llvm-project/llvm/test/CodeGen/AMDGPU/setcc-opt.ll

297 lines
10 KiB
LLVM
Raw Normal View History

; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=GCN -check-prefix=FUNC %s
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=VI -check-prefix=GCN -check-prefix=FUNC %s
; RUN: llc -march=r600 -mcpu=cypress -verify-machineinstrs < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s
; FUNC-LABEL: {{^}}sext_bool_icmp_eq_0:
; GCN-NOT: v_cmp
; GCN: v_cmp_ne_i32_e32 vcc,
; GCN-NEXT: v_cndmask_b32_e64 [[RESULT:v[0-9]+]], 0, 1, vcc
; GCN-NEXT:buffer_store_byte [[RESULT]]
; GCN-NEXT: s_endpgm
; EG: SETNE_INT * [[CMP:T[0-9]+]].[[CMPCHAN:[XYZW]]], KC0[2].Z, KC0[2].W
; EG: AND_INT T{{[0-9]+.[XYZW]}}, PS, 1
define void @sext_bool_icmp_eq_0(i1 addrspace(1)* %out, i32 %a, i32 %b) nounwind {
%icmp0 = icmp eq i32 %a, %b
%ext = sext i1 %icmp0 to i32
%icmp1 = icmp eq i32 %ext, 0
store i1 %icmp1, i1 addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}sext_bool_icmp_ne_0:
; GCN-NOT: v_cmp
; GCN: v_cmp_ne_i32_e32 vcc,
; GCN-NEXT: v_cndmask_b32_e64 [[RESULT:v[0-9]+]], 0, 1, vcc
; GCN-NEXT: buffer_store_byte [[RESULT]]
; GCN-NEXT: s_endpgm
; EG: SETNE_INT * [[CMP:T[0-9]+]].[[CMPCHAN:[XYZW]]], KC0[2].Z, KC0[2].W
; EG: AND_INT T{{[0-9]+.[XYZW]}}, PS, 1
define void @sext_bool_icmp_ne_0(i1 addrspace(1)* %out, i32 %a, i32 %b) nounwind {
%icmp0 = icmp ne i32 %a, %b
%ext = sext i1 %icmp0 to i32
%icmp1 = icmp ne i32 %ext, 0
store i1 %icmp1, i1 addrspace(1)* %out
ret void
}
; This really folds away to false
; FUNC-LABEL: {{^}}sext_bool_icmp_eq_1:
; GCN: v_cmp_eq_i32_e32 vcc,
; GCN-NEXT: v_cndmask_b32_e64 [[TMP:v[0-9]+]], 0, -1, vcc
; GCN-NEXT: v_cmp_eq_i32_e32 vcc, 1, [[TMP]]{{$}}
; GCN-NEXT: v_cndmask_b32_e64 [[TMP:v[0-9]+]], 0, 1,
; GCN-NEXT: buffer_store_byte [[TMP]]
; GCN-NEXT: s_endpgm
define void @sext_bool_icmp_eq_1(i1 addrspace(1)* %out, i32 %a, i32 %b) nounwind {
%icmp0 = icmp eq i32 %a, %b
%ext = sext i1 %icmp0 to i32
%icmp1 = icmp eq i32 %ext, 1
store i1 %icmp1, i1 addrspace(1)* %out
ret void
}
; This really folds away to true
; FUNC-LABEL: {{^}}sext_bool_icmp_ne_1:
; GCN: v_cmp_ne_i32_e32 vcc,
; GCN-NEXT: v_cndmask_b32_e64 [[TMP:v[0-9]+]], 0, -1, vcc
; GCN-NEXT: v_cmp_ne_i32_e32 vcc, 1, [[TMP]]{{$}}
; GCN-NEXT: v_cndmask_b32_e64 [[TMP:v[0-9]+]], 0, 1,
; GCN-NEXT: buffer_store_byte [[TMP]]
; GCN-NEXT: s_endpgm
define void @sext_bool_icmp_ne_1(i1 addrspace(1)* %out, i32 %a, i32 %b) nounwind {
%icmp0 = icmp ne i32 %a, %b
%ext = sext i1 %icmp0 to i32
%icmp1 = icmp ne i32 %ext, 1
store i1 %icmp1, i1 addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}sext_bool_icmp_eq_neg1:
; GCN-NOT: v_cmp
; GCN: v_cmp_eq_i32_e32 vcc,
; GCN-NEXT: v_cndmask_b32_e64 [[RESULT:v[0-9]+]], 0, 1, vcc
; GCN-NEXT: buffer_store_byte [[RESULT]]
; GCN-NEXT: s_endpgm
define void @sext_bool_icmp_eq_neg1(i1 addrspace(1)* %out, i32 %a, i32 %b) nounwind {
%icmp0 = icmp eq i32 %a, %b
%ext = sext i1 %icmp0 to i32
%icmp1 = icmp eq i32 %ext, -1
store i1 %icmp1, i1 addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}sext_bool_icmp_ne_neg1:
; GCN-NOT: v_cmp
; GCN: v_cmp_eq_i32_e32 vcc,
; GCN-NEXT: v_cndmask_b32_e64 [[RESULT:v[0-9]+]], 0, 1, vcc
; GCN-NEXT: buffer_store_byte [[RESULT]]
; GCN-NEXT: s_endpgm
define void @sext_bool_icmp_ne_neg1(i1 addrspace(1)* %out, i32 %a, i32 %b) nounwind {
%icmp0 = icmp ne i32 %a, %b
%ext = sext i1 %icmp0 to i32
%icmp1 = icmp ne i32 %ext, -1
store i1 %icmp1, i1 addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}zext_bool_icmp_eq_0:
; GCN-NOT: v_cmp
; GCN: v_cmp_ne_i32_e32 vcc,
; GCN-NEXT: v_cndmask_b32_e64 [[RESULT:v[0-9]+]], 0, 1, vcc
; GCN-NEXT: buffer_store_byte [[RESULT]]
; GCN-NEXT: s_endpgm
define void @zext_bool_icmp_eq_0(i1 addrspace(1)* %out, i32 %a, i32 %b) nounwind {
%icmp0 = icmp eq i32 %a, %b
%ext = zext i1 %icmp0 to i32
%icmp1 = icmp eq i32 %ext, 0
store i1 %icmp1, i1 addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}zext_bool_icmp_ne_0:
; GCN-NOT: v_cmp
; GCN: v_cmp_ne_i32_e32 vcc,
; GCN-NEXT: v_cndmask_b32_e64 [[RESULT:v[0-9]+]], 0, 1, vcc
; GCN-NEXT: buffer_store_byte [[RESULT]]
; GCN-NEXT: s_endpgm
define void @zext_bool_icmp_ne_0(i1 addrspace(1)* %out, i32 %a, i32 %b) nounwind {
%icmp0 = icmp ne i32 %a, %b
%ext = zext i1 %icmp0 to i32
%icmp1 = icmp ne i32 %ext, 0
store i1 %icmp1, i1 addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}zext_bool_icmp_eq_1:
; GCN-NOT: v_cmp
; GCN: v_cmp_eq_i32_e32 vcc,
; GCN-NEXT: v_cndmask_b32_e64 [[RESULT:v[0-9]+]], 0, 1, vcc
; GCN-NEXT: buffer_store_byte [[RESULT]]
; GCN-NEXT: s_endpgm
define void @zext_bool_icmp_eq_1(i1 addrspace(1)* %out, i32 %a, i32 %b) nounwind {
%icmp0 = icmp eq i32 %a, %b
%ext = zext i1 %icmp0 to i32
%icmp1 = icmp eq i32 %ext, 1
store i1 %icmp1, i1 addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}zext_bool_icmp_ne_1:
; GCN-NOT: v_cmp
; GCN: v_cmp_eq_i32_e32 vcc,
; GCN-NEXT: v_cndmask_b32_e64 [[RESULT:v[0-9]+]], 0, 1, vcc
; GCN-NEXT: buffer_store_byte [[RESULT]]
define void @zext_bool_icmp_ne_1(i1 addrspace(1)* %out, i32 %a, i32 %b) nounwind {
%icmp0 = icmp ne i32 %a, %b
%ext = zext i1 %icmp0 to i32
%icmp1 = icmp ne i32 %ext, 1
store i1 %icmp1, i1 addrspace(1)* %out
ret void
}
; Reduces to false:
; FUNC-LABEL: {{^}}zext_bool_icmp_eq_neg1:
; GCN: v_mov_b32_e32 [[TMP:v[0-9]+]], 0{{$}}
; GCN: buffer_store_byte [[TMP]]
; GCN-NEXT: s_endpgm
define void @zext_bool_icmp_eq_neg1(i1 addrspace(1)* %out, i32 %a, i32 %b) nounwind {
%icmp0 = icmp eq i32 %a, %b
%ext = zext i1 %icmp0 to i32
%icmp1 = icmp eq i32 %ext, -1
store i1 %icmp1, i1 addrspace(1)* %out
ret void
}
; Reduces to true:
; FUNC-LABEL: {{^}}zext_bool_icmp_ne_neg1:
; GCN: v_mov_b32_e32 [[TMP:v[0-9]+]], 1{{$}}
; GCN: buffer_store_byte [[TMP]]
; GCN-NEXT: s_endpgm
define void @zext_bool_icmp_ne_neg1(i1 addrspace(1)* %out, i32 %a, i32 %b) nounwind {
%icmp0 = icmp ne i32 %a, %b
%ext = zext i1 %icmp0 to i32
%icmp1 = icmp ne i32 %ext, -1
store i1 %icmp1, i1 addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}sext_bool_icmp_ne_k:
; SI-DAG: s_load_dword [[A:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0xb
; SI-DAG: s_load_dword [[B:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0xc
; VI-DAG: s_load_dword [[A:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x2c
; VI-DAG: s_load_dword [[B:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x30
; GCN: v_mov_b32_e32 [[VB:v[0-9]+]], [[B]]
; GCN: v_cmp_ne_i32_e32 vcc, 2, [[VB]]{{$}}
; GCN: v_cndmask_b32_e64 [[RESULT:v[0-9]+]], 0, 1, vcc
; GCN: buffer_store_byte
; GCN: s_endpgm
define void @sext_bool_icmp_ne_k(i1 addrspace(1)* %out, i32 %a, i32 %b) nounwind {
%icmp0 = icmp ne i32 %a, %b
%ext = sext i1 %icmp0 to i32
%icmp1 = icmp ne i32 %ext, 2
store i1 %icmp1, i1 addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}cmp_zext_k_i8max:
; SI: s_load_dword [[VALUE:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0xb
; VI: s_load_dword [[VALUE:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x2c
; GCN: s_movk_i32 [[K255:s[0-9]+]], 0xff
; GCN: s_and_b32 [[B:s[0-9]+]], [[VALUE]], [[K255]]
; GCN: v_mov_b32_e32 [[VK255:v[0-9]+]], [[K255]]
; GCN: v_cmp_ne_i32_e32 vcc, [[B]], [[VK255]]
; GCN-NEXT: v_cndmask_b32_e64 [[RESULT:v[0-9]+]], 0, 1, vcc
AMDGPU/SI: Better handle s_wait insertion We can wait on either VM, EXP or LGKM. The waits are independent. Without this patch, a wait inserted because of one of them would also wait for all the previous others. This patch makes s_wait only wait for the ones we need for the next instruction. Here's an example of subtle perf reduction this patch solves: This is without the patch: buffer_load_format_xyzw v[8:11], v0, s[44:47], 0 idxen buffer_load_format_xyzw v[12:15], v0, s[48:51], 0 idxen s_load_dwordx4 s[44:47], s[8:9], 0xc s_waitcnt lgkmcnt(0) buffer_load_format_xyzw v[16:19], v0, s[52:55], 0 idxen s_load_dwordx4 s[48:51], s[8:9], 0x10 s_waitcnt vmcnt(1) buffer_load_format_xyzw v[20:23], v0, s[44:47], 0 idxen The s_waitcnt vmcnt(1) is useless. The reason it is added is because the last buffer_load_format_xyzw needs s[44:47], which was issued by the first s_load_dwordx4. It waits for all VM before that call to have finished. Internally after every instruction, 3 counters (for VM, EXP and LGTM) are updated after every instruction. For example buffer_load_format_xyzw will increase the VM counter, and s_load_dwordx4 the LGKM one. Without the patch, for every defined register, the current 3 counters are stored, and are used to know how long to wait when an instruction needs the register. Because of that, the s[44:47] counter includes that to use the register you need to wait for the previous buffer_load_format_xyzw. Instead this patch stores only the counters that matter for the register, and puts zero for the other ones, since we don't need any wait for them. Patch by: Axel Davy Differential Revision: http://reviews.llvm.org/D11883 llvm-svn: 245755
2015-08-22 06:47:27 +08:00
; GCN: buffer_store_byte [[RESULT]]
; GCN: s_endpgm
define void @cmp_zext_k_i8max(i1 addrspace(1)* %out, i8 %b) nounwind {
%b.ext = zext i8 %b to i32
%icmp0 = icmp ne i32 %b.ext, 255
store i1 %icmp0, i1 addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}cmp_sext_k_neg1:
; GCN: buffer_load_sbyte [[B:v[0-9]+]]
; GCN: v_cmp_ne_i32_e32 vcc, -1, [[B]]{{$}}
; GCN-NEXT: v_cndmask_b32_e64 [[RESULT:v[0-9]+]], 0, 1, vcc
; GCN: buffer_store_byte [[RESULT]]
; GCN: s_endpgm
define void @cmp_sext_k_neg1(i1 addrspace(1)* %out, i8 addrspace(1)* %b.ptr) nounwind {
%b = load i8, i8 addrspace(1)* %b.ptr
%b.ext = sext i8 %b to i32
%icmp0 = icmp ne i32 %b.ext, -1
store i1 %icmp0, i1 addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}cmp_sext_k_neg1_i8_sext_arg:
; GCN: s_load_dword [[B:s[0-9]+]]
; GCN: v_cmp_ne_i32_e64 [[CMP:s\[[0-9]+:[0-9]+\]]], -1, [[B]]
; GCN-NEXT: v_cndmask_b32_e64 [[RESULT:v[0-9]+]], 0, 1, [[CMP]]
; GCN-NEXT: buffer_store_byte [[RESULT]]
; GCN: s_endpgm
define void @cmp_sext_k_neg1_i8_sext_arg(i1 addrspace(1)* %out, i8 signext %b) nounwind {
%b.ext = sext i8 %b to i32
%icmp0 = icmp ne i32 %b.ext, -1
store i1 %icmp0, i1 addrspace(1)* %out
ret void
}
; FIXME: This ends up doing a buffer_load_ubyte, and and compare to
; 255. Seems to be because of ordering problems when not allowing load widths to be reduced.
; Should do a buffer_load_sbyte and compare with -1
; FUNC-LABEL: {{^}}cmp_sext_k_neg1_i8_arg:
; SI: s_load_dword [[VAL:s[0-9]+]], s[{{[0-9]+:[0-9]+}}], 0xb
; VI: s_load_dword [[VAL:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x2c
; GCN: s_movk_i32 [[K:s[0-9]+]], 0xff
; GCN: s_and_b32 [[B:s[0-9]+]], [[VAL]], [[K]]
; GCN: v_mov_b32_e32 [[VK:v[0-9]+]], [[K]]
; GCN: v_cmp_ne_i32_e32 vcc, [[B]], [[VK]]{{$}}
; GCN-NEXT: v_cndmask_b32_e64 [[RESULT:v[0-9]+]], 0, 1, vcc
AMDGPU/SI: Better handle s_wait insertion We can wait on either VM, EXP or LGKM. The waits are independent. Without this patch, a wait inserted because of one of them would also wait for all the previous others. This patch makes s_wait only wait for the ones we need for the next instruction. Here's an example of subtle perf reduction this patch solves: This is without the patch: buffer_load_format_xyzw v[8:11], v0, s[44:47], 0 idxen buffer_load_format_xyzw v[12:15], v0, s[48:51], 0 idxen s_load_dwordx4 s[44:47], s[8:9], 0xc s_waitcnt lgkmcnt(0) buffer_load_format_xyzw v[16:19], v0, s[52:55], 0 idxen s_load_dwordx4 s[48:51], s[8:9], 0x10 s_waitcnt vmcnt(1) buffer_load_format_xyzw v[20:23], v0, s[44:47], 0 idxen The s_waitcnt vmcnt(1) is useless. The reason it is added is because the last buffer_load_format_xyzw needs s[44:47], which was issued by the first s_load_dwordx4. It waits for all VM before that call to have finished. Internally after every instruction, 3 counters (for VM, EXP and LGTM) are updated after every instruction. For example buffer_load_format_xyzw will increase the VM counter, and s_load_dwordx4 the LGKM one. Without the patch, for every defined register, the current 3 counters are stored, and are used to know how long to wait when an instruction needs the register. Because of that, the s[44:47] counter includes that to use the register you need to wait for the previous buffer_load_format_xyzw. Instead this patch stores only the counters that matter for the register, and puts zero for the other ones, since we don't need any wait for them. Patch by: Axel Davy Differential Revision: http://reviews.llvm.org/D11883 llvm-svn: 245755
2015-08-22 06:47:27 +08:00
; GCN: buffer_store_byte [[RESULT]]
; GCN: s_endpgm
define void @cmp_sext_k_neg1_i8_arg(i1 addrspace(1)* %out, i8 %b) nounwind {
%b.ext = sext i8 %b to i32
%icmp0 = icmp ne i32 %b.ext, -1
store i1 %icmp0, i1 addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}cmp_zext_k_neg1:
; GCN: v_mov_b32_e32 [[RESULT:v[0-9]+]], 1{{$}}
; GCN: buffer_store_byte [[RESULT]]
; GCN: s_endpgm
define void @cmp_zext_k_neg1(i1 addrspace(1)* %out, i8 %b) nounwind {
%b.ext = zext i8 %b to i32
%icmp0 = icmp ne i32 %b.ext, -1
store i1 %icmp0, i1 addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}zext_bool_icmp_ne_k:
; GCN: v_mov_b32_e32 [[RESULT:v[0-9]+]], 1{{$}}
; GCN: buffer_store_byte [[RESULT]]
; GCN-NEXT: s_endpgm
define void @zext_bool_icmp_ne_k(i1 addrspace(1)* %out, i32 %a, i32 %b) nounwind {
%icmp0 = icmp ne i32 %a, %b
%ext = zext i1 %icmp0 to i32
%icmp1 = icmp ne i32 %ext, 2
store i1 %icmp1, i1 addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}zext_bool_icmp_eq_k:
; GCN: v_mov_b32_e32 [[RESULT:v[0-9]+]], 0{{$}}
; GCN: buffer_store_byte [[RESULT]]
; GCN-NEXT: s_endpgm
define void @zext_bool_icmp_eq_k(i1 addrspace(1)* %out, i32 %a, i32 %b) nounwind {
%icmp0 = icmp ne i32 %a, %b
%ext = zext i1 %icmp0 to i32
%icmp1 = icmp eq i32 %ext, 2
store i1 %icmp1, i1 addrspace(1)* %out
ret void
}