RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-23 13:02:52 +02:00
Code Issues Projects Releases Wiki Activity
6de13f8bcf
llvm-mirror/test/CodeGen/AMDGPU/udivrem.ll
Tom Stellard d773f533b9 AMDGPU/SI: Implement a custom MachineSchedStrategy 
Summary:
GCNSchedStrategy re-uses most of GenericScheduler, it's just uses
a different method to compute the excess and critical register
pressure limits.

It's not enabled by default, to enable it you need to pass -misched=gcn
to llc.

Shader DB stats:

32464 shaders in 17874 tests
Totals:
SGPRS: 1542846 -> 1643125 (6.50 %)
VGPRS: 1005595 -> 904653 (-10.04 %)
Spilled SGPRs: 29929 -> 27745 (-7.30 %)
Spilled VGPRs: 334 -> 352 (5.39 %)
Scratch VGPRs: 1612 -> 1624 (0.74 %) dwords per thread
Code Size: 36688188 -> 37034900 (0.95 %) bytes
LDS: 1913 -> 1913 (0.00 %) blocks
Max Waves: 254101 -> 265125 (4.34 %)
Wait states: 0 -> 0 (0.00 %)

Totals from affected shaders:
SGPRS: 1338220 -> 1438499 (7.49 %)
VGPRS: 886221 -> 785279 (-11.39 %)
Spilled SGPRs: 29869 -> 27685 (-7.31 %)
Spilled VGPRs: 334 -> 352 (5.39 %)
Scratch VGPRs: 1612 -> 1624 (0.74 %) dwords per thread
Code Size: 34315716 -> 34662428 (1.01 %) bytes
LDS: 1551 -> 1551 (0.00 %) blocks
Max Waves: 188127 -> 199151 (5.86 %)
Wait states: 0 -> 0 (0.00 %)

Reviewers: arsenm, mareko, nhaehnle, MatzeB, atrick

Subscribers: arsenm, kzhuravl, llvm-commits

Differential Revision: https://reviews.llvm.org/D23688

llvm-svn: 279995
2016-08-29 19:42:52 +00:00

350 lines
8.6 KiB
LLVM
Raw Blame History

; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck --check-prefix=SI --check-prefix=FUNC %s
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck --check-prefix=SI --check-prefix=FUNC %s
; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck --check-prefix=EG --check-prefix=FUNC %s
; FUNC-LABEL: {{^}}test_udivrem:
; EG: RECIP_UINT
; EG-DAG: MULHI
; EG-DAG: MULLO_INT
; EG-DAG: SUB_INT
; EG: CNDE_INT
; EG: MULHI
; EG-DAG: ADD_INT
; EG-DAG: SUB_INT
; EG: CNDE_INT
; EG: MULHI
; EG: MULLO_INT
; EG: SUB_INT
; EG-DAG: SETGE_UINT
; EG-DAG: SETGE_UINT
; EG: AND_INT
; EG-DAG: ADD_INT
; EG-DAG: SUB_INT
; EG-DAG: CNDE_INT
; EG-DAG: CNDE_INT
; EG-DAG: ADD_INT
; EG-DAG: SUB_INT
; EG-DAG: CNDE_INT
; EG-DAG: CNDE_INT
; SI: v_rcp_iflag_f32_e32 [[RCP:v[0-9]+]]
; SI-DAG: v_mul_hi_u32 [[RCP_HI:v[0-9]+]], [[RCP]]
; SI-DAG: v_mul_lo_i32 [[RCP_LO:v[0-9]+]], [[RCP]]
; SI-DAG: v_sub_i32_e32 [[NEG_RCP_LO:v[0-9]+]], vcc, 0, [[RCP_LO]]
; SI: v_cndmask_b32_e64
; SI: v_mul_hi_u32 [[E:v[0-9]+]], {{v[0-9]+}}, [[RCP]]
; SI-DAG: v_add_i32_e32 [[RCP_A_E:v[0-9]+]], vcc, [[E]], [[RCP]]
; SI-DAG: v_subrev_i32_e32 [[RCP_S_E:v[0-9]+]], vcc, [[E]], [[RCP]]
; SI: v_cndmask_b32_e64
; SI: v_mul_hi_u32 [[Quotient:v[0-9]+]]
; SI: v_mul_lo_i32 [[Num_S_Remainder:v[0-9]+]]
; SI-DAG: v_add_i32_e32 [[Quotient_A_One:v[0-9]+]], vcc, 1, [[Quotient]]
; SI-DAG: v_sub_i32_e32 [[Remainder:v[0-9]+]], vcc, {{[vs][0-9]+}}, [[Num_S_Remainder]]
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_subrev_i32_e32 [[Quotient_S_One:v[0-9]+]],
; SI-DAG: v_subrev_i32_e32 [[Remainder_S_Den:v[0-9]+]],
; SI: v_and_b32_e32 [[Tmp1:v[0-9]+]]
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_add_i32_e32 [[Remainder_A_Den:v[0-9]+]],
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_cndmask_b32_e64
; SI: s_endpgm
define void @test_udivrem(i32 addrspace(1)* %out0, i32 addrspace(1)* %out1, i32 %x, i32 %y) {
%result0 = udiv i32 %x, %y
store i32 %result0, i32 addrspace(1)* %out0
%result1 = urem i32 %x, %y
store i32 %result1, i32 addrspace(1)* %out1
ret void
}
; FUNC-LABEL: {{^}}test_udivrem_v2:
; EG-DAG: RECIP_UINT
; EG-DAG: MULHI
; EG-DAG: MULLO_INT
; EG-DAG: SUB_INT
; EG-DAG: CNDE_INT
; EG-DAG: MULHI
; EG-DAG: ADD_INT
; EG-DAG: SUB_INT
; EG-DAG: CNDE_INT
; EG-DAG: MULHI
; EG-DAG: MULLO_INT
; EG-DAG: SUB_INT
; EG-DAG: SETGE_UINT
; EG-DAG: SETGE_UINT
; EG-DAG: AND_INT
; EG-DAG: ADD_INT
; EG-DAG: SUB_INT
; EG-DAG: CNDE_INT
; EG-DAG: CNDE_INT
; EG-DAG: ADD_INT
; EG-DAG: SUB_INT
; EG-DAG: CNDE_INT
; EG-DAG: CNDE_INT
; EG-DAG: RECIP_UINT
; EG-DAG: MULHI
; EG-DAG: MULLO_INT
; EG-DAG: SUB_INT
; EG-DAG: CNDE_INT
; EG-DAG: MULHI
; EG-DAG: ADD_INT
; EG-DAG: SUB_INT
; EG-DAG: CNDE_INT
; EG-DAG: MULHI
; EG-DAG: MULLO_INT
; EG-DAG: SUB_INT
; EG-DAG: SETGE_UINT
; EG-DAG: SETGE_UINT
; EG-DAG: AND_INT
; EG-DAG: ADD_INT
; EG-DAG: SUB_INT
; EG-DAG: CNDE_INT
; EG-DAG: CNDE_INT
; EG-DAG: ADD_INT
; EG-DAG: SUB_INT
; EG-DAG: CNDE_INT
; EG-DAG: CNDE_INT
; For SI, we used to have checks for the input and output registers
; of the instructions, but these are way too fragile. The division for
; the two vector elements can be intermixed which makes it impossible to
; accurately check all the operands.
; SI-DAG: v_rcp_iflag_f32_e32
; SI-DAG: v_mul_hi_u32
; SI-DAG: v_mul_lo_i32
; SI-DAG: v_sub_i32_e32
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_mul_hi_u32
; SI-DAG: v_add_i32_e32
; SI-DAG: v_subrev_i32_e32
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_mul_hi_u32
; SI-DAG: v_mul_lo_i32
; SI-DAG: v_subrev_i32_e32
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_and_b32_e32
; SI-DAG: v_add_i32_e32
; SI-DAG: v_subrev_i32_e32
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_add_i32_e32
; SI-DAG: v_subrev_i32_e32
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_rcp_iflag_f32_e32
; SI-DAG: v_mul_hi_u32
; SI-DAG: v_mul_lo_i32
; SI-DAG: v_sub_i32_e32
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_mul_hi_u32
; SI-DAG: v_add_i32_e32
; SI-DAG: v_subrev_i32_e32
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_mul_hi_u32
; SI-DAG: v_mul_lo_i32
; SI-DAG: v_subrev_i32_e32
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_and_b32_e32
; SI-DAG: v_add_i32_e32
; SI-DAG: v_subrev_i32_e32
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_add_i32_e32
; SI-DAG: v_subrev_i32_e32
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_cndmask_b32_e64
; SI: s_endpgm
define void @test_udivrem_v2(<2 x i32> addrspace(1)* %out, <2 x i32> %x, <2 x i32> %y) {
%result0 = udiv <2 x i32> %x, %y
store <2 x i32> %result0, <2 x i32> addrspace(1)* %out
%result1 = urem <2 x i32> %x, %y
store <2 x i32> %result1, <2 x i32> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}test_udivrem_v4:
; EG-DAG: RECIP_UINT
; EG-DAG: MULHI
; EG-DAG: MULLO_INT
; EG-DAG: SUB_INT
; EG-DAG: CNDE_INT
; EG-DAG: MULHI
; EG-DAG: ADD_INT
; EG-DAG: SUB_INT
; EG-DAG: CNDE_INT
; EG-DAG: MULHI
; EG-DAG: MULLO_INT
; EG-DAG: SUB_INT
; EG-DAG: SETGE_UINT
; EG-DAG: SETGE_UINT
; EG-DAG: AND_INT
; EG-DAG: ADD_INT
; EG-DAG: SUB_INT
; EG-DAG: CNDE_INT
; EG-DAG: CNDE_INT
; EG-DAG: ADD_INT
; EG-DAG: SUB_INT
; EG-DAG: CNDE_INT
; EG-DAG: CNDE_INT
; EG-DAG: RECIP_UINT
; EG-DAG: MULHI
; EG-DAG: MULLO_INT
; EG-DAG: SUB_INT
; EG-DAG: CNDE_INT
; EG-DAG: MULHI
; EG-DAG: ADD_INT
; EG-DAG: SUB_INT
; EG-DAG: CNDE_INT
; EG-DAG: MULHI
; EG-DAG: MULLO_INT
; EG-DAG: SUB_INT
; EG-DAG: SETGE_UINT
; EG-DAG: SETGE_UINT
; EG-DAG: AND_INT
; EG-DAG: ADD_INT
; EG-DAG: SUB_INT
; EG-DAG: CNDE_INT
; EG-DAG: CNDE_INT
; EG-DAG: ADD_INT
; EG-DAG: SUB_INT
; EG-DAG: CNDE_INT
; EG-DAG: CNDE_INT
; EG-DAG: RECIP_UINT
; EG-DAG: MULHI
; EG-DAG: MULLO_INT
; EG-DAG: SUB_INT
; EG-DAG: CNDE_INT
; EG-DAG: MULHI
; EG-DAG: ADD_INT
; EG-DAG: SUB_INT
; EG-DAG: CNDE_INT
; EG-DAG: MULHI
; EG-DAG: MULLO_INT
; EG-DAG: SUB_INT
; EG-DAG: SETGE_UINT
; EG-DAG: SETGE_UINT
; EG-DAG: AND_INT
; EG-DAG: ADD_INT
; EG-DAG: SUB_INT
; EG-DAG: CNDE_INT
; EG-DAG: CNDE_INT
; EG-DAG: ADD_INT
; EG-DAG: SUB_INT
; EG-DAG: CNDE_INT
; EG-DAG: CNDE_INT
; EG-DAG: RECIP_UINT
; EG-DAG: MULHI
; EG-DAG: MULLO_INT
; EG-DAG: SUB_INT
; EG-DAG: CNDE_INT
; EG-DAG: MULHI
; EG-DAG: ADD_INT
; EG-DAG: SUB_INT
; EG-DAG: CNDE_INT
; EG-DAG: MULHI
; EG-DAG: MULLO_INT
; EG-DAG: SUB_INT
; EG-DAG: SETGE_UINT
; EG-DAG: SETGE_UINT
; EG-DAG: AND_INT
; EG-DAG: ADD_INT
; EG-DAG: SUB_INT
; EG-DAG: CNDE_INT
; EG-DAG: CNDE_INT
; EG-DAG: ADD_INT
; EG-DAG: SUB_INT
; EG-DAG: CNDE_INT
; EG-DAG: CNDE_INT
; SI-DAG: v_rcp_iflag_f32_e32
; SI-DAG: v_mul_hi_u32
; SI-DAG: v_mul_lo_i32
; SI-DAG: v_sub_i32_e32
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_mul_hi_u32
; SI-DAG: v_add_i32_e32
; SI-DAG: v_subrev_i32_e32
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_mul_hi_u32
; SI-DAG: v_mul_lo_i32
; SI-DAG: v_subrev_i32_e32
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_and_b32_e32
; SI-DAG: v_add_i32_e32
; SI-DAG: v_subrev_i32_e32
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_add_i32_e32
; SI-DAG: v_subrev_i32_e32
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_rcp_iflag_f32_e32
; SI-DAG: v_mul_hi_u32
; SI-DAG: v_mul_lo_i32
; SI-DAG: v_sub_i32_e32
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_mul_hi_u32
; SI-DAG: v_add_i32_e32
; SI-DAG: v_subrev_i32_e32
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_mul_hi_u32
; SI-DAG: v_mul_lo_i32
; SI-DAG: v_subrev_i32_e32
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_and_b32_e32
; SI-DAG: v_add_i32_e32
; SI-DAG: v_subrev_i32_e32
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_add_i32_e32
; SI-DAG: v_subrev_i32_e32
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_rcp_iflag_f32_e32
; SI-DAG: v_mul_hi_u32
; SI-DAG: v_mul_lo_i32
; SI-DAG: v_sub_i32_e32
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_mul_hi_u32
; SI-DAG: v_add_i32_e32
; SI-DAG: v_subrev_i32_e32
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_mul_hi_u32
; SI-DAG: v_mul_lo_i32
; SI-DAG: v_subrev_i32_e32
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_and_b32_e32
; SI-DAG: v_add_i32_e32
; SI-DAG: v_subrev_i32_e32
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_add_i32_e32
; SI-DAG: v_subrev_i32_e32
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_rcp_iflag_f32_e32
; SI-DAG: v_mul_hi_u32
; SI-DAG: v_mul_lo_i32
; SI-DAG: v_sub_i32_e32
; SI-DAG: v_cndmask_b32_e64
; SI-DAG: v_mul_hi_u32
; SI-DAG: v_add_i32_e32
; SI-DAG: v_subrev_i32_e32
; SI-DAG: v_cndmask_b32_e64
; SI: s_endpgm
define void @test_udivrem_v4(<4 x i32> addrspace(1)* %out, <4 x i32> %x, <4 x i32> %y) {
%result0 = udiv <4 x i32> %x, %y
store <4 x i32> %result0, <4 x i32> addrspace(1)* %out
%result1 = urem <4 x i32> %x, %y
store <4 x i32> %result1, <4 x i32> addrspace(1)* %out
ret void
}
Reference in New Issue View Git Blame Copy Permalink