i965: Drop bogus F32TO16/F16TO32 instructions on Broadwell - use MOV.

Broadwell removed the F32TO16 and F16TO32 instructions.  However, it has
actual support for HF values, so they're actually just MOV.

Fixes vs-packHalf2x16 and vs-unpackHalf2x16 tests (both the ARB
extension and ES 3.0 variants).

v2: Emulate F32TO16's align16 zeroing bug, since Chad's front end code
    relies on it happening.  We can probably refactor this code to be
    better later.

Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Eric Anholt <eric@anholt.net>
This commit is contained in:
Kenneth Graunke 2014-01-29 14:16:27 -08:00
parent 3663bbe773
commit 850e372fc7
3 changed files with 6 additions and 6 deletions

View file

@ -920,10 +920,10 @@ gen8_fs_generator::generate_code(exec_list *instructions)
break;
case BRW_OPCODE_F32TO16:
F32TO16(dst, src[0]);
MOV(retype(dst, BRW_REGISTER_TYPE_HF), src[0]);
break;
case BRW_OPCODE_F16TO32:
F16TO32(dst, src[0]);
MOV(dst, retype(src[0], BRW_REGISTER_TYPE_HF));
break;
case BRW_OPCODE_CMP:

View file

@ -154,8 +154,6 @@ ALU2(ASR)
ALU3(BFE)
ALU2(BFI1)
ALU3(BFI2)
ALU1(F32TO16)
ALU1(F16TO32)
ALU1(BFREV)
ALU1(CBIT)
ALU2_ACCUMULATE(ADDC)

View file

@ -586,11 +586,13 @@ gen8_vec4_generator::generate_vec4_instruction(vec4_instruction *instruction,
break;
case BRW_OPCODE_F32TO16:
F32TO16(dst, src[0]);
/* Emulate the Gen7 zeroing bug. */
MOV(retype(dst, BRW_REGISTER_TYPE_UD), brw_imm_ud(0u));
MOV(retype(dst, BRW_REGISTER_TYPE_HF), src[0]);
break;
case BRW_OPCODE_F16TO32:
F16TO32(dst, src[0]);
MOV(dst, retype(src[0], BRW_REGISTER_TYPE_HF));
break;
case BRW_OPCODE_LRP: