diff --git a/llvm/lib/Target/R600/AMDGPUISelLowering.cpp b/llvm/lib/Target/R600/AMDGPUISelLowering.cpp index ad557077f3f3..7c5235d15075 100644 --- a/llvm/lib/Target/R600/AMDGPUISelLowering.cpp +++ b/llvm/lib/Target/R600/AMDGPUISelLowering.cpp @@ -126,6 +126,8 @@ AMDGPUTargetLowering::AMDGPUTargetLowering(TargetMachine &TM, setOperationAction(ISD::FFLOOR, MVT::f32, Legal); setOperationAction(ISD::FRINT, MVT::f32, Legal); setOperationAction(ISD::FTRUNC, MVT::f32, Legal); + setOperationAction(ISD::FMINNUM, MVT::f32, Legal); + setOperationAction(ISD::FMAXNUM, MVT::f32, Legal); setOperationAction(ISD::FROUND, MVT::f32, Custom); setOperationAction(ISD::FROUND, MVT::f64, Custom); diff --git a/llvm/lib/Target/R600/R600Instructions.td b/llvm/lib/Target/R600/R600Instructions.td index 291fb0459e2f..7126c82c0331 100644 --- a/llvm/lib/Target/R600/R600Instructions.td +++ b/llvm/lib/Target/R600/R600Instructions.td @@ -683,6 +683,11 @@ def MUL_IEEE : R600_2OP_Helper <0x2, "MUL_IEEE", fmul>; // TODO: Do these actually match the regular fmin/fmax behavior? def MAX : R600_2OP_Helper <0x3, "MAX", AMDGPUfmax_legacy>; def MIN : R600_2OP_Helper <0x4, "MIN", AMDGPUfmin_legacy>; +// According to https://msdn.microsoft.com/en-us/library/windows/desktop/cc308050%28v=vs.85%29.aspx +// DX10 min/max returns the other operand if one is NaN, +// this matches http://llvm.org/docs/LangRef.html#llvm-minnum-intrinsic +def MAX_DX10 : R600_2OP_Helper <0x5, "MAX_DX10", fmaxnum>; +def MIN_DX10 : R600_2OP_Helper <0x6, "MIN_DX10", fminnum>; // For the SET* instructions there is a naming conflict in TargetSelectionDAG.td, // so some of the instruction names don't match the asm string. diff --git a/llvm/lib/Target/R600/SIISelLowering.cpp b/llvm/lib/Target/R600/SIISelLowering.cpp index 0a6166da58d6..43507d8bf330 100644 --- a/llvm/lib/Target/R600/SIISelLowering.cpp +++ b/llvm/lib/Target/R600/SIISelLowering.cpp @@ -76,8 +76,6 @@ SITargetLowering::SITargetLowering(TargetMachine &TM, setOperationAction(ISD::FSIN, MVT::f32, Custom); setOperationAction(ISD::FCOS, MVT::f32, Custom); - setOperationAction(ISD::FMINNUM, MVT::f32, Legal); - setOperationAction(ISD::FMAXNUM, MVT::f32, Legal); setOperationAction(ISD::FMINNUM, MVT::f64, Legal); setOperationAction(ISD::FMAXNUM, MVT::f64, Legal); diff --git a/llvm/test/CodeGen/R600/fmaxnum.ll b/llvm/test/CodeGen/R600/fmaxnum.ll index c105598ff811..3029bd02e4db 100644 --- a/llvm/test/CodeGen/R600/fmaxnum.ll +++ b/llvm/test/CodeGen/R600/fmaxnum.ll @@ -11,6 +11,9 @@ declare double @llvm.maxnum.f64(double, double) ; FUNC-LABEL: @test_fmax_f32 ; SI: v_max_f32_e32 + +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT:T[0-9]+\.[XYZW]]] +; EG: MAX_DX10 {{.*}}[[OUT]] define void @test_fmax_f32(float addrspace(1)* %out, float %a, float %b) nounwind { %val = call float @llvm.maxnum.f32(float %a, float %b) #0 store float %val, float addrspace(1)* %out, align 4 @@ -20,6 +23,10 @@ define void @test_fmax_f32(float addrspace(1)* %out, float %a, float %b) nounwin ; FUNC-LABEL: @test_fmax_v2f32 ; SI: v_max_f32_e32 ; SI: v_max_f32_e32 + +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT:T[0-9]+]] +; EG: MAX_DX10 {{.*}}[[OUT]] +; EG: MAX_DX10 {{.*}}[[OUT]] define void @test_fmax_v2f32(<2 x float> addrspace(1)* %out, <2 x float> %a, <2 x float> %b) nounwind { %val = call <2 x float> @llvm.maxnum.v2f32(<2 x float> %a, <2 x float> %b) #0 store <2 x float> %val, <2 x float> addrspace(1)* %out, align 8 @@ -31,6 +38,12 @@ define void @test_fmax_v2f32(<2 x float> addrspace(1)* %out, <2 x float> %a, <2 ; SI: v_max_f32_e32 ; SI: v_max_f32_e32 ; SI: v_max_f32_e32 + +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT:T[0-9]+]] +; EG: MAX_DX10 {{.*}}[[OUT]] +; EG: MAX_DX10 {{.*}}[[OUT]] +; EG: MAX_DX10 {{.*}}[[OUT]] +; EG: MAX_DX10 {{.*}}[[OUT]] define void @test_fmax_v4f32(<4 x float> addrspace(1)* %out, <4 x float> %a, <4 x float> %b) nounwind { %val = call <4 x float> @llvm.maxnum.v4f32(<4 x float> %a, <4 x float> %b) #0 store <4 x float> %val, <4 x float> addrspace(1)* %out, align 16 @@ -46,6 +59,17 @@ define void @test_fmax_v4f32(<4 x float> addrspace(1)* %out, <4 x float> %a, <4 ; SI: v_max_f32_e32 ; SI: v_max_f32_e32 ; SI: v_max_f32_e32 + +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT1:T[0-9]+]] +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT2:T[0-9]+]] +; EG-DAG: MAX_DX10 {{.*}}[[OUT1]].X +; EG-DAG: MAX_DX10 {{.*}}[[OUT1]].Y +; EG-DAG: MAX_DX10 {{.*}}[[OUT1]].Z +; EG-DAG: MAX_DX10 {{.*}}[[OUT1]].W +; EG-DAG: MAX_DX10 {{.*}}[[OUT2]].X +; EG-DAG: MAX_DX10 {{.*}}[[OUT2]].Y +; EG-DAG: MAX_DX10 {{.*}}[[OUT2]].Z +; EG-DAG: MAX_DX10 {{.*}}[[OUT2]].W define void @test_fmax_v8f32(<8 x float> addrspace(1)* %out, <8 x float> %a, <8 x float> %b) nounwind { %val = call <8 x float> @llvm.maxnum.v8f32(<8 x float> %a, <8 x float> %b) #0 store <8 x float> %val, <8 x float> addrspace(1)* %out, align 32 @@ -69,6 +93,27 @@ define void @test_fmax_v8f32(<8 x float> addrspace(1)* %out, <8 x float> %a, <8 ; SI: v_max_f32_e32 ; SI: v_max_f32_e32 ; SI: v_max_f32_e32 + +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT1:T[0-9]+]] +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT2:T[0-9]+]] +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT3:T[0-9]+]] +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT4:T[0-9]+]] +; EG-DAG: MAX_DX10 {{.*}}[[OUT1]].X +; EG-DAG: MAX_DX10 {{.*}}[[OUT1]].Y +; EG-DAG: MAX_DX10 {{.*}}[[OUT1]].Z +; EG-DAG: MAX_DX10 {{.*}}[[OUT1]].W +; EG-DAG: MAX_DX10 {{.*}}[[OUT2]].X +; EG-DAG: MAX_DX10 {{.*}}[[OUT2]].Y +; EG-DAG: MAX_DX10 {{.*}}[[OUT2]].Z +; EG-DAG: MAX_DX10 {{.*}}[[OUT2]].W +; EG-DAG: MAX_DX10 {{.*}}[[OUT3]].X +; EG-DAG: MAX_DX10 {{.*}}[[OUT3]].Y +; EG-DAG: MAX_DX10 {{.*}}[[OUT3]].Z +; EG-DAG: MAX_DX10 {{.*}}[[OUT3]].W +; EG-DAG: MAX_DX10 {{.*}}[[OUT4]].X +; EG-DAG: MAX_DX10 {{.*}}[[OUT4]].Y +; EG-DAG: MAX_DX10 {{.*}}[[OUT4]].Z +; EG-DAG: MAX_DX10 {{.*}}[[OUT4]].W define void @test_fmax_v16f32(<16 x float> addrspace(1)* %out, <16 x float> %a, <16 x float> %b) nounwind { %val = call <16 x float> @llvm.maxnum.v16f32(<16 x float> %a, <16 x float> %b) #0 store <16 x float> %val, <16 x float> addrspace(1)* %out, align 64 @@ -79,6 +124,10 @@ define void @test_fmax_v16f32(<16 x float> addrspace(1)* %out, <16 x float> %a, ; SI-NOT: v_max_f32_e32 ; SI: v_mov_b32_e32 [[REG:v[0-9]+]], 2.0 ; SI: buffer_store_dword [[REG]] + +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT:T[0-9]+\.[XYZW]]] +; EG-NOT: MAX_DX10 +; EG: MOV {{.*}}[[OUT]], literal.{{[xy]}} define void @constant_fold_fmax_f32(float addrspace(1)* %out) nounwind { %val = call float @llvm.maxnum.f32(float 1.0, float 2.0) #0 store float %val, float addrspace(1)* %out, align 4 @@ -89,6 +138,11 @@ define void @constant_fold_fmax_f32(float addrspace(1)* %out) nounwind { ; SI-NOT: v_max_f32_e32 ; SI: v_mov_b32_e32 [[REG:v[0-9]+]], 0x7fc00000 ; SI: buffer_store_dword [[REG]] + +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT:T[0-9]+\.[XYZW]]] +; EG-NOT: MAX_DX10 +; EG: MOV {{.*}}[[OUT]], literal.{{[xy]}} +; EG: 2143289344(nan) define void @constant_fold_fmax_f32_nan_nan(float addrspace(1)* %out) nounwind { %val = call float @llvm.maxnum.f32(float 0x7FF8000000000000, float 0x7FF8000000000000) #0 store float %val, float addrspace(1)* %out, align 4 @@ -99,6 +153,10 @@ define void @constant_fold_fmax_f32_nan_nan(float addrspace(1)* %out) nounwind { ; SI-NOT: v_max_f32_e32 ; SI: v_mov_b32_e32 [[REG:v[0-9]+]], 1.0 ; SI: buffer_store_dword [[REG]] + +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT:T[0-9]+\.[XYZW]]] +; EG-NOT: MAX_DX10 +; EG: MOV {{.*}}[[OUT]], literal.{{[xy]}} define void @constant_fold_fmax_f32_val_nan(float addrspace(1)* %out) nounwind { %val = call float @llvm.maxnum.f32(float 1.0, float 0x7FF8000000000000) #0 store float %val, float addrspace(1)* %out, align 4 @@ -109,6 +167,10 @@ define void @constant_fold_fmax_f32_val_nan(float addrspace(1)* %out) nounwind { ; SI-NOT: v_max_f32_e32 ; SI: v_mov_b32_e32 [[REG:v[0-9]+]], 1.0 ; SI: buffer_store_dword [[REG]] + +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT:T[0-9]+\.[XYZW]]] +; EG-NOT: MAX_DX10 +; EG: MOV {{.*}}[[OUT]], literal.{{[xy]}} define void @constant_fold_fmax_f32_nan_val(float addrspace(1)* %out) nounwind { %val = call float @llvm.maxnum.f32(float 0x7FF8000000000000, float 1.0) #0 store float %val, float addrspace(1)* %out, align 4 @@ -119,6 +181,10 @@ define void @constant_fold_fmax_f32_nan_val(float addrspace(1)* %out) nounwind { ; SI-NOT: v_max_f32_e32 ; SI: v_mov_b32_e32 [[REG:v[0-9]+]], 0 ; SI: buffer_store_dword [[REG]] + +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT:T[0-9]+\.[XYZW]]] +; EG-NOT: MAX_DX10 +; EG: MOV {{.*}}[[OUT]], literal.{{[xy]}} define void @constant_fold_fmax_f32_p0_p0(float addrspace(1)* %out) nounwind { %val = call float @llvm.maxnum.f32(float 0.0, float 0.0) #0 store float %val, float addrspace(1)* %out, align 4 @@ -129,6 +195,10 @@ define void @constant_fold_fmax_f32_p0_p0(float addrspace(1)* %out) nounwind { ; SI-NOT: v_max_f32_e32 ; SI: v_mov_b32_e32 [[REG:v[0-9]+]], 0 ; SI: buffer_store_dword [[REG]] + +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT:T[0-9]+\.[XYZW]]] +; EG-NOT: MAX_DX10 +; EG: MOV {{.*}}[[OUT]], literal.{{[xy]}} define void @constant_fold_fmax_f32_p0_n0(float addrspace(1)* %out) nounwind { %val = call float @llvm.maxnum.f32(float 0.0, float -0.0) #0 store float %val, float addrspace(1)* %out, align 4 @@ -139,6 +209,10 @@ define void @constant_fold_fmax_f32_p0_n0(float addrspace(1)* %out) nounwind { ; SI-NOT: v_max_f32_e32 ; SI: v_mov_b32_e32 [[REG:v[0-9]+]], 0x80000000 ; SI: buffer_store_dword [[REG]] + +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT:T[0-9]+\.[XYZW]]] +; EG-NOT: MAX_DX10 +; EG: MOV {{.*}}[[OUT]], literal.{{[xy]}} define void @constant_fold_fmax_f32_n0_p0(float addrspace(1)* %out) nounwind { %val = call float @llvm.maxnum.f32(float -0.0, float 0.0) #0 store float %val, float addrspace(1)* %out, align 4 @@ -149,6 +223,10 @@ define void @constant_fold_fmax_f32_n0_p0(float addrspace(1)* %out) nounwind { ; SI-NOT: v_max_f32_e32 ; SI: v_mov_b32_e32 [[REG:v[0-9]+]], 0x80000000 ; SI: buffer_store_dword [[REG]] + +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT:T[0-9]+\.[XYZW]]] +; EG-NOT: MAX_DX10 +; EG: MOV {{.*}}[[OUT]], literal.{{[xy]}} define void @constant_fold_fmax_f32_n0_n0(float addrspace(1)* %out) nounwind { %val = call float @llvm.maxnum.f32(float -0.0, float -0.0) #0 store float %val, float addrspace(1)* %out, align 4 @@ -157,6 +235,10 @@ define void @constant_fold_fmax_f32_n0_n0(float addrspace(1)* %out) nounwind { ; FUNC-LABEL: @fmax_var_immediate_f32 ; SI: v_max_f32_e64 {{v[0-9]+}}, 2.0, {{s[0-9]+}} + +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT:T[0-9]+\.[XYZW]]] +; EG-NOT: MAX_DX10 +; EG: MOV {{.*}}[[OUT]], literal.{{[xy]}} define void @fmax_var_immediate_f32(float addrspace(1)* %out, float %a) nounwind { %val = call float @llvm.maxnum.f32(float %a, float 2.0) #0 store float %val, float addrspace(1)* %out, align 4 @@ -165,6 +247,9 @@ define void @fmax_var_immediate_f32(float addrspace(1)* %out, float %a) nounwind ; FUNC-LABEL: @fmax_immediate_var_f32 ; SI: v_max_f32_e64 {{v[0-9]+}}, 2.0, {{s[0-9]+}} + +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT:T[0-9]+\.[XYZW]]] +; EG: MAX_DX10 {{.*}}[[OUT]], {{KC0\[[0-9]\].[XYZW]}}, literal.{{[xy]}} define void @fmax_immediate_var_f32(float addrspace(1)* %out, float %a) nounwind { %val = call float @llvm.maxnum.f32(float 2.0, float %a) #0 store float %val, float addrspace(1)* %out, align 4 @@ -174,6 +259,9 @@ define void @fmax_immediate_var_f32(float addrspace(1)* %out, float %a) nounwind ; FUNC-LABEL: @fmax_var_literal_f32 ; SI: v_mov_b32_e32 [[REG:v[0-9]+]], 0x42c60000 ; SI: v_max_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}, [[REG]] + +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT:T[0-9]+\.[XYZW]]] +; EG: MAX_DX10 {{.*}}[[OUT]], {{KC0\[[0-9]\].[XYZW]}}, literal.{{[xy]}} define void @fmax_var_literal_f32(float addrspace(1)* %out, float %a) nounwind { %val = call float @llvm.maxnum.f32(float %a, float 99.0) #0 store float %val, float addrspace(1)* %out, align 4 @@ -183,6 +271,9 @@ define void @fmax_var_literal_f32(float addrspace(1)* %out, float %a) nounwind { ; FUNC-LABEL: @fmax_literal_var_f32 ; SI: v_mov_b32_e32 [[REG:v[0-9]+]], 0x42c60000 ; SI: v_max_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}, [[REG]] + +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT:T[0-9]+\.[XYZW]]] +; EG: MAX_DX10 {{.*}}[[OUT]], {{KC0\[[0-9]\].[XYZW]}}, literal.{{[xy]}} define void @fmax_literal_var_f32(float addrspace(1)* %out, float %a) nounwind { %val = call float @llvm.maxnum.f32(float 99.0, float %a) #0 store float %val, float addrspace(1)* %out, align 4 diff --git a/llvm/test/CodeGen/R600/fminnum.ll b/llvm/test/CodeGen/R600/fminnum.ll index 6b93b830033b..92666fea096c 100644 --- a/llvm/test/CodeGen/R600/fminnum.ll +++ b/llvm/test/CodeGen/R600/fminnum.ll @@ -1,5 +1,6 @@ ; RUN: llc -march=amdgcn -mcpu=SI < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s ; RUN: llc -march=amdgcn -mcpu=tonga < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s +; RUN: llc -march=r600 -mcpu=cypress < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s declare float @llvm.minnum.f32(float, float) #0 declare <2 x float> @llvm.minnum.v2f32(<2 x float>, <2 x float>) #0 @@ -9,6 +10,9 @@ declare <16 x float> @llvm.minnum.v16f32(<16 x float>, <16 x float>) #0 ; FUNC-LABEL: @test_fmin_f32 ; SI: v_min_f32_e32 + +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT:T[0-9]+\.[XYZW]]] +; EG: MIN_DX10 {{.*}}[[OUT]] define void @test_fmin_f32(float addrspace(1)* %out, float %a, float %b) nounwind { %val = call float @llvm.minnum.f32(float %a, float %b) #0 store float %val, float addrspace(1)* %out, align 4 @@ -18,6 +22,10 @@ define void @test_fmin_f32(float addrspace(1)* %out, float %a, float %b) nounwin ; FUNC-LABEL: @test_fmin_v2f32 ; SI: v_min_f32_e32 ; SI: v_min_f32_e32 + +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT:T[0-9]+]] +; EG: MIN_DX10 {{.*}}[[OUT]] +; EG: MIN_DX10 {{.*}}[[OUT]] define void @test_fmin_v2f32(<2 x float> addrspace(1)* %out, <2 x float> %a, <2 x float> %b) nounwind { %val = call <2 x float> @llvm.minnum.v2f32(<2 x float> %a, <2 x float> %b) #0 store <2 x float> %val, <2 x float> addrspace(1)* %out, align 8 @@ -29,6 +37,12 @@ define void @test_fmin_v2f32(<2 x float> addrspace(1)* %out, <2 x float> %a, <2 ; SI: v_min_f32_e32 ; SI: v_min_f32_e32 ; SI: v_min_f32_e32 + +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT:T[0-9]+]] +; EG: MIN_DX10 {{.*}}[[OUT]] +; EG: MIN_DX10 {{.*}}[[OUT]] +; EG: MIN_DX10 {{.*}}[[OUT]] +; EG: MIN_DX10 {{.*}}[[OUT]] define void @test_fmin_v4f32(<4 x float> addrspace(1)* %out, <4 x float> %a, <4 x float> %b) nounwind { %val = call <4 x float> @llvm.minnum.v4f32(<4 x float> %a, <4 x float> %b) #0 store <4 x float> %val, <4 x float> addrspace(1)* %out, align 16 @@ -44,6 +58,17 @@ define void @test_fmin_v4f32(<4 x float> addrspace(1)* %out, <4 x float> %a, <4 ; SI: v_min_f32_e32 ; SI: v_min_f32_e32 ; SI: v_min_f32_e32 + +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT1:T[0-9]+]] +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT2:T[0-9]+]] +; EG-DAG: MIN_DX10 {{.*}}[[OUT1]].X +; EG-DAG: MIN_DX10 {{.*}}[[OUT1]].Y +; EG-DAG: MIN_DX10 {{.*}}[[OUT1]].Z +; EG-DAG: MIN_DX10 {{.*}}[[OUT1]].W +; EG-DAG: MIN_DX10 {{.*}}[[OUT2]].X +; EG-DAG: MIN_DX10 {{.*}}[[OUT2]].Y +; EG-DAG: MIN_DX10 {{.*}}[[OUT2]].Z +; EG-DAG: MIN_DX10 {{.*}}[[OUT2]].W define void @test_fmin_v8f32(<8 x float> addrspace(1)* %out, <8 x float> %a, <8 x float> %b) nounwind { %val = call <8 x float> @llvm.minnum.v8f32(<8 x float> %a, <8 x float> %b) #0 store <8 x float> %val, <8 x float> addrspace(1)* %out, align 32 @@ -67,6 +92,27 @@ define void @test_fmin_v8f32(<8 x float> addrspace(1)* %out, <8 x float> %a, <8 ; SI: v_min_f32_e32 ; SI: v_min_f32_e32 ; SI: v_min_f32_e32 + +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT1:T[0-9]+]] +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT2:T[0-9]+]] +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT3:T[0-9]+]] +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT4:T[0-9]+]] +; EG-DAG: MIN_DX10 {{.*}}[[OUT1]].X +; EG-DAG: MIN_DX10 {{.*}}[[OUT1]].Y +; EG-DAG: MIN_DX10 {{.*}}[[OUT1]].Z +; EG-DAG: MIN_DX10 {{.*}}[[OUT1]].W +; EG-DAG: MIN_DX10 {{.*}}[[OUT2]].X +; EG-DAG: MIN_DX10 {{.*}}[[OUT2]].Y +; EG-DAG: MIN_DX10 {{.*}}[[OUT2]].Z +; EG-DAG: MIN_DX10 {{.*}}[[OUT2]].W +; EG-DAG: MIN_DX10 {{.*}}[[OUT3]].X +; EG-DAG: MIN_DX10 {{.*}}[[OUT3]].Y +; EG-DAG: MIN_DX10 {{.*}}[[OUT3]].Z +; EG-DAG: MIN_DX10 {{.*}}[[OUT3]].W +; EG-DAG: MIN_DX10 {{.*}}[[OUT4]].X +; EG-DAG: MIN_DX10 {{.*}}[[OUT4]].Y +; EG-DAG: MIN_DX10 {{.*}}[[OUT4]].Z +; EG-DAG: MIN_DX10 {{.*}}[[OUT4]].W define void @test_fmin_v16f32(<16 x float> addrspace(1)* %out, <16 x float> %a, <16 x float> %b) nounwind { %val = call <16 x float> @llvm.minnum.v16f32(<16 x float> %a, <16 x float> %b) #0 store <16 x float> %val, <16 x float> addrspace(1)* %out, align 64 @@ -77,6 +123,10 @@ define void @test_fmin_v16f32(<16 x float> addrspace(1)* %out, <16 x float> %a, ; SI-NOT: v_min_f32_e32 ; SI: v_mov_b32_e32 [[REG:v[0-9]+]], 1.0 ; SI: buffer_store_dword [[REG]] + +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT:T[0-9]+\.[XYZW]]] +; EG-NOT: MIN_DX10 +; EG: MOV {{.*}}[[OUT]], literal.{{[xy]}} define void @constant_fold_fmin_f32(float addrspace(1)* %out) nounwind { %val = call float @llvm.minnum.f32(float 1.0, float 2.0) #0 store float %val, float addrspace(1)* %out, align 4 @@ -87,6 +137,11 @@ define void @constant_fold_fmin_f32(float addrspace(1)* %out) nounwind { ; SI-NOT: v_min_f32_e32 ; SI: v_mov_b32_e32 [[REG:v[0-9]+]], 0x7fc00000 ; SI: buffer_store_dword [[REG]] + +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT:T[0-9]+\.[XYZW]]] +; EG-NOT: MIN_DX10 +; EG: MOV {{.*}}[[OUT]], literal.{{[xy]}} +; EG: 2143289344(nan) define void @constant_fold_fmin_f32_nan_nan(float addrspace(1)* %out) nounwind { %val = call float @llvm.minnum.f32(float 0x7FF8000000000000, float 0x7FF8000000000000) #0 store float %val, float addrspace(1)* %out, align 4 @@ -97,6 +152,10 @@ define void @constant_fold_fmin_f32_nan_nan(float addrspace(1)* %out) nounwind { ; SI-NOT: v_min_f32_e32 ; SI: v_mov_b32_e32 [[REG:v[0-9]+]], 1.0 ; SI: buffer_store_dword [[REG]] + +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT:T[0-9]+\.[XYZW]]] +; EG-NOT: MIN_DX10 +; EG: MOV {{.*}}[[OUT]], literal.{{[xy]}} define void @constant_fold_fmin_f32_val_nan(float addrspace(1)* %out) nounwind { %val = call float @llvm.minnum.f32(float 1.0, float 0x7FF8000000000000) #0 store float %val, float addrspace(1)* %out, align 4 @@ -107,6 +166,10 @@ define void @constant_fold_fmin_f32_val_nan(float addrspace(1)* %out) nounwind { ; SI-NOT: v_min_f32_e32 ; SI: v_mov_b32_e32 [[REG:v[0-9]+]], 1.0 ; SI: buffer_store_dword [[REG]] + +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT:T[0-9]+\.[XYZW]]] +; EG-NOT: MIN_DX10 +; EG: MOV {{.*}}[[OUT]], literal.{{[xy]}} define void @constant_fold_fmin_f32_nan_val(float addrspace(1)* %out) nounwind { %val = call float @llvm.minnum.f32(float 0x7FF8000000000000, float 1.0) #0 store float %val, float addrspace(1)* %out, align 4 @@ -117,6 +180,10 @@ define void @constant_fold_fmin_f32_nan_val(float addrspace(1)* %out) nounwind { ; SI-NOT: v_min_f32_e32 ; SI: v_mov_b32_e32 [[REG:v[0-9]+]], 0 ; SI: buffer_store_dword [[REG]] + +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT:T[0-9]+\.[XYZW]]] +; EG-NOT: MIN_DX10 +; EG: MOV {{.*}}[[OUT]], literal.{{[xy]}} define void @constant_fold_fmin_f32_p0_p0(float addrspace(1)* %out) nounwind { %val = call float @llvm.minnum.f32(float 0.0, float 0.0) #0 store float %val, float addrspace(1)* %out, align 4 @@ -127,6 +194,10 @@ define void @constant_fold_fmin_f32_p0_p0(float addrspace(1)* %out) nounwind { ; SI-NOT: v_min_f32_e32 ; SI: v_mov_b32_e32 [[REG:v[0-9]+]], 0 ; SI: buffer_store_dword [[REG]] + +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT:T[0-9]+\.[XYZW]]] +; EG-NOT: MIN_DX10 +; EG: MOV {{.*}}[[OUT]], literal.{{[xy]}} define void @constant_fold_fmin_f32_p0_n0(float addrspace(1)* %out) nounwind { %val = call float @llvm.minnum.f32(float 0.0, float -0.0) #0 store float %val, float addrspace(1)* %out, align 4 @@ -137,6 +208,10 @@ define void @constant_fold_fmin_f32_p0_n0(float addrspace(1)* %out) nounwind { ; SI-NOT: v_min_f32_e32 ; SI: v_mov_b32_e32 [[REG:v[0-9]+]], 0x80000000 ; SI: buffer_store_dword [[REG]] + +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT:T[0-9]+\.[XYZW]]] +; EG-NOT: MIN_DX10 +; EG: MOV {{.*}}[[OUT]], literal.{{[xy]}} define void @constant_fold_fmin_f32_n0_p0(float addrspace(1)* %out) nounwind { %val = call float @llvm.minnum.f32(float -0.0, float 0.0) #0 store float %val, float addrspace(1)* %out, align 4 @@ -147,6 +222,10 @@ define void @constant_fold_fmin_f32_n0_p0(float addrspace(1)* %out) nounwind { ; SI-NOT: v_min_f32_e32 ; SI: v_mov_b32_e32 [[REG:v[0-9]+]], 0x80000000 ; SI: buffer_store_dword [[REG]] + +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT:T[0-9]+\.[XYZW]]] +; EG-NOT: MIN_DX10 +; EG: MOV {{.*}}[[OUT]], literal.{{[xy]}} define void @constant_fold_fmin_f32_n0_n0(float addrspace(1)* %out) nounwind { %val = call float @llvm.minnum.f32(float -0.0, float -0.0) #0 store float %val, float addrspace(1)* %out, align 4 @@ -155,6 +234,9 @@ define void @constant_fold_fmin_f32_n0_n0(float addrspace(1)* %out) nounwind { ; FUNC-LABEL: @fmin_var_immediate_f32 ; SI: v_min_f32_e64 {{v[0-9]+}}, 2.0, {{s[0-9]+}} + +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT:T[0-9]+\.[XYZW]]] +; EG: MIN_DX10 {{.*}}[[OUT]], {{KC0\[[0-9]\].[XYZW]}}, literal.{{[xy]}} define void @fmin_var_immediate_f32(float addrspace(1)* %out, float %a) nounwind { %val = call float @llvm.minnum.f32(float %a, float 2.0) #0 store float %val, float addrspace(1)* %out, align 4 @@ -163,6 +245,9 @@ define void @fmin_var_immediate_f32(float addrspace(1)* %out, float %a) nounwind ; FUNC-LABEL: @fmin_immediate_var_f32 ; SI: v_min_f32_e64 {{v[0-9]+}}, 2.0, {{s[0-9]+}} + +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT:T[0-9]+\.[XYZW]]] +; EG: MIN_DX10 {{.*}}[[OUT]], {{KC0\[[0-9]\].[XYZW]}}, literal.{{[xy]}} define void @fmin_immediate_var_f32(float addrspace(1)* %out, float %a) nounwind { %val = call float @llvm.minnum.f32(float 2.0, float %a) #0 store float %val, float addrspace(1)* %out, align 4 @@ -172,6 +257,9 @@ define void @fmin_immediate_var_f32(float addrspace(1)* %out, float %a) nounwind ; FUNC-LABEL: @fmin_var_literal_f32 ; SI: v_mov_b32_e32 [[REG:v[0-9]+]], 0x42c60000 ; SI: v_min_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}, [[REG]] + +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT:T[0-9]+\.[XYZW]]] +; EG: MIN_DX10 {{.*}}[[OUT]], {{KC0\[[0-9]\].[XYZW]}}, literal.{{[xy]}} define void @fmin_var_literal_f32(float addrspace(1)* %out, float %a) nounwind { %val = call float @llvm.minnum.f32(float %a, float 99.0) #0 store float %val, float addrspace(1)* %out, align 4 @@ -181,6 +269,9 @@ define void @fmin_var_literal_f32(float addrspace(1)* %out, float %a) nounwind { ; FUNC-LABEL: @fmin_literal_var_f32 ; SI: v_mov_b32_e32 [[REG:v[0-9]+]], 0x42c60000 ; SI: v_min_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}, [[REG]] + +; EG: MEM_RAT_CACHELESS STORE_RAW [[OUT:T[0-9]+\.[XYZW]]] +; EG: MIN_DX10 {{.*}}[[OUT]], {{KC0\[[0-9]\].[XYZW]}}, literal.{{[xy]}} define void @fmin_literal_var_f32(float addrspace(1)* %out, float %a) nounwind { %val = call float @llvm.minnum.f32(float 99.0, float %a) #0 store float %val, float addrspace(1)* %out, align 4