AMDGPU: Assume spilling will occur at -O0
Because everything live is spilled at the end of a block by fast regalloc, assume this will happen and avoid the copies of the resource descriptor. llvm-svn: 284119
This commit is contained in:
Matt Arsenault
parent
26b6dbc369
commit
253640e18d
|
|
@ -881,8 +881,12 @@ SDValue SITargetLowering::LowerFormalArguments(
|
|||
if (HasStackObjects)
|
||||
Info->setHasNonSpillStackObjects(true);
|
||||
|
||||
// Everything live out of a block is spilled with fast regalloc, so it's
|
||||
// almost certain that spilling will be required.
|
||||
if (getTargetMachine().getOptLevel() == CodeGenOpt::None)
|
||||
HasStackObjects = true;
|
||||
|
||||
if (ST.isAmdCodeObjectV2()) {
|
||||
// TODO: Assume we will spill without optimizations.
|
||||
if (HasStackObjects) {
|
||||
// If we have stack objects, we unquestionably need the private buffer
|
||||
// resource. For the Code Object V2 ABI, this will be the first 4 user
|
||||
|
|
|
|||
|
|
@ -26,12 +26,12 @@
|
|||
|
||||
|
||||
; VMEM: v_mov_b32_e32 v[[V_SAVEEXEC_LO:[0-9]+]], s[[SAVEEXEC_LO]]
|
||||
; VMEM: buffer_store_dword v[[V_SAVEEXEC_LO]], off, s[8:11], s12 ; 8-byte Folded Spill
|
||||
; VMEM: buffer_store_dword v[[V_SAVEEXEC_LO]], off, s[0:3], s7 ; 8-byte Folded Spill
|
||||
; VMEM: v_mov_b32_e32 v[[V_SAVEEXEC_HI:[0-9]+]], s[[SAVEEXEC_HI]]
|
||||
; VMEM: buffer_store_dword v[[V_SAVEEXEC_HI]], off, s[8:11], s12 offset:4 ; 8-byte Folded Spill
|
||||
; VMEM: buffer_store_dword v[[V_SAVEEXEC_HI]], off, s[0:3], s7 offset:4 ; 8-byte Folded Spill
|
||||
|
||||
; Spill load
|
||||
; GCN: buffer_store_dword [[LOAD0]], off, s[8:11], s12 offset:[[LOAD0_OFFSET:[0-9]+]] ; 4-byte Folded Spill
|
||||
; GCN: buffer_store_dword [[LOAD0]], off, s[0:3], s7 offset:[[LOAD0_OFFSET:[0-9]+]] ; 4-byte Folded Spill
|
||||
; GCN: s_mov_b64 exec, s{{\[}}[[ANDEXEC_LO]]:[[ANDEXEC_HI]]{{\]}}
|
||||
|
||||
; GCN: s_waitcnt vmcnt(0) expcnt(0)
|
||||
|
|
@ -40,12 +40,12 @@
|
|||
; GCN: {{^}}BB{{[0-9]+}}_1: ; %if
|
||||
; GCN: s_mov_b32 m0, -1
|
||||
; GCN: ds_read_b32 [[LOAD1:v[0-9]+]]
|
||||
; GCN: buffer_load_dword [[RELOAD_LOAD0:v[0-9]+]], off, s[8:11], s12 offset:[[LOAD0_OFFSET]] ; 4-byte Folded Reload
|
||||
; GCN: buffer_load_dword [[RELOAD_LOAD0:v[0-9]+]], off, s[0:3], s7 offset:[[LOAD0_OFFSET]] ; 4-byte Folded Reload
|
||||
; GCN: s_waitcnt vmcnt(0)
|
||||
|
||||
; Spill val register
|
||||
; GCN: v_add_i32_e32 [[VAL:v[0-9]+]], vcc, [[LOAD1]], [[RELOAD_LOAD0]]
|
||||
; GCN: buffer_store_dword [[VAL]], off, s[8:11], s12 offset:[[VAL_OFFSET:[0-9]+]] ; 4-byte Folded Spill
|
||||
; GCN: buffer_store_dword [[VAL]], off, s[0:3], s7 offset:[[VAL_OFFSET:[0-9]+]] ; 4-byte Folded Spill
|
||||
; GCN: s_waitcnt vmcnt(0)
|
||||
|
||||
; VMEM: [[ENDIF]]:
|
||||
|
|
@ -55,18 +55,18 @@
|
|||
|
||||
|
||||
|
||||
; VMEM: buffer_load_dword v[[V_RELOAD_SAVEEXEC_LO:[0-9]+]], off, s[8:11], s12 ; 8-byte Folded Reload
|
||||
; VMEM: buffer_load_dword v[[V_RELOAD_SAVEEXEC_LO:[0-9]+]], off, s[0:3], s7 ; 8-byte Folded Reload
|
||||
; VMEM: s_waitcnt vmcnt(0)
|
||||
; VMEM: v_readfirstlane_b32 s[[S_RELOAD_SAVEEXEC_LO:[0-9]+]], v[[V_RELOAD_SAVEEXEC_LO]]
|
||||
|
||||
; VMEM: buffer_load_dword v[[V_RELOAD_SAVEEXEC_HI:[0-9]+]], off, s[8:11], s12 offset:4 ; 8-byte Folded Reload
|
||||
; VMEM: buffer_load_dword v[[V_RELOAD_SAVEEXEC_HI:[0-9]+]], off, s[0:3], s7 offset:4 ; 8-byte Folded Reload
|
||||
; VMEM: s_waitcnt vmcnt(0)
|
||||
; VMEM: v_readfirstlane_b32 s[[S_RELOAD_SAVEEXEC_HI:[0-9]+]], v[[V_RELOAD_SAVEEXEC_HI]]
|
||||
|
||||
; GCN: s_or_b64 exec, exec, s{{\[}}[[S_RELOAD_SAVEEXEC_LO]]:[[S_RELOAD_SAVEEXEC_HI]]{{\]}}
|
||||
|
||||
; Restore val
|
||||
; GCN: buffer_load_dword [[RELOAD_VAL:v[0-9]+]], off, s[8:11], s12 offset:[[VAL_OFFSET]] ; 4-byte Folded Reload
|
||||
; GCN: buffer_load_dword [[RELOAD_VAL:v[0-9]+]], off, s[0:3], s7 offset:[[VAL_OFFSET]] ; 4-byte Folded Reload
|
||||
|
||||
; GCN: flat_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[RELOAD_VAL]]
|
||||
define void @divergent_if_endif(i32 addrspace(1)* %out) #0 {
|
||||
|
|
@ -105,12 +105,12 @@ endif:
|
|||
|
||||
|
||||
; VMEM: v_mov_b32_e32 v[[V_SAVEEXEC_LO:[0-9]+]], s[[SAVEEXEC_LO]]
|
||||
; VMEM: buffer_store_dword v[[V_SAVEEXEC_LO]], off, s[8:11], s12 ; 8-byte Folded Spill
|
||||
; VMEM: buffer_store_dword v[[V_SAVEEXEC_LO]], off, s[0:3], s7 ; 8-byte Folded Spill
|
||||
; VMEM: v_mov_b32_e32 v[[V_SAVEEXEC_HI:[0-9]+]], s[[SAVEEXEC_HI]]
|
||||
; VMEM: buffer_store_dword v[[V_SAVEEXEC_HI]], off, s[8:11], s12 offset:4 ; 8-byte Folded Spill
|
||||
; VMEM: buffer_store_dword v[[V_SAVEEXEC_HI]], off, s[0:3], s7 offset:4 ; 8-byte Folded Spill
|
||||
|
||||
; Spill load
|
||||
; GCN: buffer_store_dword [[LOAD0]], off, s[8:11], s12 offset:[[VAL_OFFSET:[0-9]+]] ; 4-byte Folded Spill
|
||||
; GCN: buffer_store_dword [[LOAD0]], off, s[0:3], s7 offset:[[VAL_OFFSET:[0-9]+]] ; 4-byte Folded Spill
|
||||
|
||||
; GCN: s_mov_b64 exec, s{{\[}}[[ANDEXEC_LO]]:[[ANDEXEC_HI]]{{\]}}
|
||||
|
||||
|
|
@ -120,11 +120,11 @@ endif:
|
|||
|
||||
|
||||
; GCN: [[LOOP:BB[0-9]+_[0-9]+]]:
|
||||
; GCN: buffer_load_dword v[[VAL_LOOP_RELOAD:[0-9]+]], off, s[8:11], s12 offset:[[VAL_OFFSET]] ; 4-byte Folded Reload
|
||||
; GCN: buffer_load_dword v[[VAL_LOOP_RELOAD:[0-9]+]], off, s[0:3], s7 offset:[[VAL_OFFSET]] ; 4-byte Folded Reload
|
||||
; GCN: v_subrev_i32_e32 [[VAL_LOOP:v[0-9]+]], vcc, v{{[0-9]+}}, v[[VAL_LOOP_RELOAD]]
|
||||
; GCN: v_cmp_ne_u32_e32 vcc,
|
||||
; GCN: s_and_b64 vcc, exec, vcc
|
||||
; GCN: buffer_store_dword [[VAL_LOOP]], off, s[8:11], s12 offset:[[VAL_SUB_OFFSET:[0-9]+]] ; 4-byte Folded Spill
|
||||
; GCN: buffer_store_dword [[VAL_LOOP]], off, s[0:3], s7 offset:[[VAL_SUB_OFFSET:[0-9]+]] ; 4-byte Folded Spill
|
||||
; GCN: s_waitcnt vmcnt(0) expcnt(0)
|
||||
; GCN-NEXT: s_cbranch_vccnz [[LOOP]]
|
||||
|
||||
|
|
@ -133,16 +133,16 @@ endif:
|
|||
; VGPR: v_readlane_b32 s[[S_RELOAD_SAVEEXEC_LO:[0-9]+]], [[SPILL_VGPR]], [[SAVEEXEC_LO_LANE]]
|
||||
; VGPR: v_readlane_b32 s[[S_RELOAD_SAVEEXEC_HI:[0-9]+]], [[SPILL_VGPR]], [[SAVEEXEC_HI_LANE]]
|
||||
|
||||
; VMEM: buffer_load_dword v[[V_RELOAD_SAVEEXEC_LO:[0-9]+]], off, s[8:11], s12 ; 8-byte Folded Reload
|
||||
; VMEM: buffer_load_dword v[[V_RELOAD_SAVEEXEC_LO:[0-9]+]], off, s[0:3], s7 ; 8-byte Folded Reload
|
||||
; VMEM: s_waitcnt vmcnt(0)
|
||||
; VMEM: v_readfirstlane_b32 s[[S_RELOAD_SAVEEXEC_LO:[0-9]+]], v[[V_RELOAD_SAVEEXEC_LO]]
|
||||
|
||||
; VMEM: buffer_load_dword v[[V_RELOAD_SAVEEXEC_HI:[0-9]+]], off, s[8:11], s12 offset:4 ; 8-byte Folded Reload
|
||||
; VMEM: buffer_load_dword v[[V_RELOAD_SAVEEXEC_HI:[0-9]+]], off, s[0:3], s7 offset:4 ; 8-byte Folded Reload
|
||||
; VMEM: s_waitcnt vmcnt(0)
|
||||
; VMEM: v_readfirstlane_b32 s[[S_RELOAD_SAVEEXEC_HI:[0-9]+]], v[[V_RELOAD_SAVEEXEC_HI]]
|
||||
|
||||
; GCN: s_or_b64 exec, exec, s{{\[}}[[S_RELOAD_SAVEEXEC_LO]]:[[S_RELOAD_SAVEEXEC_HI]]{{\]}}
|
||||
; GCN: buffer_load_dword v[[VAL_END:[0-9]+]], off, s[8:11], s12 offset:[[VAL_SUB_OFFSET]] ; 4-byte Folded Reload
|
||||
; GCN: buffer_load_dword v[[VAL_END:[0-9]+]], off, s[0:3], s7 offset:[[VAL_SUB_OFFSET]] ; 4-byte Folded Reload
|
||||
|
||||
; GCN: flat_store_dword v{{\[[0-9]+:[0-9]+\]}}, v[[VAL_END]]
|
||||
define void @divergent_loop(i32 addrspace(1)* %out) #0 {
|
||||
|
|
@ -180,16 +180,16 @@ end:
|
|||
; GCN: s_xor_b64 s{{\[}}[[SAVEEXEC_LO]]:[[SAVEEXEC_HI]]{{\]}}, s{{\[}}[[ANDEXEC_LO]]:[[ANDEXEC_HI]]{{\]}}, s{{\[}}[[SAVEEXEC_LO]]:[[SAVEEXEC_HI]]{{\]}}
|
||||
|
||||
; Spill load
|
||||
; GCN: buffer_store_dword [[LOAD0]], off, s[8:11], s12 ; 4-byte Folded Spill
|
||||
; GCN: buffer_store_dword [[LOAD0]], off, s[0:3], s7 ; 4-byte Folded Spill
|
||||
|
||||
; Spill saved exec
|
||||
; VGPR: v_writelane_b32 [[SPILL_VGPR:v[0-9]+]], s[[SAVEEXEC_LO]], [[SAVEEXEC_LO_LANE:[0-9]+]]
|
||||
; VGPR: v_writelane_b32 [[SPILL_VGPR]], s[[SAVEEXEC_HI]], [[SAVEEXEC_HI_LANE:[0-9]+]]
|
||||
|
||||
; VMEM: v_mov_b32_e32 v[[V_SAVEEXEC_LO:[0-9]+]], s[[SAVEEXEC_LO]]
|
||||
; VMEM: buffer_store_dword v[[V_SAVEEXEC_LO]], off, s[8:11], s12 offset:[[SAVEEXEC_LO_OFFSET:[0-9]+]] ; 8-byte Folded Spill
|
||||
; VMEM: buffer_store_dword v[[V_SAVEEXEC_LO]], off, s[0:3], s7 offset:[[SAVEEXEC_LO_OFFSET:[0-9]+]] ; 8-byte Folded Spill
|
||||
; VMEM: v_mov_b32_e32 v[[V_SAVEEXEC_HI:[0-9]+]], s[[SAVEEXEC_HI]]
|
||||
; VMEM: buffer_store_dword v[[V_SAVEEXEC_HI]], off, s[8:11], s12 offset:[[SAVEEXEC_HI_OFFSET:[0-9]+]] ; 8-byte Folded Spill
|
||||
; VMEM: buffer_store_dword v[[V_SAVEEXEC_HI]], off, s[0:3], s7 offset:[[SAVEEXEC_HI_OFFSET:[0-9]+]] ; 8-byte Folded Spill
|
||||
|
||||
; GCN: s_mov_b64 exec, [[CMP0]]
|
||||
; GCN: s_waitcnt vmcnt(0) expcnt(0)
|
||||
|
|
@ -204,18 +204,18 @@ end:
|
|||
; VGPR: v_readlane_b32 s[[FLOW_S_RELOAD_SAVEEXEC_HI:[0-9]+]], [[SPILL_VGPR]], [[SAVEEXEC_HI_LANE]]
|
||||
|
||||
|
||||
; VMEM: buffer_load_dword v[[FLOW_V_RELOAD_SAVEEXEC_LO:[0-9]+]], off, s[8:11], s12 offset:[[SAVEEXEC_LO_OFFSET]]
|
||||
; VMEM: buffer_load_dword v[[FLOW_V_RELOAD_SAVEEXEC_LO:[0-9]+]], off, s[0:3], s7 offset:[[SAVEEXEC_LO_OFFSET]]
|
||||
; VMEM: s_waitcnt vmcnt(0)
|
||||
; VMEM: v_readfirstlane_b32 s[[FLOW_S_RELOAD_SAVEEXEC_LO:[0-9]+]], v[[FLOW_V_RELOAD_SAVEEXEC_LO]]
|
||||
|
||||
; VMEM: buffer_load_dword v[[FLOW_V_RELOAD_SAVEEXEC_HI:[0-9]+]], off, s[8:11], s12 offset:[[SAVEEXEC_HI_OFFSET]] ; 8-byte Folded Reload
|
||||
; VMEM: buffer_load_dword v[[FLOW_V_RELOAD_SAVEEXEC_HI:[0-9]+]], off, s[0:3], s7 offset:[[SAVEEXEC_HI_OFFSET]] ; 8-byte Folded Reload
|
||||
; VMEM: s_waitcnt vmcnt(0)
|
||||
; VMEM: v_readfirstlane_b32 s[[FLOW_S_RELOAD_SAVEEXEC_HI:[0-9]+]], v[[FLOW_V_RELOAD_SAVEEXEC_HI]]
|
||||
|
||||
; GCN: s_or_saveexec_b64 s{{\[}}[[FLOW_S_RELOAD_SAVEEXEC_LO]]:[[FLOW_S_RELOAD_SAVEEXEC_HI]]{{\]}}, s{{\[}}[[FLOW_S_RELOAD_SAVEEXEC_LO]]:[[FLOW_S_RELOAD_SAVEEXEC_HI]]{{\]}}
|
||||
|
||||
; Regular spill value restored after exec modification
|
||||
; GCN: buffer_load_dword [[FLOW_VAL:v[0-9]+]], off, s[8:11], s12 offset:[[FLOW_VAL_OFFSET:[0-9]+]] ; 4-byte Folded Reload
|
||||
; GCN: buffer_load_dword [[FLOW_VAL:v[0-9]+]], off, s[0:3], s7 offset:[[FLOW_VAL_OFFSET:[0-9]+]] ; 4-byte Folded Reload
|
||||
|
||||
|
||||
; Spill saved exec
|
||||
|
|
@ -224,11 +224,11 @@ end:
|
|||
|
||||
|
||||
; VMEM: v_mov_b32_e32 v[[FLOW_V_SAVEEXEC_LO:[0-9]+]], s[[FLOW_S_RELOAD_SAVEEXEC_LO]]
|
||||
; VMEM: buffer_store_dword v[[FLOW_V_SAVEEXEC_LO]], off, s[8:11], s12 offset:[[FLOW_SAVEEXEC_LO_OFFSET:[0-9]+]] ; 8-byte Folded Spill
|
||||
; VMEM: buffer_store_dword v[[FLOW_V_SAVEEXEC_LO]], off, s[0:3], s7 offset:[[FLOW_SAVEEXEC_LO_OFFSET:[0-9]+]] ; 8-byte Folded Spill
|
||||
; VMEM: v_mov_b32_e32 v[[FLOW_V_SAVEEXEC_HI:[0-9]+]], s[[FLOW_S_RELOAD_SAVEEXEC_HI]]
|
||||
; VMEM: buffer_store_dword v[[FLOW_V_SAVEEXEC_HI]], off, s[8:11], s12 offset:[[FLOW_SAVEEXEC_HI_OFFSET:[0-9]+]] ; 8-byte Folded Spill
|
||||
; VMEM: buffer_store_dword v[[FLOW_V_SAVEEXEC_HI]], off, s[0:3], s7 offset:[[FLOW_SAVEEXEC_HI_OFFSET:[0-9]+]] ; 8-byte Folded Spill
|
||||
|
||||
; GCN: buffer_store_dword [[FLOW_VAL]], off, s[8:11], s12 offset:[[RESULT_OFFSET:[0-9]+]] ; 4-byte Folded Spill
|
||||
; GCN: buffer_store_dword [[FLOW_VAL]], off, s[0:3], s7 offset:[[RESULT_OFFSET:[0-9]+]] ; 4-byte Folded Spill
|
||||
; GCN: s_xor_b64 exec, exec, s{{\[}}[[FLOW_S_RELOAD_SAVEEXEC_LO]]:[[FLOW_S_RELOAD_SAVEEXEC_HI]]{{\]}}
|
||||
; GCN-NEXT: s_waitcnt vmcnt(0) expcnt(0)
|
||||
; GCN-NEXT: ; mask branch [[ENDIF:BB[0-9]+_[0-9]+]]
|
||||
|
|
@ -237,16 +237,16 @@ end:
|
|||
|
||||
; GCN: BB{{[0-9]+}}_2: ; %if
|
||||
; GCN: ds_read_b32
|
||||
; GCN: buffer_load_dword v[[LOAD0_RELOAD:[0-9]+]], off, s[8:11], s12 ; 4-byte Folded Reload
|
||||
; GCN: buffer_load_dword v[[LOAD0_RELOAD:[0-9]+]], off, s[0:3], s7 ; 4-byte Folded Reload
|
||||
; GCN: v_add_i32_e32 [[ADD:v[0-9]+]], vcc, v{{[0-9]+}}, v[[LOAD0_RELOAD]]
|
||||
; GCN: buffer_store_dword [[ADD]], off, s[8:11], s12 offset:[[RESULT_OFFSET]] ; 4-byte Folded Spill
|
||||
; GCN: buffer_store_dword [[ADD]], off, s[0:3], s7 offset:[[RESULT_OFFSET]] ; 4-byte Folded Spill
|
||||
; GCN: s_waitcnt vmcnt(0) expcnt(0)
|
||||
; GCN-NEXT: s_branch [[ENDIF:BB[0-9]+_[0-9]+]]
|
||||
|
||||
; GCN: [[ELSE]]: ; %else
|
||||
; GCN: buffer_load_dword v[[LOAD0_RELOAD:[0-9]+]], off, s[8:11], s12 ; 4-byte Folded Reload
|
||||
; GCN: buffer_load_dword v[[LOAD0_RELOAD:[0-9]+]], off, s[0:3], s7 ; 4-byte Folded Reload
|
||||
; GCN: v_subrev_i32_e32 [[SUB:v[0-9]+]], vcc, v{{[0-9]+}}, v[[LOAD0_RELOAD]]
|
||||
; GCN: buffer_store_dword [[ADD]], off, s[8:11], s12 offset:[[FLOW_RESULT_OFFSET:[0-9]+]] ; 4-byte Folded Spill
|
||||
; GCN: buffer_store_dword [[ADD]], off, s[0:3], s7 offset:[[FLOW_RESULT_OFFSET:[0-9]+]] ; 4-byte Folded Spill
|
||||
; GCN: s_waitcnt vmcnt(0) expcnt(0)
|
||||
; GCN-NEXT: s_branch [[FLOW]]
|
||||
|
||||
|
|
@ -255,17 +255,17 @@ end:
|
|||
; VGPR: v_readlane_b32 s[[S_RELOAD_SAVEEXEC_HI:[0-9]+]], [[SPILL_VGPR]], [[FLOW_SAVEEXEC_HI_LANE]]
|
||||
|
||||
|
||||
; VMEM: buffer_load_dword v[[V_RELOAD_SAVEEXEC_LO:[0-9]+]], off, s[8:11], s12 offset:[[FLOW_SAVEEXEC_LO_OFFSET]] ; 8-byte Folded Reload
|
||||
; VMEM: buffer_load_dword v[[V_RELOAD_SAVEEXEC_LO:[0-9]+]], off, s[0:3], s7 offset:[[FLOW_SAVEEXEC_LO_OFFSET]] ; 8-byte Folded Reload
|
||||
; VMEM: s_waitcnt vmcnt(0)
|
||||
; VMEM: v_readfirstlane_b32 s[[S_RELOAD_SAVEEXEC_LO:[0-9]+]], v[[V_RELOAD_SAVEEXEC_LO]]
|
||||
|
||||
; VMEM: buffer_load_dword v[[V_RELOAD_SAVEEXEC_HI:[0-9]+]], off, s[8:11], s12 offset:[[FLOW_SAVEEXEC_HI_OFFSET]] ; 8-byte Folded Reload
|
||||
; VMEM: buffer_load_dword v[[V_RELOAD_SAVEEXEC_HI:[0-9]+]], off, s[0:3], s7 offset:[[FLOW_SAVEEXEC_HI_OFFSET]] ; 8-byte Folded Reload
|
||||
; VMEM: s_waitcnt vmcnt(0)
|
||||
; VMEM: v_readfirstlane_b32 s[[S_RELOAD_SAVEEXEC_HI:[0-9]+]], v[[V_RELOAD_SAVEEXEC_HI]]
|
||||
|
||||
; GCN: s_or_b64 exec, exec, s{{\[}}[[S_RELOAD_SAVEEXEC_LO]]:[[S_RELOAD_SAVEEXEC_HI]]{{\]}}
|
||||
|
||||
; GCN: buffer_load_dword v[[RESULT:[0-9]+]], off, s[8:11], s12 offset:[[RESULT_OFFSET]] ; 4-byte Folded Reload
|
||||
; GCN: buffer_load_dword v[[RESULT:[0-9]+]], off, s[0:3], s7 offset:[[RESULT_OFFSET]] ; 4-byte Folded Reload
|
||||
; GCN: flat_store_dword v{{\[[0-9]+:[0-9]+\]}}, v[[RESULT]]
|
||||
define void @divergent_if_else_endif(i32 addrspace(1)* %out) #0 {
|
||||
entry:
|
||||
|
|
|
|||
|
|
@ -0,0 +1,33 @@
|
|||
; RUN: llc -O0 -mtriple=amdgcn--amdhsa -mcpu=fiji -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VI -check-prefix=OPTNONE %s
|
||||
|
||||
; GCN-LABEL: {{^}}store_to_undef:
|
||||
|
||||
; -O0 should assume spilling, so the input scratch resource descriptor
|
||||
; -should be used directly without any copies.
|
||||
|
||||
; OPTNONE-NOT: s_mov_b32
|
||||
; OPTNONE: buffer_store_dword v{{[0-9]+}}, v{{[0-9]+}}, s[0:3], s7 offen{{$}}
|
||||
define void @store_to_undef() #0 {
|
||||
store volatile i32 0, i32* undef
|
||||
ret void
|
||||
}
|
||||
|
||||
; GCN-LABEL: {{^}}store_to_inttoptr:
|
||||
define void @store_to_inttoptr() #0 {
|
||||
store volatile i32 0, i32* inttoptr (i32 123 to i32*)
|
||||
ret void
|
||||
}
|
||||
|
||||
; GCN-LABEL: {{^}}load_from_undef:
|
||||
define void @load_from_undef() #0 {
|
||||
%ld = load volatile i32, i32* undef
|
||||
ret void
|
||||
}
|
||||
|
||||
; GCN-LABEL: {{^}}load_from_inttoptr:
|
||||
define void @load_from_inttoptr() #0 {
|
||||
%ld = load volatile i32, i32* inttoptr (i32 123 to i32*)
|
||||
ret void
|
||||
}
|
||||
|
||||
attributes #0 = { nounwind }
|
||||
Loading…
Reference in New Issue