s_cbranch_execz BB24_2
|
|
; GFX8-NEXT: BB24_1:
|
|
; GFX8-NEXT: v_mov_b32_e32 v0, 5
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
|
|
; GFX8-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX8-NEXT: s_mov_b32 m0, -1
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: ds_min_rtn_u64 v[0:1], v2, v[0:1]
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_wbinvl1_vol
|
|
; GFX8-NEXT: BB24_2:
|
|
; GFX8-NEXT: s_or_b64 exec, exec, s[2:3]
|
|
; GFX8-NEXT: v_readfirstlane_b32 s5, v1
|
|
; GFX8-NEXT: v_readfirstlane_b32 s4, v0
|
|
; GFX8-NEXT: v_cndmask_b32_e64 v1, 0, -1, vcc
|
|
; GFX8-NEXT: v_cndmask_b32_e64 v0, 5, -1, vcc
|
|
; GFX8-NEXT: v_cmp_lt_u64_e32 vcc, s[4:5], v[0:1]
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, s5
|
|
; GFX8-NEXT: v_cndmask_b32_e32 v1, v1, v2, vcc
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, s4
|
|
; GFX8-NEXT: s_mov_b32 s2, -1
|
|
; GFX8-NEXT: v_cndmask_b32_e32 v0, v0, v2, vcc
|
|
; GFX8-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX8-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX8-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: umin_i64_constant:
|
|
; GFX9: ; %bb.0: ; %entry
|
|
; GFX9-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX9-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX9-NEXT: v_mbcnt_lo_u32_b32 v0, s2, 0
|
|
; GFX9-NEXT: v_mbcnt_hi_u32_b32 v0, s3, v0
|
|
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX9-NEXT: ; implicit-def: $vgpr0_vgpr1
|
|
; GFX9-NEXT: s_and_saveexec_b64 s[2:3], vcc
|
|
; GFX9-NEXT: ; mask branch BB24_2
|
|
; GFX9-NEXT: s_cbranch_execz BB24_2
|
|
; GFX9-NEXT: BB24_1:
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, 5
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
|
|
; GFX9-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: ds_min_rtn_u64 v[0:1], v2, v[0:1]
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_wbinvl1_vol
|
|
; GFX9-NEXT: BB24_2:
|
|
; GFX9-NEXT: s_or_b64 exec, exec, s[2:3]
|
|
; GFX9-NEXT: v_readfirstlane_b32 s5, v1
|
|
; GFX9-NEXT: v_readfirstlane_b32 s4, v0
|
|
; GFX9-NEXT: v_cndmask_b32_e64 v1, 0, -1, vcc
|
|
; GFX9-NEXT: v_cndmask_b32_e64 v0, 5, -1, vcc
|
|
; GFX9-NEXT: v_cmp_lt_u64_e32 vcc, s[4:5], v[0:1]
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, s5
|
|
; GFX9-NEXT: v_cndmask_b32_e32 v1, v1, v2, vcc
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, s4
|
|
; GFX9-NEXT: s_mov_b32 s2, -1
|
|
; GFX9-NEXT: v_cndmask_b32_e32 v0, v0, v2, vcc
|
|
; GFX9-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX1064-LABEL: umin_i64_constant:
|
|
; GFX1064: ; %bb.0: ; %entry
|
|
; GFX1064-NEXT: v_cmp_ne_u32_e64 s[2:3], 1, 0
|
|
; GFX1064-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1064-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s2, 0
|
|
; GFX1064-NEXT: v_mbcnt_hi_u32_b32_e64 v0, s3, v0
|
|
; GFX1064-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GFX1064-NEXT: ; implicit-def: $vgpr0_vgpr1
|
|
; GFX1064-NEXT: s_and_saveexec_b64 s[2:3], vcc
|
|
; GFX1064-NEXT: ; mask branch BB24_2
|
|
; GFX1064-NEXT: s_cbranch_execz BB24_2
|
|
; GFX1064-NEXT: BB24_1:
|
|
; GFX1064-NEXT: v_mov_b32_e32 v0, 5
|
|
; GFX1064-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
|
|
; GFX1064-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1064-NEXT: ds_min_rtn_u64 v[0:1], v2, v[0:1]
|
|
; GFX1064-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_gl0_inv
|
|
; GFX1064-NEXT: buffer_gl1_inv
|
|
; GFX1064-NEXT: BB24_2:
|
|
; GFX1064-NEXT: v_nop
|
|
; GFX1064-NEXT: s_or_b64 exec, exec, s[2:3]
|
|
; GFX1064-NEXT: v_readfirstlane_b32 s4, v0
|
|
; GFX1064-NEXT: v_readfirstlane_b32 s5, v1
|
|
; GFX1064-NEXT: v_cndmask_b32_e64 v1, 0, -1, vcc
|
|
; GFX1064-NEXT: v_cndmask_b32_e64 v0, 5, -1, vcc
|
|
; GFX1064-NEXT: s_mov_b32 s2, -1
|
|
; GFX1064-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1064-NEXT: v_cmp_lt_u64_e32 vcc, s[4:5], v[0:1]
|
|
; GFX1064-NEXT: v_cndmask_b32_e64 v1, v1, s5, vcc
|
|
; GFX1064-NEXT: v_cndmask_b32_e64 v0, v0, s4, vcc
|
|
; GFX1064-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1064-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX1064-NEXT: s_endpgm
|
|
;
|
|
; GFX1032-LABEL: umin_i64_constant:
|
|
; GFX1032: ; %bb.0: ; %entry
|
|
; GFX1032-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; GFX1032-NEXT: v_cmp_ne_u32_e64 s2, 1, 0
|
|
; GFX1032-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX1032-NEXT: v_mbcnt_lo_u32_b32_e64 v0, s2, 0
|
|
; GFX1032-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v0
|
|
; GFX1032-NEXT: ; implicit-def: $vgpr0_vgpr1
|
|
; GFX1032-NEXT: s_and_saveexec_b32 s2, vcc_lo
|
|
; GFX1032-NEXT: ; mask branch BB24_2
|
|
; GFX1032-NEXT: s_cbranch_execz BB24_2
|
|
; GFX1032-NEXT: BB24_1:
|
|
; GFX1032-NEXT: v_mov_b32_e32 v0, 5
|
|
; GFX1032-NEXT: v_mov_b32_e32 v2, local_var64@abs32@lo
|
|
; GFX1032-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX1032-NEXT: ds_min_rtn_u64 v[0:1], v2, v[0:1]
|
|
; GFX1032-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_gl0_inv
|
|
; GFX1032-NEXT: buffer_gl1_inv
|
|
; GFX1032-NEXT: BB24_2:
|
|
; GFX1032-NEXT: v_nop
|
|
; GFX1032-NEXT: s_or_b32 exec_lo, exec_lo, s2
|
|
; GFX1032-NEXT: v_readfirstlane_b32 s4, v0
|
|
; GFX1032-NEXT: v_readfirstlane_b32 s5, v1
|
|
; GFX1032-NEXT: v_cndmask_b32_e64 v1, 0, -1, vcc_lo
|
|
; GFX1032-NEXT: v_cndmask_b32_e64 v0, 5, -1, vcc_lo
|
|
; GFX1032-NEXT: s_mov_b32 s2, -1
|
|
; GFX1032-NEXT: s_mov_b32 s3, 0x31016000
|
|
; GFX1032-NEXT: v_cmp_lt_u64_e32 vcc_lo, s[4:5], v[0:1]
|
|
; GFX1032-NEXT: v_cndmask_b32_e64 v1, v1, s5, vcc_lo
|
|
; GFX1032-NEXT: v_cndmask_b32_e64 v0, v0, s4, vcc_lo
|
|
; GFX1032-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX1032-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
|
|
; GFX1032-NEXT: s_endpgm
|
|
entry:
|
|
%old = atomicrmw umin i64 addrspace(3)* @local_var64, i64 5 acq_rel
|
|
store i64 %old, i64 addrspace(1)* %out
|
|
ret void
|
|
}
|