forked from OSchip/llvm-project
1745 lines
59 KiB
LLVM
1745 lines
59 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -verify-machineinstrs < %s | FileCheck --check-prefix=SI %s
|
|
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck --check-prefix=VI %s
|
|
|
|
define amdgpu_kernel void @bfe_u32_arg_arg_arg(i32 addrspace(1)* %out, i32 %src0, i32 %src1, i32 %src2) #0 {
|
|
; SI-LABEL: bfe_u32_arg_arg_arg:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0xb
|
|
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: v_mov_b32_e32 v0, s4
|
|
; SI-NEXT: v_bfe_u32 v0, v0, s5, s5
|
|
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_arg_arg_arg:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x24
|
|
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x2c
|
|
; VI-NEXT: s_mov_b32 s7, 0xf000
|
|
; VI-NEXT: s_mov_b32 s6, -1
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_mov_b32_e32 v0, s0
|
|
; VI-NEXT: v_bfe_u32 v0, v0, s1, s1
|
|
; VI-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; VI-NEXT: s_endpgm
|
|
%bfe_u32 = call i32 @llvm.amdgcn.ubfe.i32(i32 %src0, i32 %src1, i32 %src1)
|
|
store i32 %bfe_u32, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @bfe_u32_arg_arg_imm(i32 addrspace(1)* %out, i32 %src0, i32 %src1) #0 {
|
|
; SI-LABEL: bfe_u32_arg_arg_imm:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0xb
|
|
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: v_mov_b32_e32 v0, 0x7b
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: v_mov_b32_e32 v1, s5
|
|
; SI-NEXT: v_bfe_u32 v0, s4, v1, v0
|
|
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_arg_arg_imm:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x24
|
|
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x2c
|
|
; VI-NEXT: v_mov_b32_e32 v1, 0x7b
|
|
; VI-NEXT: s_mov_b32 s7, 0xf000
|
|
; VI-NEXT: s_mov_b32 s6, -1
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_mov_b32_e32 v0, s1
|
|
; VI-NEXT: v_bfe_u32 v0, s0, v0, v1
|
|
; VI-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; VI-NEXT: s_endpgm
|
|
%bfe_u32 = call i32 @llvm.amdgcn.ubfe.i32(i32 %src0, i32 %src1, i32 123)
|
|
store i32 %bfe_u32, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @bfe_u32_arg_imm_arg(i32 addrspace(1)* %out, i32 %src0, i32 %src2) #0 {
|
|
; SI-LABEL: bfe_u32_arg_imm_arg:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0xb
|
|
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: v_mov_b32_e32 v0, 0x7b
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: v_mov_b32_e32 v1, s5
|
|
; SI-NEXT: v_bfe_u32 v0, s4, v0, v1
|
|
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_arg_imm_arg:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x24
|
|
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x2c
|
|
; VI-NEXT: v_mov_b32_e32 v0, 0x7b
|
|
; VI-NEXT: s_mov_b32 s7, 0xf000
|
|
; VI-NEXT: s_mov_b32 s6, -1
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_mov_b32_e32 v1, s1
|
|
; VI-NEXT: v_bfe_u32 v0, s0, v0, v1
|
|
; VI-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; VI-NEXT: s_endpgm
|
|
%bfe_u32 = call i32 @llvm.amdgcn.ubfe.i32(i32 %src0, i32 123, i32 %src2)
|
|
store i32 %bfe_u32, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @bfe_u32_imm_arg_arg(i32 addrspace(1)* %out, i32 %src1, i32 %src2) #0 {
|
|
; SI-LABEL: bfe_u32_imm_arg_arg:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0xb
|
|
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: s_movk_i32 s6, 0x7b
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: v_mov_b32_e32 v0, s4
|
|
; SI-NEXT: v_mov_b32_e32 v1, s5
|
|
; SI-NEXT: v_bfe_u32 v0, s6, v0, v1
|
|
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_imm_arg_arg:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x24
|
|
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x2c
|
|
; VI-NEXT: s_movk_i32 s2, 0x7b
|
|
; VI-NEXT: s_mov_b32 s7, 0xf000
|
|
; VI-NEXT: s_mov_b32 s6, -1
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_mov_b32_e32 v0, s0
|
|
; VI-NEXT: v_mov_b32_e32 v1, s1
|
|
; VI-NEXT: v_bfe_u32 v0, s2, v0, v1
|
|
; VI-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; VI-NEXT: s_endpgm
|
|
%bfe_u32 = call i32 @llvm.amdgcn.ubfe.i32(i32 123, i32 %src1, i32 %src2)
|
|
store i32 %bfe_u32, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @bfe_u32_arg_0_width_reg_offset(i32 addrspace(1)* %out, i32 %src0, i32 %src1) #0 {
|
|
; SI-LABEL: bfe_u32_arg_0_width_reg_offset:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: v_mov_b32_e32 v0, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_arg_0_width_reg_offset:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: v_mov_b32_e32 v0, 0
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%bfe_u32 = call i32 @llvm.amdgcn.ubfe.i32(i32 %src0, i32 %src1, i32 0)
|
|
store i32 %bfe_u32, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @bfe_u32_arg_0_width_imm_offset(i32 addrspace(1)* %out, i32 %src0, i32 %src1) #0 {
|
|
; SI-LABEL: bfe_u32_arg_0_width_imm_offset:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: v_mov_b32_e32 v0, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_arg_0_width_imm_offset:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: v_mov_b32_e32 v0, 0
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%bfe_u32 = call i32 @llvm.amdgcn.ubfe.i32(i32 %src0, i32 8, i32 0)
|
|
store i32 %bfe_u32, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @bfe_u32_zextload_i8(i32 addrspace(1)* %out, i8 addrspace(1)* %in) #0 {
|
|
; SI-LABEL: bfe_u32_zextload_i8:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, -1
|
|
; SI-NEXT: s_mov_b32 s10, s6
|
|
; SI-NEXT: s_mov_b32 s11, s7
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b32 s8, s2
|
|
; SI-NEXT: s_mov_b32 s9, s3
|
|
; SI-NEXT: buffer_load_ubyte v0, off, s[8:11], 0
|
|
; SI-NEXT: s_mov_b32 s4, s0
|
|
; SI-NEXT: s_mov_b32 s5, s1
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_zextload_i8:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: s_mov_b32 s0, s4
|
|
; VI-NEXT: s_mov_b32 s1, s5
|
|
; VI-NEXT: s_mov_b32 s4, s6
|
|
; VI-NEXT: s_mov_b32 s5, s7
|
|
; VI-NEXT: s_mov_b32 s6, s2
|
|
; VI-NEXT: s_mov_b32 s7, s3
|
|
; VI-NEXT: buffer_load_ubyte v0, off, s[4:7], 0
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%load = load i8, i8 addrspace(1)* %in
|
|
%ext = zext i8 %load to i32
|
|
%bfe = call i32 @llvm.amdgcn.ubfe.i32(i32 %ext, i32 0, i32 8)
|
|
store i32 %bfe, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; FIXME: Should be using s_add_i32
|
|
define amdgpu_kernel void @bfe_u32_zext_in_reg_i8(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
; SI-LABEL: bfe_u32_zext_in_reg_i8:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, -1
|
|
; SI-NEXT: s_mov_b32 s10, s6
|
|
; SI-NEXT: s_mov_b32 s11, s7
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b32 s8, s2
|
|
; SI-NEXT: s_mov_b32 s9, s3
|
|
; SI-NEXT: buffer_load_dword v0, off, s[8:11], 0
|
|
; SI-NEXT: s_mov_b32 s4, s0
|
|
; SI-NEXT: s_mov_b32 s5, s1
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_add_i32_e32 v0, vcc, 1, v0
|
|
; SI-NEXT: v_and_b32_e32 v0, 0xff, v0
|
|
; SI-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_zext_in_reg_i8:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: s_mov_b32 s0, s4
|
|
; VI-NEXT: s_mov_b32 s1, s5
|
|
; VI-NEXT: s_mov_b32 s4, s6
|
|
; VI-NEXT: s_mov_b32 s5, s7
|
|
; VI-NEXT: s_mov_b32 s6, s2
|
|
; VI-NEXT: s_mov_b32 s7, s3
|
|
; VI-NEXT: buffer_load_dword v0, off, s[4:7], 0
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, 1, v0
|
|
; VI-NEXT: v_and_b32_e32 v0, 0xff, v0
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%load = load i32, i32 addrspace(1)* %in, align 4
|
|
%add = add i32 %load, 1
|
|
%ext = and i32 %add, 255
|
|
%bfe = call i32 @llvm.amdgcn.ubfe.i32(i32 %ext, i32 0, i32 8)
|
|
store i32 %bfe, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @bfe_u32_zext_in_reg_i16(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
; SI-LABEL: bfe_u32_zext_in_reg_i16:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, -1
|
|
; SI-NEXT: s_mov_b32 s10, s6
|
|
; SI-NEXT: s_mov_b32 s11, s7
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b32 s8, s2
|
|
; SI-NEXT: s_mov_b32 s9, s3
|
|
; SI-NEXT: buffer_load_dword v0, off, s[8:11], 0
|
|
; SI-NEXT: s_mov_b32 s4, s0
|
|
; SI-NEXT: s_mov_b32 s5, s1
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_add_i32_e32 v0, vcc, 1, v0
|
|
; SI-NEXT: v_and_b32_e32 v0, 0xffff, v0
|
|
; SI-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_zext_in_reg_i16:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: s_mov_b32 s0, s4
|
|
; VI-NEXT: s_mov_b32 s1, s5
|
|
; VI-NEXT: s_mov_b32 s4, s6
|
|
; VI-NEXT: s_mov_b32 s5, s7
|
|
; VI-NEXT: s_mov_b32 s6, s2
|
|
; VI-NEXT: s_mov_b32 s7, s3
|
|
; VI-NEXT: buffer_load_dword v0, off, s[4:7], 0
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, 1, v0
|
|
; VI-NEXT: v_and_b32_e32 v0, 0xffff, v0
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%load = load i32, i32 addrspace(1)* %in, align 4
|
|
%add = add i32 %load, 1
|
|
%ext = and i32 %add, 65535
|
|
%bfe = call i32 @llvm.amdgcn.ubfe.i32(i32 %ext, i32 0, i32 16)
|
|
store i32 %bfe, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @bfe_u32_zext_in_reg_i8_offset_1(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
; SI-LABEL: bfe_u32_zext_in_reg_i8_offset_1:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, -1
|
|
; SI-NEXT: s_mov_b32 s10, s6
|
|
; SI-NEXT: s_mov_b32 s11, s7
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b32 s8, s2
|
|
; SI-NEXT: s_mov_b32 s9, s3
|
|
; SI-NEXT: buffer_load_dword v0, off, s[8:11], 0
|
|
; SI-NEXT: s_mov_b32 s4, s0
|
|
; SI-NEXT: s_mov_b32 s5, s1
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_add_i32_e32 v0, vcc, 1, v0
|
|
; SI-NEXT: v_and_b32_e32 v0, 0xfe, v0
|
|
; SI-NEXT: v_bfe_u32 v0, v0, 1, 8
|
|
; SI-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_zext_in_reg_i8_offset_1:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: s_mov_b32 s0, s4
|
|
; VI-NEXT: s_mov_b32 s1, s5
|
|
; VI-NEXT: s_mov_b32 s4, s6
|
|
; VI-NEXT: s_mov_b32 s5, s7
|
|
; VI-NEXT: s_mov_b32 s6, s2
|
|
; VI-NEXT: s_mov_b32 s7, s3
|
|
; VI-NEXT: buffer_load_dword v0, off, s[4:7], 0
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, 1, v0
|
|
; VI-NEXT: v_and_b32_e32 v0, 0xfe, v0
|
|
; VI-NEXT: v_bfe_u32 v0, v0, 1, 8
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%load = load i32, i32 addrspace(1)* %in, align 4
|
|
%add = add i32 %load, 1
|
|
%ext = and i32 %add, 255
|
|
%bfe = call i32 @llvm.amdgcn.ubfe.i32(i32 %ext, i32 1, i32 8)
|
|
store i32 %bfe, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @bfe_u32_zext_in_reg_i8_offset_3(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
; SI-LABEL: bfe_u32_zext_in_reg_i8_offset_3:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, -1
|
|
; SI-NEXT: s_mov_b32 s10, s6
|
|
; SI-NEXT: s_mov_b32 s11, s7
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b32 s8, s2
|
|
; SI-NEXT: s_mov_b32 s9, s3
|
|
; SI-NEXT: buffer_load_dword v0, off, s[8:11], 0
|
|
; SI-NEXT: s_mov_b32 s4, s0
|
|
; SI-NEXT: s_mov_b32 s5, s1
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_add_i32_e32 v0, vcc, 1, v0
|
|
; SI-NEXT: v_and_b32_e32 v0, 0xf8, v0
|
|
; SI-NEXT: v_bfe_u32 v0, v0, 3, 8
|
|
; SI-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_zext_in_reg_i8_offset_3:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: s_mov_b32 s0, s4
|
|
; VI-NEXT: s_mov_b32 s1, s5
|
|
; VI-NEXT: s_mov_b32 s4, s6
|
|
; VI-NEXT: s_mov_b32 s5, s7
|
|
; VI-NEXT: s_mov_b32 s6, s2
|
|
; VI-NEXT: s_mov_b32 s7, s3
|
|
; VI-NEXT: buffer_load_dword v0, off, s[4:7], 0
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, 1, v0
|
|
; VI-NEXT: v_and_b32_e32 v0, 0xf8, v0
|
|
; VI-NEXT: v_bfe_u32 v0, v0, 3, 8
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%load = load i32, i32 addrspace(1)* %in, align 4
|
|
%add = add i32 %load, 1
|
|
%ext = and i32 %add, 255
|
|
%bfe = call i32 @llvm.amdgcn.ubfe.i32(i32 %ext, i32 3, i32 8)
|
|
store i32 %bfe, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @bfe_u32_zext_in_reg_i8_offset_7(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
; SI-LABEL: bfe_u32_zext_in_reg_i8_offset_7:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, -1
|
|
; SI-NEXT: s_mov_b32 s10, s6
|
|
; SI-NEXT: s_mov_b32 s11, s7
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b32 s8, s2
|
|
; SI-NEXT: s_mov_b32 s9, s3
|
|
; SI-NEXT: buffer_load_dword v0, off, s[8:11], 0
|
|
; SI-NEXT: s_mov_b32 s4, s0
|
|
; SI-NEXT: s_mov_b32 s5, s1
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_add_i32_e32 v0, vcc, 1, v0
|
|
; SI-NEXT: v_and_b32_e32 v0, 0x80, v0
|
|
; SI-NEXT: v_bfe_u32 v0, v0, 7, 8
|
|
; SI-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_zext_in_reg_i8_offset_7:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: s_mov_b32 s0, s4
|
|
; VI-NEXT: s_mov_b32 s1, s5
|
|
; VI-NEXT: s_mov_b32 s4, s6
|
|
; VI-NEXT: s_mov_b32 s5, s7
|
|
; VI-NEXT: s_mov_b32 s6, s2
|
|
; VI-NEXT: s_mov_b32 s7, s3
|
|
; VI-NEXT: buffer_load_dword v0, off, s[4:7], 0
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, 1, v0
|
|
; VI-NEXT: v_and_b32_e32 v0, 0x80, v0
|
|
; VI-NEXT: v_bfe_u32 v0, v0, 7, 8
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%load = load i32, i32 addrspace(1)* %in, align 4
|
|
%add = add i32 %load, 1
|
|
%ext = and i32 %add, 255
|
|
%bfe = call i32 @llvm.amdgcn.ubfe.i32(i32 %ext, i32 7, i32 8)
|
|
store i32 %bfe, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @bfe_u32_zext_in_reg_i16_offset_8(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
; SI-LABEL: bfe_u32_zext_in_reg_i16_offset_8:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, -1
|
|
; SI-NEXT: s_mov_b32 s10, s6
|
|
; SI-NEXT: s_mov_b32 s11, s7
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b32 s8, s2
|
|
; SI-NEXT: s_mov_b32 s9, s3
|
|
; SI-NEXT: buffer_load_dword v0, off, s[8:11], 0
|
|
; SI-NEXT: s_mov_b32 s4, s0
|
|
; SI-NEXT: s_mov_b32 s5, s1
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_add_i32_e32 v0, vcc, 1, v0
|
|
; SI-NEXT: v_bfe_u32 v0, v0, 8, 8
|
|
; SI-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_zext_in_reg_i16_offset_8:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: s_mov_b32 s0, s4
|
|
; VI-NEXT: s_mov_b32 s1, s5
|
|
; VI-NEXT: s_mov_b32 s4, s6
|
|
; VI-NEXT: s_mov_b32 s5, s7
|
|
; VI-NEXT: s_mov_b32 s6, s2
|
|
; VI-NEXT: s_mov_b32 s7, s3
|
|
; VI-NEXT: buffer_load_dword v0, off, s[4:7], 0
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, 1, v0
|
|
; VI-NEXT: v_bfe_u32 v0, v0, 8, 8
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%load = load i32, i32 addrspace(1)* %in, align 4
|
|
%add = add i32 %load, 1
|
|
%ext = and i32 %add, 65535
|
|
%bfe = call i32 @llvm.amdgcn.ubfe.i32(i32 %ext, i32 8, i32 8)
|
|
store i32 %bfe, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @bfe_u32_test_1(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
; SI-LABEL: bfe_u32_test_1:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, -1
|
|
; SI-NEXT: s_mov_b32 s10, s6
|
|
; SI-NEXT: s_mov_b32 s11, s7
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b32 s8, s2
|
|
; SI-NEXT: s_mov_b32 s9, s3
|
|
; SI-NEXT: buffer_load_dword v0, off, s[8:11], 0
|
|
; SI-NEXT: s_mov_b32 s4, s0
|
|
; SI-NEXT: s_mov_b32 s5, s1
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_and_b32_e32 v0, 1, v0
|
|
; SI-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_test_1:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: s_mov_b32 s0, s4
|
|
; VI-NEXT: s_mov_b32 s1, s5
|
|
; VI-NEXT: s_mov_b32 s4, s6
|
|
; VI-NEXT: s_mov_b32 s5, s7
|
|
; VI-NEXT: s_mov_b32 s6, s2
|
|
; VI-NEXT: s_mov_b32 s7, s3
|
|
; VI-NEXT: buffer_load_dword v0, off, s[4:7], 0
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_and_b32_e32 v0, 1, v0
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%x = load i32, i32 addrspace(1)* %in, align 4
|
|
%bfe = call i32 @llvm.amdgcn.ubfe.i32(i32 %x, i32 0, i32 1)
|
|
store i32 %bfe, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @bfe_u32_test_2(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
; SI-LABEL: bfe_u32_test_2:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: v_mov_b32_e32 v0, 0
|
|
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_test_2:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: v_mov_b32_e32 v0, 0
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%x = load i32, i32 addrspace(1)* %in, align 4
|
|
%shl = shl i32 %x, 31
|
|
%bfe = call i32 @llvm.amdgcn.ubfe.i32(i32 %shl, i32 0, i32 8)
|
|
store i32 %bfe, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @bfe_u32_test_3(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
; SI-LABEL: bfe_u32_test_3:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: v_mov_b32_e32 v0, 0
|
|
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_test_3:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: v_mov_b32_e32 v0, 0
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%x = load i32, i32 addrspace(1)* %in, align 4
|
|
%shl = shl i32 %x, 31
|
|
%bfe = call i32 @llvm.amdgcn.ubfe.i32(i32 %shl, i32 0, i32 1)
|
|
store i32 %bfe, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @bfe_u32_test_4(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
; SI-LABEL: bfe_u32_test_4:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: v_mov_b32_e32 v0, 0
|
|
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_test_4:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: v_mov_b32_e32 v0, 0
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%x = load i32, i32 addrspace(1)* %in, align 4
|
|
%shl = shl i32 %x, 31
|
|
%shr = lshr i32 %shl, 31
|
|
%bfe = call i32 @llvm.amdgcn.ubfe.i32(i32 %shr, i32 31, i32 1)
|
|
store i32 %bfe, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @bfe_u32_test_5(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
; SI-LABEL: bfe_u32_test_5:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, -1
|
|
; SI-NEXT: s_mov_b32 s10, s6
|
|
; SI-NEXT: s_mov_b32 s11, s7
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b32 s8, s2
|
|
; SI-NEXT: s_mov_b32 s9, s3
|
|
; SI-NEXT: buffer_load_dword v0, off, s[8:11], 0
|
|
; SI-NEXT: s_mov_b32 s4, s0
|
|
; SI-NEXT: s_mov_b32 s5, s1
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_bfe_i32 v0, v0, 0, 1
|
|
; SI-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_test_5:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: s_mov_b32 s0, s4
|
|
; VI-NEXT: s_mov_b32 s1, s5
|
|
; VI-NEXT: s_mov_b32 s4, s6
|
|
; VI-NEXT: s_mov_b32 s5, s7
|
|
; VI-NEXT: s_mov_b32 s6, s2
|
|
; VI-NEXT: s_mov_b32 s7, s3
|
|
; VI-NEXT: buffer_load_dword v0, off, s[4:7], 0
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_bfe_i32 v0, v0, 0, 1
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%x = load i32, i32 addrspace(1)* %in, align 4
|
|
%shl = shl i32 %x, 31
|
|
%shr = ashr i32 %shl, 31
|
|
%bfe = call i32 @llvm.amdgcn.ubfe.i32(i32 %shr, i32 0, i32 1)
|
|
store i32 %bfe, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @bfe_u32_test_6(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
; SI-LABEL: bfe_u32_test_6:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, -1
|
|
; SI-NEXT: s_mov_b32 s10, s6
|
|
; SI-NEXT: s_mov_b32 s11, s7
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b32 s8, s2
|
|
; SI-NEXT: s_mov_b32 s9, s3
|
|
; SI-NEXT: buffer_load_dword v0, off, s[8:11], 0
|
|
; SI-NEXT: s_mov_b32 s4, s0
|
|
; SI-NEXT: s_mov_b32 s5, s1
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_lshlrev_b32_e32 v0, 31, v0
|
|
; SI-NEXT: v_lshrrev_b32_e32 v0, 1, v0
|
|
; SI-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_test_6:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: s_mov_b32 s0, s4
|
|
; VI-NEXT: s_mov_b32 s1, s5
|
|
; VI-NEXT: s_mov_b32 s4, s6
|
|
; VI-NEXT: s_mov_b32 s5, s7
|
|
; VI-NEXT: s_mov_b32 s6, s2
|
|
; VI-NEXT: s_mov_b32 s7, s3
|
|
; VI-NEXT: buffer_load_dword v0, off, s[4:7], 0
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_lshlrev_b32_e32 v0, 31, v0
|
|
; VI-NEXT: v_lshrrev_b32_e32 v0, 1, v0
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%x = load i32, i32 addrspace(1)* %in, align 4
|
|
%shl = shl i32 %x, 31
|
|
%bfe = call i32 @llvm.amdgcn.ubfe.i32(i32 %shl, i32 1, i32 31)
|
|
store i32 %bfe, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @bfe_u32_test_7(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
; SI-LABEL: bfe_u32_test_7:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, -1
|
|
; SI-NEXT: s_mov_b32 s10, s6
|
|
; SI-NEXT: s_mov_b32 s11, s7
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b32 s8, s2
|
|
; SI-NEXT: s_mov_b32 s9, s3
|
|
; SI-NEXT: buffer_load_dword v0, off, s[8:11], 0
|
|
; SI-NEXT: s_mov_b32 s4, s0
|
|
; SI-NEXT: s_mov_b32 s5, s1
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_lshlrev_b32_e32 v0, 31, v0
|
|
; SI-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_test_7:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: s_mov_b32 s0, s4
|
|
; VI-NEXT: s_mov_b32 s1, s5
|
|
; VI-NEXT: s_mov_b32 s4, s6
|
|
; VI-NEXT: s_mov_b32 s5, s7
|
|
; VI-NEXT: s_mov_b32 s6, s2
|
|
; VI-NEXT: s_mov_b32 s7, s3
|
|
; VI-NEXT: buffer_load_dword v0, off, s[4:7], 0
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_lshlrev_b32_e32 v0, 31, v0
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%x = load i32, i32 addrspace(1)* %in, align 4
|
|
%shl = shl i32 %x, 31
|
|
%bfe = call i32 @llvm.amdgcn.ubfe.i32(i32 %shl, i32 0, i32 31)
|
|
store i32 %bfe, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @bfe_u32_test_8(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
; SI-LABEL: bfe_u32_test_8:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, -1
|
|
; SI-NEXT: s_mov_b32 s10, s6
|
|
; SI-NEXT: s_mov_b32 s11, s7
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b32 s8, s2
|
|
; SI-NEXT: s_mov_b32 s9, s3
|
|
; SI-NEXT: buffer_load_dword v0, off, s[8:11], 0
|
|
; SI-NEXT: s_mov_b32 s4, s0
|
|
; SI-NEXT: s_mov_b32 s5, s1
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_and_b32_e32 v0, 1, v0
|
|
; SI-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_test_8:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: s_mov_b32 s0, s4
|
|
; VI-NEXT: s_mov_b32 s1, s5
|
|
; VI-NEXT: s_mov_b32 s4, s6
|
|
; VI-NEXT: s_mov_b32 s5, s7
|
|
; VI-NEXT: s_mov_b32 s6, s2
|
|
; VI-NEXT: s_mov_b32 s7, s3
|
|
; VI-NEXT: buffer_load_dword v0, off, s[4:7], 0
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_and_b32_e32 v0, 1, v0
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%x = load i32, i32 addrspace(1)* %in, align 4
|
|
%shl = shl i32 %x, 31
|
|
%bfe = call i32 @llvm.amdgcn.ubfe.i32(i32 %shl, i32 31, i32 1)
|
|
store i32 %bfe, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @bfe_u32_test_9(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
; SI-LABEL: bfe_u32_test_9:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, -1
|
|
; SI-NEXT: s_mov_b32 s10, s6
|
|
; SI-NEXT: s_mov_b32 s11, s7
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b32 s8, s2
|
|
; SI-NEXT: s_mov_b32 s9, s3
|
|
; SI-NEXT: buffer_load_dword v0, off, s[8:11], 0
|
|
; SI-NEXT: s_mov_b32 s4, s0
|
|
; SI-NEXT: s_mov_b32 s5, s1
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_lshrrev_b32_e32 v0, 31, v0
|
|
; SI-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_test_9:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: s_mov_b32 s0, s4
|
|
; VI-NEXT: s_mov_b32 s1, s5
|
|
; VI-NEXT: s_mov_b32 s4, s6
|
|
; VI-NEXT: s_mov_b32 s5, s7
|
|
; VI-NEXT: s_mov_b32 s6, s2
|
|
; VI-NEXT: s_mov_b32 s7, s3
|
|
; VI-NEXT: buffer_load_dword v0, off, s[4:7], 0
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_lshrrev_b32_e32 v0, 31, v0
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%x = load i32, i32 addrspace(1)* %in, align 4
|
|
%bfe = call i32 @llvm.amdgcn.ubfe.i32(i32 %x, i32 31, i32 1)
|
|
store i32 %bfe, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @bfe_u32_test_10(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
; SI-LABEL: bfe_u32_test_10:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, -1
|
|
; SI-NEXT: s_mov_b32 s10, s6
|
|
; SI-NEXT: s_mov_b32 s11, s7
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b32 s8, s2
|
|
; SI-NEXT: s_mov_b32 s9, s3
|
|
; SI-NEXT: buffer_load_dword v0, off, s[8:11], 0
|
|
; SI-NEXT: s_mov_b32 s4, s0
|
|
; SI-NEXT: s_mov_b32 s5, s1
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_lshrrev_b32_e32 v0, 1, v0
|
|
; SI-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_test_10:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: s_mov_b32 s0, s4
|
|
; VI-NEXT: s_mov_b32 s1, s5
|
|
; VI-NEXT: s_mov_b32 s4, s6
|
|
; VI-NEXT: s_mov_b32 s5, s7
|
|
; VI-NEXT: s_mov_b32 s6, s2
|
|
; VI-NEXT: s_mov_b32 s7, s3
|
|
; VI-NEXT: buffer_load_dword v0, off, s[4:7], 0
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_lshrrev_b32_e32 v0, 1, v0
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%x = load i32, i32 addrspace(1)* %in, align 4
|
|
%bfe = call i32 @llvm.amdgcn.ubfe.i32(i32 %x, i32 1, i32 31)
|
|
store i32 %bfe, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @bfe_u32_test_11(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
; SI-LABEL: bfe_u32_test_11:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, -1
|
|
; SI-NEXT: s_mov_b32 s10, s6
|
|
; SI-NEXT: s_mov_b32 s11, s7
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b32 s8, s2
|
|
; SI-NEXT: s_mov_b32 s9, s3
|
|
; SI-NEXT: buffer_load_dword v0, off, s[8:11], 0
|
|
; SI-NEXT: s_mov_b32 s4, s0
|
|
; SI-NEXT: s_mov_b32 s5, s1
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_lshrrev_b32_e32 v0, 8, v0
|
|
; SI-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_test_11:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: s_mov_b32 s0, s4
|
|
; VI-NEXT: s_mov_b32 s1, s5
|
|
; VI-NEXT: s_mov_b32 s4, s6
|
|
; VI-NEXT: s_mov_b32 s5, s7
|
|
; VI-NEXT: s_mov_b32 s6, s2
|
|
; VI-NEXT: s_mov_b32 s7, s3
|
|
; VI-NEXT: buffer_load_dword v0, off, s[4:7], 0
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_lshrrev_b32_e32 v0, 8, v0
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%x = load i32, i32 addrspace(1)* %in, align 4
|
|
%bfe = call i32 @llvm.amdgcn.ubfe.i32(i32 %x, i32 8, i32 24)
|
|
store i32 %bfe, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @bfe_u32_test_12(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
; SI-LABEL: bfe_u32_test_12:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, -1
|
|
; SI-NEXT: s_mov_b32 s10, s6
|
|
; SI-NEXT: s_mov_b32 s11, s7
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b32 s8, s2
|
|
; SI-NEXT: s_mov_b32 s9, s3
|
|
; SI-NEXT: buffer_load_dword v0, off, s[8:11], 0
|
|
; SI-NEXT: s_mov_b32 s4, s0
|
|
; SI-NEXT: s_mov_b32 s5, s1
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_lshrrev_b32_e32 v0, 24, v0
|
|
; SI-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_test_12:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: s_mov_b32 s0, s4
|
|
; VI-NEXT: s_mov_b32 s1, s5
|
|
; VI-NEXT: s_mov_b32 s4, s6
|
|
; VI-NEXT: s_mov_b32 s5, s7
|
|
; VI-NEXT: s_mov_b32 s6, s2
|
|
; VI-NEXT: s_mov_b32 s7, s3
|
|
; VI-NEXT: buffer_load_dword v0, off, s[4:7], 0
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_lshrrev_b32_e32 v0, 24, v0
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%x = load i32, i32 addrspace(1)* %in, align 4
|
|
%bfe = call i32 @llvm.amdgcn.ubfe.i32(i32 %x, i32 24, i32 8)
|
|
store i32 %bfe, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; V_ASHRREV_U32_e32 {{v[0-9]+}}, 31, {{v[0-9]+}}
|
|
define amdgpu_kernel void @bfe_u32_test_13(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
; SI-LABEL: bfe_u32_test_13:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, -1
|
|
; SI-NEXT: s_mov_b32 s10, s6
|
|
; SI-NEXT: s_mov_b32 s11, s7
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b32 s8, s2
|
|
; SI-NEXT: s_mov_b32 s9, s3
|
|
; SI-NEXT: buffer_load_dword v0, off, s[8:11], 0
|
|
; SI-NEXT: s_mov_b32 s4, s0
|
|
; SI-NEXT: s_mov_b32 s5, s1
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_lshrrev_b32_e32 v0, 31, v0
|
|
; SI-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_test_13:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: s_mov_b32 s0, s4
|
|
; VI-NEXT: s_mov_b32 s1, s5
|
|
; VI-NEXT: s_mov_b32 s4, s6
|
|
; VI-NEXT: s_mov_b32 s5, s7
|
|
; VI-NEXT: s_mov_b32 s6, s2
|
|
; VI-NEXT: s_mov_b32 s7, s3
|
|
; VI-NEXT: buffer_load_dword v0, off, s[4:7], 0
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_lshrrev_b32_e32 v0, 31, v0
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%x = load i32, i32 addrspace(1)* %in, align 4
|
|
%shl = ashr i32 %x, 31
|
|
%bfe = call i32 @llvm.amdgcn.ubfe.i32(i32 %shl, i32 31, i32 1)
|
|
store i32 %bfe, i32 addrspace(1)* %out, align 4 ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @bfe_u32_test_14(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
; SI-LABEL: bfe_u32_test_14:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: v_mov_b32_e32 v0, 0
|
|
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_test_14:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: v_mov_b32_e32 v0, 0
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%x = load i32, i32 addrspace(1)* %in, align 4
|
|
%shl = lshr i32 %x, 31
|
|
%bfe = call i32 @llvm.amdgcn.ubfe.i32(i32 %shl, i32 31, i32 1)
|
|
store i32 %bfe, i32 addrspace(1)* %out, align 4 ret void
|
|
}
|
|
|
|
; EG-NOT: BFE
|
|
define amdgpu_kernel void @bfe_u32_constant_fold_test_0(i32 addrspace(1)* %out) #0 {
|
|
; SI-LABEL: bfe_u32_constant_fold_test_0:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: v_mov_b32_e32 v0, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_constant_fold_test_0:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: v_mov_b32_e32 v0, 0
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%bfe_u32 = call i32 @llvm.amdgcn.ubfe.i32(i32 0, i32 0, i32 0)
|
|
store i32 %bfe_u32, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; EG-NOT: BFE
|
|
define amdgpu_kernel void @bfe_u32_constant_fold_test_1(i32 addrspace(1)* %out) #0 {
|
|
; SI-LABEL: bfe_u32_constant_fold_test_1:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: v_mov_b32_e32 v0, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_constant_fold_test_1:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: v_mov_b32_e32 v0, 0
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%bfe_u32 = call i32 @llvm.amdgcn.ubfe.i32(i32 12334, i32 0, i32 0)
|
|
store i32 %bfe_u32, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; EG-NOT: BFE
|
|
define amdgpu_kernel void @bfe_u32_constant_fold_test_2(i32 addrspace(1)* %out) #0 {
|
|
; SI-LABEL: bfe_u32_constant_fold_test_2:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: v_mov_b32_e32 v0, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_constant_fold_test_2:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: v_mov_b32_e32 v0, 0
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%bfe_u32 = call i32 @llvm.amdgcn.ubfe.i32(i32 0, i32 0, i32 1)
|
|
store i32 %bfe_u32, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; EG-NOT: BFE
|
|
define amdgpu_kernel void @bfe_u32_constant_fold_test_3(i32 addrspace(1)* %out) #0 {
|
|
; SI-LABEL: bfe_u32_constant_fold_test_3:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: v_mov_b32_e32 v0, 1
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_constant_fold_test_3:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: v_mov_b32_e32 v0, 1
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%bfe_u32 = call i32 @llvm.amdgcn.ubfe.i32(i32 1, i32 0, i32 1)
|
|
store i32 %bfe_u32, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; EG-NOT: BFE
|
|
define amdgpu_kernel void @bfe_u32_constant_fold_test_4(i32 addrspace(1)* %out) #0 {
|
|
; SI-LABEL: bfe_u32_constant_fold_test_4:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: v_mov_b32_e32 v0, -1
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_constant_fold_test_4:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: v_mov_b32_e32 v0, -1
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%bfe_u32 = call i32 @llvm.amdgcn.ubfe.i32(i32 4294967295, i32 0, i32 1)
|
|
store i32 %bfe_u32, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; EG-NOT: BFE
|
|
define amdgpu_kernel void @bfe_u32_constant_fold_test_5(i32 addrspace(1)* %out) #0 {
|
|
; SI-LABEL: bfe_u32_constant_fold_test_5:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: v_mov_b32_e32 v0, 1
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_constant_fold_test_5:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: v_mov_b32_e32 v0, 1
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%bfe_u32 = call i32 @llvm.amdgcn.ubfe.i32(i32 128, i32 7, i32 1)
|
|
store i32 %bfe_u32, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; EG-NOT: BFE
|
|
define amdgpu_kernel void @bfe_u32_constant_fold_test_6(i32 addrspace(1)* %out) #0 {
|
|
; SI-LABEL: bfe_u32_constant_fold_test_6:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: v_mov_b32_e32 v0, 0x80
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_constant_fold_test_6:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: v_mov_b32_e32 v0, 0x80
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%bfe_u32 = call i32 @llvm.amdgcn.ubfe.i32(i32 128, i32 0, i32 8)
|
|
store i32 %bfe_u32, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; EG-NOT: BFE
|
|
define amdgpu_kernel void @bfe_u32_constant_fold_test_7(i32 addrspace(1)* %out) #0 {
|
|
; SI-LABEL: bfe_u32_constant_fold_test_7:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: v_mov_b32_e32 v0, 0x7f
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_constant_fold_test_7:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: v_mov_b32_e32 v0, 0x7f
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%bfe_u32 = call i32 @llvm.amdgcn.ubfe.i32(i32 127, i32 0, i32 8)
|
|
store i32 %bfe_u32, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; EG-NOT: BFE
|
|
define amdgpu_kernel void @bfe_u32_constant_fold_test_8(i32 addrspace(1)* %out) #0 {
|
|
; SI-LABEL: bfe_u32_constant_fold_test_8:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: v_mov_b32_e32 v0, 1
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_constant_fold_test_8:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: v_mov_b32_e32 v0, 1
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%bfe_u32 = call i32 @llvm.amdgcn.ubfe.i32(i32 127, i32 6, i32 8)
|
|
store i32 %bfe_u32, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; EG-NOT: BFE
|
|
define amdgpu_kernel void @bfe_u32_constant_fold_test_9(i32 addrspace(1)* %out) #0 {
|
|
; SI-LABEL: bfe_u32_constant_fold_test_9:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: v_mov_b32_e32 v0, 1
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_constant_fold_test_9:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: v_mov_b32_e32 v0, 1
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%bfe_u32 = call i32 @llvm.amdgcn.ubfe.i32(i32 65536, i32 16, i32 8)
|
|
store i32 %bfe_u32, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; EG-NOT: BFE
|
|
define amdgpu_kernel void @bfe_u32_constant_fold_test_10(i32 addrspace(1)* %out) #0 {
|
|
; SI-LABEL: bfe_u32_constant_fold_test_10:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: v_mov_b32_e32 v0, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_constant_fold_test_10:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: v_mov_b32_e32 v0, 0
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%bfe_u32 = call i32 @llvm.amdgcn.ubfe.i32(i32 65535, i32 16, i32 16)
|
|
store i32 %bfe_u32, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; EG-NOT: BFE
|
|
define amdgpu_kernel void @bfe_u32_constant_fold_test_11(i32 addrspace(1)* %out) #0 {
|
|
; SI-LABEL: bfe_u32_constant_fold_test_11:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: v_mov_b32_e32 v0, 10
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_constant_fold_test_11:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: v_mov_b32_e32 v0, 10
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%bfe_u32 = call i32 @llvm.amdgcn.ubfe.i32(i32 160, i32 4, i32 4)
|
|
store i32 %bfe_u32, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; EG-NOT: BFE
|
|
define amdgpu_kernel void @bfe_u32_constant_fold_test_12(i32 addrspace(1)* %out) #0 {
|
|
; SI-LABEL: bfe_u32_constant_fold_test_12:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: v_mov_b32_e32 v0, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_constant_fold_test_12:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: v_mov_b32_e32 v0, 0
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%bfe_u32 = call i32 @llvm.amdgcn.ubfe.i32(i32 160, i32 31, i32 1)
|
|
store i32 %bfe_u32, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; EG-NOT: BFE
|
|
define amdgpu_kernel void @bfe_u32_constant_fold_test_13(i32 addrspace(1)* %out) #0 {
|
|
; SI-LABEL: bfe_u32_constant_fold_test_13:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: v_mov_b32_e32 v0, 1
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_constant_fold_test_13:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: v_mov_b32_e32 v0, 1
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%bfe_u32 = call i32 @llvm.amdgcn.ubfe.i32(i32 131070, i32 16, i32 16)
|
|
store i32 %bfe_u32, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; EG-NOT: BFE
|
|
define amdgpu_kernel void @bfe_u32_constant_fold_test_14(i32 addrspace(1)* %out) #0 {
|
|
; SI-LABEL: bfe_u32_constant_fold_test_14:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: v_mov_b32_e32 v0, 40
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_constant_fold_test_14:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: v_mov_b32_e32 v0, 40
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%bfe_u32 = call i32 @llvm.amdgcn.ubfe.i32(i32 160, i32 2, i32 30)
|
|
store i32 %bfe_u32, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; EG-NOT: BFE
|
|
define amdgpu_kernel void @bfe_u32_constant_fold_test_15(i32 addrspace(1)* %out) #0 {
|
|
; SI-LABEL: bfe_u32_constant_fold_test_15:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: v_mov_b32_e32 v0, 10
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_constant_fold_test_15:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: v_mov_b32_e32 v0, 10
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%bfe_u32 = call i32 @llvm.amdgcn.ubfe.i32(i32 160, i32 4, i32 28)
|
|
store i32 %bfe_u32, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; EG-NOT: BFE
|
|
define amdgpu_kernel void @bfe_u32_constant_fold_test_16(i32 addrspace(1)* %out) #0 {
|
|
; SI-LABEL: bfe_u32_constant_fold_test_16:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: v_mov_b32_e32 v0, 0x7f
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_constant_fold_test_16:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: v_mov_b32_e32 v0, 0x7f
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%bfe_u32 = call i32 @llvm.amdgcn.ubfe.i32(i32 4294967295, i32 1, i32 7)
|
|
store i32 %bfe_u32, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; EG-NOT: BFE
|
|
define amdgpu_kernel void @bfe_u32_constant_fold_test_17(i32 addrspace(1)* %out) #0 {
|
|
; SI-LABEL: bfe_u32_constant_fold_test_17:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: v_mov_b32_e32 v0, 0x7f
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_constant_fold_test_17:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: v_mov_b32_e32 v0, 0x7f
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%bfe_u32 = call i32 @llvm.amdgcn.ubfe.i32(i32 255, i32 1, i32 31)
|
|
store i32 %bfe_u32, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; EG-NOT: BFE
|
|
define amdgpu_kernel void @bfe_u32_constant_fold_test_18(i32 addrspace(1)* %out) #0 {
|
|
; SI-LABEL: bfe_u32_constant_fold_test_18:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: v_mov_b32_e32 v0, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: bfe_u32_constant_fold_test_18:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; VI-NEXT: s_mov_b32 s3, 0xf000
|
|
; VI-NEXT: s_mov_b32 s2, -1
|
|
; VI-NEXT: v_mov_b32_e32 v0, 0
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
%bfe_u32 = call i32 @llvm.amdgcn.ubfe.i32(i32 255, i32 31, i32 1)
|
|
store i32 %bfe_u32, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; Make sure that SimplifyDemandedBits doesn't cause the and to be
|
|
; reduced to the bits demanded by the bfe.
|
|
|
|
; XXX: The operand to v_bfe_u32 could also just directly be the load register.
|
|
define amdgpu_kernel void @simplify_bfe_u32_multi_use_arg(i32 addrspace(1)* %out0,
|
|
; SI-LABEL: simplify_bfe_u32_multi_use_arg:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0xd
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: s_load_dwordx4 s[8:11], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s6, s2
|
|
; SI-NEXT: s_mov_b32 s7, s3
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: buffer_load_dword v0, off, s[4:7], 0
|
|
; SI-NEXT: s_mov_b32 s0, s8
|
|
; SI-NEXT: s_mov_b32 s1, s9
|
|
; SI-NEXT: s_mov_b32 s4, s10
|
|
; SI-NEXT: s_mov_b32 s5, s11
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_and_b32_e32 v0, 63, v0
|
|
; SI-NEXT: v_bfe_u32 v1, v0, 2, 2
|
|
; SI-NEXT: buffer_store_dword v1, off, s[0:3], 0
|
|
; SI-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: simplify_bfe_u32_multi_use_arg:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x24
|
|
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x34
|
|
; VI-NEXT: s_mov_b32 s11, 0xf000
|
|
; VI-NEXT: s_mov_b32 s10, -1
|
|
; VI-NEXT: s_mov_b32 s2, s10
|
|
; VI-NEXT: s_mov_b32 s3, s11
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: buffer_load_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_mov_b32 s8, s4
|
|
; VI-NEXT: s_mov_b32 s9, s5
|
|
; VI-NEXT: s_mov_b32 s0, s6
|
|
; VI-NEXT: s_mov_b32 s1, s7
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_and_b32_e32 v0, 63, v0
|
|
; VI-NEXT: v_bfe_u32 v1, v0, 2, 2
|
|
; VI-NEXT: buffer_store_dword v1, off, s[8:11], 0
|
|
; VI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; VI-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out1,
|
|
i32 addrspace(1)* %in) #0 {
|
|
%src = load i32, i32 addrspace(1)* %in, align 4
|
|
%and = and i32 %src, 63
|
|
%bfe_u32 = call i32 @llvm.amdgcn.ubfe.i32(i32 %and, i32 2, i32 2)
|
|
store i32 %bfe_u32, i32 addrspace(1)* %out0, align 4
|
|
store i32 %and, i32 addrspace(1)* %out1, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @lshr_and(i32 addrspace(1)* %out, i32 %a) #0 {
|
|
; SI-LABEL: lshr_and:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dword s2, s[0:1], 0xb
|
|
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_bfe_u32 s4, s2, 0x30006
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: v_mov_b32_e32 v0, s4
|
|
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: lshr_and:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x24
|
|
; VI-NEXT: s_load_dword s0, s[0:1], 0x2c
|
|
; VI-NEXT: s_mov_b32 s7, 0xf000
|
|
; VI-NEXT: s_mov_b32 s6, -1
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: s_bfe_u32 s0, s0, 0x30006
|
|
; VI-NEXT: v_mov_b32_e32 v0, s0
|
|
; VI-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; VI-NEXT: s_endpgm
|
|
%b = lshr i32 %a, 6
|
|
%c = and i32 %b, 7
|
|
store i32 %c, i32 addrspace(1)* %out, align 8
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @v_lshr_and(i32 addrspace(1)* %out, i32 %a, i32 %b) #0 {
|
|
; SI-LABEL: v_lshr_and:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0xb
|
|
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_lshr_b32 s2, s4, s5
|
|
; SI-NEXT: s_and_b32 s4, s2, 7
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: v_mov_b32_e32 v0, s4
|
|
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: v_lshr_and:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x24
|
|
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x2c
|
|
; VI-NEXT: s_mov_b32 s7, 0xf000
|
|
; VI-NEXT: s_mov_b32 s6, -1
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: s_lshr_b32 s0, s0, s1
|
|
; VI-NEXT: s_and_b32 s0, s0, 7
|
|
; VI-NEXT: v_mov_b32_e32 v0, s0
|
|
; VI-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; VI-NEXT: s_endpgm
|
|
%c = lshr i32 %a, %b
|
|
%d = and i32 %c, 7
|
|
store i32 %d, i32 addrspace(1)* %out, align 8
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @and_lshr(i32 addrspace(1)* %out, i32 %a) #0 {
|
|
; SI-LABEL: and_lshr:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dword s2, s[0:1], 0xb
|
|
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_bfe_u32 s4, s2, 0x30006
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: v_mov_b32_e32 v0, s4
|
|
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: and_lshr:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x24
|
|
; VI-NEXT: s_load_dword s0, s[0:1], 0x2c
|
|
; VI-NEXT: s_mov_b32 s7, 0xf000
|
|
; VI-NEXT: s_mov_b32 s6, -1
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: s_bfe_u32 s0, s0, 0x30006
|
|
; VI-NEXT: v_mov_b32_e32 v0, s0
|
|
; VI-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; VI-NEXT: s_endpgm
|
|
%b = and i32 %a, 448
|
|
%c = lshr i32 %b, 6
|
|
store i32 %c, i32 addrspace(1)* %out, align 8
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @and_lshr2(i32 addrspace(1)* %out, i32 %a) #0 {
|
|
; SI-LABEL: and_lshr2:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dword s2, s[0:1], 0xb
|
|
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_bfe_u32 s4, s2, 0x30006
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: v_mov_b32_e32 v0, s4
|
|
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: and_lshr2:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x24
|
|
; VI-NEXT: s_load_dword s0, s[0:1], 0x2c
|
|
; VI-NEXT: s_mov_b32 s7, 0xf000
|
|
; VI-NEXT: s_mov_b32 s6, -1
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: s_bfe_u32 s0, s0, 0x30006
|
|
; VI-NEXT: v_mov_b32_e32 v0, s0
|
|
; VI-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; VI-NEXT: s_endpgm
|
|
%b = and i32 %a, 511
|
|
%c = lshr i32 %b, 6
|
|
store i32 %c, i32 addrspace(1)* %out, align 8
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @shl_lshr(i32 addrspace(1)* %out, i32 %a) #0 {
|
|
; SI-LABEL: shl_lshr:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dword s2, s[0:1], 0xb
|
|
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s3, 0xf000
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_bfe_u32 s4, s2, 0x150002
|
|
; SI-NEXT: s_mov_b32 s2, -1
|
|
; SI-NEXT: v_mov_b32_e32 v0, s4
|
|
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: shl_lshr:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x24
|
|
; VI-NEXT: s_load_dword s0, s[0:1], 0x2c
|
|
; VI-NEXT: s_mov_b32 s7, 0xf000
|
|
; VI-NEXT: s_mov_b32 s6, -1
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: s_bfe_u32 s0, s0, 0x150002
|
|
; VI-NEXT: v_mov_b32_e32 v0, s0
|
|
; VI-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; VI-NEXT: s_endpgm
|
|
%b = shl i32 %a, 9
|
|
%c = lshr i32 %b, 11
|
|
store i32 %c, i32 addrspace(1)* %out, align 8
|
|
ret void
|
|
}
|
|
|
|
declare i32 @llvm.amdgcn.ubfe.i32(i32, i32, i32) #1
|
|
|
|
attributes #0 = { nounwind }
|
|
attributes #1 = { nounwind readnone }
|