Skip to content

[X86] Relax vbroadcast(vector load X) -> vbroadcast_load(X) to all types #128039

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Feb 21, 2025
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 1 addition & 3 deletions llvm/lib/Target/X86/X86ISelLowering.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -42087,9 +42087,7 @@ static SDValue combineTargetShuffle(SDValue N, const SDLoc &DL,
}

// vbroadcast(vector load X) -> vbroadcast_load
if ((SrcVT == MVT::v2f64 || SrcVT == MVT::v4f32 || SrcVT == MVT::v2i64 ||
SrcVT == MVT::v4i32) &&
Src.hasOneUse() && ISD::isNormalLoad(Src.getNode())) {
if (Src.hasOneUse() && ISD::isNormalLoad(Src.getNode())) {
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Does vNi16/f16 also work?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes, we have generic X86VBroadcastld16 patterns that will hit on any i16/f16/bf16 load (AVX2+) - and we shouldn't have introduced a X86ISD::VBROADCAST node on pre-AVX2 targets unless the equivalent X86ISD::VBROADCAST_LOAD is supported.

LoadSDNode *LN = cast<LoadSDNode>(Src);
// Unless the load is volatile or atomic.
if (LN->isSimple()) {
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -910,8 +910,8 @@ define void @vec256_i8_widen_to_i16_factor2_broadcast_to_v16i16_factor16(ptr %in
; AVX2-LABEL: vec256_i8_widen_to_i16_factor2_broadcast_to_v16i16_factor16:
; AVX2: # %bb.0:
; AVX2-NEXT: vmovdqa 32(%rdi), %ymm0
; AVX2-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[1,3,5,7,9,11,13,15,u,u,u,u,u,u,u,u,17,19,21,23,25,27,29,31,u,u,u,u,u,u,u,u]
; AVX2-NEXT: vpbroadcastb (%rdi), %ymm1
; AVX2-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[1,3,5,7,9,11,13,15,u,u,u,u,u,u,u,u,17,19,21,23,25,27,29,31,u,u,u,u,u,u,u,u]
; AVX2-NEXT: vpunpcklbw {{.*#+}} ymm0 = ymm1[0],ymm0[0],ymm1[1],ymm0[1],ymm1[2],ymm0[2],ymm1[3],ymm0[3],ymm1[4],ymm0[4],ymm1[5],ymm0[5],ymm1[6],ymm0[6],ymm1[7],ymm0[7],ymm1[16],ymm0[16],ymm1[17],ymm0[17],ymm1[18],ymm0[18],ymm1[19],ymm0[19],ymm1[20],ymm0[20],ymm1[21],ymm0[21],ymm1[22],ymm0[22],ymm1[23],ymm0[23]
; AVX2-NEXT: vpaddb (%rsi), %ymm0, %ymm0
; AVX2-NEXT: vmovdqa %ymm0, (%rdx)
Expand All @@ -920,32 +920,32 @@ define void @vec256_i8_widen_to_i16_factor2_broadcast_to_v16i16_factor16(ptr %in
;
; AVX512F-LABEL: vec256_i8_widen_to_i16_factor2_broadcast_to_v16i16_factor16:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vmovdqa 32(%rdi), %ymm0
; AVX512F-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[1,3,5,7,9,11,13,15,u,u,u,u,u,u,u,u,17,19,21,23,25,27,29,31,u,u,u,u,u,u,u,u]
; AVX512F-NEXT: vpbroadcastb (%rdi), %ymm1
; AVX512F-NEXT: vpunpcklbw {{.*#+}} ymm0 = ymm1[0],ymm0[0],ymm1[1],ymm0[1],ymm1[2],ymm0[2],ymm1[3],ymm0[3],ymm1[4],ymm0[4],ymm1[5],ymm0[5],ymm1[6],ymm0[6],ymm1[7],ymm0[7],ymm1[16],ymm0[16],ymm1[17],ymm0[17],ymm1[18],ymm0[18],ymm1[19],ymm0[19],ymm1[20],ymm0[20],ymm1[21],ymm0[21],ymm1[22],ymm0[22],ymm1[23],ymm0[23]
; AVX512F-NEXT: vpbroadcastb (%rdi), %ymm0
; AVX512F-NEXT: vmovdqa 32(%rdi), %ymm1
; AVX512F-NEXT: vpshufb {{.*#+}} ymm1 = ymm1[1,3,5,7,9,11,13,15,u,u,u,u,u,u,u,u,17,19,21,23,25,27,29,31,u,u,u,u,u,u,u,u]
; AVX512F-NEXT: vpunpcklbw {{.*#+}} ymm0 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[4],ymm1[4],ymm0[5],ymm1[5],ymm0[6],ymm1[6],ymm0[7],ymm1[7],ymm0[16],ymm1[16],ymm0[17],ymm1[17],ymm0[18],ymm1[18],ymm0[19],ymm1[19],ymm0[20],ymm1[20],ymm0[21],ymm1[21],ymm0[22],ymm1[22],ymm0[23],ymm1[23]
; AVX512F-NEXT: vpaddb (%rsi), %ymm0, %ymm0
; AVX512F-NEXT: vmovdqa %ymm0, (%rdx)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512DQ-LABEL: vec256_i8_widen_to_i16_factor2_broadcast_to_v16i16_factor16:
; AVX512DQ: # %bb.0:
; AVX512DQ-NEXT: vmovdqa 32(%rdi), %ymm0
; AVX512DQ-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[1,3,5,7,9,11,13,15,u,u,u,u,u,u,u,u,17,19,21,23,25,27,29,31,u,u,u,u,u,u,u,u]
; AVX512DQ-NEXT: vpbroadcastb (%rdi), %ymm1
; AVX512DQ-NEXT: vpunpcklbw {{.*#+}} ymm0 = ymm1[0],ymm0[0],ymm1[1],ymm0[1],ymm1[2],ymm0[2],ymm1[3],ymm0[3],ymm1[4],ymm0[4],ymm1[5],ymm0[5],ymm1[6],ymm0[6],ymm1[7],ymm0[7],ymm1[16],ymm0[16],ymm1[17],ymm0[17],ymm1[18],ymm0[18],ymm1[19],ymm0[19],ymm1[20],ymm0[20],ymm1[21],ymm0[21],ymm1[22],ymm0[22],ymm1[23],ymm0[23]
; AVX512DQ-NEXT: vpbroadcastb (%rdi), %ymm0
; AVX512DQ-NEXT: vmovdqa 32(%rdi), %ymm1
; AVX512DQ-NEXT: vpshufb {{.*#+}} ymm1 = ymm1[1,3,5,7,9,11,13,15,u,u,u,u,u,u,u,u,17,19,21,23,25,27,29,31,u,u,u,u,u,u,u,u]
; AVX512DQ-NEXT: vpunpcklbw {{.*#+}} ymm0 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[4],ymm1[4],ymm0[5],ymm1[5],ymm0[6],ymm1[6],ymm0[7],ymm1[7],ymm0[16],ymm1[16],ymm0[17],ymm1[17],ymm0[18],ymm1[18],ymm0[19],ymm1[19],ymm0[20],ymm1[20],ymm0[21],ymm1[21],ymm0[22],ymm1[22],ymm0[23],ymm1[23]
; AVX512DQ-NEXT: vpaddb (%rsi), %ymm0, %ymm0
; AVX512DQ-NEXT: vmovdqa %ymm0, (%rdx)
; AVX512DQ-NEXT: vzeroupper
; AVX512DQ-NEXT: retq
;
; AVX512BW-LABEL: vec256_i8_widen_to_i16_factor2_broadcast_to_v16i16_factor16:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vmovdqa 32(%rdi), %ymm0
; AVX512BW-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[1,3,5,7,9,11,13,15,u,u,u,u,u,u,u,u,17,19,21,23,25,27,29,31,u,u,u,u,u,u,u,u]
; AVX512BW-NEXT: vpbroadcastb (%rdi), %ymm1
; AVX512BW-NEXT: vpunpcklbw {{.*#+}} ymm0 = ymm1[0],ymm0[0],ymm1[1],ymm0[1],ymm1[2],ymm0[2],ymm1[3],ymm0[3],ymm1[4],ymm0[4],ymm1[5],ymm0[5],ymm1[6],ymm0[6],ymm1[7],ymm0[7],ymm1[16],ymm0[16],ymm1[17],ymm0[17],ymm1[18],ymm0[18],ymm1[19],ymm0[19],ymm1[20],ymm0[20],ymm1[21],ymm0[21],ymm1[22],ymm0[22],ymm1[23],ymm0[23]
; AVX512BW-NEXT: vpbroadcastb (%rdi), %ymm0
; AVX512BW-NEXT: vmovdqa 32(%rdi), %ymm1
; AVX512BW-NEXT: vpshufb {{.*#+}} ymm1 = ymm1[1,3,5,7,9,11,13,15,u,u,u,u,u,u,u,u,17,19,21,23,25,27,29,31,u,u,u,u,u,u,u,u]
; AVX512BW-NEXT: vpunpcklbw {{.*#+}} ymm0 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[4],ymm1[4],ymm0[5],ymm1[5],ymm0[6],ymm1[6],ymm0[7],ymm1[7],ymm0[16],ymm1[16],ymm0[17],ymm1[17],ymm0[18],ymm1[18],ymm0[19],ymm1[19],ymm0[20],ymm1[20],ymm0[21],ymm1[21],ymm0[22],ymm1[22],ymm0[23],ymm1[23]
; AVX512BW-NEXT: vpaddb (%rsi), %zmm0, %zmm0
; AVX512BW-NEXT: vmovdqa64 %zmm0, (%rdx)
; AVX512BW-NEXT: vzeroupper
Expand Down Expand Up @@ -1906,12 +1906,10 @@ define void @vec384_i8_widen_to_i16_factor2_broadcast_to_v24i16_factor24(ptr %in
; AVX512F-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[1,3,5,7,9,11,13,15,u,u,u,u,u,u,u,u]
; AVX512F-NEXT: vpbroadcastb (%rdi), %ymm1
; AVX512F-NEXT: vpunpcklbw {{.*#+}} ymm0 = ymm1[0],ymm0[0],ymm1[1],ymm0[1],ymm1[2],ymm0[2],ymm1[3],ymm0[3],ymm1[4],ymm0[4],ymm1[5],ymm0[5],ymm1[6],ymm0[6],ymm1[7],ymm0[7],ymm1[16],ymm0[16],ymm1[17],ymm0[17],ymm1[18],ymm0[18],ymm1[19],ymm0[19],ymm1[20],ymm0[20],ymm1[21],ymm0[21],ymm1[22],ymm0[22],ymm1[23],ymm0[23]
; AVX512F-NEXT: vpbroadcastb (%rdi), %ymm1
; AVX512F-NEXT: vinserti64x4 $1, %ymm1, %zmm1, %zmm1
; AVX512F-NEXT: vpaddb 32(%rsi), %ymm1, %ymm1
; AVX512F-NEXT: vpaddb (%rsi), %ymm0, %ymm0
; AVX512F-NEXT: vmovdqa %ymm0, (%rdx)
; AVX512F-NEXT: vpaddb 32(%rsi), %ymm1, %ymm1
; AVX512F-NEXT: vmovdqa %ymm1, 32(%rdx)
; AVX512F-NEXT: vmovdqa %ymm0, (%rdx)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
Expand All @@ -1921,12 +1919,10 @@ define void @vec384_i8_widen_to_i16_factor2_broadcast_to_v24i16_factor24(ptr %in
; AVX512DQ-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[1,3,5,7,9,11,13,15,u,u,u,u,u,u,u,u]
; AVX512DQ-NEXT: vpbroadcastb (%rdi), %ymm1
; AVX512DQ-NEXT: vpunpcklbw {{.*#+}} ymm0 = ymm1[0],ymm0[0],ymm1[1],ymm0[1],ymm1[2],ymm0[2],ymm1[3],ymm0[3],ymm1[4],ymm0[4],ymm1[5],ymm0[5],ymm1[6],ymm0[6],ymm1[7],ymm0[7],ymm1[16],ymm0[16],ymm1[17],ymm0[17],ymm1[18],ymm0[18],ymm1[19],ymm0[19],ymm1[20],ymm0[20],ymm1[21],ymm0[21],ymm1[22],ymm0[22],ymm1[23],ymm0[23]
; AVX512DQ-NEXT: vpbroadcastb (%rdi), %ymm1
; AVX512DQ-NEXT: vinserti64x4 $1, %ymm1, %zmm1, %zmm1
; AVX512DQ-NEXT: vpaddb 32(%rsi), %ymm1, %ymm1
; AVX512DQ-NEXT: vpaddb (%rsi), %ymm0, %ymm0
; AVX512DQ-NEXT: vmovdqa %ymm0, (%rdx)
; AVX512DQ-NEXT: vpaddb 32(%rsi), %ymm1, %ymm1
; AVX512DQ-NEXT: vmovdqa %ymm1, 32(%rdx)
; AVX512DQ-NEXT: vmovdqa %ymm0, (%rdx)
; AVX512DQ-NEXT: vzeroupper
; AVX512DQ-NEXT: retq
;
Expand All @@ -1936,7 +1932,6 @@ define void @vec384_i8_widen_to_i16_factor2_broadcast_to_v24i16_factor24(ptr %in
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[1,3,5,7,9,11,13,15,u,u,u,u,u,u,u,u]
; AVX512BW-NEXT: vpbroadcastb (%rdi), %ymm1
; AVX512BW-NEXT: vpunpcklbw {{.*#+}} ymm0 = ymm1[0],ymm0[0],ymm1[1],ymm0[1],ymm1[2],ymm0[2],ymm1[3],ymm0[3],ymm1[4],ymm0[4],ymm1[5],ymm0[5],ymm1[6],ymm0[6],ymm1[7],ymm0[7],ymm1[16],ymm0[16],ymm1[17],ymm0[17],ymm1[18],ymm0[18],ymm1[19],ymm0[19],ymm1[20],ymm0[20],ymm1[21],ymm0[21],ymm1[22],ymm0[22],ymm1[23],ymm0[23]
; AVX512BW-NEXT: vpbroadcastb (%rdi), %ymm1
; AVX512BW-NEXT: vinserti64x4 $1, %ymm1, %zmm0, %zmm0
; AVX512BW-NEXT: vpaddb (%rsi), %zmm0, %zmm0
; AVX512BW-NEXT: vmovdqa64 %zmm0, (%rdx)
Expand Down Expand Up @@ -2133,37 +2128,33 @@ define void @vec384_i8_widen_to_i32_factor4_broadcast_to_v12i32_factor12(ptr %in
; AVX512F: # %bb.0:
; AVX512F-NEXT: vmovdqa 48(%rdi), %xmm0
; AVX512F-NEXT: vpbroadcastb (%rdi), %ymm1
; AVX512F-NEXT: vpternlogd {{.*#+}} ymm1 = ymm1 ^ (mem & (ymm1 ^ ymm0))
; AVX512F-NEXT: vpbroadcastb (%rdi), %ymm0
; AVX512F-NEXT: vinserti64x4 $1, %ymm0, %zmm0, %zmm0
; AVX512F-NEXT: vpaddb 32(%rsi), %ymm0, %ymm0
; AVX512F-NEXT: vpaddb (%rsi), %ymm1, %ymm1
; AVX512F-NEXT: vmovdqa %ymm1, (%rdx)
; AVX512F-NEXT: vmovdqa %ymm0, 32(%rdx)
; AVX512F-NEXT: vpternlogd {{.*#+}} ymm0 = ymm1 ^ (mem & (ymm0 ^ ymm1))
; AVX512F-NEXT: vpaddb (%rsi), %ymm0, %ymm0
; AVX512F-NEXT: vpaddb 32(%rsi), %ymm1, %ymm1
; AVX512F-NEXT: vmovdqa %ymm1, 32(%rdx)
; AVX512F-NEXT: vmovdqa %ymm0, (%rdx)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512DQ-LABEL: vec384_i8_widen_to_i32_factor4_broadcast_to_v12i32_factor12:
; AVX512DQ: # %bb.0:
; AVX512DQ-NEXT: vmovdqa 48(%rdi), %xmm0
; AVX512DQ-NEXT: vpbroadcastb (%rdi), %ymm1
; AVX512DQ-NEXT: vpternlogd {{.*#+}} ymm1 = ymm1 ^ (mem & (ymm1 ^ ymm0))
; AVX512DQ-NEXT: vpbroadcastb (%rdi), %ymm0
; AVX512DQ-NEXT: vinserti64x4 $1, %ymm0, %zmm0, %zmm0
; AVX512DQ-NEXT: vpaddb 32(%rsi), %ymm0, %ymm0
; AVX512DQ-NEXT: vpaddb (%rsi), %ymm1, %ymm1
; AVX512DQ-NEXT: vmovdqa %ymm1, (%rdx)
; AVX512DQ-NEXT: vmovdqa %ymm0, 32(%rdx)
; AVX512DQ-NEXT: vpternlogd {{.*#+}} ymm0 = ymm1 ^ (mem & (ymm0 ^ ymm1))
; AVX512DQ-NEXT: vpaddb (%rsi), %ymm0, %ymm0
; AVX512DQ-NEXT: vpaddb 32(%rsi), %ymm1, %ymm1
; AVX512DQ-NEXT: vmovdqa %ymm1, 32(%rdx)
; AVX512DQ-NEXT: vmovdqa %ymm0, (%rdx)
; AVX512DQ-NEXT: vzeroupper
; AVX512DQ-NEXT: retq
;
; AVX512BW-LABEL: vec384_i8_widen_to_i32_factor4_broadcast_to_v12i32_factor12:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vmovdqa 48(%rdi), %xmm0
; AVX512BW-NEXT: vpbroadcastb (%rdi), %ymm1
; AVX512BW-NEXT: movl $286331153, %eax # imm = 0x11111111
; AVX512BW-NEXT: kmovd %eax, %k1
; AVX512BW-NEXT: vpbroadcastb (%rdi), %ymm0 {%k1}
; AVX512BW-NEXT: vpbroadcastb (%rdi), %ymm1
; AVX512BW-NEXT: vmovdqu8 %ymm1, %ymm0 {%k1}
; AVX512BW-NEXT: vinserti64x4 $1, %ymm1, %zmm0, %zmm0
; AVX512BW-NEXT: vpaddb (%rsi), %zmm0, %zmm0
; AVX512BW-NEXT: vmovdqa64 %zmm0, (%rdx)
Expand Down Expand Up @@ -2364,37 +2355,33 @@ define void @vec384_i8_widen_to_i64_factor8_broadcast_to_v6i64_factor6(ptr %in.e
; AVX512F: # %bb.0:
; AVX512F-NEXT: vmovdqa 48(%rdi), %xmm0
; AVX512F-NEXT: vpbroadcastb (%rdi), %ymm1
; AVX512F-NEXT: vpternlogq {{.*#+}} ymm1 = ymm1 ^ (mem & (ymm1 ^ ymm0))
; AVX512F-NEXT: vpbroadcastb (%rdi), %ymm0
; AVX512F-NEXT: vinserti64x4 $1, %ymm0, %zmm0, %zmm0
; AVX512F-NEXT: vpaddb 32(%rsi), %ymm0, %ymm0
; AVX512F-NEXT: vpaddb (%rsi), %ymm1, %ymm1
; AVX512F-NEXT: vmovdqa %ymm1, (%rdx)
; AVX512F-NEXT: vmovdqa %ymm0, 32(%rdx)
; AVX512F-NEXT: vpternlogq {{.*#+}} ymm0 = ymm1 ^ (mem & (ymm0 ^ ymm1))
; AVX512F-NEXT: vpaddb (%rsi), %ymm0, %ymm0
; AVX512F-NEXT: vpaddb 32(%rsi), %ymm1, %ymm1
; AVX512F-NEXT: vmovdqa %ymm1, 32(%rdx)
; AVX512F-NEXT: vmovdqa %ymm0, (%rdx)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512DQ-LABEL: vec384_i8_widen_to_i64_factor8_broadcast_to_v6i64_factor6:
; AVX512DQ: # %bb.0:
; AVX512DQ-NEXT: vmovdqa 48(%rdi), %xmm0
; AVX512DQ-NEXT: vpbroadcastb (%rdi), %ymm1
; AVX512DQ-NEXT: vpternlogq {{.*#+}} ymm1 = ymm1 ^ (mem & (ymm1 ^ ymm0))
; AVX512DQ-NEXT: vpbroadcastb (%rdi), %ymm0
; AVX512DQ-NEXT: vinserti64x4 $1, %ymm0, %zmm0, %zmm0
; AVX512DQ-NEXT: vpaddb 32(%rsi), %ymm0, %ymm0
; AVX512DQ-NEXT: vpaddb (%rsi), %ymm1, %ymm1
; AVX512DQ-NEXT: vmovdqa %ymm1, (%rdx)
; AVX512DQ-NEXT: vmovdqa %ymm0, 32(%rdx)
; AVX512DQ-NEXT: vpternlogq {{.*#+}} ymm0 = ymm1 ^ (mem & (ymm0 ^ ymm1))
; AVX512DQ-NEXT: vpaddb (%rsi), %ymm0, %ymm0
; AVX512DQ-NEXT: vpaddb 32(%rsi), %ymm1, %ymm1
; AVX512DQ-NEXT: vmovdqa %ymm1, 32(%rdx)
; AVX512DQ-NEXT: vmovdqa %ymm0, (%rdx)
; AVX512DQ-NEXT: vzeroupper
; AVX512DQ-NEXT: retq
;
; AVX512BW-LABEL: vec384_i8_widen_to_i64_factor8_broadcast_to_v6i64_factor6:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vmovdqa 48(%rdi), %xmm0
; AVX512BW-NEXT: vpbroadcastb (%rdi), %ymm1
; AVX512BW-NEXT: movl $16843009, %eax # imm = 0x1010101
; AVX512BW-NEXT: kmovd %eax, %k1
; AVX512BW-NEXT: vpbroadcastb (%rdi), %ymm0 {%k1}
; AVX512BW-NEXT: vpbroadcastb (%rdi), %ymm1
; AVX512BW-NEXT: vmovdqu8 %ymm1, %ymm0 {%k1}
; AVX512BW-NEXT: vinserti64x4 $1, %ymm1, %zmm0, %zmm0
; AVX512BW-NEXT: vpaddb (%rsi), %zmm0, %zmm0
; AVX512BW-NEXT: vmovdqa64 %zmm0, (%rdx)
Expand Down Expand Up @@ -2817,7 +2804,6 @@ define void @vec384_i16_widen_to_i32_factor2_broadcast_to_v12i32_factor12(ptr %i
; AVX512F-NEXT: vmovdqa 48(%rdi), %xmm0
; AVX512F-NEXT: vpbroadcastw (%rdi), %ymm1
; AVX512F-NEXT: vpblendw {{.*#+}} ymm0 = ymm1[0],ymm0[1],ymm1[2],ymm0[3],ymm1[4],ymm0[5],ymm1[6],ymm0[7],ymm1[8],ymm0[9],ymm1[10],ymm0[11],ymm1[12],ymm0[13],ymm1[14],ymm0[15]
; AVX512F-NEXT: vpbroadcastw (%rdi), %ymm1
; AVX512F-NEXT: vpaddb (%rsi), %ymm0, %ymm0
; AVX512F-NEXT: vpaddb 32(%rsi), %ymm1, %ymm1
; AVX512F-NEXT: vmovdqa %ymm1, 32(%rdx)
Expand All @@ -2830,7 +2816,6 @@ define void @vec384_i16_widen_to_i32_factor2_broadcast_to_v12i32_factor12(ptr %i
; AVX512DQ-NEXT: vmovdqa 48(%rdi), %xmm0
; AVX512DQ-NEXT: vpbroadcastw (%rdi), %ymm1
; AVX512DQ-NEXT: vpblendw {{.*#+}} ymm0 = ymm1[0],ymm0[1],ymm1[2],ymm0[3],ymm1[4],ymm0[5],ymm1[6],ymm0[7],ymm1[8],ymm0[9],ymm1[10],ymm0[11],ymm1[12],ymm0[13],ymm1[14],ymm0[15]
; AVX512DQ-NEXT: vpbroadcastw (%rdi), %ymm1
; AVX512DQ-NEXT: vpaddb (%rsi), %ymm0, %ymm0
; AVX512DQ-NEXT: vpaddb 32(%rsi), %ymm1, %ymm1
; AVX512DQ-NEXT: vmovdqa %ymm1, 32(%rdx)
Expand Down Expand Up @@ -2907,8 +2892,7 @@ define void @vec384_i16_widen_to_i48_factor3_broadcast_to_v8i48_factor8(ptr %in.
; AVX2-LABEL: vec384_i16_widen_to_i48_factor3_broadcast_to_v8i48_factor8:
; AVX2: # %bb.0:
; AVX2-NEXT: vpbroadcastw (%rdi), %xmm0
; AVX2-NEXT: vpbroadcastw (%rdi), %xmm1
; AVX2-NEXT: vpblendw {{.*#+}} xmm1 = xmm1[0],mem[1,2],xmm1[3],mem[4,5],xmm1[6],mem[7]
; AVX2-NEXT: vpblendw {{.*#+}} xmm1 = xmm0[0],mem[1,2],xmm0[3],mem[4,5],xmm0[6],mem[7]
; AVX2-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm1
; AVX2-NEXT: vpaddb (%rsi), %ymm1, %ymm1
; AVX2-NEXT: vpaddb 32(%rsi), %ymm0, %ymm0
Expand All @@ -2920,26 +2904,24 @@ define void @vec384_i16_widen_to_i48_factor3_broadcast_to_v8i48_factor8(ptr %in.
; AVX512F-LABEL: vec384_i16_widen_to_i48_factor3_broadcast_to_v8i48_factor8:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vpbroadcastw (%rdi), %xmm0
; AVX512F-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0],mem[1,2],xmm0[3],mem[4,5],xmm0[6],mem[7]
; AVX512F-NEXT: vpbroadcastw (%rdi), %xmm1
; AVX512F-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX512F-NEXT: vpaddb (%rsi), %ymm0, %ymm0
; AVX512F-NEXT: vpaddb 32(%rsi), %ymm1, %ymm1
; AVX512F-NEXT: vmovdqa %ymm1, 32(%rdx)
; AVX512F-NEXT: vmovdqa %ymm0, (%rdx)
; AVX512F-NEXT: vpblendw {{.*#+}} xmm1 = xmm0[0],mem[1,2],xmm0[3],mem[4,5],xmm0[6],mem[7]
; AVX512F-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm1
; AVX512F-NEXT: vpaddb (%rsi), %ymm1, %ymm1
; AVX512F-NEXT: vpaddb 32(%rsi), %ymm0, %ymm0
; AVX512F-NEXT: vmovdqa %ymm0, 32(%rdx)
; AVX512F-NEXT: vmovdqa %ymm1, (%rdx)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512DQ-LABEL: vec384_i16_widen_to_i48_factor3_broadcast_to_v8i48_factor8:
; AVX512DQ: # %bb.0:
; AVX512DQ-NEXT: vpbroadcastw (%rdi), %xmm0
; AVX512DQ-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0],mem[1,2],xmm0[3],mem[4,5],xmm0[6],mem[7]
; AVX512DQ-NEXT: vpbroadcastw (%rdi), %xmm1
; AVX512DQ-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX512DQ-NEXT: vpaddb (%rsi), %ymm0, %ymm0
; AVX512DQ-NEXT: vpaddb 32(%rsi), %ymm1, %ymm1
; AVX512DQ-NEXT: vmovdqa %ymm1, 32(%rdx)
; AVX512DQ-NEXT: vmovdqa %ymm0, (%rdx)
; AVX512DQ-NEXT: vpblendw {{.*#+}} xmm1 = xmm0[0],mem[1,2],xmm0[3],mem[4,5],xmm0[6],mem[7]
; AVX512DQ-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm1
; AVX512DQ-NEXT: vpaddb (%rsi), %ymm1, %ymm1
; AVX512DQ-NEXT: vpaddb 32(%rsi), %ymm0, %ymm0
; AVX512DQ-NEXT: vmovdqa %ymm0, 32(%rdx)
; AVX512DQ-NEXT: vmovdqa %ymm1, (%rdx)
; AVX512DQ-NEXT: vzeroupper
; AVX512DQ-NEXT: retq
;
Expand Down Expand Up @@ -3024,7 +3006,6 @@ define void @vec384_i16_widen_to_i64_factor4_broadcast_to_v6i64_factor6(ptr %in.
; AVX512F-NEXT: vmovdqa 48(%rdi), %xmm0
; AVX512F-NEXT: vpbroadcastw (%rdi), %ymm1
; AVX512F-NEXT: vpblendw {{.*#+}} ymm0 = ymm1[0],ymm0[1,2,3],ymm1[4],ymm0[5,6,7],ymm1[8],ymm0[9,10,11],ymm1[12],ymm0[13,14,15]
; AVX512F-NEXT: vpbroadcastw (%rdi), %ymm1
; AVX512F-NEXT: vpaddb (%rsi), %ymm0, %ymm0
; AVX512F-NEXT: vpaddb 32(%rsi), %ymm1, %ymm1
; AVX512F-NEXT: vmovdqa %ymm1, 32(%rdx)
Expand All @@ -3037,7 +3018,6 @@ define void @vec384_i16_widen_to_i64_factor4_broadcast_to_v6i64_factor6(ptr %in.
; AVX512DQ-NEXT: vmovdqa 48(%rdi), %xmm0
; AVX512DQ-NEXT: vpbroadcastw (%rdi), %ymm1
; AVX512DQ-NEXT: vpblendw {{.*#+}} ymm0 = ymm1[0],ymm0[1,2,3],ymm1[4],ymm0[5,6,7],ymm1[8],ymm0[9,10,11],ymm1[12],ymm0[13,14,15]
; AVX512DQ-NEXT: vpbroadcastw (%rdi), %ymm1
; AVX512DQ-NEXT: vpaddb (%rsi), %ymm0, %ymm0
; AVX512DQ-NEXT: vpaddb 32(%rsi), %ymm1, %ymm1
; AVX512DQ-NEXT: vmovdqa %ymm1, 32(%rdx)
Expand Down Expand Up @@ -3117,8 +3097,7 @@ define void @vec384_i16_widen_to_i96_factor6_broadcast_to_v4i96_factor4(ptr %in.
; AVX2-LABEL: vec384_i16_widen_to_i96_factor6_broadcast_to_v4i96_factor4:
; AVX2: # %bb.0:
; AVX2-NEXT: vpbroadcastw (%rdi), %xmm0
; AVX2-NEXT: vpbroadcastw (%rdi), %xmm1
; AVX2-NEXT: vpblendw {{.*#+}} xmm1 = xmm1[0],mem[1,2,3,4,5],xmm1[6],mem[7]
; AVX2-NEXT: vpblendw {{.*#+}} xmm1 = xmm0[0],mem[1,2,3,4,5],xmm0[6],mem[7]
; AVX2-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm1
; AVX2-NEXT: vpaddb (%rsi), %ymm1, %ymm1
; AVX2-NEXT: vpaddb 32(%rsi), %ymm0, %ymm0
Expand All @@ -3130,9 +3109,8 @@ define void @vec384_i16_widen_to_i96_factor6_broadcast_to_v4i96_factor4(ptr %in.
; AVX512F-LABEL: vec384_i16_widen_to_i96_factor6_broadcast_to_v4i96_factor4:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vpbroadcastw (%rdi), %xmm0
; AVX512F-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0],mem[1,2,3,4,5],xmm0[6],mem[7]
; AVX512F-NEXT: vpbroadcastw (%rdi), %xmm1
; AVX512F-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX512F-NEXT: vpblendw {{.*#+}} xmm1 = xmm0[0],mem[1,2,3,4,5],xmm0[6],mem[7]
; AVX512F-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX512F-NEXT: vpbroadcastw (%rdi), %ymm1
; AVX512F-NEXT: vpaddb (%rsi), %ymm0, %ymm0
; AVX512F-NEXT: vpaddb 32(%rsi), %ymm1, %ymm1
Expand All @@ -3144,9 +3122,8 @@ define void @vec384_i16_widen_to_i96_factor6_broadcast_to_v4i96_factor4(ptr %in.
; AVX512DQ-LABEL: vec384_i16_widen_to_i96_factor6_broadcast_to_v4i96_factor4:
; AVX512DQ: # %bb.0:
; AVX512DQ-NEXT: vpbroadcastw (%rdi), %xmm0
; AVX512DQ-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0],mem[1,2,3,4,5],xmm0[6],mem[7]
; AVX512DQ-NEXT: vpbroadcastw (%rdi), %xmm1
; AVX512DQ-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX512DQ-NEXT: vpblendw {{.*#+}} xmm1 = xmm0[0],mem[1,2,3,4,5],xmm0[6],mem[7]
; AVX512DQ-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX512DQ-NEXT: vpbroadcastw (%rdi), %ymm1
; AVX512DQ-NEXT: vpaddb (%rsi), %ymm0, %ymm0
; AVX512DQ-NEXT: vpaddb 32(%rsi), %ymm1, %ymm1
Expand Down
Loading