18f9351223
The compiler was generating symbols in the final code object for local branch target labels. This bloats the code object, slows down the loader, and is only used to simplify disassembly. Use '--symbolize-operands' with llvm-objdump to improve readability of the branch target operands in disassembly. Fixes: SWDEV-312223 Reviewed By: scott.linder Differential Revision: https://reviews.llvm.org/D114273
83 lines
3.8 KiB
LLVM
83 lines
3.8 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=LOOP %s
|
|
; RUN: llc -global-isel -march=amdgcn -verify-machineinstrs -amdgpu-mem-intrinsic-expand-size=5 %s -o - | FileCheck -check-prefix=UNROLL %s
|
|
|
|
declare void @llvm.memmove.p1i8.p1i8.i32(i8 addrspace(1)*, i8 addrspace(1)*, i32, i1)
|
|
|
|
define amdgpu_cs void @memmove_p1i8(i8 addrspace(1)* %dst, i8 addrspace(1)* %src) {
|
|
; LOOP-LABEL: memmove_p1i8:
|
|
; LOOP: ; %bb.0:
|
|
; LOOP-NEXT: v_cmp_ge_u64_e32 vcc, v[2:3], v[0:1]
|
|
; LOOP-NEXT: s_and_saveexec_b64 s[0:1], vcc
|
|
; LOOP-NEXT: s_xor_b64 s[4:5], exec, s[0:1]
|
|
; LOOP-NEXT: s_cbranch_execz .LBB0_3
|
|
; LOOP-NEXT: ; %bb.1: ; %copy_forward
|
|
; LOOP-NEXT: s_mov_b64 s[0:1], 0
|
|
; LOOP-NEXT: s_mov_b32 s2, 0
|
|
; LOOP-NEXT: s_mov_b32 s3, 0xf000
|
|
; LOOP-NEXT: v_mov_b32_e32 v5, s1
|
|
; LOOP-NEXT: v_mov_b32_e32 v4, s0
|
|
; LOOP-NEXT: .LBB0_2: ; %copy_forward_loop
|
|
; LOOP-NEXT: ; =>This Inner Loop Header: Depth=1
|
|
; LOOP-NEXT: v_add_i32_e32 v6, vcc, v2, v4
|
|
; LOOP-NEXT: v_addc_u32_e32 v7, vcc, v3, v5, vcc
|
|
; LOOP-NEXT: s_waitcnt expcnt(0)
|
|
; LOOP-NEXT: buffer_load_ubyte v8, v[6:7], s[0:3], 0 addr64
|
|
; LOOP-NEXT: v_add_i32_e32 v6, vcc, v0, v4
|
|
; LOOP-NEXT: v_addc_u32_e32 v7, vcc, v1, v5, vcc
|
|
; LOOP-NEXT: v_add_i32_e32 v4, vcc, 1, v4
|
|
; LOOP-NEXT: v_addc_u32_e32 v5, vcc, 0, v5, vcc
|
|
; LOOP-NEXT: v_cmp_ne_u32_e32 vcc, 4, v4
|
|
; LOOP-NEXT: s_waitcnt vmcnt(0)
|
|
; LOOP-NEXT: buffer_store_byte v8, v[6:7], s[0:3], 0 addr64
|
|
; LOOP-NEXT: s_cbranch_vccnz .LBB0_2
|
|
; LOOP-NEXT: .LBB0_3: ; %Flow14
|
|
; LOOP-NEXT: s_or_saveexec_b64 s[0:1], s[4:5]
|
|
; LOOP-NEXT: s_xor_b64 exec, exec, s[0:1]
|
|
; LOOP-NEXT: s_cbranch_execz .LBB0_6
|
|
; LOOP-NEXT: ; %bb.4: ; %copy_backwards
|
|
; LOOP-NEXT: s_mov_b64 s[4:5], 3
|
|
; LOOP-NEXT: s_mov_b32 s2, 0
|
|
; LOOP-NEXT: s_mov_b32 s3, 0xf000
|
|
; LOOP-NEXT: s_mov_b64 s[0:1], 0
|
|
; LOOP-NEXT: v_mov_b32_e32 v4, s4
|
|
; LOOP-NEXT: v_mov_b32_e32 v5, s5
|
|
; LOOP-NEXT: .LBB0_5: ; %copy_backwards_loop
|
|
; LOOP-NEXT: ; =>This Inner Loop Header: Depth=1
|
|
; LOOP-NEXT: v_add_i32_e32 v6, vcc, v2, v4
|
|
; LOOP-NEXT: v_addc_u32_e32 v7, vcc, v3, v5, vcc
|
|
; LOOP-NEXT: s_waitcnt expcnt(0)
|
|
; LOOP-NEXT: buffer_load_ubyte v8, v[6:7], s[0:3], 0 addr64
|
|
; LOOP-NEXT: v_add_i32_e32 v6, vcc, v0, v4
|
|
; LOOP-NEXT: v_addc_u32_e32 v7, vcc, v1, v5, vcc
|
|
; LOOP-NEXT: v_add_i32_e32 v4, vcc, -1, v4
|
|
; LOOP-NEXT: v_addc_u32_e32 v5, vcc, -1, v5, vcc
|
|
; LOOP-NEXT: v_cmp_eq_u32_e32 vcc, -1, v4
|
|
; LOOP-NEXT: s_waitcnt vmcnt(0)
|
|
; LOOP-NEXT: buffer_store_byte v8, v[6:7], s[0:3], 0 addr64
|
|
; LOOP-NEXT: s_cbranch_vccz .LBB0_5
|
|
; LOOP-NEXT: .LBB0_6: ; %memmove_done
|
|
; LOOP-NEXT: s_endpgm
|
|
;
|
|
; UNROLL-LABEL: memmove_p1i8:
|
|
; UNROLL: ; %bb.0:
|
|
; UNROLL-NEXT: s_mov_b32 s2, 0
|
|
; UNROLL-NEXT: s_mov_b32 s3, 0xf000
|
|
; UNROLL-NEXT: s_mov_b64 s[0:1], 0
|
|
; UNROLL-NEXT: buffer_load_ubyte v4, v[2:3], s[0:3], 0 addr64
|
|
; UNROLL-NEXT: buffer_load_ubyte v5, v[2:3], s[0:3], 0 addr64 offset:1
|
|
; UNROLL-NEXT: buffer_load_ubyte v6, v[2:3], s[0:3], 0 addr64 offset:2
|
|
; UNROLL-NEXT: buffer_load_ubyte v2, v[2:3], s[0:3], 0 addr64 offset:3
|
|
; UNROLL-NEXT: s_waitcnt vmcnt(3)
|
|
; UNROLL-NEXT: buffer_store_byte v4, v[0:1], s[0:3], 0 addr64
|
|
; UNROLL-NEXT: s_waitcnt vmcnt(3)
|
|
; UNROLL-NEXT: buffer_store_byte v5, v[0:1], s[0:3], 0 addr64 offset:1
|
|
; UNROLL-NEXT: s_waitcnt vmcnt(3)
|
|
; UNROLL-NEXT: buffer_store_byte v6, v[0:1], s[0:3], 0 addr64 offset:2
|
|
; UNROLL-NEXT: s_waitcnt vmcnt(3)
|
|
; UNROLL-NEXT: buffer_store_byte v2, v[0:1], s[0:3], 0 addr64 offset:3
|
|
; UNROLL-NEXT: s_endpgm
|
|
call void @llvm.memmove.p1i8.p1i8.i32(i8 addrspace(1)* %dst, i8 addrspace(1)* %src, i32 4, i1 false)
|
|
ret void
|
|
}
|