maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/MC/AMDGPU
History
Tim Renouf 72800f0436 [AMDGPU] implemented pal metadata 
Summary:
For the amdpal OS type:

We write an AMDGPU_PAL_METADATA record in the .note section in the ELF
(or as an assembler directive). It contains key=value pairs of 32 bit
ints. It is a merge of metadata from codegen of the shaders, and
metadata provided by the frontend as _amdgpu_pal_metadata IR metadata.
Where both sources have a key=value with the same key, the two values
are ORed together.

This .note record is part of the amdpal ABI and will be documented in
docs/AMDGPUUsage.rst in a future commit.

Eventually the amdpal OS type will stop generating the .AMDGPU.config
section once the frontend has safely moved over to using the .note
records above instead of .AMDGPU.config.

Reviewers: arsenm, nhaehnle, dstuttard

Subscribers: kzhuravl, wdng, yaxunl, llvm-commits, t-tye

Differential Revision: https://reviews.llvm.org/D37753

llvm-svn: 314829
 		2017-10-03 19:03:52 +00:00
..
regression AMDGPU: Remove -mcpu=SI 2017-08-07 18:30:35 +00:00
add-sub-no-carry.s AMDGPU: Add encoding for carryless add/sub instructions 2017-07-20 17:42:47 +00:00
buffer_wbinv1l_vol_vi.s
…
code-object-metadata-kernel-args.s Fix ODR violations due to abuse of LLVM_YAML_IS_(FLOW_)?SEQUENCE_VECTOR 2017-06-30 20:56:57 +00:00
code-object-metadata-kernel-attrs.s Fix ODR violations due to abuse of LLVM_YAML_IS_(FLOW_)?SEQUENCE_VECTOR 2017-06-30 20:56:57 +00:00
code-object-metadata-kernel-code-props.s [AMDGPU] Emit kernel debug properties as code object metadata 2017-03-22 23:10:46 +00:00
code-object-metadata-kernel-debug-props.s [AMDGPU] Emit kernel debug properties as code object metadata 2017-03-22 23:10:46 +00:00
code-object-metadata-unknown-key.s [AMDGPU] Rename Kind to ValueKind in metadata to be consistent 2017-03-24 18:43:15 +00:00
ds-err.s AMDGPU: Remove -mcpu=SI 2017-08-07 18:30:35 +00:00
ds-gfx9.s AMDGPU: Add ds_{read|write}_addtid_b32 definitions 2017-09-01 18:38:02 +00:00
ds.s [AMDGPU][MC] New syntax for ds_swizzle_b32 offset 2017-05-31 16:26:47 +00:00
exp-err.s AMDGPU: Assembler support for exp 2016-12-05 20:42:41 +00:00
exp.s [AMDGPU][MC] Fixed bugs in export instruction 2017-05-19 13:36:09 +00:00
expressions.s [AMDGPU][MC] Enabled expressions as operands 2017-08-04 13:55:24 +00:00
flat-gfx9.s AMDGPU: Add most d16 load/store instruction definitions 2017-09-01 18:36:06 +00:00
flat-global.s AMDGPU: Add most d16 load/store instruction definitions 2017-09-01 18:36:06 +00:00
flat-scratch-instructions.s AMDGPU: Add most d16 load/store instruction definitions 2017-09-01 18:36:06 +00:00
flat-scratch.s
…
flat.s AMDGPU: Remove -mcpu=SI 2017-08-07 18:30:35 +00:00
gfx7_asm_all.s [AMDGPU][mc][tests][NFC] Bulk ISA tests: Massive update. Add Gfx9 dasm tests. 2017-06-19 15:55:02 +00:00
gfx8_asm_all.s [AMDGPU][mc][tests][NFC] Bulk ISA tests: Massive update. Add Gfx9 dasm tests. 2017-06-19 15:55:02 +00:00
gfx9_asm_all.s AMDGPU: Correct operand types for v_mad_mix* 2017-08-30 22:18:40 +00:00
hsa-exp.s [AMDGPU] Change amd_kernel_code_t's minor version to 1 2017-02-28 17:17:52 +00:00
hsa-text.s
…
hsa.s [AMDGPU] Do not emit isa info as code object metadata 2017-03-22 23:27:09 +00:00
hsa_code_object_isa_args.s [AMDGPU][mc] Enable absolute expressions in .hsa_code_object_isa directive 2016-12-29 15:41:52 +00:00
labels-branch.s
…
lit.local.cfg
…
literal16-err.s AMDGPU: Fix handling of 16-bit immediates 2016-12-10 00:39:12 +00:00
literal16.s [AMDGPU][MC] Corrected v_madak/madmk to avoid printing "_e32" in disassembler output 2017-05-10 13:00:28 +00:00
literals.s [AMDGPU][MC] Fix for Bugs 28200, 28202 + LIT tests 2017-03-20 14:50:35 +00:00
literalv216-err.s AMDGPU: Add VOP3P instruction format 2017-02-27 18:49:11 +00:00
literalv216.s AMDGPU: Add VOP3P instruction format 2017-02-27 18:49:11 +00:00
macro-examples.s
…
max-branch-distance.s
…
mimg.s AMDGPU: Remove -mcpu=SI 2017-08-07 18:30:35 +00:00
mtbuf.s [AMDGPU] Add intrinsics for tbuffer load and store 2017-06-22 16:29:22 +00:00
mubuf-gfx9.s AMDGPU: Add most d16 load/store instruction definitions 2017-09-01 18:36:06 +00:00
mubuf.s
…
out-of-range-registers.s
…
pal.s [AMDGPU] implemented pal metadata 2017-10-03 19:03:52 +00:00
reg-syntax-extra.s AMDGPU: Remove -mcpu=SI 2017-08-07 18:30:35 +00:00
reloc.s
…
smem-err.s AMDGPU: Disallow exec as SMEM instruction operand 2016-11-29 19:39:53 +00:00
smem.s AMDGPU: Allow TBA, TMA, TTMP* registers with SMEM instructions 2016-12-09 17:49:11 +00:00
smrd-err.s AMDGPU: Add definitions for scalar store instructions 2016-10-28 21:55:15 +00:00
smrd.s AMDGPU: Remove -mcpu=SI 2017-08-07 18:30:35 +00:00
sop1-err.s
…
sop1.s [AMDGPU][MC] Corrected src0 size for s_cbranch_join 2017-04-12 12:40:19 +00:00
sop2-err.s [AMDGPU][MC] Enabled constants for src operands of s_cbranch_g_fork 2017-04-14 11:52:26 +00:00
sop2.s AMDGPU: Remove -mcpu=SI 2017-08-07 18:30:35 +00:00
sopc-err.s
…
sopc.s
…
sopk-err.s [AMDGPU][MC] Added check for truncation of SOPK imm operand 2017-04-26 15:34:19 +00:00
sopk.s AMDGPU: Remove -mcpu=SI 2017-08-07 18:30:35 +00:00
sopp-err.s AMDGPU: Remove -mcpu=SI 2017-08-07 18:30:35 +00:00
sopp-gfx9.s AMDGPU: Merge initial gfx9 support 2017-02-18 18:29:53 +00:00
sopp.s [AMDGPU][MC] Added arg checks for vmcnt, expcnt, lgkmcnt helpers 2017-04-26 17:55:50 +00:00
sym_kernel_scope.s [AMDGPU][llvm-mc] Predefined symbols to access register counts (.kernel.{v|s}gpr_count) 2016-12-27 16:00:11 +00:00
sym_option.s AMDGPU: Remove -mcpu=SI 2017-08-07 18:30:35 +00:00
trap.s AMDGPU: Remove -mcpu=SI 2017-08-07 18:30:35 +00:00
vintrp-err.s AMDGPU: Assembler support for vintrp instructions 2016-12-15 20:40:20 +00:00
vintrp.s AMDGPU: Assembler support for vintrp instructions 2016-12-15 20:40:20 +00:00
vop-err.s [AMDGPU][MC] Fix for Bug 30829 + LIT tests 2017-03-03 14:31:06 +00:00
vop1-gfx9-err.s AMDGPU: Add definition for v_swap_b32 2017-02-28 21:09:04 +00:00
vop1-gfx9.s AMDGPU: Add definition for v_swap_b32 2017-02-28 21:09:04 +00:00
vop1.s AMDGPU: Remove -mcpu=SI 2017-08-07 18:30:35 +00:00
vop2-err.s AMDGPU: Remove -mcpu=SI 2017-08-07 18:30:35 +00:00
vop2.s AMDGPU: fix bad test exposed by r314522 2017-09-29 16:07:05 +00:00
vop3-convert.s AMDGPU: Remove -mcpu=SI 2017-08-07 18:30:35 +00:00
vop3-errs.s AMDGPU: Remove -mcpu=SI 2017-08-07 18:30:35 +00:00
vop3-gfx9.s [AMDGPU][MC][GFX9] Added op_sel support for v_mad_*16, v_fma_f16, v_div_fixup_f16 2017-08-16 15:16:32 +00:00
vop3-modifiers-err.s [AMDGPU][MC] Fix for Bugs 28200, 28202 + LIT tests 2017-03-20 14:50:35 +00:00
vop3-modifiers.s [AMDGPU][MC] Fix for Bug 28207 + LIT tests 2017-03-27 15:57:17 +00:00
vop3-vop1-nosrc.s AMDGPU: Remove -mcpu=SI 2017-08-07 18:30:35 +00:00
vop3.s [AMDGPU][MC][GFX9] Added integer clamping support for VOP3 opcodes 2017-08-16 13:51:56 +00:00
vop3p-err.s [AMDGPU][MC] Enabled expressions as operands 2017-08-04 13:55:24 +00:00
vop3p.s AMDGPU: Fix encoding of op_sel for mad_mix* opcodes 2017-09-20 19:09:28 +00:00
vop_dpp.s AMDGPU: Remove -mcpu=SI 2017-08-07 18:30:35 +00:00
vop_dpp_expr.s [AMDGPU] DPP: add support for GFX9 2017-04-27 15:42:38 +00:00
vop_sdwa.s AMDGPU: Remove -mcpu=SI 2017-08-07 18:30:35 +00:00
vopc-errs.s AMDGPU: Remove -mcpu=SI 2017-08-07 18:30:35 +00:00
vopc-vi.s AMDGPU: Fix missing 16-bit cmpx instructions 2016-12-22 16:27:14 +00:00
vopc.s AMDGPU: Remove -mcpu=SI 2017-08-07 18:30:35 +00:00