36527cbe02
Legalize G_MEMCPY, G_MEMMOVE, G_MEMSET and G_MEMCPY_INLINE. Corresponding intrinsics are replaced by a loop that uses loads/stores in AMDGPULowerIntrinsics pass unless their length is a constant lower then MemIntrinsicExpandSizeThresholdOpt (default 1024). Any G_MEM* instruction that reaches legalizer should have a const length argument and should be expanded into appropriate number of loads + stores. Differential Revision: https://reviews.llvm.org/D108357
31 lines
1.5 KiB
LLVM
31 lines
1.5 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -global-isel -march=amdgcn -verify-machineinstrs -amdgpu-mem-intrinsic-expand-size=3 %s -o - | FileCheck -check-prefix=GCN %s
|
|
; RUN: llc -global-isel -march=amdgcn -verify-machineinstrs -amdgpu-mem-intrinsic-expand-size=5 %s -o - | FileCheck -check-prefix=GCN %s
|
|
|
|
declare void @llvm.memcpy.inline.p1i8.p1i8.i32(i8 addrspace(1)*, i8 addrspace(1)*, i32, i1 immarg)
|
|
|
|
define amdgpu_cs void @test(i8 addrspace(1)* %dst, i8 addrspace(1)* %src) {
|
|
; GCN-LABEL: test:
|
|
; GCN: ; %bb.0:
|
|
; GCN-NEXT: s_mov_b32 s2, 0
|
|
; GCN-NEXT: s_mov_b32 s3, 0xf000
|
|
; GCN-NEXT: s_mov_b64 s[0:1], 0
|
|
; GCN-NEXT: buffer_load_ubyte v4, v[2:3], s[0:3], 0 addr64
|
|
; GCN-NEXT: s_waitcnt vmcnt(0)
|
|
; GCN-NEXT: buffer_store_byte v4, v[0:1], s[0:3], 0 addr64
|
|
; GCN-NEXT: s_waitcnt expcnt(0)
|
|
; GCN-NEXT: buffer_load_ubyte v4, v[2:3], s[0:3], 0 addr64 offset:1
|
|
; GCN-NEXT: s_waitcnt vmcnt(0)
|
|
; GCN-NEXT: buffer_store_byte v4, v[0:1], s[0:3], 0 addr64 offset:1
|
|
; GCN-NEXT: s_waitcnt expcnt(0)
|
|
; GCN-NEXT: buffer_load_ubyte v4, v[2:3], s[0:3], 0 addr64 offset:2
|
|
; GCN-NEXT: s_waitcnt vmcnt(0)
|
|
; GCN-NEXT: buffer_store_byte v4, v[0:1], s[0:3], 0 addr64 offset:2
|
|
; GCN-NEXT: buffer_load_ubyte v2, v[2:3], s[0:3], 0 addr64 offset:3
|
|
; GCN-NEXT: s_waitcnt vmcnt(0)
|
|
; GCN-NEXT: buffer_store_byte v2, v[0:1], s[0:3], 0 addr64 offset:3
|
|
; GCN-NEXT: s_endpgm
|
|
call void @llvm.memcpy.inline.p1i8.p1i8.i32(i8 addrspace(1)* %dst, i8 addrspace(1)* %src, i32 4, i1 false)
|
|
ret void
|
|
}
|