ef0680ba54
This has no functional effect since these source fields are unused, but it can avoid some conservative stalls due to these instructions looking like they read from an SGPR, since 0 is the encoding for s0. Using 0x80 is more benign since it is the encoding for inline immediate 0. Fixes: SWDEV-574953
29 lines
1.4 KiB
LLVM
29 lines
1.4 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: llc -mtriple=amdgcn -mcpu=gfx1250 -show-mc-encoding < %s | FileCheck -check-prefixes=GFX1250 %s
|
|
|
|
define i16 @cvt_pk_bf8_f16_v(ptr addrspace(1) %out) {
|
|
; GFX1250-LABEL: cvt_pk_bf8_f16_v:
|
|
; GFX1250: ; %bb.0:
|
|
; GFX1250-NEXT: s_wait_loadcnt_dscnt 0x0 ; encoding: [0x00,0x00,0xc8,0xbf]
|
|
; GFX1250-NEXT: s_wait_kmcnt 0x0 ; encoding: [0x00,0x00,0xc7,0xbf]
|
|
; GFX1250-NEXT: v_cvt_pk_bf8_f16 v0, 0x38003800 ; encoding: [0x00,0x00,0x73,0xd7,0xff,0x00,0x01,0x02,0x00,0x38,0x00,0x38]
|
|
; GFX1250-NEXT: s_set_pc_i64 s[30:31] ; encoding: [0x1e,0x48,0x80,0xbe]
|
|
%cvt = tail call i16 @llvm.amdgcn.cvt.pk.bf8.f16(<2 x half> <half 0xH3800, half 0xH3800>)
|
|
ret i16 %cvt
|
|
}
|
|
|
|
; GFX1250: codeLenInByte = 24
|
|
|
|
define i16 @cvt_pk_fp8_f16_v(ptr addrspace(1) %out) {
|
|
; GFX1250-LABEL: cvt_pk_fp8_f16_v:
|
|
; GFX1250: ; %bb.0:
|
|
; GFX1250-NEXT: s_wait_loadcnt_dscnt 0x0 ; encoding: [0x00,0x00,0xc8,0xbf]
|
|
; GFX1250-NEXT: s_wait_kmcnt 0x0 ; encoding: [0x00,0x00,0xc7,0xbf]
|
|
; GFX1250-NEXT: v_cvt_pk_fp8_f16 v0, 0x3800 ; encoding: [0x00,0x00,0x72,0xd7,0xff,0x00,0x01,0x02,0x00,0x38,0x00,0x00]
|
|
; GFX1250-NEXT: s_set_pc_i64 s[30:31] ; encoding: [0x1e,0x48,0x80,0xbe]
|
|
%cvt = tail call i16 @llvm.amdgcn.cvt.pk.fp8.f16(<2 x half> <half 0xH3800, half 0xH0>)
|
|
ret i16 %cvt
|
|
}
|
|
|
|
; GFX1250: codeLenInByte = 24
|