search for: mov2

Displaying 7 results from an estimated 7 matches for "mov2".

Did you mean: mov
2017 Dec 20
2
[PATCH] gm107/ir: use lane 0 for manual textureGrad handling
...ers/nouveau/codegen/nv50_ir_lowering_gm107.cpp +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_gm107.cpp @@ -95,18 +95,15 @@ GM107LegalizeSSA::visit(Instruction *i) bool GM107LoweringPass::handleManualTXD(TexInstruction *i) { - static const uint8_t qOps[4][2] = - { - { QUADOP(MOV2, ADD, MOV2, ADD), QUADOP(MOV2, MOV2, ADD, ADD) }, // l0 - { QUADOP(SUBR, MOV2, SUBR, MOV2), QUADOP(MOV2, MOV2, ADD, ADD) }, // l1 - { QUADOP(MOV2, ADD, MOV2, ADD), QUADOP(SUBR, SUBR, MOV2, MOV2) }, // l2 - { QUADOP(SUBR, MOV2, SUBR, MOV2), QUADOP(SUBR, SUBR, MOV2, MOV2) }, // l...
2017 Dec 20
0
[PATCH] gm107/ir: use lane 0 for manual textureGrad handling
...07.cpp > +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_gm107.cpp > @@ -95,18 +95,15 @@ GM107LegalizeSSA::visit(Instruction *i) > bool > GM107LoweringPass::handleManualTXD(TexInstruction *i) > { > - static const uint8_t qOps[4][2] = > - { > - { QUADOP(MOV2, ADD, MOV2, ADD), QUADOP(MOV2, MOV2, ADD, ADD) }, // l0 > - { QUADOP(SUBR, MOV2, SUBR, MOV2), QUADOP(MOV2, MOV2, ADD, ADD) }, // l1 > - { QUADOP(MOV2, ADD, MOV2, ADD), QUADOP(SUBR, SUBR, MOV2, MOV2) }, // l2 > - { QUADOP(SUBR, MOV2, SUBR, MOV2), QUADOP(SUBR, SUBR, MOV2...
2012 Dec 04
5
[LLVMdev] Proposal: Adding aligned instruction bundle support to MC
...ode was encountered with an argument > 0, which is the power of 2 to which the bundle size is equal), single instructions and groups of instructions between .bundle_lock and .bundle_unlock directives cannot cross a bundle boundary. For example, consider the following: .bundle_align_mode 4 mov1 mov2 mov3 Assuming that each of the mov instructions is 7 bytes long and mov1 is aligned to a 16-byte boundary, two bytes of NOP padding will be inserted between mov2 and mov3 to make sure that mov3 does not cross a 16-byte bundle boundary. A slightly modified example: .bundle_align_mode 4 mov1 .bund...
2012 Dec 05
0
[LLVMdev] Proposal: Adding aligned instruction bundle support to MC
..., which is the > power of 2 to which the bundle size is equal), single > instructions and groups of instructions between .bundle_lock and > .bundle_unlock directives cannot cross a bundle boundary. > > For example, consider the following: > > .bundle_align_mode 4 > mov1 > mov2 > mov3 > > Assuming that each of the mov instructions is 7 bytes long and mov1 is > aligned to a 16-byte boundary, two bytes of NOP padding will be > inserted between mov2 and mov3 to make sure that mov3 does not cross a > 16-byte bundle boundary. > > A slightly modified exa...
2012 Dec 05
2
[LLVMdev] Proposal: Adding aligned instruction bundle support to MC
...o which the bundle size is equal), single >> instructions and groups of instructions between .bundle_lock and >> .bundle_unlock directives cannot cross a bundle boundary. >> >> For example, consider the following: >> >> .bundle_align_mode 4 >> mov1 >> mov2 >> mov3 >> >> Assuming that each of the mov instructions is 7 bytes long and mov1 is >> aligned to a 16-byte boundary, two bytes of NOP padding will be >> inserted between mov2 and mov3 to make sure that mov3 does not cross a >> 16-byte bundle boundary. >>...
2012 Dec 06
0
[LLVMdev] Proposal: Adding aligned instruction bundle support to MC
...which is the > power of 2 to which the bundle size is equal), single > instructions and groups of instructions between .bundle_lock and > .bundle_unlock directives cannot cross a bundle boundary. > > For example, consider the following: > > .bundle_align_mode 4 > mov1 > mov2 > mov3 > > Assuming that each of the mov instructions is 7 bytes long and mov1 is > aligned to a 16-byte boundary, two bytes of NOP padding will be > inserted between mov2 and mov3 to make sure that mov3 does not cross a > 16-byte bundle boundary. > > A slightly modified e...
2012 Dec 06
0
[LLVMdev] Proposal: Adding aligned instruction bundle support to MC
...e > >> instructions and groups of instructions between .bundle_lock and > >> .bundle_unlock directives cannot cross a bundle boundary. > >> > >> For example, consider the following: > >> > >> .bundle_align_mode 4 > >> mov1 > >> mov2 > >> mov3 > >> > >> Assuming that each of the mov instructions is 7 bytes long and mov1 is > >> aligned to a 16-byte boundary, two bytes of NOP padding will be > >> inserted between mov2 and mov3 to make sure that mov3 does not cross a > >> 16-b...