mirror of
https://github.com/RPCSX/llvm.git
synced 2025-01-10 06:00:30 +00:00
d3adac51fc
Summary: This results in higher register usage, but should make it easier for the compiler to hide latency. This pass is a prerequisite for some more scheduler improvements, and I think the increase register usage with this patch is acceptable, because when combined with the scheduler improvements, the total register usage will decrease. shader-db stats: 2382 shaders in 478 tests Totals: SGPRS: 48672 -> 49088 (0.85 %) VGPRS: 34148 -> 34847 (2.05 %) Code Size: 1285816 -> 1289128 (0.26 %) bytes LDS: 28 -> 28 (0.00 %) blocks Scratch: 492544 -> 573440 (16.42 %) bytes per wave Max Waves: 6856 -> 6846 (-0.15 %) Wait states: 0 -> 0 (0.00 %) Depends on D18451 Reviewers: nhaehnle, arsenm Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D18452 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@264876 91177308-0d34-0410-b5e6-96231b3b80d8
128 lines
4.3 KiB
LLVM
128 lines
4.3 KiB
LLVM
; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs -enable-unsafe-fp-math < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
|
|
; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs -enable-unsafe-fp-math < %s | FileCheck -check-prefix=CI -check-prefix=FUNC %s
|
|
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs -enable-unsafe-fp-math < %s | FileCheck -check-prefix=CI -check-prefix=FUNC %s
|
|
|
|
declare double @llvm.fabs.f64(double %Val)
|
|
declare double @llvm.floor.f64(double) nounwind readnone
|
|
declare <2 x double> @llvm.floor.v2f64(<2 x double>) nounwind readnone
|
|
declare <3 x double> @llvm.floor.v3f64(<3 x double>) nounwind readnone
|
|
declare <4 x double> @llvm.floor.v4f64(<4 x double>) nounwind readnone
|
|
declare <8 x double> @llvm.floor.v8f64(<8 x double>) nounwind readnone
|
|
declare <16 x double> @llvm.floor.v16f64(<16 x double>) nounwind readnone
|
|
|
|
; FUNC-LABEL: {{^}}ffloor_f64:
|
|
; CI: v_floor_f64_e32
|
|
; SI: v_fract_f64_e32
|
|
; SI-DAG: v_min_f64
|
|
; SI-DAG: v_cmp_class_f64_e64
|
|
; SI: v_cndmask_b32_e64
|
|
; SI: v_cndmask_b32_e64
|
|
; SI: v_add_f64
|
|
; SI: s_endpgm
|
|
define void @ffloor_f64(double addrspace(1)* %out, double %x) {
|
|
%y = call double @llvm.floor.f64(double %x) nounwind readnone
|
|
store double %y, double addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}ffloor_f64_neg:
|
|
; CI: v_floor_f64_e64
|
|
; SI: v_fract_f64_e64 {{v[[0-9]+:[0-9]+]}}, -[[INPUT:s[[0-9]+:[0-9]+]]]
|
|
; SI-DAG: v_min_f64
|
|
; SI-DAG: v_cmp_class_f64_e64
|
|
; SI: v_cndmask_b32_e64
|
|
; SI: v_cndmask_b32_e64
|
|
; SI: v_add_f64 {{v[[0-9]+:[0-9]+]}}, -[[INPUT]]
|
|
; SI: s_endpgm
|
|
define void @ffloor_f64_neg(double addrspace(1)* %out, double %x) {
|
|
%neg = fsub double 0.0, %x
|
|
%y = call double @llvm.floor.f64(double %neg) nounwind readnone
|
|
store double %y, double addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}ffloor_f64_neg_abs:
|
|
; CI: v_floor_f64_e64
|
|
; SI: v_fract_f64_e64 {{v[[0-9]+:[0-9]+]}}, -|[[INPUT:s[[0-9]+:[0-9]+]]]|
|
|
; SI-DAG: v_min_f64
|
|
; SI-DAG: v_cmp_class_f64_e64
|
|
; SI: v_cndmask_b32_e64
|
|
; SI: v_cndmask_b32_e64
|
|
; SI: v_add_f64 {{v[[0-9]+:[0-9]+]}}, -|[[INPUT]]|
|
|
; SI: s_endpgm
|
|
define void @ffloor_f64_neg_abs(double addrspace(1)* %out, double %x) {
|
|
%abs = call double @llvm.fabs.f64(double %x)
|
|
%neg = fsub double 0.0, %abs
|
|
%y = call double @llvm.floor.f64(double %neg) nounwind readnone
|
|
store double %y, double addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}ffloor_v2f64:
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
define void @ffloor_v2f64(<2 x double> addrspace(1)* %out, <2 x double> %x) {
|
|
%y = call <2 x double> @llvm.floor.v2f64(<2 x double> %x) nounwind readnone
|
|
store <2 x double> %y, <2 x double> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FIXME-FUNC-LABEL: {{^}}ffloor_v3f64:
|
|
; FIXME-CI: v_floor_f64_e32
|
|
; FIXME-CI: v_floor_f64_e32
|
|
; FIXME-CI: v_floor_f64_e32
|
|
; define void @ffloor_v3f64(<3 x double> addrspace(1)* %out, <3 x double> %x) {
|
|
; %y = call <3 x double> @llvm.floor.v3f64(<3 x double> %x) nounwind readnone
|
|
; store <3 x double> %y, <3 x double> addrspace(1)* %out
|
|
; ret void
|
|
; }
|
|
|
|
; FUNC-LABEL: {{^}}ffloor_v4f64:
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
define void @ffloor_v4f64(<4 x double> addrspace(1)* %out, <4 x double> %x) {
|
|
%y = call <4 x double> @llvm.floor.v4f64(<4 x double> %x) nounwind readnone
|
|
store <4 x double> %y, <4 x double> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}ffloor_v8f64:
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
define void @ffloor_v8f64(<8 x double> addrspace(1)* %out, <8 x double> %x) {
|
|
%y = call <8 x double> @llvm.floor.v8f64(<8 x double> %x) nounwind readnone
|
|
store <8 x double> %y, <8 x double> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}ffloor_v16f64:
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
define void @ffloor_v16f64(<16 x double> addrspace(1)* %out, <16 x double> %x) {
|
|
%y = call <16 x double> @llvm.floor.v16f64(<16 x double> %x) nounwind readnone
|
|
store <16 x double> %y, <16 x double> addrspace(1)* %out
|
|
ret void
|
|
}
|