maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

AMDGPU: Select clamp pattern with v2f16 

llvm-svn: 312087
This commit is contained in:
Matt Arsenault 2017-08-30 01:20:17 +00:00
parent 5409d95d5b
commit 6b114d2c50
3 changed files with 226 additions and 49 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
llvm/lib/Target/AMDGPU/SIISelLowering.cpp
View File

@ -5644,15 +5644,27 @@ SDValue SITargetLowering::performIntMed3ImmCombine(
return DAG.getNode(ISD::TRUNCATE, SL, VT, Med3);
}
static ConstantFPSDNode *getSplatConstantFP(SDValue Op) {
if (ConstantFPSDNode *C = dyn_cast<ConstantFPSDNode>(Op))
return C;
if (BuildVectorSDNode *BV = dyn_cast<BuildVectorSDNode>(Op)) {
if (ConstantFPSDNode *C = BV->getConstantFPSplatNode())
return C;
}
return nullptr;
}
SDValue SITargetLowering::performFPMed3ImmCombine(SelectionDAG &DAG,
const SDLoc &SL,
SDValue Op0,
SDValue Op1) const {
ConstantFPSDNode *K1 = dyn_cast<ConstantFPSDNode>(Op1);
ConstantFPSDNode *K1 = getSplatConstantFP(Op1);
if (!K1)
return SDValue();
ConstantFPSDNode *K0 = dyn_cast<ConstantFPSDNode>(Op0.getOperand(1));
ConstantFPSDNode *K0 = getSplatConstantFP(Op0.getOperand(1));
if (!K0)
return SDValue();
@ -5662,7 +5674,7 @@ SDValue SITargetLowering::performFPMed3ImmCombine(SelectionDAG &DAG,
return SDValue();
// TODO: Check IEEE bit enabled?
EVT VT = K0->getValueType(0);
EVT VT = Op0.getValueType();
if (Subtarget->enableDX10Clamp()) {
// If dx10_clamp is enabled, NaNs clamp to 0.0. This is the same as the
// hardware fmed3 behavior converting to a min.
@ -5671,13 +5683,12 @@ SDValue SITargetLowering::performFPMed3ImmCombine(SelectionDAG &DAG,
return DAG.getNode(AMDGPUISD::CLAMP, SL, VT, Op0.getOperand(0));
}
// med3 for f16 is only available on gfx9+.
if (VT == MVT::f64 || (VT == MVT::f16 && !Subtarget->hasMed3_16()))
return SDValue();
// med3 for f16 is only available on gfx9+, and not available for v2f16.
if (VT == MVT::f32 || (VT == MVT::f16 && Subtarget->hasMed3_16())) {
// This isn't safe with signaling NaNs because in IEEE mode, min/max on a
// signaling NaN gives a quiet NaN. The quiet NaN input to the min would then
// give the other result, which is different from med3 with a NaN input.
// signaling NaN gives a quiet NaN. The quiet NaN input to the min would
// then give the other result, which is different from med3 with a NaN
// input.
SDValue Var = Op0.getOperand(0);
if (!isKnownNeverSNan(DAG, Var))
return SDValue();
@ -5686,6 +5697,9 @@ SDValue SITargetLowering::performFPMed3ImmCombine(SelectionDAG &DAG,
Var, SDValue(K0, 0), SDValue(K1, 0));
}
return SDValue();
}
SDValue SITargetLowering::performMinMaxCombine(SDNode *N,
DAGCombinerInfo &DCI) const {
SelectionDAG &DAG = DCI.DAG;
@ -5744,7 +5758,8 @@ SDValue SITargetLowering::performMinMaxCombine(SDNode *N,
(Opc == AMDGPUISD::FMIN_LEGACY &&
Op0.getOpcode() == AMDGPUISD::FMAX_LEGACY)) &&
(VT == MVT::f32 || VT == MVT::f64 ||
(VT == MVT::f16 && Subtarget->has16BitInsts())) &&
(VT == MVT::f16 && Subtarget->has16BitInsts()) ||
(VT == MVT::v2f16 && Subtarget->hasVOP3PInsts())) &&
Op0.hasOneUse()) {
if (SDValue Res = performFPMed3ImmCombine(DAG, SDLoc(N), Op0, Op1))
return Res;

6
llvm/lib/Target/AMDGPU/SIInstructions.td
View File

@ -825,6 +825,12 @@ def : ClampPat<V_MAX_F32_e64, f32>;
def : ClampPat<V_MAX_F64, f64>;
def : ClampPat<V_MAX_F16_e64, f16>;
def : Pat <
(v2f16 (AMDGPUclamp (VOP3PMods v2f16:$src0, i32:$src0_modifiers))),
(V_PK_MAX_F16 $src0_modifiers, $src0,
$src0_modifiers, $src0, DSTCLAMP.ENABLE)
>;
/********** ================================ **********/
/********** Floating point absolute/negative **********/
/********** ================================ **********/

224
llvm/test/CodeGen/AMDGPU/clamp.ll
View File

@ -1,8 +1,9 @@
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=SI %s
; RUN: llc -march=amdgcn -mcpu=fiji -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VI %s
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,SI %s
; RUN: llc -march=amdgcn -mcpu=fiji -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX89,VI %s
; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX89,GFX9 %s
; GCN-LABEL: {{^}}v_clamp_f32:
; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
; GCN: {{buffer|flat|global}}_load_dword [[A:v[0-9]+]]
; GCN: v_max_f32_e64 v{{[0-9]+}}, [[A]], [[A]] clamp{{$}}
define amdgpu_kernel void @v_clamp_f32(float addrspace(1)* %out, float addrspace(1)* %aptr) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
@ -17,7 +18,7 @@ define amdgpu_kernel void @v_clamp_f32(float addrspace(1)* %out, float addrspace
}
; GCN-LABEL: {{^}}v_clamp_neg_f32:
; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
; GCN: {{buffer|flat|global}}_load_dword [[A:v[0-9]+]]
; GCN: v_max_f32_e64 v{{[0-9]+}}, -[[A]], -[[A]] clamp{{$}}
define amdgpu_kernel void @v_clamp_neg_f32(float addrspace(1)* %out, float addrspace(1)* %aptr) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
@ -33,7 +34,7 @@ define amdgpu_kernel void @v_clamp_neg_f32(float addrspace(1)* %out, float addrs
}
; GCN-LABEL: {{^}}v_clamp_negabs_f32:
; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
; GCN: {{buffer|flat|global}}_load_dword [[A:v[0-9]+]]
; GCN: v_max_f32_e64 v{{[0-9]+}}, -|[[A]]|, -|[[A]]| clamp{{$}}
define amdgpu_kernel void @v_clamp_negabs_f32(float addrspace(1)* %out, float addrspace(1)* %aptr) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
@ -51,7 +52,7 @@ define amdgpu_kernel void @v_clamp_negabs_f32(float addrspace(1)* %out, float ad
}
; GCN-LABEL: {{^}}v_clamp_negzero_f32:
; GCN-DAG: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
; GCN-DAG: {{buffer|flat|global}}_load_dword [[A:v[0-9]+]]
; GCN-DAG: v_bfrev_b32_e32 [[SIGNBIT:v[0-9]+]], 1
; GCN: v_med3_f32 v{{[0-9]+}}, [[A]], [[SIGNBIT]], 1.0
define amdgpu_kernel void @v_clamp_negzero_f32(float addrspace(1)* %out, float addrspace(1)* %aptr) #0 {
@ -67,7 +68,7 @@ define amdgpu_kernel void @v_clamp_negzero_f32(float addrspace(1)* %out, float a
}
; GCN-LABEL: {{^}}v_clamp_multi_use_max_f32:
; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
; GCN: {{buffer|flat|global}}_load_dword [[A:v[0-9]+]]
; GCN: v_max_f32_e32 [[MAX:v[0-9]+]], 0, [[A]]
; GCN: v_min_f32_e32 [[MIN:v[0-9]+]], 1.0, [[MAX]]
define amdgpu_kernel void @v_clamp_multi_use_max_f32(float addrspace(1)* %out, float addrspace(1)* %aptr) #0 {
@ -84,8 +85,8 @@ define amdgpu_kernel void @v_clamp_multi_use_max_f32(float addrspace(1)* %out, f
}
; GCN-LABEL: {{^}}v_clamp_f16:
; GCN: {{buffer|flat}}_load_ushort [[A:v[0-9]+]]
; VI: v_max_f16_e64 v{{[0-9]+}}, [[A]], [[A]] clamp{{$}}
; GCN: {{buffer|flat|global}}_load_ushort [[A:v[0-9]+]]
; GFX89: v_max_f16_e64 v{{[0-9]+}}, [[A]], [[A]] clamp{{$}}
; SI: v_cvt_f32_f16_e64 [[CVT:v[0-9]+]], [[A]] clamp{{$}}
; SI: v_cvt_f16_f32_e32 v{{[0-9]+}}, [[CVT]]
@ -102,8 +103,8 @@ define amdgpu_kernel void @v_clamp_f16(half addrspace(1)* %out, half addrspace(1
}
; GCN-LABEL: {{^}}v_clamp_neg_f16:
; GCN: {{buffer|flat}}_load_ushort [[A:v[0-9]+]]
; VI: v_max_f16_e64 v{{[0-9]+}}, -[[A]], -[[A]] clamp{{$}}
; GCN: {{buffer|flat|global}}_load_ushort [[A:v[0-9]+]]
; GFX89: v_max_f16_e64 v{{[0-9]+}}, -[[A]], -[[A]] clamp{{$}}
; FIXME: Better to fold neg into max
; SI: v_cvt_f32_f16_e64 [[CVT:v[0-9]+]], -[[A]] clamp{{$}}
@ -122,8 +123,8 @@ define amdgpu_kernel void @v_clamp_neg_f16(half addrspace(1)* %out, half addrspa
}
; GCN-LABEL: {{^}}v_clamp_negabs_f16:
; GCN: {{buffer|flat}}_load_ushort [[A:v[0-9]+]]
; VI: v_max_f16_e64 v{{[0-9]+}}, -|[[A]]|, -|[[A]]| clamp{{$}}
; GCN: {{buffer|flat|global}}_load_ushort [[A:v[0-9]+]]
; GFX89: v_max_f16_e64 v{{[0-9]+}}, -|[[A]]|, -|[[A]]| clamp{{$}}
; FIXME: Better to fold neg/abs into max
@ -146,7 +147,7 @@ define amdgpu_kernel void @v_clamp_negabs_f16(half addrspace(1)* %out, half addr
; FIXME: Do f64 instructions support clamp?
; GCN-LABEL: {{^}}v_clamp_f64:
; GCN: {{buffer|flat}}_load_dwordx2 [[A:v\[[0-9]+:[0-9]+\]]]
; GCN: {{buffer|flat|global}}_load_dwordx2 [[A:v\[[0-9]+:[0-9]+\]]]
; GCN: v_max_f64 v{{\[[0-9]+:[0-9]+\]}}, [[A]], [[A]] clamp{{$}}
define amdgpu_kernel void @v_clamp_f64(double addrspace(1)* %out, double addrspace(1)* %aptr) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
@ -161,7 +162,7 @@ define amdgpu_kernel void @v_clamp_f64(double addrspace(1)* %out, double addrspa
}
; GCN-LABEL: {{^}}v_clamp_neg_f64:
; GCN: {{buffer|flat}}_load_dwordx2 [[A:v\[[0-9]+:[0-9]+\]]]
; GCN: {{buffer|flat|global}}_load_dwordx2 [[A:v\[[0-9]+:[0-9]+\]]]
; GCN: v_max_f64 v{{\[[0-9]+:[0-9]+\]}}, -[[A]], -[[A]] clamp{{$}}
define amdgpu_kernel void @v_clamp_neg_f64(double addrspace(1)* %out, double addrspace(1)* %aptr) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
@ -177,7 +178,7 @@ define amdgpu_kernel void @v_clamp_neg_f64(double addrspace(1)* %out, double add
}
; GCN-LABEL: {{^}}v_clamp_negabs_f64:
; GCN: {{buffer|flat}}_load_dwordx2 [[A:v\[[0-9]+:[0-9]+\]]]
; GCN: {{buffer|flat|global}}_load_dwordx2 [[A:v\[[0-9]+:[0-9]+\]]]
; GCN: v_max_f64 v{{\[[0-9]+:[0-9]+\]}}, -|[[A]]|, -|[[A]]| clamp{{$}}
define amdgpu_kernel void @v_clamp_negabs_f64(double addrspace(1)* %out, double addrspace(1)* %aptr) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
@ -195,7 +196,7 @@ define amdgpu_kernel void @v_clamp_negabs_f64(double addrspace(1)* %out, double
}
; GCN-LABEL: {{^}}v_clamp_med3_aby_negzero_f32:
; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
; GCN: {{buffer|flat|global}}_load_dword [[A:v[0-9]+]]
; GCN: v_med3_f32
define amdgpu_kernel void @v_clamp_med3_aby_negzero_f32(float addrspace(1)* %out, float addrspace(1)* %aptr) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
@ -208,7 +209,7 @@ define amdgpu_kernel void @v_clamp_med3_aby_negzero_f32(float addrspace(1)* %out
}
; GCN-LABEL: {{^}}v_clamp_med3_aby_f32:
; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
; GCN: {{buffer|flat|global}}_load_dword [[A:v[0-9]+]]
; GCN: v_max_f32_e64 v{{[0-9]+}}, [[A]], [[A]] clamp{{$}}
define amdgpu_kernel void @v_clamp_med3_aby_f32(float addrspace(1)* %out, float addrspace(1)* %aptr) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
@ -221,7 +222,7 @@ define amdgpu_kernel void @v_clamp_med3_aby_f32(float addrspace(1)* %out, float
}
; GCN-LABEL: {{^}}v_clamp_med3_bay_f32:
; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
; GCN: {{buffer|flat|global}}_load_dword [[A:v[0-9]+]]
; GCN: v_max_f32_e64 v{{[0-9]+}}, [[A]], [[A]] clamp{{$}}
define amdgpu_kernel void @v_clamp_med3_bay_f32(float addrspace(1)* %out, float addrspace(1)* %aptr) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
@ -234,7 +235,7 @@ define amdgpu_kernel void @v_clamp_med3_bay_f32(float addrspace(1)* %out, float
}
; GCN-LABEL: {{^}}v_clamp_med3_yab_f32:
; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
; GCN: {{buffer|flat|global}}_load_dword [[A:v[0-9]+]]
; GCN: v_max_f32_e64 v{{[0-9]+}}, [[A]], [[A]] clamp{{$}}
define amdgpu_kernel void @v_clamp_med3_yab_f32(float addrspace(1)* %out, float addrspace(1)* %aptr) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
@ -247,7 +248,7 @@ define amdgpu_kernel void @v_clamp_med3_yab_f32(float addrspace(1)* %out, float
}
; GCN-LABEL: {{^}}v_clamp_med3_yba_f32:
; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
; GCN: {{buffer|flat|global}}_load_dword [[A:v[0-9]+]]
; GCN: v_max_f32_e64 v{{[0-9]+}}, [[A]], [[A]] clamp{{$}}
define amdgpu_kernel void @v_clamp_med3_yba_f32(float addrspace(1)* %out, float addrspace(1)* %aptr) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
@ -260,7 +261,7 @@ define amdgpu_kernel void @v_clamp_med3_yba_f32(float addrspace(1)* %out, float
}
; GCN-LABEL: {{^}}v_clamp_med3_ayb_f32:
; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
; GCN: {{buffer|flat|global}}_load_dword [[A:v[0-9]+]]
; GCN: v_max_f32_e64 v{{[0-9]+}}, [[A]], [[A]] clamp{{$}}
define amdgpu_kernel void @v_clamp_med3_ayb_f32(float addrspace(1)* %out, float addrspace(1)* %aptr) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
@ -273,7 +274,7 @@ define amdgpu_kernel void @v_clamp_med3_ayb_f32(float addrspace(1)* %out, float
}
; GCN-LABEL: {{^}}v_clamp_med3_bya_f32:
; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
; GCN: {{buffer|flat|global}}_load_dword [[A:v[0-9]+]]
; GCN: v_max_f32_e64 v{{[0-9]+}}, [[A]], [[A]] clamp{{$}}
define amdgpu_kernel void @v_clamp_med3_bya_f32(float addrspace(1)* %out, float addrspace(1)* %aptr) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
@ -350,7 +351,7 @@ define amdgpu_kernel void @v_clamp_constant_snan_f32(float addrspace(1)* %out) #
; ---------------------------------------------------------------------
; GCN-LABEL: {{^}}v_clamp_f32_no_dx10_clamp:
; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
; GCN: {{buffer|flat|global}}_load_dword [[A:v[0-9]+]]
; GCN: v_med3_f32 v{{[0-9]+}}, [[A]], 0, 1.0
define amdgpu_kernel void @v_clamp_f32_no_dx10_clamp(float addrspace(1)* %out, float addrspace(1)* %aptr) #2 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
@ -365,7 +366,7 @@ define amdgpu_kernel void @v_clamp_f32_no_dx10_clamp(float addrspace(1)* %out, f
}
; GCN-LABEL: {{^}}v_clamp_f32_snan_dx10clamp:
; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
; GCN: {{buffer|flat|global}}_load_dword [[A:v[0-9]+]]
; GCN: v_max_f32_e64 v{{[0-9]+}}, [[A]], [[A]] clamp{{$}}
define amdgpu_kernel void @v_clamp_f32_snan_dx10clamp(float addrspace(1)* %out, float addrspace(1)* %aptr) #3 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
@ -380,7 +381,7 @@ define amdgpu_kernel void @v_clamp_f32_snan_dx10clamp(float addrspace(1)* %out,
}
; GCN-LABEL: {{^}}v_clamp_f32_snan_no_dx10clamp:
; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
; GCN: {{buffer|flat|global}}_load_dword [[A:v[0-9]+]]
; GCN: v_max_f32_e32 [[MAX:v[0-9]+]], 0, [[A]]
; GCN: v_min_f32_e32 [[MIN:v[0-9]+]], 1.0, [[MAX]]
define amdgpu_kernel void @v_clamp_f32_snan_no_dx10clamp(float addrspace(1)* %out, float addrspace(1)* %aptr) #4 {
@ -396,7 +397,7 @@ define amdgpu_kernel void @v_clamp_f32_snan_no_dx10clamp(float addrspace(1)* %ou
}
; GCN-LABEL: {{^}}v_clamp_f32_snan_no_dx10clamp_nnan_src:
; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
; GCN: {{buffer|flat|global}}_load_dword [[A:v[0-9]+]]
; GCN: v_med3_f32 v{{[0-9]+}}, [[A]], 0, 1.0
define amdgpu_kernel void @v_clamp_f32_snan_no_dx10clamp_nnan_src(float addrspace(1)* %out, float addrspace(1)* %aptr) #4 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
@ -412,7 +413,7 @@ define amdgpu_kernel void @v_clamp_f32_snan_no_dx10clamp_nnan_src(float addrspac
}
; GCN-LABEL: {{^}}v_clamp_med3_aby_f32_no_dx10_clamp:
; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
; GCN: {{buffer|flat|global}}_load_dword [[A:v[0-9]+]]
; GCN: v_max_f32_e64 v{{[0-9]+}}, [[A]], [[A]] clamp{{$}}
define amdgpu_kernel void @v_clamp_med3_aby_f32_no_dx10_clamp(float addrspace(1)* %out, float addrspace(1)* %aptr) #2 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
@ -425,7 +426,7 @@ define amdgpu_kernel void @v_clamp_med3_aby_f32_no_dx10_clamp(float addrspace(1)
}
; GCN-LABEL: {{^}}v_clamp_med3_bay_f32_no_dx10_clamp:
; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
; GCN: {{buffer|flat|global}}_load_dword [[A:v[0-9]+]]
; GCN: v_max_f32_e64 v{{[0-9]+}}, [[A]], [[A]] clamp{{$}}
define amdgpu_kernel void @v_clamp_med3_bay_f32_no_dx10_clamp(float addrspace(1)* %out, float addrspace(1)* %aptr) #2 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
@ -438,7 +439,7 @@ define amdgpu_kernel void @v_clamp_med3_bay_f32_no_dx10_clamp(float addrspace(1)
}
; GCN-LABEL: {{^}}v_clamp_med3_yab_f32_no_dx10_clamp:
; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
; GCN: {{buffer|flat|global}}_load_dword [[A:v[0-9]+]]
; GCN: v_med3_f32 v{{[0-9]+}}, [[A]], 0, 1.0
define amdgpu_kernel void @v_clamp_med3_yab_f32_no_dx10_clamp(float addrspace(1)* %out, float addrspace(1)* %aptr) #2 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
@ -451,7 +452,7 @@ define amdgpu_kernel void @v_clamp_med3_yab_f32_no_dx10_clamp(float addrspace(1)
}
; GCN-LABEL: {{^}}v_clamp_med3_yba_f32_no_dx10_clamp:
; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
; GCN: {{buffer|flat|global}}_load_dword [[A:v[0-9]+]]
; GCN: v_med3_f32 v{{[0-9]+}}, [[A]], 1.0, 0
define amdgpu_kernel void @v_clamp_med3_yba_f32_no_dx10_clamp(float addrspace(1)* %out, float addrspace(1)* %aptr) #2 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
@ -464,7 +465,7 @@ define amdgpu_kernel void @v_clamp_med3_yba_f32_no_dx10_clamp(float addrspace(1)
}
; GCN-LABEL: {{^}}v_clamp_med3_ayb_f32_no_dx10_clamp:
; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
; GCN: {{buffer|flat|global}}_load_dword [[A:v[0-9]+]]
; GCN: v_med3_f32 v{{[0-9]+}}, 0, [[A]], 1.0
define amdgpu_kernel void @v_clamp_med3_ayb_f32_no_dx10_clamp(float addrspace(1)* %out, float addrspace(1)* %aptr) #2 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
@ -477,7 +478,7 @@ define amdgpu_kernel void @v_clamp_med3_ayb_f32_no_dx10_clamp(float addrspace(1)
}
; GCN-LABEL: {{^}}v_clamp_med3_bya_f32_no_dx10_clamp:
; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
; GCN: {{buffer|flat|global}}_load_dword [[A:v[0-9]+]]
; GCN: v_med3_f32 v{{[0-9]+}}, 1.0, [[A]], 0
define amdgpu_kernel void @v_clamp_med3_bya_f32_no_dx10_clamp(float addrspace(1)* %out, float addrspace(1)* %aptr) #2 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
@ -509,6 +510,159 @@ define amdgpu_kernel void @v_clamp_constant_snan_f32_no_dx10_clamp(float addrspa
ret void
}
; GCN-LABEL: {{^}}v_clamp_v2f16:
; GCN: {{buffer|flat|global}}_load_dword [[A:v[0-9]+]]
; GFX9-NOT: [[A]]
; GFX9: v_pk_max_f16 [[CLAMP:v[0-9]+]], [[A]], [[A]] clamp{{$}}
define amdgpu_kernel void @v_clamp_v2f16(<2 x half> addrspace(1)* %out, <2 x half> addrspace(1)* %aptr) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%gep0 = getelementptr <2 x half>, <2 x half> addrspace(1)* %aptr, i32 %tid
%out.gep = getelementptr <2 x half>, <2 x half> addrspace(1)* %out, i32 %tid
%a = load <2 x half>, <2 x half> addrspace(1)* %gep0
%max = call <2 x half> @llvm.maxnum.v2f16(<2 x half> %a, <2 x half> zeroinitializer)
%med = call <2 x half> @llvm.minnum.v2f16(<2 x half> %max, <2 x half> <half 1.0, half 1.0>)
store <2 x half> %med, <2 x half> addrspace(1)* %out.gep
ret void
}
; GCN-LABEL: {{^}}v_clamp_v2f16_undef_elt:
; GCN: {{buffer|flat|global}}_load_dword [[A:v[0-9]+]]
; GFX9-NOT: [[A]]
; GFX9: v_pk_max_f16 [[CLAMP:v[0-9]+]], [[A]], [[A]] clamp{{$}}
define amdgpu_kernel void @v_clamp_v2f16_undef_elt(<2 x half> addrspace(1)* %out, <2 x half> addrspace(1)* %aptr) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%gep0 = getelementptr <2 x half>, <2 x half> addrspace(1)* %aptr, i32 %tid
%out.gep = getelementptr <2 x half>, <2 x half> addrspace(1)* %out, i32 %tid
%a = load <2 x half>, <2 x half> addrspace(1)* %gep0
%max = call <2 x half> @llvm.maxnum.v2f16(<2 x half> %a, <2 x half> <half undef, half 0.0>)
%med = call <2 x half> @llvm.minnum.v2f16(<2 x half> %max, <2 x half> <half 1.0, half undef>)
store <2 x half> %med, <2 x half> addrspace(1)* %out.gep
ret void
}
; GCN-LABEL: {{^}}v_clamp_v2f16_not_zero:
; GFX9: v_pk_max_f16
; GFX9: v_pk_min_f16
define amdgpu_kernel void @v_clamp_v2f16_not_zero(<2 x half> addrspace(1)* %out, <2 x half> addrspace(1)* %aptr) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%gep0 = getelementptr <2 x half>, <2 x half> addrspace(1)* %aptr, i32 %tid
%out.gep = getelementptr <2 x half>, <2 x half> addrspace(1)* %out, i32 %tid
%a = load <2 x half>, <2 x half> addrspace(1)* %gep0
%max = call <2 x half> @llvm.maxnum.v2f16(<2 x half> %a, <2 x half> <half 2.0, half 0.0>)
%med = call <2 x half> @llvm.minnum.v2f16(<2 x half> %max, <2 x half> <half 1.0, half 1.0>)
store <2 x half> %med, <2 x half> addrspace(1)* %out.gep
ret void
}
; GCN-LABEL: {{^}}v_clamp_v2f16_not_one:
; GFX9: v_pk_max_f16
; GFX9: v_pk_min_f16
define amdgpu_kernel void @v_clamp_v2f16_not_one(<2 x half> addrspace(1)* %out, <2 x half> addrspace(1)* %aptr) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%gep0 = getelementptr <2 x half>, <2 x half> addrspace(1)* %aptr, i32 %tid
%out.gep = getelementptr <2 x half>, <2 x half> addrspace(1)* %out, i32 %tid
%a = load <2 x half>, <2 x half> addrspace(1)* %gep0
%max = call <2 x half> @llvm.maxnum.v2f16(<2 x half> %a, <2 x half> <half 0.0, half 0.0>)
%med = call <2 x half> @llvm.minnum.v2f16(<2 x half> %max, <2 x half> <half 0.0, half 1.0>)
store <2 x half> %med, <2 x half> addrspace(1)* %out.gep
ret void
}
; GCN-LABEL: {{^}}v_clamp_neg_v2f16:
; GCN: {{buffer|flat|global}}_load_dword [[A:v[0-9]+]]
; GFX9-NOT: [[A]]
; GFX9: v_pk_max_f16 [[CLAMP:v[0-9]+]], [[A]], [[A]] neg_lo:[1,1] neg_hi:[1,1] clamp{{$}}
define amdgpu_kernel void @v_clamp_neg_v2f16(<2 x half> addrspace(1)* %out, <2 x half> addrspace(1)* %aptr) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%gep0 = getelementptr <2 x half>, <2 x half> addrspace(1)* %aptr, i32 %tid
%out.gep = getelementptr <2 x half>, <2 x half> addrspace(1)* %out, i32 %tid
%a = load <2 x half>, <2 x half> addrspace(1)* %gep0
%fneg.a = fsub <2 x half> <half -0.0, half -0.0>, %a
%max = call <2 x half> @llvm.maxnum.v2f16(<2 x half> %fneg.a, <2 x half> zeroinitializer)
%med = call <2 x half> @llvm.minnum.v2f16(<2 x half> %max, <2 x half> <half 1.0, half 1.0>)
store <2 x half> %med, <2 x half> addrspace(1)* %out.gep
ret void
}
; GCN-LABEL: {{^}}v_clamp_negabs_v2f16:
; GCN: {{buffer|flat|global}}_load_dword [[A:v[0-9]+]]
; GFX9: v_and_b32_e32 [[ABS:v[0-9]+]], 0x7fff7fff, [[A]]
; GFX9: v_pk_max_f16 [[CLAMP:v[0-9]+]], [[ABS]], [[ABS]] neg_lo:[1,1] neg_hi:[1,1] clamp{{$}}
define amdgpu_kernel void @v_clamp_negabs_v2f16(<2 x half> addrspace(1)* %out, <2 x half> addrspace(1)* %aptr) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%gep0 = getelementptr <2 x half>, <2 x half> addrspace(1)* %aptr, i32 %tid
%out.gep = getelementptr <2 x half>, <2 x half> addrspace(1)* %out, i32 %tid
%a = load <2 x half>, <2 x half> addrspace(1)* %gep0
%fabs.a = call <2 x half> @llvm.fabs.v2f16(<2 x half> %a)
%fneg.fabs.a = fsub <2 x half> <half -0.0, half -0.0>, %fabs.a
%max = call <2 x half> @llvm.maxnum.v2f16(<2 x half> %fneg.fabs.a, <2 x half> zeroinitializer)
%med = call <2 x half> @llvm.minnum.v2f16(<2 x half> %max, <2 x half> <half 1.0, half 1.0>)
store <2 x half> %med, <2 x half> addrspace(1)* %out.gep
ret void
}
; GCN-LABEL: {{^}}v_clamp_neglo_v2f16:
; GCN: {{buffer|flat|global}}_load_dword [[A:v[0-9]+]]
; GFX9-NOT: [[A]]
; GFX9: v_pk_max_f16 [[CLAMP:v[0-9]+]], [[A]], [[A]] neg_lo:[1,1] clamp{{$}}
define amdgpu_kernel void @v_clamp_neglo_v2f16(<2 x half> addrspace(1)* %out, <2 x half> addrspace(1)* %aptr) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%gep0 = getelementptr <2 x half>, <2 x half> addrspace(1)* %aptr, i32 %tid
%out.gep = getelementptr <2 x half>, <2 x half> addrspace(1)* %out, i32 %tid
%a = load <2 x half>, <2 x half> addrspace(1)* %gep0
%lo = extractelement <2 x half> %a, i32 0
%neg.lo = fsub half -0.0, %lo
%neg.lo.vec = insertelement <2 x half> %a, half %neg.lo, i32 0
%max = call <2 x half> @llvm.maxnum.v2f16(<2 x half> %neg.lo.vec, <2 x half> zeroinitializer)
%med = call <2 x half> @llvm.minnum.v2f16(<2 x half> %max, <2 x half> <half 1.0, half 1.0>)
store <2 x half> %med, <2 x half> addrspace(1)* %out.gep
ret void
}
; GCN-LABEL: {{^}}v_clamp_neghi_v2f16:
; GCN: {{buffer|flat|global}}_load_dword [[A:v[0-9]+]]
; GFX9-NOT: [[A]]
; GFX9: v_pk_max_f16 [[CLAMP:v[0-9]+]], [[A]], [[A]] neg_hi:[1,1] clamp{{$}}
define amdgpu_kernel void @v_clamp_neghi_v2f16(<2 x half> addrspace(1)* %out, <2 x half> addrspace(1)* %aptr) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%gep0 = getelementptr <2 x half>, <2 x half> addrspace(1)* %aptr, i32 %tid
%out.gep = getelementptr <2 x half>, <2 x half> addrspace(1)* %out, i32 %tid
%a = load <2 x half>, <2 x half> addrspace(1)* %gep0
%hi = extractelement <2 x half> %a, i32 1
%neg.hi = fsub half -0.0, %hi
%neg.hi.vec = insertelement <2 x half> %a, half %neg.hi, i32 1
%max = call <2 x half> @llvm.maxnum.v2f16(<2 x half> %neg.hi.vec, <2 x half> zeroinitializer)
%med = call <2 x half> @llvm.minnum.v2f16(<2 x half> %max, <2 x half> <half 1.0, half 1.0>)
store <2 x half> %med, <2 x half> addrspace(1)* %out.gep
ret void
}
; GCN-LABEL: {{^}}v_clamp_v2f16_shuffle:
; GCN: {{buffer|flat|global}}_load_dword [[A:v[0-9]+]]
; GFX9-NOT: [[A]]
; GFX9: v_pk_max_f16 [[CLAMP:v[0-9]+]], [[A]], [[A]] op_sel:[1,1] op_sel_hi:[0,0] clamp{{$}}
define amdgpu_kernel void @v_clamp_v2f16_shuffle(<2 x half> addrspace(1)* %out, <2 x half> addrspace(1)* %aptr) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%gep0 = getelementptr <2 x half>, <2 x half> addrspace(1)* %aptr, i32 %tid
%out.gep = getelementptr <2 x half>, <2 x half> addrspace(1)* %out, i32 %tid
%a = load <2 x half>, <2 x half> addrspace(1)* %gep0
%shuf = shufflevector <2 x half> %a, <2 x half> undef, <2 x i32> <i32 1, i32 0>
%max = call <2 x half> @llvm.maxnum.v2f16(<2 x half> %shuf, <2 x half> zeroinitializer)
%med = call <2 x half> @llvm.minnum.v2f16(<2 x half> %max, <2 x half> <half 1.0, half 1.0>)
store <2 x half> %med, <2 x half> addrspace(1)* %out.gep
ret void
}
declare i32 @llvm.amdgcn.workitem.id.x() #1
declare float @llvm.fabs.f32(float) #1
declare float @llvm.minnum.f32(float, float) #1
@ -520,7 +674,9 @@ declare double @llvm.maxnum.f64(double, double) #1
declare half @llvm.fabs.f16(half) #1
declare half @llvm.minnum.f16(half, half) #1
declare half @llvm.maxnum.f16(half, half) #1
declare <2 x half> @llvm.fabs.v2f16(<2 x half>) #1
declare <2 x half> @llvm.minnum.v2f16(<2 x half>, <2 x half>) #1
declare <2 x half> @llvm.maxnum.v2f16(<2 x half>, <2 x half>) #1
attributes #0 = { nounwind }
attributes #1 = { nounwind readnone }