[llvm] [AMDGPU]: Add regbank legalize rules for amdgcn exp2 intrinsics (PR #191953)

[via llvm-commits]

github-actions[bot] wrote:

<!--PREMERGE ADVISOR COMMENT: Windows-->
# :window: Windows x64 Test Results

* 133438 tests passed
* 3094 tests skipped
* 1 test failed

## Failed Tests
(click on a test name to see its output)

### LLVM
<details>
<summary>LLVM.CodeGen/AMDGPU/pseudo-scalar-transcendental-regbank.ll</summary>

```
Exit Code: 1

Command Output (stdout):
--
# RUN: at line 2
c:\_work\llvm-project\llvm-project\build\bin\llc.exe -global-isel=1 -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx1100 < C:\_work\llvm-project\llvm-project\llvm\test\CodeGen\AMDGPU\pseudo-scalar-transcendental-regbank.ll | c:\_work\llvm-project\llvm-project\build\bin\filecheck.exe -check-prefixes=GFX11 C:\_work\llvm-project\llvm-project\llvm\test\CodeGen\AMDGPU\pseudo-scalar-transcendental-regbank.ll
# executed command: 'c:\_work\llvm-project\llvm-project\build\bin\llc.exe' -global-isel=1 -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx1100
# note: command had no output on stdout or stderr
# executed command: 'c:\_work\llvm-project\llvm-project\build\bin\filecheck.exe' -check-prefixes=GFX11 'C:\_work\llvm-project\llvm-project\llvm\test\CodeGen\AMDGPU\pseudo-scalar-transcendental-regbank.ll'
# note: command had no output on stdout or stderr
# RUN: at line 3
c:\_work\llvm-project\llvm-project\build\bin\llc.exe -global-isel=1 -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx1200 < C:\_work\llvm-project\llvm-project\llvm\test\CodeGen\AMDGPU\pseudo-scalar-transcendental-regbank.ll | c:\_work\llvm-project\llvm-project\build\bin\filecheck.exe -check-prefixes=GFX12 C:\_work\llvm-project\llvm-project\llvm\test\CodeGen\AMDGPU\pseudo-scalar-transcendental-regbank.ll
# executed command: 'c:\_work\llvm-project\llvm-project\build\bin\llc.exe' -global-isel=1 -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx1200
# note: command had no output on stdout or stderr
# executed command: 'c:\_work\llvm-project\llvm-project\build\bin\filecheck.exe' -check-prefixes=GFX12 'C:\_work\llvm-project\llvm-project\llvm\test\CodeGen\AMDGPU\pseudo-scalar-transcendental-regbank.ll'
# .---command stderr------------
# | C:\_work\llvm-project\llvm-project\llvm\test\CodeGen\AMDGPU\pseudo-scalar-transcendental-regbank.ll:13:15: error: GFX12-NEXT: expected string not found in input
# | ; GFX12-NEXT: v_s_exp_f16 s0, s0
# |               ^
# | <stdin>:17:9: note: scanning from here
# | ; %bb.0:
# |         ^
# | <stdin>:18:2: note: possible intended match here
# |  v_exp_f16_e32 v0.l, s0
# |  ^
# | 
# | Input file: <stdin>
# | Check file: C:\_work\llvm-project\llvm-project\llvm\test\CodeGen\AMDGPU\pseudo-scalar-transcendental-regbank.ll
# | 
# | -dump-input=help explains the following input dump.
# | 
# | Input was:
# | <<<<<<
# |            .
# |            .
# |            .
# |           12:  .text 
# |           13:  .globl exp2_f16_uniform ; -- Begin function exp2_f16_uniform 
# |           14:  .p2align 8 
# |           15:  .type exp2_f16_uniform, at function 
# |           16: exp2_f16_uniform: ; @exp2_f16_uniform 
# |           17: ; %bb.0: 
# | next:13'0             X error: no match found
# |           18:  v_exp_f16_e32 v0.l, s0 
# | next:13'0     ~~~~~~~~~~~~~~~~~~~~~~~~
# | next:13'1      ?                       possible intended match
# |           19:  ; return to shader part epilog 
# | next:13'0     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# |           20: .Lfunc_end0: 
# | next:13'0     ~~~~~~~~~~~~~
# |           21:  .size exp2_f16_uniform, .Lfunc_end0-exp2_f16_uniform 
# | next:13'0     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# |           22:  ; -- End function 
# | next:13'0     ~~~~~~~~~~~~~~~~~~~
# |           23:  .set .Lexp2_f16_uniform.num_vgpr, 1 
# | next:13'0     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# |            .
# |            .
# |            .
# | >>>>>>
# `-----------------------------
# error: command failed with exit status: 1

--

```
</details>

If these failures are unrelated to your changes (for example tests are broken or flaky at HEAD), please open an issue at https://github.com/llvm/llvm-project/issues and add the `infrastructure` label.

https://github.com/llvm/llvm-project/pull/191953