mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-09-01 19:29:22 +00:00
We can't enable the verifier for tests with SI_IF and SI_ELSE, because these instructions are always followed by a COPY which copies their result to the next basic block. This violates the machine verifier's rule that non-terminators can not folow terminators. Reviewed-by: Vincent Lejeune<vljn at ovi.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192366 91177308-0d34-0410-b5e6-96231b3b80d8
50 lines
1.7 KiB
LLVM
50 lines
1.7 KiB
LLVM
; RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck %s --check-prefix=R600-CHECK
|
|
; RUN: llc < %s -march=r600 -mcpu=SI -verify-machineinstrs | FileCheck %s --check-prefix=SI-CHECK
|
|
|
|
; R600-CHECK: @fmul_f32
|
|
; R600-CHECK: MUL_IEEE {{\** *}}{{T[0-9]+\.[XYZW]}}, KC0[2].Z, KC0[2].W
|
|
; SI-CHECK: @fmul_f32
|
|
; SI-CHECK: V_MUL_F32
|
|
define void @fmul_f32(float addrspace(1)* %out, float %a, float %b) {
|
|
entry:
|
|
%0 = fmul float %a, %b
|
|
store float %0, float addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
declare float @llvm.R600.load.input(i32) readnone
|
|
|
|
declare void @llvm.AMDGPU.store.output(float, i32)
|
|
|
|
; R600-CHECK: @fmul_v2f32
|
|
; R600-CHECK: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW]}}
|
|
; R600-CHECK: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW]}}
|
|
; SI-CHECK: @fmul_v2f32
|
|
; SI-CHECK: V_MUL_F32
|
|
; SI-CHECK: V_MUL_F32
|
|
define void @fmul_v2f32(<2 x float> addrspace(1)* %out, <2 x float> %a, <2 x float> %b) {
|
|
entry:
|
|
%0 = fmul <2 x float> %a, %b
|
|
store <2 x float> %0, <2 x float> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; R600-CHECK: @fmul_v4f32
|
|
; R600-CHECK: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
; R600-CHECK: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
; R600-CHECK: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
; R600-CHECK: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
; SI-CHECK: @fmul_v4f32
|
|
; SI-CHECK: V_MUL_F32
|
|
; SI-CHECK: V_MUL_F32
|
|
; SI-CHECK: V_MUL_F32
|
|
; SI-CHECK: V_MUL_F32
|
|
define void @fmul_v4f32(<4 x float> addrspace(1)* %out, <4 x float> addrspace(1)* %in) {
|
|
%b_ptr = getelementptr <4 x float> addrspace(1)* %in, i32 1
|
|
%a = load <4 x float> addrspace(1) * %in
|
|
%b = load <4 x float> addrspace(1) * %b_ptr
|
|
%result = fmul <4 x float> %a, %b
|
|
store <4 x float> %result, <4 x float> addrspace(1)* %out
|
|
ret void
|
|
}
|