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

AMDGPU: Select strict_fadd

This commit is contained in:
Matt Arsenault 2020-05-23 10:41:40 -04:00
parent 5c990d6994
commit ae26c064ce
6 changed files with 407 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
llvm/lib/Target/AMDGPU/VOP2Instructions.td
View File

@ -466,7 +466,7 @@ defm V_CNDMASK_B32 : VOP2eInst <"v_cndmask_b32", VOP2e_I32_I32_I32_I1>;
def V_MADMK_F32 : VOP2_Pseudo <"v_madmk_f32", VOP_MADMK_F32, []>;
let isCommutable = 1 in {
defm V_ADD_F32 : VOP2Inst <"v_add_f32", VOP_F32_F32_F32, fadd>;
defm V_ADD_F32 : VOP2Inst <"v_add_f32", VOP_F32_F32_F32, any_fadd>;
defm V_SUB_F32 : VOP2Inst <"v_sub_f32", VOP_F32_F32_F32, fsub>;
defm V_SUBREV_F32 : VOP2Inst <"v_subrev_f32", VOP_F32_F32_F32, null_frag, "v_sub_f32">;
defm V_MUL_LEGACY_F32 : VOP2Inst <"v_mul_legacy_f32", VOP_F32_F32_F32, AMDGPUfmul_legacy>;
@ -630,7 +630,7 @@ defm V_ASHRREV_I16 : VOP2Inst <"v_ashrrev_i16", VOP_I16_I16_I16, ashr_rev>;
let isCommutable = 1 in {
let FPDPRounding = 1 in {
defm V_ADD_F16 : VOP2Inst <"v_add_f16", VOP_F16_F16_F16, fadd>;
defm V_ADD_F16 : VOP2Inst <"v_add_f16", VOP_F16_F16_F16, any_fadd>;
defm V_SUB_F16 : VOP2Inst <"v_sub_f16", VOP_F16_F16_F16, fsub>;
defm V_SUBREV_F16 : VOP2Inst <"v_subrev_f16", VOP_F16_F16_F16, null_frag, "v_sub_f16">;
defm V_MUL_F16 : VOP2Inst <"v_mul_f16", VOP_F16_F16_F16, fmul>;

2
llvm/lib/Target/AMDGPU/VOP3Instructions.td
View File

@ -304,7 +304,7 @@ def V_LERP_U8 : VOP3Inst <"v_lerp_u8", VOP3_Profile<VOP_I32_I32_I32_I32>, int_am
let SchedRW = [WriteDoubleAdd] in {
let FPDPRounding = 1 in {
def V_FMA_F64 : VOP3Inst <"v_fma_f64", VOP3_Profile<VOP_F64_F64_F64_F64>, fma>;
def V_ADD_F64 : VOP3Inst <"v_add_f64", VOP3_Profile<VOP_F64_F64_F64>, fadd, 1>;
def V_ADD_F64 : VOP3Inst <"v_add_f64", VOP3_Profile<VOP_F64_F64_F64>, any_fadd, 1>;
def V_MUL_F64 : VOP3Inst <"v_mul_f64", VOP3_Profile<VOP_F64_F64_F64>, fmul, 1>;
} // End FPDPRounding = 1
def V_MIN_F64 : VOP3Inst <"v_min_f64", VOP3_Profile<VOP_F64_F64_F64>, fminnum_like, 1>;

2
llvm/lib/Target/AMDGPU/VOP3PInstructions.td
View File

@ -53,7 +53,7 @@ def V_PK_MAD_U16 : VOP3PInst<"v_pk_mad_u16", VOP3_Profile<VOP_V2I16_V2I16_V2I16_
let FPDPRounding = 1 in {
def V_PK_FMA_F16 : VOP3PInst<"v_pk_fma_f16", VOP3_Profile<VOP_V2F16_V2F16_V2F16_V2F16>, fma>;
def V_PK_ADD_F16 : VOP3PInst<"v_pk_add_f16", VOP3_Profile<VOP_V2F16_V2F16_V2F16>, fadd>;
def V_PK_ADD_F16 : VOP3PInst<"v_pk_add_f16", VOP3_Profile<VOP_V2F16_V2F16_V2F16>, any_fadd>;
def V_PK_MUL_F16 : VOP3PInst<"v_pk_mul_f16", VOP3_Profile<VOP_V2F16_V2F16_V2F16>, fmul>;
} // End FPDPRounding = 1
def V_PK_MAX_F16 : VOP3PInst<"v_pk_max_f16", VOP3_Profile<VOP_V2F16_V2F16_V2F16>, fmaxnum_like>;

178
llvm/test/CodeGen/AMDGPU/strict_fadd.f16.ll Normal file
View File

@ -0,0 +1,178 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx900 < %s | FileCheck -check-prefixes=GCN,GFX9 %s
; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=fiji < %s | FileCheck -check-prefixes=GCN,GFX8 %s
; FIXME: promotion not handled without f16 insts
define half @v_constained_fadd_f16_fpexcept_strict(half %x, half %y) #0 {
; GCN-LABEL: v_constained_fadd_f16_fpexcept_strict:
; GCN: ; %bb.0:
; GCN-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GCN-NEXT: v_add_f16_e32 v0, v0, v1
; GCN-NEXT: s_setpc_b64 s[30:31]
%val = call half @llvm.experimental.constrained.fadd.f16(half %x, half %y, metadata !"round.tonearest", metadata !"fpexcept.strict")
ret half %val
}
define half @v_constained_fadd_f16_fpexcept_ignore(half %x, half %y) #0 {
; GCN-LABEL: v_constained_fadd_f16_fpexcept_ignore:
; GCN: ; %bb.0:
; GCN-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GCN-NEXT: v_add_f16_e32 v0, v0, v1
; GCN-NEXT: s_setpc_b64 s[30:31]
%val = call half @llvm.experimental.constrained.fadd.f16(half %x, half %y, metadata !"round.tonearest", metadata !"fpexcept.ignore")
ret half %val
}
define half @v_constained_fadd_f16_fpexcept_maytrap(half %x, half %y) #0 {
; GCN-LABEL: v_constained_fadd_f16_fpexcept_maytrap:
; GCN: ; %bb.0:
; GCN-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GCN-NEXT: v_add_f16_e32 v0, v0, v1
; GCN-NEXT: s_setpc_b64 s[30:31]
%val = call half @llvm.experimental.constrained.fadd.f16(half %x, half %y, metadata !"round.tonearest", metadata !"fpexcept.maytrap")
ret half %val
}
define <2 x half> @v_constained_fadd_v2f16_fpexcept_strict(<2 x half> %x, <2 x half> %y) #0 {
; GFX9-LABEL: v_constained_fadd_v2f16_fpexcept_strict:
; GFX9: ; %bb.0:
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT: v_pk_add_f16 v0, v0, v1
; GFX9-NEXT: s_setpc_b64 s[30:31]
;
; GFX8-LABEL: v_constained_fadd_v2f16_fpexcept_strict:
; GFX8: ; %bb.0:
; GFX8-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX8-NEXT: v_add_f16_sdwa v2, v0, v1 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
; GFX8-NEXT: v_add_f16_e32 v0, v0, v1
; GFX8-NEXT: v_or_b32_sdwa v0, v0, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0 src1_sel:DWORD
; GFX8-NEXT: s_setpc_b64 s[30:31]
%val = call <2 x half> @llvm.experimental.constrained.fadd.v2f16(<2 x half> %x, <2 x half> %y, metadata !"round.tonearest", metadata !"fpexcept.strict")
ret <2 x half> %val
}
define <2 x half> @v_constained_fadd_v2f16_fpexcept_ignore(<2 x half> %x, <2 x half> %y) #0 {
; GFX9-LABEL: v_constained_fadd_v2f16_fpexcept_ignore:
; GFX9: ; %bb.0:
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT: v_pk_add_f16 v0, v0, v1
; GFX9-NEXT: s_setpc_b64 s[30:31]
;
; GFX8-LABEL: v_constained_fadd_v2f16_fpexcept_ignore:
; GFX8: ; %bb.0:
; GFX8-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX8-NEXT: v_add_f16_sdwa v2, v0, v1 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
; GFX8-NEXT: v_add_f16_e32 v0, v0, v1
; GFX8-NEXT: v_or_b32_sdwa v0, v0, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0 src1_sel:DWORD
; GFX8-NEXT: s_setpc_b64 s[30:31]
%val = call <2 x half> @llvm.experimental.constrained.fadd.v2f16(<2 x half> %x, <2 x half> %y, metadata !"round.tonearest", metadata !"fpexcept.ignore")
ret <2 x half> %val
}
define <2 x half> @v_constained_fadd_v2f16_fpexcept_maytrap(<2 x half> %x, <2 x half> %y) #0 {
; GFX9-LABEL: v_constained_fadd_v2f16_fpexcept_maytrap:
; GFX9: ; %bb.0:
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT: v_pk_add_f16 v0, v0, v1
; GFX9-NEXT: s_setpc_b64 s[30:31]
;
; GFX8-LABEL: v_constained_fadd_v2f16_fpexcept_maytrap:
; GFX8: ; %bb.0:
; GFX8-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX8-NEXT: v_add_f16_sdwa v2, v0, v1 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
; GFX8-NEXT: v_add_f16_e32 v0, v0, v1
; GFX8-NEXT: v_or_b32_sdwa v0, v0, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0 src1_sel:DWORD
; GFX8-NEXT: s_setpc_b64 s[30:31]
%val = call <2 x half> @llvm.experimental.constrained.fadd.v2f16(<2 x half> %x, <2 x half> %y, metadata !"round.tonearest", metadata !"fpexcept.maytrap")
ret <2 x half> %val
}
define <3 x half> @v_constained_fadd_v3f16_fpexcept_strict(<3 x half> %x, <3 x half> %y) #0 {
; GFX9-LABEL: v_constained_fadd_v3f16_fpexcept_strict:
; GFX9: ; %bb.0:
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT: v_pk_add_f16 v0, v0, v2
; GFX9-NEXT: v_add_f16_e32 v1, v1, v3
; GFX9-NEXT: s_setpc_b64 s[30:31]
;
; GFX8-LABEL: v_constained_fadd_v3f16_fpexcept_strict:
; GFX8: ; %bb.0:
; GFX8-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX8-NEXT: v_add_f16_sdwa v4, v0, v2 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
; GFX8-NEXT: v_add_f16_e32 v0, v0, v2
; GFX8-NEXT: v_or_b32_sdwa v0, v0, v4 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0 src1_sel:DWORD
; GFX8-NEXT: v_add_f16_e32 v1, v1, v3
; GFX8-NEXT: s_setpc_b64 s[30:31]
%val = call <3 x half> @llvm.experimental.constrained.fadd.v3f16(<3 x half> %x, <3 x half> %y, metadata !"round.tonearest", metadata !"fpexcept.strict")
ret <3 x half> %val
}
; FIXME: Scalarized
define <4 x half> @v_constained_fadd_v4f16_fpexcept_strict(<4 x half> %x, <4 x half> %y) #0 {
; GFX9-LABEL: v_constained_fadd_v4f16_fpexcept_strict:
; GFX9: ; %bb.0:
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT: v_add_f16_sdwa v4, v1, v3 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
; GFX9-NEXT: v_add_f16_sdwa v5, v0, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
; GFX9-NEXT: v_add_f16_e32 v0, v0, v2
; GFX9-NEXT: v_mov_b32_e32 v2, 0xffff
; GFX9-NEXT: v_add_f16_e32 v1, v1, v3
; GFX9-NEXT: v_and_b32_e32 v0, v2, v0
; GFX9-NEXT: v_and_b32_e32 v1, v2, v1
; GFX9-NEXT: v_lshl_or_b32 v0, v5, 16, v0
; GFX9-NEXT: v_lshl_or_b32 v1, v4, 16, v1
; GFX9-NEXT: s_setpc_b64 s[30:31]
;
; GFX8-LABEL: v_constained_fadd_v4f16_fpexcept_strict:
; GFX8: ; %bb.0:
; GFX8-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX8-NEXT: v_add_f16_sdwa v4, v1, v3 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
; GFX8-NEXT: v_add_f16_e32 v1, v1, v3
; GFX8-NEXT: v_add_f16_sdwa v5, v0, v2 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
; GFX8-NEXT: v_add_f16_e32 v0, v0, v2
; GFX8-NEXT: v_or_b32_sdwa v0, v0, v5 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0 src1_sel:DWORD
; GFX8-NEXT: v_or_b32_sdwa v1, v1, v4 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0 src1_sel:DWORD
; GFX8-NEXT: s_setpc_b64 s[30:31]
%val = call <4 x half> @llvm.experimental.constrained.fadd.v4f16(<4 x half> %x, <4 x half> %y, metadata !"round.tonearest", metadata !"fpexcept.strict")
ret <4 x half> %val
}
define amdgpu_ps half @s_constained_fadd_f16_fpexcept_strict(half inreg %x, half inreg %y) #0 {
; GCN-LABEL: s_constained_fadd_f16_fpexcept_strict:
; GCN: ; %bb.0:
; GCN-NEXT: v_mov_b32_e32 v0, s3
; GCN-NEXT: v_add_f16_e32 v0, s2, v0
; GCN-NEXT: ; return to shader part epilog
%val = call half @llvm.experimental.constrained.fadd.f16(half %x, half %y, metadata !"round.tonearest", metadata !"fpexcept.strict")
ret half %val
}
define amdgpu_ps <2 x half> @s_constained_fadd_v2f16_fpexcept_strict(<2 x half> inreg %x, <2 x half> inreg %y) #0 {
; GFX9-LABEL: s_constained_fadd_v2f16_fpexcept_strict:
; GFX9: ; %bb.0:
; GFX9-NEXT: v_mov_b32_e32 v0, s3
; GFX9-NEXT: v_pk_add_f16 v0, s2, v0
; GFX9-NEXT: ; return to shader part epilog
;
; GFX8-LABEL: s_constained_fadd_v2f16_fpexcept_strict:
; GFX8: ; %bb.0:
; GFX8-NEXT: s_lshr_b32 s0, s3, 16
; GFX8-NEXT: s_lshr_b32 s1, s2, 16
; GFX8-NEXT: v_mov_b32_e32 v0, s0
; GFX8-NEXT: v_mov_b32_e32 v1, s1
; GFX8-NEXT: v_add_f16_sdwa v0, v1, v0 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD
; GFX8-NEXT: v_mov_b32_e32 v1, s3
; GFX8-NEXT: v_add_f16_e32 v1, s2, v1
; GFX8-NEXT: v_or_b32_sdwa v0, v1, v0 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0 src1_sel:DWORD
; GFX8-NEXT: ; return to shader part epilog
%val = call <2 x half> @llvm.experimental.constrained.fadd.v2f16(<2 x half> %x, <2 x half> %y, metadata !"round.tonearest", metadata !"fpexcept.strict")
ret <2 x half> %val
}
declare half @llvm.experimental.constrained.fadd.f16(half, half, metadata, metadata) #1
declare <2 x half> @llvm.experimental.constrained.fadd.v2f16(<2 x half>, <2 x half>, metadata, metadata) #1
declare <3 x half> @llvm.experimental.constrained.fadd.v3f16(<3 x half>, <3 x half>, metadata, metadata) #1
declare <4 x half> @llvm.experimental.constrained.fadd.v4f16(<4 x half>, <4 x half>, metadata, metadata) #1
attributes #0 = { strictfp }
attributes #1 = { inaccessiblememonly nounwind willreturn }

129
llvm/test/CodeGen/AMDGPU/strict_fadd.f32.ll Normal file
View File

@ -0,0 +1,129 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx900 < %s | FileCheck -check-prefix=GCN %s
define float @v_constained_fadd_f32_fpexcept_strict(float %x, float %y) #0 {
; GCN-LABEL: v_constained_fadd_f32_fpexcept_strict:
; GCN: ; %bb.0:
; GCN-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GCN-NEXT: v_add_f32_e32 v0, v0, v1
; GCN-NEXT: s_setpc_b64 s[30:31]
%val = call float @llvm.experimental.constrained.fadd.f32(float %x, float %y, metadata !"round.tonearest", metadata !"fpexcept.strict")
ret float %val
}
define float @v_constained_fadd_f32_fpexcept_ignore(float %x, float %y) #0 {
; GCN-LABEL: v_constained_fadd_f32_fpexcept_ignore:
; GCN: ; %bb.0:
; GCN-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GCN-NEXT: v_add_f32_e32 v0, v0, v1
; GCN-NEXT: s_setpc_b64 s[30:31]
%val = call float @llvm.experimental.constrained.fadd.f32(float %x, float %y, metadata !"round.tonearest", metadata !"fpexcept.ignore")
ret float %val
}
define float @v_constained_fadd_f32_fpexcept_maytrap(float %x, float %y) #0 {
; GCN-LABEL: v_constained_fadd_f32_fpexcept_maytrap:
; GCN: ; %bb.0:
; GCN-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GCN-NEXT: v_add_f32_e32 v0, v0, v1
; GCN-NEXT: s_setpc_b64 s[30:31]
%val = call float @llvm.experimental.constrained.fadd.f32(float %x, float %y, metadata !"round.tonearest", metadata !"fpexcept.maytrap")
ret float %val
}
define <2 x float> @v_constained_fadd_v2f32_fpexcept_strict(<2 x float> %x, <2 x float> %y) #0 {
; GCN-LABEL: v_constained_fadd_v2f32_fpexcept_strict:
; GCN: ; %bb.0:
; GCN-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GCN-NEXT: v_add_f32_e32 v0, v0, v2
; GCN-NEXT: v_add_f32_e32 v1, v1, v3
; GCN-NEXT: s_setpc_b64 s[30:31]
%val = call <2 x float> @llvm.experimental.constrained.fadd.v2f32(<2 x float> %x, <2 x float> %y, metadata !"round.tonearest", metadata !"fpexcept.strict")
ret <2 x float> %val
}
define <2 x float> @v_constained_fadd_v2f32_fpexcept_ignore(<2 x float> %x, <2 x float> %y) #0 {
; GCN-LABEL: v_constained_fadd_v2f32_fpexcept_ignore:
; GCN: ; %bb.0:
; GCN-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GCN-NEXT: v_add_f32_e32 v0, v0, v2
; GCN-NEXT: v_add_f32_e32 v1, v1, v3
; GCN-NEXT: s_setpc_b64 s[30:31]
%val = call <2 x float> @llvm.experimental.constrained.fadd.v2f32(<2 x float> %x, <2 x float> %y, metadata !"round.tonearest", metadata !"fpexcept.ignore")
ret <2 x float> %val
}
define <2 x float> @v_constained_fadd_v2f32_fpexcept_maytrap(<2 x float> %x, <2 x float> %y) #0 {
; GCN-LABEL: v_constained_fadd_v2f32_fpexcept_maytrap:
; GCN: ; %bb.0:
; GCN-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GCN-NEXT: v_add_f32_e32 v0, v0, v2
; GCN-NEXT: v_add_f32_e32 v1, v1, v3
; GCN-NEXT: s_setpc_b64 s[30:31]
%val = call <2 x float> @llvm.experimental.constrained.fadd.v2f32(<2 x float> %x, <2 x float> %y, metadata !"round.tonearest", metadata !"fpexcept.maytrap")
ret <2 x float> %val
}
define <3 x float> @v_constained_fadd_v3f32_fpexcept_strict(<3 x float> %x, <3 x float> %y) #0 {
; GCN-LABEL: v_constained_fadd_v3f32_fpexcept_strict:
; GCN: ; %bb.0:
; GCN-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GCN-NEXT: v_add_f32_e32 v0, v0, v3
; GCN-NEXT: v_add_f32_e32 v1, v1, v4
; GCN-NEXT: v_add_f32_e32 v2, v2, v5
; GCN-NEXT: s_setpc_b64 s[30:31]
%val = call <3 x float> @llvm.experimental.constrained.fadd.v3f32(<3 x float> %x, <3 x float> %y, metadata !"round.tonearest", metadata !"fpexcept.strict")
ret <3 x float> %val
}
define amdgpu_ps float @s_constained_fadd_f32_fpexcept_strict(float inreg %x, float inreg %y) #0 {
; GCN-LABEL: s_constained_fadd_f32_fpexcept_strict:
; GCN: ; %bb.0:
; GCN-NEXT: v_mov_b32_e32 v0, s3
; GCN-NEXT: v_add_f32_e32 v0, s2, v0
; GCN-NEXT: ; return to shader part epilog
%val = call float @llvm.experimental.constrained.fadd.f32(float %x, float %y, metadata !"round.tonearest", metadata !"fpexcept.strict")
ret float %val
}
define float @v_constained_fadd_f32_fpexcept_strict_fabs_lhs(float %x, float %y) #0 {
; GCN-LABEL: v_constained_fadd_f32_fpexcept_strict_fabs_lhs:
; GCN: ; %bb.0:
; GCN-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GCN-NEXT: v_add_f32_e64 v0, |v0|, v1
; GCN-NEXT: s_setpc_b64 s[30:31]
%fabs.x = call float @llvm.fabs.f32(float %x)
%val = call float @llvm.experimental.constrained.fadd.f32(float %fabs.x, float %y, metadata !"round.tonearest", metadata !"fpexcept.strict")
ret float %val
}
define float @v_constained_fadd_f32_fpexcept_strict_fabs_rhs(float %x, float %y) #0 {
; GCN-LABEL: v_constained_fadd_f32_fpexcept_strict_fabs_rhs:
; GCN: ; %bb.0:
; GCN-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GCN-NEXT: v_add_f32_e64 v0, v0, |v1|
; GCN-NEXT: s_setpc_b64 s[30:31]
%fabs.y = call float @llvm.fabs.f32(float %y)
%val = call float @llvm.experimental.constrained.fadd.f32(float %x, float %fabs.y, metadata !"round.tonearest", metadata !"fpexcept.strict")
ret float %val
}
define float @v_constained_fadd_f32_fpexcept_strict_fneg_fabs_lhs(float %x, float %y) #0 {
; GCN-LABEL: v_constained_fadd_f32_fpexcept_strict_fneg_fabs_lhs:
; GCN: ; %bb.0:
; GCN-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GCN-NEXT: v_add_f32_e64 v0, -|v0|, v1
; GCN-NEXT: s_setpc_b64 s[30:31]
%fabs.x = call float @llvm.fabs.f32(float %x)
%neg.fabs.x = fneg float %fabs.x
%val = call float @llvm.experimental.constrained.fadd.f32(float %neg.fabs.x, float %y, metadata !"round.tonearest", metadata !"fpexcept.strict")
ret float %val
}
declare float @llvm.fabs.f32(float) #1
declare float @llvm.experimental.constrained.fadd.f32(float, float, metadata, metadata) #1
declare <2 x float> @llvm.experimental.constrained.fadd.v2f32(<2 x float>, <2 x float>, metadata, metadata) #1
declare <3 x float> @llvm.experimental.constrained.fadd.v3f32(<3 x float>, <3 x float>, metadata, metadata) #1
attributes #0 = { strictfp }
attributes #1 = { inaccessiblememonly nounwind willreturn }

96
llvm/test/CodeGen/AMDGPU/strict_fadd.f64.ll Normal file
View File

@ -0,0 +1,96 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx900 < %s | FileCheck -check-prefix=GCN %s
define double @v_constained_fadd_f64_fpexcept_strict(double %x, double %y) #0 {
; GCN-LABEL: v_constained_fadd_f64_fpexcept_strict:
; GCN: ; %bb.0:
; GCN-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GCN-NEXT: v_add_f64 v[0:1], v[0:1], v[2:3]
; GCN-NEXT: s_setpc_b64 s[30:31]
%val = call double @llvm.experimental.constrained.fadd.f64(double %x, double %y, metadata !"round.tonearest", metadata !"fpexcept.strict")
ret double %val
}
define double @v_constained_fadd_f64_fpexcept_ignore(double %x, double %y) #0 {
; GCN-LABEL: v_constained_fadd_f64_fpexcept_ignore:
; GCN: ; %bb.0:
; GCN-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GCN-NEXT: v_add_f64 v[0:1], v[0:1], v[2:3]
; GCN-NEXT: s_setpc_b64 s[30:31]
%val = call double @llvm.experimental.constrained.fadd.f64(double %x, double %y, metadata !"round.tonearest", metadata !"fpexcept.ignore")
ret double %val
}
define double @v_constained_fadd_f64_fpexcept_maytrap(double %x, double %y) #0 {
; GCN-LABEL: v_constained_fadd_f64_fpexcept_maytrap:
; GCN: ; %bb.0:
; GCN-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GCN-NEXT: v_add_f64 v[0:1], v[0:1], v[2:3]
; GCN-NEXT: s_setpc_b64 s[30:31]
%val = call double @llvm.experimental.constrained.fadd.f64(double %x, double %y, metadata !"round.tonearest", metadata !"fpexcept.maytrap")
ret double %val
}
define <2 x double> @v_constained_fadd_v2f64_fpexcept_strict(<2 x double> %x, <2 x double> %y) #0 {
; GCN-LABEL: v_constained_fadd_v2f64_fpexcept_strict:
; GCN: ; %bb.0:
; GCN-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GCN-NEXT: v_add_f64 v[0:1], v[0:1], v[4:5]
; GCN-NEXT: v_add_f64 v[2:3], v[2:3], v[6:7]
; GCN-NEXT: s_setpc_b64 s[30:31]
%val = call <2 x double> @llvm.experimental.constrained.fadd.v2f64(<2 x double> %x, <2 x double> %y, metadata !"round.tonearest", metadata !"fpexcept.strict")
ret <2 x double> %val
}
define <2 x double> @v_constained_fadd_v2f64_fpexcept_ignore(<2 x double> %x, <2 x double> %y) #0 {
; GCN-LABEL: v_constained_fadd_v2f64_fpexcept_ignore:
; GCN: ; %bb.0:
; GCN-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GCN-NEXT: v_add_f64 v[0:1], v[0:1], v[4:5]
; GCN-NEXT: v_add_f64 v[2:3], v[2:3], v[6:7]
; GCN-NEXT: s_setpc_b64 s[30:31]
%val = call <2 x double> @llvm.experimental.constrained.fadd.v2f64(<2 x double> %x, <2 x double> %y, metadata !"round.tonearest", metadata !"fpexcept.ignore")
ret <2 x double> %val
}
define <2 x double> @v_constained_fadd_v2f64_fpexcept_maytrap(<2 x double> %x, <2 x double> %y) #0 {
; GCN-LABEL: v_constained_fadd_v2f64_fpexcept_maytrap:
; GCN: ; %bb.0:
; GCN-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GCN-NEXT: v_add_f64 v[0:1], v[0:1], v[4:5]
; GCN-NEXT: v_add_f64 v[2:3], v[2:3], v[6:7]
; GCN-NEXT: s_setpc_b64 s[30:31]
%val = call <2 x double> @llvm.experimental.constrained.fadd.v2f64(<2 x double> %x, <2 x double> %y, metadata !"round.tonearest", metadata !"fpexcept.maytrap")
ret <2 x double> %val
}
define <3 x double> @v_constained_fadd_v3f64_fpexcept_strict(<3 x double> %x, <3 x double> %y) #0 {
; GCN-LABEL: v_constained_fadd_v3f64_fpexcept_strict:
; GCN: ; %bb.0:
; GCN-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GCN-NEXT: v_add_f64 v[0:1], v[0:1], v[6:7]
; GCN-NEXT: v_add_f64 v[2:3], v[2:3], v[8:9]
; GCN-NEXT: v_add_f64 v[4:5], v[4:5], v[10:11]
; GCN-NEXT: s_setpc_b64 s[30:31]
%val = call <3 x double> @llvm.experimental.constrained.fadd.v3f64(<3 x double> %x, <3 x double> %y, metadata !"round.tonearest", metadata !"fpexcept.strict")
ret <3 x double> %val
}
define amdgpu_ps <2 x float> @s_constained_fadd_f64_fpexcept_strict(double inreg %x, double inreg %y) #0 {
; GCN-LABEL: s_constained_fadd_f64_fpexcept_strict:
; GCN: ; %bb.0:
; GCN-NEXT: v_mov_b32_e32 v0, s4
; GCN-NEXT: v_mov_b32_e32 v1, s5
; GCN-NEXT: v_add_f64 v[0:1], s[2:3], v[0:1]
; GCN-NEXT: ; return to shader part epilog
%val = call double @llvm.experimental.constrained.fadd.f64(double %x, double %y, metadata !"round.tonearest", metadata !"fpexcept.strict")
%cast = bitcast double %val to <2 x float>
ret <2 x float> %cast
}
declare double @llvm.experimental.constrained.fadd.f64(double, double, metadata, metadata) #1
declare <2 x double> @llvm.experimental.constrained.fadd.v2f64(<2 x double>, <2 x double>, metadata, metadata) #1
declare <3 x double> @llvm.experimental.constrained.fadd.v3f64(<3 x double>, <3 x double>, metadata, metadata) #1
attributes #0 = { strictfp }
attributes #1 = { inaccessiblememonly nounwind willreturn }