OpenHarmony/third_party_mesa3d
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

aco: implement nir_op_f2i64/nir_op_f2u64 on GFX6

Browse Source 
V_TRUNC_F64 and V_FLOOR_F64 needs to be lowered on GFX6.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3477>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3477>
This commit is contained in:
Samuel Pitoiset
2020-01-21 09:13:46 +01:00
parent 4d92601715
commit 8d5203dad2
1 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
src/amd/compiler/aco_instruction_selection.cpp
View File

@@ -2068,10 +2068,10 @@ void visit_alu_instr(isel_context *ctx, nir_alu_instr *instr)
} else if (instr->src[0].src.ssa->bit_size == 64) {
Temp vec = bld.pseudo(aco_opcode::p_create_vector, bld.def(s2), Operand(0u), Operand(0x3df00000u));
Temp trunc = bld.vop1(aco_opcode::v_trunc_f64, bld.def(v2), src);
Temp trunc = emit_trunc_f64(ctx, bld, bld.def(v2), src);
Temp mul = bld.vop3(aco_opcode::v_mul_f64, bld.def(v2), trunc, vec);
vec = bld.pseudo(aco_opcode::p_create_vector, bld.def(s2), Operand(0u), Operand(0xc1f00000u));
Temp floor = bld.vop1(aco_opcode::v_floor_f64, bld.def(v2), mul);
Temp floor = emit_floor_f64(ctx, bld, bld.def(v2), mul);
Temp fma = bld.vop3(aco_opcode::v_fma_f64, bld.def(v2), floor, vec, trunc);
Temp lower = bld.vop1(aco_opcode::v_cvt_u32_f64, bld.def(v1), fma);
Temp upper = bld.vop1(aco_opcode::v_cvt_i32_f64, bld.def(v1), floor);
@@ -2137,10 +2137,10 @@ void visit_alu_instr(isel_context *ctx, nir_alu_instr *instr)
} else if (instr->src[0].src.ssa->bit_size == 64) {
Temp vec = bld.pseudo(aco_opcode::p_create_vector, bld.def(s2), Operand(0u), Operand(0x3df00000u));
Temp trunc = bld.vop1(aco_opcode::v_trunc_f64, bld.def(v2), src);
Temp trunc = emit_trunc_f64(ctx, bld, bld.def(v2), src);
Temp mul = bld.vop3(aco_opcode::v_mul_f64, bld.def(v2), trunc, vec);
vec = bld.pseudo(aco_opcode::p_create_vector, bld.def(s2), Operand(0u), Operand(0xc1f00000u));
Temp floor = bld.vop1(aco_opcode::v_floor_f64, bld.def(v2), mul);
Temp floor = emit_floor_f64(ctx, bld, bld.def(v2), mul);
Temp fma = bld.vop3(aco_opcode::v_fma_f64, bld.def(v2), floor, vec, trunc);
Temp lower = bld.vop1(aco_opcode::v_cvt_u32_f64, bld.def(v1), fma);
Temp upper = bld.vop1(aco_opcode::v_cvt_u32_f64, bld.def(v1), floor);