From: Matt Turner Date: Wed, 13 Jan 2016 19:08:37 +0000 (-0800) Subject: nir: Handle =32 case in bitfield_insert lowering. X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=15640ee77ae601cba33cbbc72256e55e03a363e5;p=mesa.git nir: Handle =32 case in bitfield_insert lowering. The OpenGL specifications for bitfieldInsert() says: The result will be undefined if or is negative, or if the sum of and is greater than the number of bits used to store the operand. Therefore passing bits=32, offset=0 is legal and defined in GLSL. But the earlier SM5 bfi opcode is specified to accept a bitfield width ranging from 0-31. As such, Intel and AMD instructions read only the low 5 bits of the width operand, making them not able to implement the GLSL-specified behavior directly. This commit fixes the lowering of bitfield_insert to handle the trivial case of = 32 as bitfieldInsert: bits > 31 ? insert : bfi(bfm(bits, offset), insert, base) Fixes: ES31-CTS.shader_bitfield_operation.bitfieldInsert.uint_2 ES31-CTS.shader_bitfield_operation.bitfieldInsert.uvec4_3 Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=92595 Reviewed-by: Connor Abbott Tested-by: Marta Lofstedt --- diff --git a/src/glsl/nir/nir_opcodes.py b/src/glsl/nir/nir_opcodes.py index 1c65def691a..3e43438ff67 100644 --- a/src/glsl/nir/nir_opcodes.py +++ b/src/glsl/nir/nir_opcodes.py @@ -558,6 +558,7 @@ triop("fcsel", tfloat, "(src0 != 0.0f) ? src1 : src2") opcode("bcsel", 0, tuint, [0, 0, 0], [tbool, tuint, tuint], "", "src0 ? src1 : src2") +# SM5 bfi assembly triop("bfi", tuint, """ unsigned mask = src0, insert = src1, base = src2; if (mask == 0) { diff --git a/src/glsl/nir/nir_opt_algebraic.py b/src/glsl/nir/nir_opt_algebraic.py index 1eb044a5a20..0d31e39ea8e 100644 --- a/src/glsl/nir/nir_opt_algebraic.py +++ b/src/glsl/nir/nir_opt_algebraic.py @@ -225,9 +225,13 @@ optimizations = [ # Misc. lowering (('fmod', a, b), ('fsub', a, ('fmul', b, ('ffloor', ('fdiv', a, b)))), 'options->lower_fmod'), - (('bitfield_insert', a, b, c, d), ('bfi', ('bfm', d, c), b, a), 'options->lower_bitfield_insert'), (('uadd_carry', a, b), ('b2i', ('ult', ('iadd', a, b), a)), 'options->lower_uadd_carry'), (('usub_borrow', a, b), ('b2i', ('ult', a, b)), 'options->lower_usub_borrow'), + + (('bitfield_insert', 'base', 'insert', 'offset', 'bits'), + ('bcsel', ('ilt', 31, 'bits'), 'insert', + ('bfi', ('bfm', 'bits', 'offset'), 'insert', 'base')), + 'options->lower_bitfield_insert'), ] # Add optimizations to handle the case where the result of a ternary is