Re: [Beignet] [PATCH] GBE: Support storing/loading pointers to/from private array

Yes, I forget one minor case. That is when pointer operand is same pointer origin, I don't add it to pointerOrigMap. I have sent V2 to fix the issue. Thanks! Ruiling -Original Message- From: Zhigang Gong [mailto:zhigang.g...@linux.intel.com] Sent: Monday, June 01, 2015 10:01 AM To:

Re: [Beignet] [PATCH V2] GBE: Support storing/loading pointers to/from private array

LGTM, pushed. Thanks, Zhigang Gong. On Tue, Jun 02, 2015 at 03:26:28PM +0800, Ruiling Song wrote: The idea is create two additional array for holding pointer-base and bti. v2: When pointer operand is exactly the pointer origin, we do not insert into pointerOrigMap. so, don't directly find

Re: [Beignet] [PATCH] GBE: fix one potential register spilling bug.

Thanks for the careful review comment. Just fixed it and pushed. On Tue, Jun 02, 2015 at 06:29:41AM +, Song, Ruiling wrote: if ((regSize == ctx.getSimdWidth()/8 * GEN_REG_SIZE family == ir::FAMILY_DWORD) - || (regSize == 2 * ctx.getSimdWidth()/8 * GEN_REG_SIZE

[Beignet] [PATCH V2] GBE: Support storing/loading pointers to/from private array

The idea is create two additional array for holding pointer-base and bti. v2: When pointer operand is exactly the pointer origin, we do not insert into pointerOrigMap. so, don't directly find in pointerOrigMap, instead find BtiMap first, which contains all of the pointer origins. Signed-off-by:

Re: [Beignet] [PATCH] GBE: fix one potential register spilling bug.

if ((regSize == ctx.getSimdWidth()/8 * GEN_REG_SIZE family == ir::FAMILY_DWORD) - || (regSize == 2 * ctx.getSimdWidth()/8 * GEN_REG_SIZE family == ir::FAMILY_QWORD)) { + || (regSize == 2 * ctx.getSimdWidth()/8 * GEN_REG_SIZE family == ir::FAMILY_QWORD) +