NVIDIA ISA Viewer

SHFL

Warp Wide Register Shuffle

4 variants on SM90 (H100)

SHFL

P,R,R,R,R

distilled: @P0 SHFL.IDX P0, R0, R0, R0, R0 ;

key: SHFL_P_R_R_R_R

0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7
1	0	0	1	0	0	0	1	1	1	0	0	pred				operand 1								operand 2								operand 3								0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	modi 1		0	0	0	0
0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7
operand 4								0	0	0	0	0	0	0	0	operand 0				0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	stall				y	r-bar			w-bar			b-mask						reuse				0	0

Modifier Group 1

Binary	Value
00	IDX
01	UP
10	DOWN
11	BFLY

SHFL

P,R,R,R,I

distilled: @P0 SHFL.IDX P0, R0, R0, R0, 0x0 ;

key: SHFL_P_R_R_R_I

0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7
1	0	0	1	0	0	0	1	1	0	1	0	pred				operand 1								operand 2								operand 3								operand 4														0	0	0	0	modi 1		0	0	0	0
0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7
0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	operand 0				0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	stall				y	r-bar			w-bar			b-mask						reuse				0	0

Modifier Group 1

Binary	Value
00	IDX
01	UP
10	DOWN
11	BFLY

SHFL

P,R,R,I,R

distilled: @P0 SHFL.IDX P0, R0, R0, 0x0, R0 ;

key: SHFL_P_R_R_I_R

0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7
1	0	0	1	0	0	0	1	1	0	0	1	pred				operand 1								operand 2								0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	operand 3						modi 1		0	0	0	0
0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7
operand 4								0	0	0	0	0	0	0	0	operand 0				0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	stall				y	r-bar			w-bar			b-mask						reuse				0	0

Modifier Group 1

Binary	Value
00	IDX
01	UP
10	DOWN
11	BFLY

SHFL

P,R,R,I,I

distilled: @P0 SHFL.IDX P0, R0, R0, 0x0, 0x0 ;

key: SHFL_P_R_R_I_I

0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7
1	0	0	1	0	0	0	1	1	1	1	1	pred				operand 1								operand 2								0	0	0	0	0	0	0	0	operand 4												operand 3	operand 4	operand 3				modi 1		0	0	0	0
0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7	0	1	2	3	4	5	6	7
0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	operand 0				0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	stall				y	r-bar			w-bar			b-mask						reuse				0	0

Modifier Group 1

Binary	Value
00	IDX
01	UP
10	DOWN
11	BFLY