shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AMDGPU/set-dx10.ll
Fangrui Song 9e9907f1cf
[AMDGPU,test] Change llc -march= to -mtriple= (#75982) 
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
```
2024-01-16 21:54:58 -08:00

162 lines
5.1 KiB
LLVM
Raw Permalink Blame History

; RUN: llc < %s -mtriple=r600 -mcpu=redwood | FileCheck %s
; These tests check that floating point comparisons which are used by select
; to store integer true (-1) and false (0) values are lowered to one of the
; SET*DX10 instructions.
; CHECK: {{^}}fcmp_une_select_fptosi:
; CHECK: LSHR
; CHECK-NEXT: SETNE_DX10 * {{\** *}}T{{[0-9]+\.[XYZW]}}, KC0[2].Z, literal.y,
; CHECK-NEXT: 1084227584(5.000000e+00)
define amdgpu_kernel void @fcmp_une_select_fptosi(ptr addrspace(1) %out, float %in) {
entry:
%0 = fcmp une float %in, 5.0
%1 = select i1 %0, float 1.000000e+00, float 0.000000e+00
%2 = fneg float %1
%3 = fptosi float %2 to i32
store i32 %3, ptr addrspace(1) %out
ret void
}
; CHECK: {{^}}fcmp_une_select_i32:
; CHECK: LSHR
; CHECK-NEXT: SETNE_DX10 * {{\** *}}T{{[0-9]+\.[XYZW]}}, KC0[2].Z, literal.y,
; CHECK-NEXT: 1084227584(5.000000e+00)
define amdgpu_kernel void @fcmp_une_select_i32(ptr addrspace(1) %out, float %in) {
entry:
%0 = fcmp une float %in, 5.0
%1 = select i1 %0, i32 -1, i32 0
store i32 %1, ptr addrspace(1) %out
ret void
}
; CHECK: {{^}}fcmp_oeq_select_fptosi:
; CHECK: LSHR
; CHECK-NEXT: SETE_DX10 * {{\** *}}T{{[0-9]+\.[XYZW]}}, KC0[2].Z, literal.y,
; CHECK-NEXT: 1084227584(5.000000e+00)
define amdgpu_kernel void @fcmp_oeq_select_fptosi(ptr addrspace(1) %out, float %in) {
entry:
%0 = fcmp oeq float %in, 5.0
%1 = select i1 %0, float 1.000000e+00, float 0.000000e+00
%2 = fneg float %1
%3 = fptosi float %2 to i32
store i32 %3, ptr addrspace(1) %out
ret void
}
; CHECK: {{^}}fcmp_oeq_select_i32:
; CHECK: LSHR
; CHECK-NEXT: SETE_DX10 * {{\** *}}T{{[0-9]+\.[XYZW]}}, KC0[2].Z, literal.y,
; CHECK-NEXT: 1084227584(5.000000e+00)
define amdgpu_kernel void @fcmp_oeq_select_i32(ptr addrspace(1) %out, float %in) {
entry:
%0 = fcmp oeq float %in, 5.0
%1 = select i1 %0, i32 -1, i32 0
store i32 %1, ptr addrspace(1) %out
ret void
}
; CHECK: {{^}}fcmp_ogt_select_fptosi:
; CHECK: LSHR
; CHECK-NEXT: SETGT_DX10 * {{\** *}}T{{[0-9]+\.[XYZW]}}, KC0[2].Z, literal.y,
; CHECK-NEXT: 1084227584(5.000000e+00)
define amdgpu_kernel void @fcmp_ogt_select_fptosi(ptr addrspace(1) %out, float %in) {
entry:
%0 = fcmp ogt float %in, 5.0
%1 = select i1 %0, float 1.000000e+00, float 0.000000e+00
%2 = fneg float %1
%3 = fptosi float %2 to i32
store i32 %3, ptr addrspace(1) %out
ret void
}
; CHECK: {{^}}fcmp_ogt_select_i32:
; CHECK: LSHR
; CHECK-NEXT: SETGT_DX10 * {{\** *}}T{{[0-9]+\.[XYZW]}}, KC0[2].Z, literal.y,
; CHECK-NEXT: 1084227584(5.000000e+00)
define amdgpu_kernel void @fcmp_ogt_select_i32(ptr addrspace(1) %out, float %in) {
entry:
%0 = fcmp ogt float %in, 5.0
%1 = select i1 %0, i32 -1, i32 0
store i32 %1, ptr addrspace(1) %out
ret void
}
; CHECK: {{^}}fcmp_oge_select_fptosi:
; CHECK: LSHR
; CHECK-NEXT: SETGE_DX10 * {{\** *}}T{{[0-9]+\.[XYZW]}}, KC0[2].Z, literal.y,
; CHECK-NEXT: 1084227584(5.000000e+00)
define amdgpu_kernel void @fcmp_oge_select_fptosi(ptr addrspace(1) %out, float %in) {
entry:
%0 = fcmp oge float %in, 5.0
%1 = select i1 %0, float 1.000000e+00, float 0.000000e+00
%2 = fneg float %1
%3 = fptosi float %2 to i32
store i32 %3, ptr addrspace(1) %out
ret void
}
; CHECK: {{^}}fcmp_oge_select_i32:
; CHECK: LSHR
; CHECK-NEXT: SETGE_DX10 * {{\** *}}T{{[0-9]+\.[XYZW]}}, KC0[2].Z, literal.y,
; CHECK-NEXT: 1084227584(5.000000e+00)
define amdgpu_kernel void @fcmp_oge_select_i32(ptr addrspace(1) %out, float %in) {
entry:
%0 = fcmp oge float %in, 5.0
%1 = select i1 %0, i32 -1, i32 0
store i32 %1, ptr addrspace(1) %out
ret void
}
; CHECK: {{^}}fcmp_ole_select_fptosi:
; CHECK: LSHR
; CHECK-NEXT: SETGE_DX10 * {{\** *}}T{{[0-9]+\.[XYZW]}}, literal.y, KC0[2].Z,
; CHECK-NEXT: 1084227584(5.000000e+00)
define amdgpu_kernel void @fcmp_ole_select_fptosi(ptr addrspace(1) %out, float %in) {
entry:
%0 = fcmp ole float %in, 5.0
%1 = select i1 %0, float 1.000000e+00, float 0.000000e+00
%2 = fneg float %1
%3 = fptosi float %2 to i32
store i32 %3, ptr addrspace(1) %out
ret void
}
; CHECK: {{^}}fcmp_ole_select_i32:
; CHECK: LSHR
; CHECK-NEXT: SETGE_DX10 * {{\** *}}T{{[0-9]+\.[XYZW]}}, literal.y, KC0[2].Z,
; CHECK-NEXT: 1084227584(5.000000e+00)
define amdgpu_kernel void @fcmp_ole_select_i32(ptr addrspace(1) %out, float %in) {
entry:
%0 = fcmp ole float %in, 5.0
%1 = select i1 %0, i32 -1, i32 0
store i32 %1, ptr addrspace(1) %out
ret void
}
; CHECK: {{^}}fcmp_olt_select_fptosi:
; CHECK: LSHR
; CHECK-NEXT: SETGT_DX10 * {{\** *}}T{{[0-9]+\.[XYZW]}}, literal.y, KC0[2].Z,
; CHECK-NEXT: 1084227584(5.000000e+00)
define amdgpu_kernel void @fcmp_olt_select_fptosi(ptr addrspace(1) %out, float %in) {
entry:
%0 = fcmp olt float %in, 5.0
%1 = select i1 %0, float 1.000000e+00, float 0.000000e+00
%2 = fneg float %1
%3 = fptosi float %2 to i32
store i32 %3, ptr addrspace(1) %out
ret void
}
; CHECK: {{^}}fcmp_olt_select_i32:
; CHECK: LSHR
; CHECK-NEXT: SETGT_DX10 * {{\** *}}T{{[0-9]+\.[XYZW]}}, literal.y, KC0[2].Z,
; CHECK-NEXT: 1084227584(5.000000e+00)
define amdgpu_kernel void @fcmp_olt_select_i32(ptr addrspace(1) %out, float %in) {
entry:
%0 = fcmp olt float %in, 5.0
%1 = select i1 %0, i32 -1, i32 0
store i32 %1, ptr addrspace(1) %out
ret void
}
Reference in New Issue View Git Blame Copy Permalink