llvm/test/CodeGen/AMDGPU/fsub.ll
Nicolai Haehnle 702b589510 AMDGPU/SI: Fold operands with sub-registers
Summary:
Multi-dword constant loads generated unnecessary moves from SGPRs into VGPRs,
increasing the code size and VGPR pressure. These moves are now folded away.

Note that this lack of operand folding was not a problem for VMEM loads,
because COPY nodes from VReg_Nnn to VGPR32 are eliminated by the register
coalescer.

Some tests are updated, note that the fsub.ll test explicitly checks that
the move is elided.

With the IR generated by current Mesa, the changes are obviously relatively
minor:

7063 shaders in 3531 tests
Totals:
SGPRS: 351872 -> 352560 (0.20 %)
VGPRS: 199984 -> 200732 (0.37 %)
Code Size: 9876968 -> 9881112 (0.04 %) bytes
LDS: 91 -> 91 (0.00 %) blocks
Scratch: 1779712 -> 1767424 (-0.69 %) bytes per wave
Wait states: 295164 -> 295337 (0.06 %)

Totals from affected shaders:
SGPRS: 65784 -> 66472 (1.05 %)
VGPRS: 38064 -> 38812 (1.97 %)
Code Size: 1993828 -> 1997972 (0.21 %) bytes
LDS: 42 -> 42 (0.00 %) blocks
Scratch: 795648 -> 783360 (-1.54 %) bytes per wave
Wait states: 54026 -> 54199 (0.32 %)

Reviewers: tstellarAMD, arsenm, mareko

Subscribers: arsenm, llvm-commits

Differential Revision: http://reviews.llvm.org/D15875

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@257074 91177308-0d34-0410-b5e6-96231b3b80d8
2016-01-07 17:10:29 +00:00

73 lines
3.1 KiB
LLVM

; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=R600 -check-prefix=FUNC %s
; RUN: llc -march=amdgcn -mcpu=SI -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
; FUNC-LABEL: {{^}}v_fsub_f32:
; SI: v_subrev_f32_e32 {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
define void @v_fsub_f32(float addrspace(1)* %out, float addrspace(1)* %in) {
%b_ptr = getelementptr float, float addrspace(1)* %in, i32 1
%a = load float, float addrspace(1)* %in, align 4
%b = load float, float addrspace(1)* %b_ptr, align 4
%result = fsub float %a, %b
store float %result, float addrspace(1)* %out, align 4
ret void
}
; FUNC-LABEL: {{^}}s_fsub_f32:
; R600: ADD {{\** *}}T{{[0-9]+\.[XYZW]}}, KC0[2].Z, -KC0[2].W
; SI: v_sub_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}
define void @s_fsub_f32(float addrspace(1)* %out, float %a, float %b) {
%sub = fsub float %a, %b
store float %sub, float addrspace(1)* %out, align 4
ret void
}
declare float @llvm.R600.load.input(i32) readnone
declare void @llvm.AMDGPU.store.output(float, i32)
; FUNC-LABEL: {{^}}fsub_v2f32:
; R600-DAG: ADD {{\** *}}T{{[0-9]+\.[XYZW]}}, KC0[3].X, -KC0[3].Z
; R600-DAG: ADD {{\** *}}T{{[0-9]+\.[XYZW]}}, KC0[2].W, -KC0[3].Y
; SI: v_subrev_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}
; SI: v_subrev_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}
define void @fsub_v2f32(<2 x float> addrspace(1)* %out, <2 x float> %a, <2 x float> %b) {
%sub = fsub <2 x float> %a, %b
store <2 x float> %sub, <2 x float> addrspace(1)* %out, align 8
ret void
}
; FUNC-LABEL: {{^}}v_fsub_v4f32:
; R600: ADD {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], -T[0-9]+\.[XYZW]}}
; R600: ADD {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], -T[0-9]+\.[XYZW]}}
; R600: ADD {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], -T[0-9]+\.[XYZW]}}
; R600: ADD {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], -T[0-9]+\.[XYZW]}}
; SI: v_subrev_f32_e32 {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
; SI: v_subrev_f32_e32 {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
; SI: v_subrev_f32_e32 {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
; SI: v_subrev_f32_e32 {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
define void @v_fsub_v4f32(<4 x float> addrspace(1)* %out, <4 x float> addrspace(1)* %in) {
%b_ptr = getelementptr <4 x float>, <4 x float> addrspace(1)* %in, i32 1
%a = load <4 x float>, <4 x float> addrspace(1)* %in, align 16
%b = load <4 x float>, <4 x float> addrspace(1)* %b_ptr, align 16
%result = fsub <4 x float> %a, %b
store <4 x float> %result, <4 x float> addrspace(1)* %out, align 16
ret void
}
; FUNC-LABEL: {{^}}s_fsub_v4f32:
; SI: v_subrev_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}
; SI: v_subrev_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}
; SI: v_subrev_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}
; SI: v_subrev_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}
; SI: s_endpgm
define void @s_fsub_v4f32(<4 x float> addrspace(1)* %out, <4 x float> %a, <4 x float> %b) {
%result = fsub <4 x float> %a, %b
store <4 x float> %result, <4 x float> addrspace(1)* %out, align 16
ret void
}