mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-22 10:42:39 +01:00
f6f8f3bacb
Summary: For OS type AMDPAL, the scratch descriptor is loaded from offset 0 of the GIT, whose 32 bit pointer is in s0 (s8 for gfx9 merged shaders). This commit fixes that to use offset 0x10 instead of offset 0 for a compute shader, per the PAL ABI spec. V2: Ensure s0 (s8 for gfx9 merged shader) is marked live-in when loading scratch descriptor from GIT. Reviewers: kzhuravl, nhaehnle, timcorringham Subscribers: kzhuravl, wdng, yaxunl, t-tye, llvm-commits, dstuttard, nhaehnle, arsenm Differential Revision: https://reviews.llvm.org/D44468 Change-Id: I93dffa647758e37f613bb5e0dfca840d82e6d26f llvm-svn: 329690
88 lines
3.5 KiB
LLVM
88 lines
3.5 KiB
LLVM
; RUN: llc < %s -mtriple=amdgcn--amdpal -mcpu=tahiti | FileCheck --check-prefix=PAL --enable-var-scope %s
|
|
|
|
; PAL-NOT: .AMDGPU.config
|
|
; PAL-LABEL: {{^}}simple:
|
|
define amdgpu_kernel void @simple(i32 addrspace(1)* %out) {
|
|
entry:
|
|
store i32 0, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; Check code sequence for amdpal use of scratch for alloca. This is the case
|
|
; where the high half of the address comes from s_getpc.
|
|
|
|
; PAL-LABEL: {{^}}scratch:
|
|
; PAL: s_getpc_b64 s{{\[}}[[GITPTR:[0-9]+]]:
|
|
; PAL: s_mov_b32 s[[GITPTR]], s0
|
|
; PAL: s_load_dwordx4 s{{\[}}[[SCRATCHDESC:[0-9]+]]:{{[0-9]+]}}, s{{\[}}[[GITPTR]]:
|
|
; PAL: buffer_store{{.*}}, s{{\[}}[[SCRATCHDESC]]:
|
|
|
|
define amdgpu_kernel void @scratch(<2 x i32> %in, i32 %idx, i32 addrspace(5)* %out) {
|
|
entry:
|
|
%v = alloca [2 x i32], addrspace(5)
|
|
%vv = bitcast [2 x i32] addrspace(5)* %v to <2 x i32> addrspace(5)*
|
|
store <2 x i32> %in, <2 x i32> addrspace(5)* %vv
|
|
%e = getelementptr [2 x i32], [2 x i32] addrspace(5)* %v, i32 0, i32 %idx
|
|
%x = load i32, i32 addrspace(5)* %e
|
|
store i32 %x, i32 addrspace(5)* %out
|
|
ret void
|
|
}
|
|
|
|
; Check code sequence for amdpal use of scratch for alloca. This is the case
|
|
; where the amdgpu-git-ptr-high function attribute gives the high half of the
|
|
; address to use.
|
|
; Looks like you can't do arithmetic on a filecheck variable, so we can't test
|
|
; that the s_movk_i32 is into a reg that is one more than the following
|
|
; s_mov_b32.
|
|
|
|
; PAL-LABEL: {{^}}scratch2:
|
|
; PAL: s_movk_i32 s{{[0-9]+}}, 0x1234
|
|
; PAL: s_mov_b32 s[[GITPTR:[0-9]+]], s0
|
|
; PAL: s_load_dwordx4 s{{\[}}[[SCRATCHDESC:[0-9]+]]:{{[0-9]+]}}, s{{\[}}[[GITPTR]]:
|
|
; PAL: buffer_store{{.*}}, s{{\[}}[[SCRATCHDESC]]:
|
|
|
|
define amdgpu_kernel void @scratch2(<2 x i32> %in, i32 %idx, i32 addrspace(5)* %out) #0 {
|
|
entry:
|
|
%v = alloca [2 x i32], addrspace(5)
|
|
%vv = bitcast [2 x i32] addrspace(5)* %v to <2 x i32> addrspace(5)*
|
|
store <2 x i32> %in, <2 x i32> addrspace(5)* %vv
|
|
%e = getelementptr [2 x i32], [2 x i32] addrspace(5)* %v, i32 0, i32 %idx
|
|
%x = load i32, i32 addrspace(5)* %e
|
|
store i32 %x, i32 addrspace(5)* %out
|
|
ret void
|
|
}
|
|
|
|
; Check code sequence for amdpal use of scratch for alloca in a compute shader.
|
|
; The scratch descriptor is loaded from offset 0x10 of the GIT, rather than offset
|
|
; 0 in a graphics shader.
|
|
|
|
; PAL-LABEL: {{^}}scratch2_cs:
|
|
; PAL: s_movk_i32 s{{[0-9]+}}, 0x1234
|
|
; PAL: s_mov_b32 s[[GITPTR:[0-9]+]], s0
|
|
; PAL: s_load_dwordx4 s{{\[}}[[SCRATCHDESC:[0-9]+]]:{{[0-9]+]}}, s{{\[}}[[GITPTR]]:{{[0-9]+\]}}, 0x10
|
|
; PAL: buffer_store{{.*}}, s{{\[}}[[SCRATCHDESC]]:
|
|
|
|
define amdgpu_cs void @scratch2_cs(i32 inreg, i32 inreg, i32 inreg, <3 x i32> inreg, i32 inreg, <3 x i32> %coord, <2 x i32> %in, i32 %extra, i32 %idx) #0 {
|
|
entry:
|
|
%v = alloca [3 x i32], addrspace(5)
|
|
%v0 = getelementptr [3 x i32], [3 x i32] addrspace(5)* %v, i32 0, i32 0
|
|
%v1 = getelementptr [3 x i32], [3 x i32] addrspace(5)* %v, i32 0, i32 1
|
|
store i32 %extra, i32 addrspace(5)* %v0
|
|
%v1a = bitcast i32 addrspace(5)* %v1 to [2 x i32] addrspace(5)*
|
|
%vv = bitcast [2 x i32] addrspace(5)* %v1a to <2 x i32> addrspace(5)*
|
|
store <2 x i32> %in, <2 x i32> addrspace(5)* %vv
|
|
%e = getelementptr [2 x i32], [2 x i32] addrspace(5)* %v1a, i32 0, i32 %idx
|
|
%x = load i32, i32 addrspace(5)* %e
|
|
%xf = bitcast i32 %x to float
|
|
call void @llvm.amdgcn.buffer.store.f32(float %xf, <4 x i32> undef, i32 0, i32 0, i1 0, i1 0)
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind "amdgpu-git-ptr-high"="0x1234" }
|
|
|
|
declare void @llvm.amdgcn.buffer.store.f32(float, <4 x i32>, i32, i32, i1, i1)
|
|
|
|
|
|
; Check we have CS_NUM_USED_VGPRS in PAL metadata.
|
|
; PAL: .amd_amdgpu_pal_metadata {{.*}},0x10000027,
|