1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-25 04:02:41 +01:00
llvm-mirror/test/CodeGen/AMDGPU/lds-bounds.ll
Nicolai Haehnle ea47e86cdc AMDGPU: Avoid selecting ds_{read,write}2_b32 on SI
Summary:
To workaround a hardware issue in the (base + offset) calculation
when base is negative. The impact on code quality should be limited
since SILoadStoreOptimizer still runs afterwards and is able to
combine loads/stores based on known sign information.

This fixes visible corruption in Hitman on SI (easily reproducible
by running benchmark mode).

Change-Id: Ia178d207a5e2ac38ae7cd98b532ea2ae74704e5f
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=99923

Reviewers: arsenm, mareko

Subscribers: jholewinski, kzhuravl, jvesely, wdng, yaxunl, dstuttard, tpr, t-tye, llvm-commits

Differential Revision: https://reviews.llvm.org/D53160

llvm-svn: 344698
2018-10-17 15:37:48 +00:00

130 lines
4.0 KiB
LLVM

; RUN: llc -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,SI %s
; RUN: llc -march=amdgcn -mcpu=hawaii -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,NOSI %s
@compute_lds = external addrspace(3) global [512 x i32], align 16
; GCN-LABEL: {{^}}store_aligned:
; GCN: ds_write_b64
define amdgpu_cs void @store_aligned(i32 addrspace(3)* %ptr) #0 {
entry:
%ptr.gep.1 = getelementptr i32, i32 addrspace(3)* %ptr, i32 1
store i32 42, i32 addrspace(3)* %ptr, align 8
store i32 43, i32 addrspace(3)* %ptr.gep.1
ret void
}
; GCN-LABEL: {{^}}load_aligned:
; GCN: ds_read_b64
define amdgpu_cs <2 x float> @load_aligned(i32 addrspace(3)* %ptr) #0 {
entry:
%ptr.gep.1 = getelementptr i32, i32 addrspace(3)* %ptr, i32 1
%v.0 = load i32, i32 addrspace(3)* %ptr, align 8
%v.1 = load i32, i32 addrspace(3)* %ptr.gep.1
%r.0 = insertelement <2 x i32> undef, i32 %v.0, i32 0
%r.1 = insertelement <2 x i32> %r.0, i32 %v.1, i32 1
%bc = bitcast <2 x i32> %r.1 to <2 x float>
ret <2 x float> %bc
}
; GCN-LABEL: {{^}}store_global_const_idx:
; GCN: ds_write2_b32
define amdgpu_cs void @store_global_const_idx() #0 {
entry:
%ptr.a = getelementptr [512 x i32], [512 x i32] addrspace(3)* @compute_lds, i32 0, i32 3
%ptr.b = getelementptr [512 x i32], [512 x i32] addrspace(3)* @compute_lds, i32 0, i32 4
store i32 42, i32 addrspace(3)* %ptr.a
store i32 43, i32 addrspace(3)* %ptr.b
ret void
}
; GCN-LABEL: {{^}}load_global_const_idx:
; GCN: ds_read2_b32
define amdgpu_cs <2 x float> @load_global_const_idx() #0 {
entry:
%ptr.a = getelementptr [512 x i32], [512 x i32] addrspace(3)* @compute_lds, i32 0, i32 3
%ptr.b = getelementptr [512 x i32], [512 x i32] addrspace(3)* @compute_lds, i32 0, i32 4
%v.0 = load i32, i32 addrspace(3)* %ptr.a
%v.1 = load i32, i32 addrspace(3)* %ptr.b
%r.0 = insertelement <2 x i32> undef, i32 %v.0, i32 0
%r.1 = insertelement <2 x i32> %r.0, i32 %v.1, i32 1
%bc = bitcast <2 x i32> %r.1 to <2 x float>
ret <2 x float> %bc
}
; GCN-LABEL: {{^}}store_global_var_idx_case1:
; SI: ds_write_b32
; SI: ds_write_b32
; NONSI: ds_write2_b32
define amdgpu_cs void @store_global_var_idx_case1(i32 %idx) #0 {
entry:
%ptr.a = getelementptr [512 x i32], [512 x i32] addrspace(3)* @compute_lds, i32 0, i32 %idx
%ptr.b = getelementptr i32, i32 addrspace(3)* %ptr.a, i32 1
store i32 42, i32 addrspace(3)* %ptr.a
store i32 43, i32 addrspace(3)* %ptr.b
ret void
}
; GCN-LABEL: {{^}}load_global_var_idx_case1:
; SI: ds_read_b32
; SI: ds_read_b32
; NONSI: ds_read2_b32
define amdgpu_cs <2 x float> @load_global_var_idx_case1(i32 %idx) #0 {
entry:
%ptr.a = getelementptr [512 x i32], [512 x i32] addrspace(3)* @compute_lds, i32 0, i32 %idx
%ptr.b = getelementptr i32, i32 addrspace(3)* %ptr.a, i32 1
%v.0 = load i32, i32 addrspace(3)* %ptr.a
%v.1 = load i32, i32 addrspace(3)* %ptr.b
%r.0 = insertelement <2 x i32> undef, i32 %v.0, i32 0
%r.1 = insertelement <2 x i32> %r.0, i32 %v.1, i32 1
%bc = bitcast <2 x i32> %r.1 to <2 x float>
ret <2 x float> %bc
}
; GCN-LABEL: {{^}}store_global_var_idx_case2:
; GCN: ds_write2_b32
define amdgpu_cs void @store_global_var_idx_case2(i32 %idx) #0 {
entry:
%idx.and = and i32 %idx, 255
%ptr.a = getelementptr [512 x i32], [512 x i32] addrspace(3)* @compute_lds, i32 0, i32 %idx.and
%ptr.b = getelementptr i32, i32 addrspace(3)* %ptr.a, i32 1
store i32 42, i32 addrspace(3)* %ptr.a
store i32 43, i32 addrspace(3)* %ptr.b
ret void
}
; GCN-LABEL: {{^}}load_global_var_idx_case2:
; GCN: ds_read2_b32
define amdgpu_cs <2 x float> @load_global_var_idx_case2(i32 %idx) #0 {
entry:
%idx.and = and i32 %idx, 255
%ptr.a = getelementptr [512 x i32], [512 x i32] addrspace(3)* @compute_lds, i32 0, i32 %idx.and
%ptr.b = getelementptr i32, i32 addrspace(3)* %ptr.a, i32 1
%v.0 = load i32, i32 addrspace(3)* %ptr.a
%v.1 = load i32, i32 addrspace(3)* %ptr.b
%r.0 = insertelement <2 x i32> undef, i32 %v.0, i32 0
%r.1 = insertelement <2 x i32> %r.0, i32 %v.1, i32 1
%bc = bitcast <2 x i32> %r.1 to <2 x float>
ret <2 x float> %bc
}
attributes #0 = { nounwind }