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 ```
67 lines
1.6 KiB
LLVM
67 lines
1.6 KiB
LLVM
; RUN: llc -mtriple=amdgcn -mcpu=verde < %s | FileCheck %s
|
|
|
|
; Test a simple uniform loop that lives inside non-uniform control flow.
|
|
|
|
; CHECK-LABEL: {{^}}test1:
|
|
; CHECK: v_cmp_ne_u32_e32 vcc, 0
|
|
; CHECK: s_and_saveexec_b64
|
|
; CHECK-NEXT: s_cbranch_execz .LBB{{[0-9]+_[0-9]+}}
|
|
|
|
; CHECK: [[LOOP_BODY_LABEL:.LBB[0-9]+_[0-9]+]]: ; %loop_body
|
|
; CHECK: s_cbranch_scc1 [[LOOP_BODY_LABEL]]
|
|
|
|
; CHECK: s_endpgm
|
|
define amdgpu_ps void @test1(<8 x i32> inreg %rsrc, <2 x i32> %addr.base, i32 %y, i32 %p) {
|
|
main_body:
|
|
%cc = icmp eq i32 %p, 0
|
|
br i1 %cc, label %out, label %loop_body
|
|
|
|
loop_body:
|
|
%counter = phi i32 [ 0, %main_body ], [ %incr, %loop_body ]
|
|
|
|
; Prevent the loop from being optimized out
|
|
call void asm sideeffect "", "" ()
|
|
|
|
%incr = add i32 %counter, 1
|
|
%lc = icmp sge i32 %incr, 1000
|
|
br i1 %lc, label %out, label %loop_body
|
|
|
|
out:
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: {{^}}test2:
|
|
; CHECK: s_and_saveexec_b64
|
|
; CHECK-NEXT: s_cbranch_execz
|
|
define amdgpu_kernel void @test2(ptr addrspace(1) %out, i32 %a, i32 %b) {
|
|
main_body:
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x() #1
|
|
%cc = icmp eq i32 %tid, 0
|
|
br i1 %cc, label %done1, label %if
|
|
|
|
if:
|
|
%cmp = icmp eq i32 %a, 0
|
|
br i1 %cmp, label %done0, label %loop_body
|
|
|
|
loop_body:
|
|
%counter = phi i32 [ 0, %if ], [0, %done0], [ %incr, %loop_body ]
|
|
|
|
; Prevent the loop from being optimized out
|
|
call void asm sideeffect "", "" ()
|
|
|
|
%incr = add i32 %counter, 1
|
|
%lc = icmp sge i32 %incr, 1000
|
|
br i1 %lc, label %done1, label %loop_body
|
|
|
|
done0:
|
|
%cmp0 = icmp eq i32 %b, 0
|
|
br i1 %cmp0, label %done1, label %loop_body
|
|
|
|
done1:
|
|
ret void
|
|
}
|
|
|
|
declare i32 @llvm.amdgcn.workitem.id.x() #1
|
|
|
|
attributes #1 = { nounwind readonly }
|