9e9907f1cf
Similar to 806761a7629df268c8aed49657aeccffa6bca449. For IR files without a target triple, -mtriple= specifies the full target triple while -march= merely sets the architecture part of the default target triple, leaving a target triple which may not make sense, e.g. amdgpu-apple-darwin. Therefore, -march= is error-prone and not recommended for tests without a target triple. The issue has been benign as we recognize $unknown-apple-darwin as ELF instead of rejecting it outrightly. This patch changes AMDGPU tests to not rely on the default OS/environment components. Tests that need fixes are not changed: ``` LLVM :: CodeGen/AMDGPU/fabs.f64.ll LLVM :: CodeGen/AMDGPU/fabs.ll LLVM :: CodeGen/AMDGPU/floor.ll LLVM :: CodeGen/AMDGPU/fneg-fabs.f64.ll LLVM :: CodeGen/AMDGPU/fneg-fabs.ll LLVM :: CodeGen/AMDGPU/r600-infinite-loop-bug-while-reorganizing-vector.ll LLVM :: CodeGen/AMDGPU/schedule-if-2.ll ```
66 lines
3.4 KiB
LLVM
66 lines
3.4 KiB
LLVM
; RUN: llc < %s -mtriple=amdgcn -mcpu=tonga -verify-machineinstrs -show-mc-encoding | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=UNPACKED %s
|
|
; RUN: llc < %s -mtriple=amdgcn -mcpu=gfx810 -verify-machineinstrs | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=PACKED %s
|
|
; RUN: llc < %s -mtriple=amdgcn -mcpu=gfx900 -verify-machineinstrs | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=PACKED %s
|
|
|
|
; GCN-LABEL: {{^}}buffer_load_format_d16_x:
|
|
; GCN: buffer_load_format_d16_x v{{[0-9]+}}, {{v[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 idxen
|
|
define amdgpu_ps half @buffer_load_format_d16_x(<4 x i32> inreg %rsrc) {
|
|
main_body:
|
|
%data = call half @llvm.amdgcn.struct.buffer.load.format.f16(<4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0)
|
|
ret half %data
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}buffer_load_format_d16_xy:
|
|
; UNPACKED: buffer_load_format_d16_xy v[{{[0-9]+}}:[[HI:[0-9]+]]], {{v[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 idxen
|
|
; UNPACKED: v_mov_b32_e32 v{{[0-9]+}}, v[[HI]]
|
|
|
|
; PACKED: buffer_load_format_d16_xy v[[FULL:[0-9]+]], {{v[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 idxen
|
|
; PACKED: v_lshrrev_b32_e32 v{{[0-9]+}}, 16, v[[FULL]]
|
|
define amdgpu_ps half @buffer_load_format_d16_xy(<4 x i32> inreg %rsrc) {
|
|
main_body:
|
|
%data = call <2 x half> @llvm.amdgcn.struct.buffer.load.format.v2f16(<4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0)
|
|
%elt = extractelement <2 x half> %data, i32 1
|
|
ret half %elt
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}buffer_load_format_d16_xyz:
|
|
; UNPACKED: buffer_load_format_d16_xyz v[{{[0-9]+}}:[[HI:[0-9]+]]], {{v[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 idxen
|
|
; UNPACKED: v_mov_b32_e32 v{{[0-9]+}}, v[[HI]]
|
|
|
|
; PACKED: buffer_load_format_d16_xyz v[{{[0-9]+}}:[[HI:[0-9]+]]], {{v[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 idxen
|
|
; PACKED: v_mov_b32_e32 v{{[0-9]+}}, v[[HI]]
|
|
define amdgpu_ps half @buffer_load_format_d16_xyz(<4 x i32> inreg %rsrc) {
|
|
main_body:
|
|
%data = call <3 x half> @llvm.amdgcn.struct.buffer.load.format.v3f16(<4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0)
|
|
%elt = extractelement <3 x half> %data, i32 2
|
|
ret half %elt
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}buffer_load_format_d16_xyzw:
|
|
; UNPACKED: buffer_load_format_d16_xyzw v[{{[0-9]+}}:[[HI:[0-9]+]]], {{v[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 idxen
|
|
; UNPACKED: v_mov_b32_e32 v{{[0-9]+}}, v[[HI]]
|
|
|
|
; PACKED: buffer_load_format_d16_xyzw v[{{[0-9]+}}:[[HI:[0-9]+]]], {{v[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 idxen
|
|
; PACKED: v_lshrrev_b32_e32 v{{[0-9]+}}, 16, v[[HI]]
|
|
define amdgpu_ps half @buffer_load_format_d16_xyzw(<4 x i32> inreg %rsrc) {
|
|
main_body:
|
|
%data = call <4 x half> @llvm.amdgcn.struct.buffer.load.format.v4f16(<4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0)
|
|
%elt = extractelement <4 x half> %data, i32 3
|
|
ret half %elt
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}buffer_load_format_i16_x:
|
|
; GCN: buffer_load_format_d16_x v{{[0-9]+}}, {{v[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 idxen
|
|
define amdgpu_ps half @buffer_load_format_i16_x(<4 x i32> inreg %rsrc) {
|
|
main_body:
|
|
%data = call i16 @llvm.amdgcn.struct.buffer.load.format.i16(<4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0)
|
|
%fdata = bitcast i16 %data to half
|
|
ret half %fdata
|
|
}
|
|
|
|
declare half @llvm.amdgcn.struct.buffer.load.format.f16(<4 x i32>, i32, i32, i32, i32)
|
|
declare <2 x half> @llvm.amdgcn.struct.buffer.load.format.v2f16(<4 x i32>, i32, i32, i32, i32)
|
|
declare <3 x half> @llvm.amdgcn.struct.buffer.load.format.v3f16(<4 x i32>, i32, i32, i32, i32)
|
|
declare <4 x half> @llvm.amdgcn.struct.buffer.load.format.v4f16(<4 x i32>, i32, i32, i32, i32)
|
|
declare i16 @llvm.amdgcn.struct.buffer.load.format.i16(<4 x i32>, i32, i32, i32, i32)
|