mirror of
https://github.com/RPCS3/llvm.git
synced 2026-08-28 05:10:05 -04:00
Matt Arsenault
e536396218
------------------------------------------------------------------------ r292982 | arsenm | 2017-01-24 14:02:15 -0800 (Tue, 24 Jan 2017) | 8 lines Enable FeatureFlatForGlobal on Volcanic Islands This switches to the workaround that HSA defaults to for the mesa path. This should be applied to the 4.0 branch. Patch by Vedran Miletić <vedran@miletic.net> ------------------------------------------------------------------------ git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_40@293326 91177308-0d34-0410-b5e6-96231b3b80d8
92 lines
2.8 KiB
LLVM
92 lines
2.8 KiB
LLVM
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=FUNC %s
|
|
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=FUNC %s
|
|
; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=R600 -check-prefix=FUNC %s
|
|
|
|
; FUNC-LABEL: {{^}}fmul_f32:
|
|
; GCN: v_mul_f32
|
|
|
|
; R600: MUL_IEEE {{\** *}}{{T[0-9]+\.[XYZW]}}, KC0[2].Z, KC0[2].W
|
|
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)
|
|
|
|
; FUNC-LABEL: {{^}}fmul_v2f32:
|
|
; GCN: v_mul_f32
|
|
; GCN: v_mul_f32
|
|
|
|
; R600: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW]}}
|
|
; R600: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW]}}
|
|
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
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fmul_v4f32:
|
|
; GCN: v_mul_f32
|
|
; GCN: v_mul_f32
|
|
; GCN: v_mul_f32
|
|
; GCN: v_mul_f32
|
|
|
|
; R600: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
; R600: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
; R600: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
; R600: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
define void @fmul_v4f32(<4 x float> addrspace(1)* %out, <4 x float> addrspace(1)* %in) {
|
|
%b_ptr = getelementptr <4 x float>, <4 x float> addrspace(1)* %in, i32 1
|
|
%a = load <4 x float>, <4 x float> addrspace(1) * %in
|
|
%b = load <4 x float>, <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
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}test_mul_2_k:
|
|
; GCN: v_mul_f32
|
|
; GCN-NOT: v_mul_f32
|
|
; GCN: s_endpgm
|
|
define void @test_mul_2_k(float addrspace(1)* %out, float %x) #0 {
|
|
%y = fmul float %x, 2.0
|
|
%z = fmul float %y, 3.0
|
|
store float %z, float addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}test_mul_2_k_inv:
|
|
; GCN: v_mul_f32
|
|
; GCN-NOT: v_mul_f32
|
|
; GCN-NOT: v_mad_f32
|
|
; GCN: s_endpgm
|
|
define void @test_mul_2_k_inv(float addrspace(1)* %out, float %x) #0 {
|
|
%y = fmul float %x, 3.0
|
|
%z = fmul float %y, 2.0
|
|
store float %z, float addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; There should be three multiplies here; %a should be used twice (once
|
|
; negated), not duplicated into mul x, 5.0 and mul x, -5.0.
|
|
; FUNC-LABEL: {{^}}test_mul_twouse:
|
|
; GCN: v_mul_f32
|
|
; GCN: v_mul_f32
|
|
; GCN: v_mul_f32
|
|
; GCN-NOT: v_mul_f32
|
|
define void @test_mul_twouse(float addrspace(1)* %out, float %x, float %y) #0 {
|
|
%a = fmul float %x, 5.0
|
|
%b = fsub float -0.0, %a
|
|
%c = fmul float %b, %y
|
|
%d = fmul float %c, %a
|
|
store float %d, float addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind }
|