Files
clang-p2996/llvm/test/CodeGen/AMDGPU/sram-ecc-default.ll
Austin Kerbow 2291bd137d [AMDGPU] Update subtarget features for new target ID support
Support for XNACK and SRAMECC is not static on some GPUs. We must be able
to differentiate between different scenarios for these dynamic subtarget
features.

The possible settings are:

- Unsupported: The GPU has no support for XNACK/SRAMECC.
- Any: Preference is unspecified. Use conservative settings that can run anywhere.
- Off: Request support for XNACK/SRAMECC Off
- On: Request support for XNACK/SRAMECC On

GCNSubtarget will track the four options based on the following criteria. If
the subtarget does not support XNACK/SRAMECC we say the setting is
"Unsupported". If no subtarget features for XNACK/SRAMECC are requested we
must support "Any" mode. If the subtarget features XNACK/SRAMECC exist in the
feature string when initializing the subtarget, the settings are "On/Off".

The defaults are updated to be conservatively correct, meaning if no setting
for XNACK or SRAMECC is explicitly requested, defaults will be used which
generate code that can be run anywhere. This corresponds to the "Any" setting.

Differential Revision: https://reviews.llvm.org/D85882
2021-01-26 11:25:51 -08:00

23 lines
1.1 KiB
LLVM

; RUN: llc -march=amdgcn -mcpu=gfx900 < %s | FileCheck -check-prefixes=GCN,NO-ECC %s
; RUN: llc -march=amdgcn -mcpu=gfx900 < %s | FileCheck -check-prefixes=GCN,NO-ECC %s
; RUN: llc -march=amdgcn -mcpu=gfx904 -mattr=+sramecc < %s | FileCheck -check-prefixes=GCN,NO-ECC %s
; RUN: llc -march=amdgcn -mcpu=gfx906 -mattr=+sramecc < %s | FileCheck -check-prefixes=GCN,ECC %s
; RUN: llc -march=amdgcn -mcpu=gfx906 -mattr=-sramecc < %s | FileCheck -check-prefixes=GCN,NO-ECC %s
; Make sure the correct set of targets are marked with
; FeatureDoesNotSupportSRAMECC, and +sram-ecc is ignored if it's never
; supported.
; GCN-LABEL: {{^}}load_global_hi_v2i16_reglo_vreg:
; NO-ECC: global_load_short_d16_hi
; ECC: global_load_ushort
define void @load_global_hi_v2i16_reglo_vreg(i16 addrspace(1)* %in, i16 %reg) {
entry:
%gep = getelementptr inbounds i16, i16 addrspace(1)* %in, i64 -2047
%load = load i16, i16 addrspace(1)* %gep
%build0 = insertelement <2 x i16> undef, i16 %reg, i32 0
%build1 = insertelement <2 x i16> %build0, i16 %load, i32 1
store <2 x i16> %build1, <2 x i16> addrspace(1)* undef
ret void
}